├── model └── .keep ├── out └── .keep ├── table_embedder ├── models │ ├── __init__.py │ └── lib │ │ └── __init__.py ├── readers │ ├── lib │ │ └── __init__.py │ ├── epoch_callbacks │ │ └── __init__.py │ └── __init__.py ├── predictors │ └── __init__.py └── __init__.py ├── data ├── clscol.npy ├── clsrow.npy ├── ft_col │ ├── test_csv │ │ ├── 1438042988399.65__CC-MAIN-20150728002308-00257-ip-10-236-191-2.ec2.internal__2153.csv │ │ ├── 1438042990609.0__CC-MAIN-20150728002310-00065-ip-10-236-191-2.ec2.internal__2037.csv │ │ ├── 1438042991076.30__CC-MAIN-20150728002311-00041-ip-10-236-191-2.ec2.internal__1901.csv │ │ ├── 1438042990112.50__CC-MAIN-20150728002310-00303-ip-10-236-191-2.ec2.internal__1888.csv │ │ ├── 1438043060830.93__CC-MAIN-20150728002420-00072-ip-10-236-191-2.ec2.internal__1045.csv │ │ ├── 1438042988308.23__CC-MAIN-20150728002308-00294-ip-10-236-191-2.ec2.internal__2445.csv │ │ ├── 1438042981921.1__CC-MAIN-20150728002301-00294-ip-10-236-191-2.ec2.internal__444.csv │ │ ├── 1438042982502.13__CC-MAIN-20150728002302-00111-ip-10-236-191-2.ec2.internal__1274.csv │ │ ├── 1438042990900.28__CC-MAIN-20150728002310-00070-ip-10-236-191-2.ec2.internal__1337.csv │ │ ├── 1438042989018.48__CC-MAIN-20150728002309-00112-ip-10-236-191-2.ec2.internal__1789.csv │ │ ├── 1438042981753.21__CC-MAIN-20150728002301-00208-ip-10-236-191-2.ec2.internal__1874.csv │ │ ├── 1438042986625.58__CC-MAIN-20150728002306-00239-ip-10-236-191-2.ec2.internal__2767.csv │ │ ├── 1438042987155.85__CC-MAIN-20150728002307-00192-ip-10-236-191-2.ec2.internal__2107.csv │ │ ├── 1438042988962.66__CC-MAIN-20150728002308-00249-ip-10-236-191-2.ec2.internal__2362.csv │ │ ├── 1438042989826.86__CC-MAIN-20150728002309-00179-ip-10-236-191-2.ec2.internal__2223.csv │ │ ├── 1438043062635.98__CC-MAIN-20150728002422-00156-ip-10-236-191-2.ec2.internal__1687.csv │ │ ├── 1438042988310.3__CC-MAIN-20150728002308-00191-ip-10-236-191-2.ec2.internal__1723.csv │ │ ├── 1438042988650.53__CC-MAIN-20150728002308-00168-ip-10-236-191-2.ec2.internal__1772.csv │ │ ├── 1438042989301.17__CC-MAIN-20150728002309-00076-ip-10-236-191-2.ec2.internal__518.csv │ │ ├── 1438042992543.60__CC-MAIN-20150728002312-00232-ip-10-236-191-2.ec2.internal__1998.csv │ │ ├── 1438042988860.88__CC-MAIN-20150728002308-00317-ip-10-236-191-2.ec2.internal__1033.csv │ │ ├── 1438042989891.18__CC-MAIN-20150728002309-00046-ip-10-236-191-2.ec2.internal__1544.csv │ │ ├── 1438042990112.92__CC-MAIN-20150728002310-00221-ip-10-236-191-2.ec2.internal__1384.csv │ │ ├── 1438042989507.42__CC-MAIN-20150728002309-00037-ip-10-236-191-2.ec2.internal__1161.csv │ │ ├── 1438042988317.67__CC-MAIN-20150728002308-00041-ip-10-236-191-2.ec2.internal__159.csv │ │ ├── 1438042988860.88__CC-MAIN-20150728002308-00278-ip-10-236-191-2.ec2.internal__245.csv │ │ ├── 1438042989018.48__CC-MAIN-20150728002309-00056-ip-10-236-191-2.ec2.internal__1290.csv │ │ ├── 1438042992543.60__CC-MAIN-20150728002312-00162-ip-10-236-191-2.ec2.internal__375.csv │ │ ├── 1438042991019.80__CC-MAIN-20150728002311-00290-ip-10-236-191-2.ec2.internal__1606.csv │ │ ├── 1438042989891.18__CC-MAIN-20150728002309-00291-ip-10-236-191-2.ec2.internal__436.csv │ │ ├── 1438042988051.33__CC-MAIN-20150728002308-00108-ip-10-236-191-2.ec2.internal__614.csv │ │ ├── 1438042986444.39__CC-MAIN-20150728002306-00031-ip-10-236-191-2.ec2.internal__523.csv │ │ ├── 1438042989234.2__CC-MAIN-20150728002309-00204-ip-10-236-191-2.ec2.internal__253.csv │ │ ├── 1438042990123.20__CC-MAIN-20150728002310-00184-ip-10-236-191-2.ec2.internal__2231.csv │ │ ├── 1438042988065.26__CC-MAIN-20150728002308-00287-ip-10-236-191-2.ec2.internal__1557.csv │ │ ├── 1438042989331.34__CC-MAIN-20150728002309-00143-ip-10-236-191-2.ec2.internal__1055.csv │ │ ├── 1438042986423.95__CC-MAIN-20150728002306-00337-ip-10-236-191-2.ec2.internal__484.csv │ │ ├── 1438042986615.83__CC-MAIN-20150728002306-00084-ip-10-236-191-2.ec2.internal__747.csv │ │ ├── 1438042987174.71__CC-MAIN-20150728002307-00249-ip-10-236-191-2.ec2.internal__1312.csv │ │ ├── 1438042990603.54__CC-MAIN-20150728002310-00257-ip-10-236-191-2.ec2.internal__130.csv │ │ ├── 1438042988311.72__CC-MAIN-20150728002308-00230-ip-10-236-191-2.ec2.internal__1981.csv │ │ ├── 1438042988930.94__CC-MAIN-20150728002308-00013-ip-10-236-191-2.ec2.internal__1079.csv │ │ ├── 1438043062723.96__CC-MAIN-20150728002422-00214-ip-10-236-191-2.ec2.internal__833.csv │ │ ├── 1438042989897.84__CC-MAIN-20150728002309-00300-ip-10-236-191-2.ec2.internal__309.csv │ │ ├── 1438042990112.92__CC-MAIN-20150728002310-00222-ip-10-236-191-2.ec2.internal__22.csv │ │ ├── 1438042989142.82__CC-MAIN-20150728002309-00099-ip-10-236-191-2.ec2.internal__2068.csv │ │ ├── 1438042991076.30__CC-MAIN-20150728002311-00254-ip-10-236-191-2.ec2.internal__35.csv │ │ ├── 1438042982502.13__CC-MAIN-20150728002302-00239-ip-10-236-191-2.ec2.internal__685.csv │ │ ├── 1438042986148.56__CC-MAIN-20150728002306-00235-ip-10-236-191-2.ec2.internal__1751.csv │ │ ├── 1438042988930.94__CC-MAIN-20150728002308-00259-ip-10-236-191-2.ec2.internal__1515.csv │ │ ├── 1438042987155.85__CC-MAIN-20150728002307-00318-ip-10-236-191-2.ec2.internal__2644.csv │ │ ├── 1438042989331.34__CC-MAIN-20150728002309-00335-ip-10-236-191-2.ec2.internal__2086.csv │ │ ├── 1438042992201.62__CC-MAIN-20150728002312-00292-ip-10-236-191-2.ec2.internal__2128.csv │ │ ├── 1438042990112.50__CC-MAIN-20150728002310-00124-ip-10-236-191-2.ec2.internal__1282.csv │ │ ├── 1438042988250.59__CC-MAIN-20150728002308-00240-ip-10-236-191-2.ec2.internal__817.csv │ │ ├── 1438042986423.95__CC-MAIN-20150728002306-00124-ip-10-236-191-2.ec2.internal__1089.csv │ │ ├── 1438042990217.27__CC-MAIN-20150728002310-00075-ip-10-236-191-2.ec2.internal__1439.csv │ │ ├── 1438042989018.48__CC-MAIN-20150728002309-00040-ip-10-236-191-2.ec2.internal__1358.csv │ │ ├── 1438042989331.34__CC-MAIN-20150728002309-00246-ip-10-236-191-2.ec2.internal__1255.csv │ │ ├── 1438042985647.51__CC-MAIN-20150728002305-00269-ip-10-236-191-2.ec2.internal__1236.csv │ │ ├── 1438042990217.27__CC-MAIN-20150728002310-00322-ip-10-236-191-2.ec2.internal__2306.csv │ │ ├── 1438042988065.26__CC-MAIN-20150728002308-00033-ip-10-236-191-2.ec2.internal__865.csv │ │ └── 1438042989234.2__CC-MAIN-20150728002309-00282-ip-10-236-191-2.ec2.internal__1016.csv │ ├── train_csv │ │ ├── 1438043058631.99__CC-MAIN-20150728002418-00261-ip-10-236-191-2.ec2.internal__2006.csv │ │ ├── 1438042988458.74__CC-MAIN-20150728002308-00212-ip-10-236-191-2.ec2.internal__1724.csv │ │ ├── 1438042986451.45__CC-MAIN-20150728002306-00067-ip-10-236-191-2.ec2.internal__128.csv │ │ ├── 1438042987628.47__CC-MAIN-20150728002307-00145-ip-10-236-191-2.ec2.internal__1041.csv │ │ ├── 1438042989018.40__CC-MAIN-20150728002309-00123-ip-10-236-191-2.ec2.internal__2275.csv │ │ ├── 1438042986615.83__CC-MAIN-20150728002306-00051-ip-10-236-191-2.ec2.internal__1024.csv │ │ ├── 1438042987127.36__CC-MAIN-20150728002307-00141-ip-10-236-191-2.ec2.internal__156.csv │ │ ├── 1438043062635.98__CC-MAIN-20150728002422-00203-ip-10-236-191-2.ec2.internal__1734.csv │ │ ├── 1438042988860.4__CC-MAIN-20150728002308-00197-ip-10-236-191-2.ec2.internal__2236.csv │ │ ├── 1438042990900.28__CC-MAIN-20150728002310-00251-ip-10-236-191-2.ec2.internal__2279.csv │ │ ├── 1438043062635.98__CC-MAIN-20150728002422-00266-ip-10-236-191-2.ec2.internal__1392.csv │ │ ├── 1438042987228.91__CC-MAIN-20150728002307-00122-ip-10-236-191-2.ec2.internal__88.csv │ │ ├── 1438042988250.59__CC-MAIN-20150728002308-00009-ip-10-236-191-2.ec2.internal__1805.csv │ │ ├── 1438042987628.47__CC-MAIN-20150728002307-00125-ip-10-236-191-2.ec2.internal__980.csv │ │ ├── 1438042988650.6__CC-MAIN-20150728002308-00014-ip-10-236-191-2.ec2.internal__1639.csv │ │ ├── 1438042989891.18__CC-MAIN-20150728002309-00110-ip-10-236-191-2.ec2.internal__1467.csv │ │ ├── 1438042990217.27__CC-MAIN-20150728002310-00130-ip-10-236-191-2.ec2.internal__376.csv │ │ ├── 1438042988399.65__CC-MAIN-20150728002308-00127-ip-10-236-191-2.ec2.internal__1207.csv │ │ ├── 1438042987034.19__CC-MAIN-20150728002307-00101-ip-10-236-191-2.ec2.internal__2095.csv │ │ ├── 1438042985647.51__CC-MAIN-20150728002305-00318-ip-10-236-191-2.ec2.internal__105.csv │ │ ├── 1438042988061.16__CC-MAIN-20150728002308-00120-ip-10-236-191-2.ec2.internal__883.csv │ │ ├── 1438042981460.12__CC-MAIN-20150728002301-00003-ip-10-236-191-2.ec2.internal__1387.csv │ │ ├── 1438042986615.83__CC-MAIN-20150728002306-00215-ip-10-236-191-2.ec2.internal__1920.csv │ │ ├── 1438042990217.27__CC-MAIN-20150728002310-00111-ip-10-236-191-2.ec2.internal__2531.csv │ │ ├── 1438042988924.75__CC-MAIN-20150728002308-00052-ip-10-236-191-2.ec2.internal__2363.csv │ │ ├── 1438042991019.80__CC-MAIN-20150728002311-00109-ip-10-236-191-2.ec2.internal__710.csv │ │ ├── 1438042989507.42__CC-MAIN-20150728002309-00199-ip-10-236-191-2.ec2.internal__2601.csv │ │ ├── 1438042990112.92__CC-MAIN-20150728002310-00030-ip-10-236-191-2.ec2.internal__954.csv │ │ ├── 1438042989826.86__CC-MAIN-20150728002309-00046-ip-10-236-191-2.ec2.internal__1968.csv │ │ ├── 1438042988051.33__CC-MAIN-20150728002308-00270-ip-10-236-191-2.ec2.internal__770.csv │ │ ├── 1438042989042.37__CC-MAIN-20150728002309-00074-ip-10-236-191-2.ec2.internal__2439.csv │ │ ├── 1438042989331.34__CC-MAIN-20150728002309-00098-ip-10-236-191-2.ec2.internal__350.csv │ │ ├── 1438042987402.78__CC-MAIN-20150728002307-00143-ip-10-236-191-2.ec2.internal__1993.csv │ │ ├── 1438042988650.6__CC-MAIN-20150728002308-00168-ip-10-236-191-2.ec2.internal__2261.csv │ │ ├── 1438042989018.40__CC-MAIN-20150728002309-00178-ip-10-236-191-2.ec2.internal__1420.csv │ │ ├── 1438042987775.70__CC-MAIN-20150728002307-00015-ip-10-236-191-2.ec2.internal__437.csv │ │ ├── 1438042987228.91__CC-MAIN-20150728002307-00306-ip-10-236-191-2.ec2.internal__1005.csv │ │ ├── 1438042988051.33__CC-MAIN-20150728002308-00259-ip-10-236-191-2.ec2.internal__541.csv │ │ ├── 1438043062635.98__CC-MAIN-20150728002422-00195-ip-10-236-191-2.ec2.internal__742.csv │ │ ├── 1438042981856.5__CC-MAIN-20150728002301-00062-ip-10-236-191-2.ec2.internal__1831.csv │ │ ├── 1438042989510.73__CC-MAIN-20150728002309-00063-ip-10-236-191-2.ec2.internal__1159.csv │ │ ├── 1438042988458.74__CC-MAIN-20150728002308-00210-ip-10-236-191-2.ec2.internal__1149.csv │ │ ├── 1438042989178.64__CC-MAIN-20150728002309-00150-ip-10-236-191-2.ec2.internal__362.csv │ │ ├── 1438042981460.12__CC-MAIN-20150728002301-00202-ip-10-236-191-2.ec2.internal__2064.csv │ │ ├── 1438042989234.2__CC-MAIN-20150728002309-00315-ip-10-236-191-2.ec2.internal__200.csv │ │ ├── 1438042988065.26__CC-MAIN-20150728002308-00173-ip-10-236-191-2.ec2.internal__453.csv │ │ ├── 1438042987552.57__CC-MAIN-20150728002307-00259-ip-10-236-191-2.ec2.internal__2423.csv │ │ ├── 1438042986806.32__CC-MAIN-20150728002306-00163-ip-10-236-191-2.ec2.internal__55.csv │ │ ├── 1438042988860.88__CC-MAIN-20150728002308-00239-ip-10-236-191-2.ec2.internal__2107.csv │ │ ├── 1438042988924.75__CC-MAIN-20150728002308-00339-ip-10-236-191-2.ec2.internal__1863.csv │ │ ├── 1438042988317.67__CC-MAIN-20150728002308-00292-ip-10-236-191-2.ec2.internal__440.csv │ │ ├── 1438042985647.51__CC-MAIN-20150728002305-00301-ip-10-236-191-2.ec2.internal__2228.csv │ │ ├── 1438042990217.27__CC-MAIN-20150728002310-00064-ip-10-236-191-2.ec2.internal__1370.csv │ │ ├── 1438042988317.67__CC-MAIN-20150728002308-00033-ip-10-236-191-2.ec2.internal__2355.csv │ │ ├── 1438042990112.92__CC-MAIN-20150728002310-00240-ip-10-236-191-2.ec2.internal__1247.csv │ │ ├── 1438043058631.99__CC-MAIN-20150728002418-00126-ip-10-236-191-2.ec2.internal__1329.csv │ │ └── 1438042987866.61__CC-MAIN-20150728002307-00252-ip-10-236-191-2.ec2.internal__1295.csv │ └── valid_csv │ │ ├── 1438042988650.6__CC-MAIN-20150728002308-00203-ip-10-236-191-2.ec2.internal__1883.csv │ │ ├── 1438043060830.93__CC-MAIN-20150728002420-00057-ip-10-236-191-2.ec2.internal__1060.csv │ │ ├── 1438042986806.32__CC-MAIN-20150728002306-00126-ip-10-236-191-2.ec2.internal__1540.csv │ │ ├── 1438042990112.92__CC-MAIN-20150728002310-00244-ip-10-236-191-2.ec2.internal__470.csv │ │ ├── 1438042985140.15__CC-MAIN-20150728002305-00339-ip-10-236-191-2.ec2.internal__723.csv │ │ ├── 1438042987552.57__CC-MAIN-20150728002307-00229-ip-10-236-191-2.ec2.internal__1750.csv │ │ ├── 1438042989178.64__CC-MAIN-20150728002309-00069-ip-10-236-191-2.ec2.internal__120.csv │ │ ├── 1438042988048.90__CC-MAIN-20150728002308-00213-ip-10-236-191-2.ec2.internal__784.csv │ │ ├── 1438042987155.85__CC-MAIN-20150728002307-00006-ip-10-236-191-2.ec2.internal__1038.csv │ │ ├── 1438042989126.22__CC-MAIN-20150728002309-00181-ip-10-236-191-2.ec2.internal__1685.csv │ │ ├── 1438042988840.31__CC-MAIN-20150728002308-00310-ip-10-236-191-2.ec2.internal__630.csv │ │ ├── 1438042992201.62__CC-MAIN-20150728002312-00098-ip-10-236-191-2.ec2.internal__1505.csv │ │ ├── 1438042987628.47__CC-MAIN-20150728002307-00335-ip-10-236-191-2.ec2.internal__1368.csv │ │ ├── 1438042988840.31__CC-MAIN-20150728002308-00067-ip-10-236-191-2.ec2.internal__1817.csv │ │ ├── 1438042989897.84__CC-MAIN-20150728002309-00095-ip-10-236-191-2.ec2.internal__1199.csv │ │ ├── 1438042986444.39__CC-MAIN-20150728002306-00060-ip-10-236-191-2.ec2.internal__549.csv │ │ ├── 1438042988065.26__CC-MAIN-20150728002308-00076-ip-10-236-191-2.ec2.internal__1719.csv │ │ ├── 1438042988650.6__CC-MAIN-20150728002308-00126-ip-10-236-191-2.ec2.internal__477.csv │ │ ├── 1438042986444.39__CC-MAIN-20150728002306-00217-ip-10-236-191-2.ec2.internal__2206.csv │ │ ├── 1438042989018.40__CC-MAIN-20150728002309-00317-ip-10-236-191-2.ec2.internal__2.csv │ │ ├── 1438042985140.15__CC-MAIN-20150728002305-00141-ip-10-236-191-2.ec2.internal__886.csv │ │ ├── 1438042985140.15__CC-MAIN-20150728002305-00185-ip-10-236-191-2.ec2.internal__576.csv │ │ ├── 1438042986444.39__CC-MAIN-20150728002306-00119-ip-10-236-191-2.ec2.internal__2126.csv │ │ ├── 1438042989790.89__CC-MAIN-20150728002309-00266-ip-10-236-191-2.ec2.internal__593.csv │ │ ├── 1438042982502.13__CC-MAIN-20150728002302-00303-ip-10-236-191-2.ec2.internal__551.csv │ │ ├── 1438042986615.83__CC-MAIN-20150728002306-00049-ip-10-236-191-2.ec2.internal__1859.csv │ │ ├── 1438042988312.76__CC-MAIN-20150728002308-00140-ip-10-236-191-2.ec2.internal__1485.csv │ │ ├── 1438042987228.91__CC-MAIN-20150728002307-00257-ip-10-236-191-2.ec2.internal__622.csv │ │ ├── 1438042988962.66__CC-MAIN-20150728002308-00231-ip-10-236-191-2.ec2.internal__1481.csv │ │ ├── 1438042986806.32__CC-MAIN-20150728002306-00042-ip-10-236-191-2.ec2.internal__367.csv │ │ ├── 1438042987127.36__CC-MAIN-20150728002307-00308-ip-10-236-191-2.ec2.internal__1005.csv │ │ ├── 1438042989142.82__CC-MAIN-20150728002309-00287-ip-10-236-191-2.ec2.internal__1807.csv │ │ ├── 1438042986806.32__CC-MAIN-20150728002306-00186-ip-10-236-191-2.ec2.internal__960.csv │ │ ├── 1438042988840.31__CC-MAIN-20150728002308-00323-ip-10-236-191-2.ec2.internal__634.csv │ │ ├── 1438042990177.43__CC-MAIN-20150728002310-00003-ip-10-236-191-2.ec2.internal__2195.csv │ │ ├── 1438042988061.16__CC-MAIN-20150728002308-00295-ip-10-236-191-2.ec2.internal__1098.csv │ │ ├── 1438042987228.91__CC-MAIN-20150728002307-00319-ip-10-236-191-2.ec2.internal__1580.csv │ │ ├── 1438042988308.23__CC-MAIN-20150728002308-00218-ip-10-236-191-2.ec2.internal__2226.csv │ │ ├── 1438043058631.99__CC-MAIN-20150728002418-00210-ip-10-236-191-2.ec2.internal__769.csv │ │ ├── 1438042987135.9__CC-MAIN-20150728002307-00175-ip-10-236-191-2.ec2.internal__1018.csv │ │ ├── 1438042986357.49__CC-MAIN-20150728002306-00316-ip-10-236-191-2.ec2.internal__2351.csv │ │ ├── 1438042988860.88__CC-MAIN-20150728002308-00188-ip-10-236-191-2.ec2.internal__18.csv │ │ ├── 1438042988311.72__CC-MAIN-20150728002308-00175-ip-10-236-191-2.ec2.internal__1284.csv │ │ ├── 1438042988924.75__CC-MAIN-20150728002308-00019-ip-10-236-191-2.ec2.internal__1335.csv │ │ ├── 1438042986451.45__CC-MAIN-20150728002306-00229-ip-10-236-191-2.ec2.internal__463.csv │ │ └── 1438042988048.90__CC-MAIN-20150728002308-00117-ip-10-236-191-2.ec2.internal__1172.csv ├── ft_cell │ ├── test_csv │ │ ├── 1438042988399.65__CC-MAIN-20150728002308-00257-ip-10-236-191-2.ec2.internal__2153.csv │ │ ├── 1438042990609.0__CC-MAIN-20150728002310-00065-ip-10-236-191-2.ec2.internal__2037.csv │ │ ├── 1438042991076.30__CC-MAIN-20150728002311-00041-ip-10-236-191-2.ec2.internal__1901.csv │ │ ├── 1438043060830.93__CC-MAIN-20150728002420-00072-ip-10-236-191-2.ec2.internal__1045.csv │ │ ├── 1438042988308.23__CC-MAIN-20150728002308-00294-ip-10-236-191-2.ec2.internal__2445.csv │ │ ├── 1438042981921.1__CC-MAIN-20150728002301-00294-ip-10-236-191-2.ec2.internal__444.csv │ │ ├── 1438042990112.50__CC-MAIN-20150728002310-00303-ip-10-236-191-2.ec2.internal__1888.csv │ │ ├── 1438042989018.48__CC-MAIN-20150728002309-00112-ip-10-236-191-2.ec2.internal__1789.csv │ │ ├── 1438042990900.28__CC-MAIN-20150728002310-00070-ip-10-236-191-2.ec2.internal__1337.csv │ │ ├── 1438042981753.21__CC-MAIN-20150728002301-00208-ip-10-236-191-2.ec2.internal__1874.csv │ │ ├── 1438042982502.13__CC-MAIN-20150728002302-00111-ip-10-236-191-2.ec2.internal__1274.csv │ │ ├── 1438042986625.58__CC-MAIN-20150728002306-00239-ip-10-236-191-2.ec2.internal__2767.csv │ │ ├── 1438042987155.85__CC-MAIN-20150728002307-00192-ip-10-236-191-2.ec2.internal__2107.csv │ │ ├── 1438042988962.66__CC-MAIN-20150728002308-00249-ip-10-236-191-2.ec2.internal__2362.csv │ │ ├── 1438042988650.53__CC-MAIN-20150728002308-00168-ip-10-236-191-2.ec2.internal__1772.csv │ │ ├── 1438042992543.60__CC-MAIN-20150728002312-00232-ip-10-236-191-2.ec2.internal__1998.csv │ │ ├── 1438043062635.98__CC-MAIN-20150728002422-00156-ip-10-236-191-2.ec2.internal__1687.csv │ │ ├── 1438042988310.3__CC-MAIN-20150728002308-00191-ip-10-236-191-2.ec2.internal__1723.csv │ │ ├── 1438042989301.17__CC-MAIN-20150728002309-00076-ip-10-236-191-2.ec2.internal__518.csv │ │ ├── 1438042988317.67__CC-MAIN-20150728002308-00041-ip-10-236-191-2.ec2.internal__159.csv │ │ ├── 1438042988860.88__CC-MAIN-20150728002308-00317-ip-10-236-191-2.ec2.internal__1033.csv │ │ ├── 1438042989507.42__CC-MAIN-20150728002309-00037-ip-10-236-191-2.ec2.internal__1161.csv │ │ ├── 1438042989891.18__CC-MAIN-20150728002309-00046-ip-10-236-191-2.ec2.internal__1544.csv │ │ ├── 1438042990123.20__CC-MAIN-20150728002310-00184-ip-10-236-191-2.ec2.internal__2231.csv │ │ ├── 1438042988860.88__CC-MAIN-20150728002308-00278-ip-10-236-191-2.ec2.internal__245.csv │ │ ├── 1438042989826.86__CC-MAIN-20150728002309-00179-ip-10-236-191-2.ec2.internal__2223.csv │ │ ├── 1438042989018.48__CC-MAIN-20150728002309-00056-ip-10-236-191-2.ec2.internal__1290.csv │ │ ├── 1438042991019.80__CC-MAIN-20150728002311-00290-ip-10-236-191-2.ec2.internal__1606.csv │ │ ├── 1438042989891.18__CC-MAIN-20150728002309-00291-ip-10-236-191-2.ec2.internal__436.csv │ │ ├── 1438042990112.92__CC-MAIN-20150728002310-00221-ip-10-236-191-2.ec2.internal__1384.csv │ │ ├── 1438042992543.60__CC-MAIN-20150728002312-00162-ip-10-236-191-2.ec2.internal__375.csv │ │ ├── 1438042988051.33__CC-MAIN-20150728002308-00108-ip-10-236-191-2.ec2.internal__614.csv │ │ ├── 1438042986444.39__CC-MAIN-20150728002306-00031-ip-10-236-191-2.ec2.internal__523.csv │ │ ├── 1438042988065.26__CC-MAIN-20150728002308-00287-ip-10-236-191-2.ec2.internal__1557.csv │ │ ├── 1438042989234.2__CC-MAIN-20150728002309-00204-ip-10-236-191-2.ec2.internal__253.csv │ │ ├── 1438042989331.34__CC-MAIN-20150728002309-00143-ip-10-236-191-2.ec2.internal__1055.csv │ │ ├── 1438042986615.83__CC-MAIN-20150728002306-00084-ip-10-236-191-2.ec2.internal__747.csv │ │ ├── 1438042986423.95__CC-MAIN-20150728002306-00337-ip-10-236-191-2.ec2.internal__484.csv │ │ ├── 1438042990603.54__CC-MAIN-20150728002310-00257-ip-10-236-191-2.ec2.internal__130.csv │ │ ├── 1438042987174.71__CC-MAIN-20150728002307-00249-ip-10-236-191-2.ec2.internal__1312.csv │ │ ├── 1438042989018.48__CC-MAIN-20150728002309-00040-ip-10-236-191-2.ec2.internal__1358.csv │ │ ├── 1438042988930.94__CC-MAIN-20150728002308-00013-ip-10-236-191-2.ec2.internal__1079.csv │ │ ├── 1438043062723.96__CC-MAIN-20150728002422-00214-ip-10-236-191-2.ec2.internal__833.csv │ │ ├── 1438042988311.72__CC-MAIN-20150728002308-00230-ip-10-236-191-2.ec2.internal__1981.csv │ │ ├── 1438042990112.92__CC-MAIN-20150728002310-00222-ip-10-236-191-2.ec2.internal__22.csv │ │ ├── 1438042982502.13__CC-MAIN-20150728002302-00239-ip-10-236-191-2.ec2.internal__685.csv │ │ ├── 1438042991076.30__CC-MAIN-20150728002311-00254-ip-10-236-191-2.ec2.internal__35.csv │ │ ├── 1438042986148.56__CC-MAIN-20150728002306-00235-ip-10-236-191-2.ec2.internal__1751.csv │ │ ├── 1438042988930.94__CC-MAIN-20150728002308-00259-ip-10-236-191-2.ec2.internal__1515.csv │ │ ├── 1438042989897.84__CC-MAIN-20150728002309-00300-ip-10-236-191-2.ec2.internal__309.csv │ │ ├── 1438042987155.85__CC-MAIN-20150728002307-00318-ip-10-236-191-2.ec2.internal__2644.csv │ │ ├── 1438042989331.34__CC-MAIN-20150728002309-00335-ip-10-236-191-2.ec2.internal__2086.csv │ │ ├── 1438042992201.62__CC-MAIN-20150728002312-00292-ip-10-236-191-2.ec2.internal__2128.csv │ │ ├── 1438042989142.82__CC-MAIN-20150728002309-00099-ip-10-236-191-2.ec2.internal__2068.csv │ │ ├── 1438042990112.50__CC-MAIN-20150728002310-00124-ip-10-236-191-2.ec2.internal__1282.csv │ │ ├── 1438042988065.26__CC-MAIN-20150728002308-00033-ip-10-236-191-2.ec2.internal__865.csv │ │ ├── 1438042988250.59__CC-MAIN-20150728002308-00240-ip-10-236-191-2.ec2.internal__817.csv │ │ ├── 1438042989331.34__CC-MAIN-20150728002309-00246-ip-10-236-191-2.ec2.internal__1255.csv │ │ ├── 1438042990217.27__CC-MAIN-20150728002310-00075-ip-10-236-191-2.ec2.internal__1439.csv │ │ ├── 1438042989234.2__CC-MAIN-20150728002309-00282-ip-10-236-191-2.ec2.internal__1016.csv │ │ └── 1438042990217.27__CC-MAIN-20150728002310-00322-ip-10-236-191-2.ec2.internal__2306.csv │ ├── train_csv │ │ ├── 1438043058631.99__CC-MAIN-20150728002418-00261-ip-10-236-191-2.ec2.internal__2006.csv │ │ ├── 1438042988458.74__CC-MAIN-20150728002308-00212-ip-10-236-191-2.ec2.internal__1724.csv │ │ ├── 1438042987628.47__CC-MAIN-20150728002307-00145-ip-10-236-191-2.ec2.internal__1041.csv │ │ ├── 1438042986451.45__CC-MAIN-20150728002306-00067-ip-10-236-191-2.ec2.internal__128.csv │ │ ├── 1438043062635.98__CC-MAIN-20150728002422-00203-ip-10-236-191-2.ec2.internal__1734.csv │ │ ├── 1438042989018.40__CC-MAIN-20150728002309-00123-ip-10-236-191-2.ec2.internal__2275.csv │ │ ├── 1438042987127.36__CC-MAIN-20150728002307-00141-ip-10-236-191-2.ec2.internal__156.csv │ │ ├── 1438042990900.28__CC-MAIN-20150728002310-00251-ip-10-236-191-2.ec2.internal__2279.csv │ │ ├── 1438042986615.83__CC-MAIN-20150728002306-00051-ip-10-236-191-2.ec2.internal__1024.csv │ │ ├── 1438042988860.4__CC-MAIN-20150728002308-00197-ip-10-236-191-2.ec2.internal__2236.csv │ │ ├── 1438042987228.91__CC-MAIN-20150728002307-00122-ip-10-236-191-2.ec2.internal__88.csv │ │ ├── 1438042987628.47__CC-MAIN-20150728002307-00125-ip-10-236-191-2.ec2.internal__980.csv │ │ ├── 1438043062635.98__CC-MAIN-20150728002422-00266-ip-10-236-191-2.ec2.internal__1392.csv │ │ ├── 1438042988250.59__CC-MAIN-20150728002308-00009-ip-10-236-191-2.ec2.internal__1805.csv │ │ ├── 1438042986615.83__CC-MAIN-20150728002306-00215-ip-10-236-191-2.ec2.internal__1920.csv │ │ ├── 1438042988061.16__CC-MAIN-20150728002308-00120-ip-10-236-191-2.ec2.internal__883.csv │ │ ├── 1438042989891.18__CC-MAIN-20150728002309-00110-ip-10-236-191-2.ec2.internal__1467.csv │ │ ├── 1438042990217.27__CC-MAIN-20150728002310-00130-ip-10-236-191-2.ec2.internal__376.csv │ │ ├── 1438042988650.6__CC-MAIN-20150728002308-00014-ip-10-236-191-2.ec2.internal__1639.csv │ │ ├── 1438042988399.65__CC-MAIN-20150728002308-00127-ip-10-236-191-2.ec2.internal__1207.csv │ │ ├── 1438042987034.19__CC-MAIN-20150728002307-00101-ip-10-236-191-2.ec2.internal__2095.csv │ │ ├── 1438042990112.92__CC-MAIN-20150728002310-00030-ip-10-236-191-2.ec2.internal__954.csv │ │ ├── 1438042990217.27__CC-MAIN-20150728002310-00111-ip-10-236-191-2.ec2.internal__2531.csv │ │ ├── 1438042981460.12__CC-MAIN-20150728002301-00003-ip-10-236-191-2.ec2.internal__1387.csv │ │ ├── 1438042988924.75__CC-MAIN-20150728002308-00052-ip-10-236-191-2.ec2.internal__2363.csv │ │ ├── 1438042985647.51__CC-MAIN-20150728002305-00318-ip-10-236-191-2.ec2.internal__105.csv │ │ ├── 1438042981856.5__CC-MAIN-20150728002301-00062-ip-10-236-191-2.ec2.internal__1831.csv │ │ ├── 1438042989507.42__CC-MAIN-20150728002309-00199-ip-10-236-191-2.ec2.internal__2601.csv │ │ ├── 1438042989826.86__CC-MAIN-20150728002309-00046-ip-10-236-191-2.ec2.internal__1968.csv │ │ ├── 1438042988051.33__CC-MAIN-20150728002308-00270-ip-10-236-191-2.ec2.internal__770.csv │ │ ├── 1438042991019.80__CC-MAIN-20150728002311-00109-ip-10-236-191-2.ec2.internal__710.csv │ │ ├── 1438042987775.70__CC-MAIN-20150728002307-00015-ip-10-236-191-2.ec2.internal__437.csv │ │ ├── 1438042989042.37__CC-MAIN-20150728002309-00074-ip-10-236-191-2.ec2.internal__2439.csv │ │ ├── 1438042988650.6__CC-MAIN-20150728002308-00168-ip-10-236-191-2.ec2.internal__2261.csv │ │ ├── 1438042989018.40__CC-MAIN-20150728002309-00178-ip-10-236-191-2.ec2.internal__1420.csv │ │ ├── 1438042989331.34__CC-MAIN-20150728002309-00098-ip-10-236-191-2.ec2.internal__350.csv │ │ ├── 1438042987402.78__CC-MAIN-20150728002307-00143-ip-10-236-191-2.ec2.internal__1993.csv │ │ ├── 1438042987228.91__CC-MAIN-20150728002307-00306-ip-10-236-191-2.ec2.internal__1005.csv │ │ ├── 1438042988051.33__CC-MAIN-20150728002308-00259-ip-10-236-191-2.ec2.internal__541.csv │ │ ├── 1438043062635.98__CC-MAIN-20150728002422-00195-ip-10-236-191-2.ec2.internal__742.csv │ │ ├── 1438042988458.74__CC-MAIN-20150728002308-00210-ip-10-236-191-2.ec2.internal__1149.csv │ │ ├── 1438042989178.64__CC-MAIN-20150728002309-00150-ip-10-236-191-2.ec2.internal__362.csv │ │ ├── 1438042981460.12__CC-MAIN-20150728002301-00202-ip-10-236-191-2.ec2.internal__2064.csv │ │ ├── 1438042988065.26__CC-MAIN-20150728002308-00173-ip-10-236-191-2.ec2.internal__453.csv │ │ ├── 1438042989234.2__CC-MAIN-20150728002309-00315-ip-10-236-191-2.ec2.internal__200.csv │ │ ├── 1438042989510.73__CC-MAIN-20150728002309-00063-ip-10-236-191-2.ec2.internal__1159.csv │ │ ├── 1438042987552.57__CC-MAIN-20150728002307-00259-ip-10-236-191-2.ec2.internal__2423.csv │ │ ├── 1438042986806.32__CC-MAIN-20150728002306-00163-ip-10-236-191-2.ec2.internal__55.csv │ │ ├── 1438042988860.88__CC-MAIN-20150728002308-00239-ip-10-236-191-2.ec2.internal__2107.csv │ │ ├── 1438042988924.75__CC-MAIN-20150728002308-00339-ip-10-236-191-2.ec2.internal__1863.csv │ │ ├── 1438042988317.67__CC-MAIN-20150728002308-00292-ip-10-236-191-2.ec2.internal__440.csv │ │ ├── 1438042985647.51__CC-MAIN-20150728002305-00301-ip-10-236-191-2.ec2.internal__2228.csv │ │ ├── 1438042990217.27__CC-MAIN-20150728002310-00064-ip-10-236-191-2.ec2.internal__1370.csv │ │ ├── 1438042987866.61__CC-MAIN-20150728002307-00252-ip-10-236-191-2.ec2.internal__1295.csv │ │ ├── 1438042988317.67__CC-MAIN-20150728002308-00033-ip-10-236-191-2.ec2.internal__2355.csv │ │ ├── 1438042990112.92__CC-MAIN-20150728002310-00240-ip-10-236-191-2.ec2.internal__1247.csv │ │ └── 1438043058631.99__CC-MAIN-20150728002418-00126-ip-10-236-191-2.ec2.internal__1329.csv │ └── valid_csv │ │ ├── 1438042988650.6__CC-MAIN-20150728002308-00203-ip-10-236-191-2.ec2.internal__1883.csv │ │ ├── 1438042990112.92__CC-MAIN-20150728002310-00244-ip-10-236-191-2.ec2.internal__470.csv │ │ ├── 1438043060830.93__CC-MAIN-20150728002420-00057-ip-10-236-191-2.ec2.internal__1060.csv │ │ ├── 1438042986806.32__CC-MAIN-20150728002306-00126-ip-10-236-191-2.ec2.internal__1540.csv │ │ ├── 1438042985140.15__CC-MAIN-20150728002305-00339-ip-10-236-191-2.ec2.internal__723.csv │ │ ├── 1438042987552.57__CC-MAIN-20150728002307-00229-ip-10-236-191-2.ec2.internal__1750.csv │ │ ├── 1438042989178.64__CC-MAIN-20150728002309-00069-ip-10-236-191-2.ec2.internal__120.csv │ │ ├── 1438042988048.90__CC-MAIN-20150728002308-00213-ip-10-236-191-2.ec2.internal__784.csv │ │ ├── 1438042987155.85__CC-MAIN-20150728002307-00006-ip-10-236-191-2.ec2.internal__1038.csv │ │ ├── 1438042988840.31__CC-MAIN-20150728002308-00067-ip-10-236-191-2.ec2.internal__1817.csv │ │ ├── 1438042989126.22__CC-MAIN-20150728002309-00181-ip-10-236-191-2.ec2.internal__1685.csv │ │ ├── 1438042987628.47__CC-MAIN-20150728002307-00335-ip-10-236-191-2.ec2.internal__1368.csv │ │ ├── 1438042988065.26__CC-MAIN-20150728002308-00076-ip-10-236-191-2.ec2.internal__1719.csv │ │ ├── 1438042988840.31__CC-MAIN-20150728002308-00310-ip-10-236-191-2.ec2.internal__630.csv │ │ ├── 1438042992201.62__CC-MAIN-20150728002312-00098-ip-10-236-191-2.ec2.internal__1505.csv │ │ ├── 1438042989897.84__CC-MAIN-20150728002309-00095-ip-10-236-191-2.ec2.internal__1199.csv │ │ ├── 1438042986444.39__CC-MAIN-20150728002306-00060-ip-10-236-191-2.ec2.internal__549.csv │ │ ├── 1438042988650.6__CC-MAIN-20150728002308-00126-ip-10-236-191-2.ec2.internal__477.csv │ │ ├── 1438042986444.39__CC-MAIN-20150728002306-00217-ip-10-236-191-2.ec2.internal__2206.csv │ │ ├── 1438042989790.89__CC-MAIN-20150728002309-00266-ip-10-236-191-2.ec2.internal__593.csv │ │ ├── 1438042985140.15__CC-MAIN-20150728002305-00141-ip-10-236-191-2.ec2.internal__886.csv │ │ ├── 1438042989018.40__CC-MAIN-20150728002309-00317-ip-10-236-191-2.ec2.internal__2.csv │ │ ├── 1438042985140.15__CC-MAIN-20150728002305-00185-ip-10-236-191-2.ec2.internal__576.csv │ │ ├── 1438042982502.13__CC-MAIN-20150728002302-00303-ip-10-236-191-2.ec2.internal__551.csv │ │ ├── 1438042986444.39__CC-MAIN-20150728002306-00119-ip-10-236-191-2.ec2.internal__2126.csv │ │ ├── 1438042986615.83__CC-MAIN-20150728002306-00049-ip-10-236-191-2.ec2.internal__1859.csv │ │ ├── 1438042987228.91__CC-MAIN-20150728002307-00257-ip-10-236-191-2.ec2.internal__622.csv │ │ ├── 1438042986806.32__CC-MAIN-20150728002306-00186-ip-10-236-191-2.ec2.internal__960.csv │ │ ├── 1438042988962.66__CC-MAIN-20150728002308-00231-ip-10-236-191-2.ec2.internal__1481.csv │ │ ├── 1438042986806.32__CC-MAIN-20150728002306-00042-ip-10-236-191-2.ec2.internal__367.csv │ │ ├── 1438042988061.16__CC-MAIN-20150728002308-00295-ip-10-236-191-2.ec2.internal__1098.csv │ │ ├── 1438042989142.82__CC-MAIN-20150728002309-00287-ip-10-236-191-2.ec2.internal__1807.csv │ │ ├── 1438042987127.36__CC-MAIN-20150728002307-00308-ip-10-236-191-2.ec2.internal__1005.csv │ │ ├── 1438042990177.43__CC-MAIN-20150728002310-00003-ip-10-236-191-2.ec2.internal__2195.csv │ │ ├── 1438042988840.31__CC-MAIN-20150728002308-00323-ip-10-236-191-2.ec2.internal__634.csv │ │ ├── 1438042988308.23__CC-MAIN-20150728002308-00218-ip-10-236-191-2.ec2.internal__2226.csv │ │ ├── 1438042988312.76__CC-MAIN-20150728002308-00140-ip-10-236-191-2.ec2.internal__1485.csv │ │ ├── 1438042988924.75__CC-MAIN-20150728002308-00019-ip-10-236-191-2.ec2.internal__1335.csv │ │ ├── 1438043058631.99__CC-MAIN-20150728002418-00210-ip-10-236-191-2.ec2.internal__769.csv │ │ ├── 1438042987228.91__CC-MAIN-20150728002307-00319-ip-10-236-191-2.ec2.internal__1580.csv │ │ ├── 1438042987135.9__CC-MAIN-20150728002307-00175-ip-10-236-191-2.ec2.internal__1018.csv │ │ ├── 1438042986357.49__CC-MAIN-20150728002306-00316-ip-10-236-191-2.ec2.internal__2351.csv │ │ ├── 1438042986451.45__CC-MAIN-20150728002306-00229-ip-10-236-191-2.ec2.internal__463.csv │ │ ├── 1438042988311.72__CC-MAIN-20150728002308-00175-ip-10-236-191-2.ec2.internal__1284.csv │ │ ├── 1438042988860.88__CC-MAIN-20150728002308-00188-ip-10-236-191-2.ec2.internal__18.csv │ │ └── 1438042988048.90__CC-MAIN-20150728002308-00117-ip-10-236-191-2.ec2.internal__1172.csv └── ft_table │ ├── test_csv │ ├── 1438042988399.65__CC-MAIN-20150728002308-00257-ip-10-236-191-2.ec2.internal__2153.csv │ ├── 1438042990609.0__CC-MAIN-20150728002310-00065-ip-10-236-191-2.ec2.internal__2037.csv │ ├── 1438042991076.30__CC-MAIN-20150728002311-00041-ip-10-236-191-2.ec2.internal__1901.csv │ ├── 1438043060830.93__CC-MAIN-20150728002420-00072-ip-10-236-191-2.ec2.internal__1045.csv │ ├── 1438042981921.1__CC-MAIN-20150728002301-00294-ip-10-236-191-2.ec2.internal__444.csv │ ├── 1438042988308.23__CC-MAIN-20150728002308-00294-ip-10-236-191-2.ec2.internal__2445.csv │ ├── 1438042990112.50__CC-MAIN-20150728002310-00303-ip-10-236-191-2.ec2.internal__1888.csv │ ├── 1438042989018.48__CC-MAIN-20150728002309-00112-ip-10-236-191-2.ec2.internal__1789.csv │ ├── 1438042990900.28__CC-MAIN-20150728002310-00070-ip-10-236-191-2.ec2.internal__1337.csv │ ├── 1438042981753.21__CC-MAIN-20150728002301-00208-ip-10-236-191-2.ec2.internal__1874.csv │ ├── 1438042982502.13__CC-MAIN-20150728002302-00111-ip-10-236-191-2.ec2.internal__1274.csv │ ├── 1438042986625.58__CC-MAIN-20150728002306-00239-ip-10-236-191-2.ec2.internal__2767.csv │ ├── 1438042987155.85__CC-MAIN-20150728002307-00192-ip-10-236-191-2.ec2.internal__2107.csv │ ├── 1438042988650.53__CC-MAIN-20150728002308-00168-ip-10-236-191-2.ec2.internal__1772.csv │ ├── 1438042988962.66__CC-MAIN-20150728002308-00249-ip-10-236-191-2.ec2.internal__2362.csv │ ├── 1438042989826.86__CC-MAIN-20150728002309-00179-ip-10-236-191-2.ec2.internal__2223.csv │ ├── 1438042992543.60__CC-MAIN-20150728002312-00232-ip-10-236-191-2.ec2.internal__1998.csv │ ├── 1438043062635.98__CC-MAIN-20150728002422-00156-ip-10-236-191-2.ec2.internal__1687.csv │ ├── 1438042989301.17__CC-MAIN-20150728002309-00076-ip-10-236-191-2.ec2.internal__518.csv │ ├── 1438042988310.3__CC-MAIN-20150728002308-00191-ip-10-236-191-2.ec2.internal__1723.csv │ ├── 1438042988317.67__CC-MAIN-20150728002308-00041-ip-10-236-191-2.ec2.internal__159.csv │ ├── 1438042988860.88__CC-MAIN-20150728002308-00317-ip-10-236-191-2.ec2.internal__1033.csv │ ├── 1438042989507.42__CC-MAIN-20150728002309-00037-ip-10-236-191-2.ec2.internal__1161.csv │ ├── 1438042989891.18__CC-MAIN-20150728002309-00046-ip-10-236-191-2.ec2.internal__1544.csv │ ├── 1438042990112.92__CC-MAIN-20150728002310-00221-ip-10-236-191-2.ec2.internal__1384.csv │ ├── 1438042988860.88__CC-MAIN-20150728002308-00278-ip-10-236-191-2.ec2.internal__245.csv │ ├── 1438042989018.48__CC-MAIN-20150728002309-00056-ip-10-236-191-2.ec2.internal__1290.csv │ ├── 1438042991019.80__CC-MAIN-20150728002311-00290-ip-10-236-191-2.ec2.internal__1606.csv │ ├── 1438042992543.60__CC-MAIN-20150728002312-00162-ip-10-236-191-2.ec2.internal__375.csv │ ├── 1438042989891.18__CC-MAIN-20150728002309-00291-ip-10-236-191-2.ec2.internal__436.csv │ ├── 1438042986444.39__CC-MAIN-20150728002306-00031-ip-10-236-191-2.ec2.internal__523.csv │ ├── 1438042988051.33__CC-MAIN-20150728002308-00108-ip-10-236-191-2.ec2.internal__614.csv │ ├── 1438042988065.26__CC-MAIN-20150728002308-00287-ip-10-236-191-2.ec2.internal__1557.csv │ ├── 1438042990123.20__CC-MAIN-20150728002310-00184-ip-10-236-191-2.ec2.internal__2231.csv │ ├── 1438042989234.2__CC-MAIN-20150728002309-00204-ip-10-236-191-2.ec2.internal__253.csv │ ├── 1438042989331.34__CC-MAIN-20150728002309-00143-ip-10-236-191-2.ec2.internal__1055.csv │ ├── 1438042986423.95__CC-MAIN-20150728002306-00337-ip-10-236-191-2.ec2.internal__484.csv │ ├── 1438042986615.83__CC-MAIN-20150728002306-00084-ip-10-236-191-2.ec2.internal__747.csv │ ├── 1438042990603.54__CC-MAIN-20150728002310-00257-ip-10-236-191-2.ec2.internal__130.csv │ ├── 1438042987174.71__CC-MAIN-20150728002307-00249-ip-10-236-191-2.ec2.internal__1312.csv │ ├── 1438042988930.94__CC-MAIN-20150728002308-00013-ip-10-236-191-2.ec2.internal__1079.csv │ ├── 1438043062723.96__CC-MAIN-20150728002422-00214-ip-10-236-191-2.ec2.internal__833.csv │ ├── 1438042988311.72__CC-MAIN-20150728002308-00230-ip-10-236-191-2.ec2.internal__1981.csv │ ├── 1438042990112.92__CC-MAIN-20150728002310-00222-ip-10-236-191-2.ec2.internal__22.csv │ ├── 1438042989142.82__CC-MAIN-20150728002309-00099-ip-10-236-191-2.ec2.internal__2068.csv │ ├── 1438042991076.30__CC-MAIN-20150728002311-00254-ip-10-236-191-2.ec2.internal__35.csv │ ├── 1438042982502.13__CC-MAIN-20150728002302-00239-ip-10-236-191-2.ec2.internal__685.csv │ ├── 1438042986148.56__CC-MAIN-20150728002306-00235-ip-10-236-191-2.ec2.internal__1751.csv │ ├── 1438042988930.94__CC-MAIN-20150728002308-00259-ip-10-236-191-2.ec2.internal__1515.csv │ ├── 1438042989897.84__CC-MAIN-20150728002309-00300-ip-10-236-191-2.ec2.internal__309.csv │ ├── 1438042987155.85__CC-MAIN-20150728002307-00318-ip-10-236-191-2.ec2.internal__2644.csv │ ├── 1438042989331.34__CC-MAIN-20150728002309-00335-ip-10-236-191-2.ec2.internal__2086.csv │ ├── 1438042992201.62__CC-MAIN-20150728002312-00292-ip-10-236-191-2.ec2.internal__2128.csv │ ├── 1438042990112.50__CC-MAIN-20150728002310-00124-ip-10-236-191-2.ec2.internal__1282.csv │ ├── 1438042988250.59__CC-MAIN-20150728002308-00240-ip-10-236-191-2.ec2.internal__817.csv │ ├── 1438042986423.95__CC-MAIN-20150728002306-00124-ip-10-236-191-2.ec2.internal__1089.csv │ ├── 1438042989018.48__CC-MAIN-20150728002309-00040-ip-10-236-191-2.ec2.internal__1358.csv │ ├── 1438042989331.34__CC-MAIN-20150728002309-00246-ip-10-236-191-2.ec2.internal__1255.csv │ ├── 1438042990217.27__CC-MAIN-20150728002310-00075-ip-10-236-191-2.ec2.internal__1439.csv │ ├── 1438042985647.51__CC-MAIN-20150728002305-00269-ip-10-236-191-2.ec2.internal__1236.csv │ └── 1438042989234.2__CC-MAIN-20150728002309-00282-ip-10-236-191-2.ec2.internal__1016.csv │ ├── train_csv │ ├── 1438043058631.99__CC-MAIN-20150728002418-00261-ip-10-236-191-2.ec2.internal__2006.csv │ ├── 1438042988458.74__CC-MAIN-20150728002308-00212-ip-10-236-191-2.ec2.internal__1724.csv │ ├── 1438042987628.47__CC-MAIN-20150728002307-00145-ip-10-236-191-2.ec2.internal__1041.csv │ ├── 1438042986451.45__CC-MAIN-20150728002306-00067-ip-10-236-191-2.ec2.internal__128.csv │ ├── 1438042989018.40__CC-MAIN-20150728002309-00123-ip-10-236-191-2.ec2.internal__2275.csv │ ├── 1438042986615.83__CC-MAIN-20150728002306-00051-ip-10-236-191-2.ec2.internal__1024.csv │ ├── 1438042987127.36__CC-MAIN-20150728002307-00141-ip-10-236-191-2.ec2.internal__156.csv │ ├── 1438043062635.98__CC-MAIN-20150728002422-00203-ip-10-236-191-2.ec2.internal__1734.csv │ ├── 1438042990900.28__CC-MAIN-20150728002310-00251-ip-10-236-191-2.ec2.internal__2279.csv │ ├── 1438042988860.4__CC-MAIN-20150728002308-00197-ip-10-236-191-2.ec2.internal__2236.csv │ ├── 1438043062635.98__CC-MAIN-20150728002422-00266-ip-10-236-191-2.ec2.internal__1392.csv │ ├── 1438042987228.91__CC-MAIN-20150728002307-00122-ip-10-236-191-2.ec2.internal__88.csv │ ├── 1438042987628.47__CC-MAIN-20150728002307-00125-ip-10-236-191-2.ec2.internal__980.csv │ ├── 1438042988250.59__CC-MAIN-20150728002308-00009-ip-10-236-191-2.ec2.internal__1805.csv │ ├── 1438042989891.18__CC-MAIN-20150728002309-00110-ip-10-236-191-2.ec2.internal__1467.csv │ ├── 1438042990217.27__CC-MAIN-20150728002310-00130-ip-10-236-191-2.ec2.internal__376.csv │ ├── 1438042986615.83__CC-MAIN-20150728002306-00215-ip-10-236-191-2.ec2.internal__1920.csv │ ├── 1438042988061.16__CC-MAIN-20150728002308-00120-ip-10-236-191-2.ec2.internal__883.csv │ ├── 1438042988650.6__CC-MAIN-20150728002308-00014-ip-10-236-191-2.ec2.internal__1639.csv │ ├── 1438042987034.19__CC-MAIN-20150728002307-00101-ip-10-236-191-2.ec2.internal__2095.csv │ ├── 1438042988399.65__CC-MAIN-20150728002308-00127-ip-10-236-191-2.ec2.internal__1207.csv │ ├── 1438042985647.51__CC-MAIN-20150728002305-00318-ip-10-236-191-2.ec2.internal__105.csv │ ├── 1438042990112.92__CC-MAIN-20150728002310-00030-ip-10-236-191-2.ec2.internal__954.csv │ ├── 1438042990217.27__CC-MAIN-20150728002310-00111-ip-10-236-191-2.ec2.internal__2531.csv │ ├── 1438042981460.12__CC-MAIN-20150728002301-00003-ip-10-236-191-2.ec2.internal__1387.csv │ ├── 1438042988924.75__CC-MAIN-20150728002308-00052-ip-10-236-191-2.ec2.internal__2363.csv │ ├── 1438042989507.42__CC-MAIN-20150728002309-00199-ip-10-236-191-2.ec2.internal__2601.csv │ ├── 1438042989826.86__CC-MAIN-20150728002309-00046-ip-10-236-191-2.ec2.internal__1968.csv │ ├── 1438042988051.33__CC-MAIN-20150728002308-00270-ip-10-236-191-2.ec2.internal__770.csv │ ├── 1438042991019.80__CC-MAIN-20150728002311-00109-ip-10-236-191-2.ec2.internal__710.csv │ ├── 1438042987402.78__CC-MAIN-20150728002307-00143-ip-10-236-191-2.ec2.internal__1993.csv │ ├── 1438042989042.37__CC-MAIN-20150728002309-00074-ip-10-236-191-2.ec2.internal__2439.csv │ ├── 1438042989018.40__CC-MAIN-20150728002309-00178-ip-10-236-191-2.ec2.internal__1420.csv │ ├── 1438042989331.34__CC-MAIN-20150728002309-00098-ip-10-236-191-2.ec2.internal__350.csv │ ├── 1438042987775.70__CC-MAIN-20150728002307-00015-ip-10-236-191-2.ec2.internal__437.csv │ ├── 1438042988650.6__CC-MAIN-20150728002308-00168-ip-10-236-191-2.ec2.internal__2261.csv │ ├── 1438042987228.91__CC-MAIN-20150728002307-00306-ip-10-236-191-2.ec2.internal__1005.csv │ ├── 1438043062635.98__CC-MAIN-20150728002422-00195-ip-10-236-191-2.ec2.internal__742.csv │ ├── 1438042988051.33__CC-MAIN-20150728002308-00259-ip-10-236-191-2.ec2.internal__541.csv │ ├── 1438042989510.73__CC-MAIN-20150728002309-00063-ip-10-236-191-2.ec2.internal__1159.csv │ ├── 1438042981856.5__CC-MAIN-20150728002301-00062-ip-10-236-191-2.ec2.internal__1831.csv │ ├── 1438042988458.74__CC-MAIN-20150728002308-00210-ip-10-236-191-2.ec2.internal__1149.csv │ ├── 1438042989178.64__CC-MAIN-20150728002309-00150-ip-10-236-191-2.ec2.internal__362.csv │ ├── 1438042981460.12__CC-MAIN-20150728002301-00202-ip-10-236-191-2.ec2.internal__2064.csv │ ├── 1438042988065.26__CC-MAIN-20150728002308-00173-ip-10-236-191-2.ec2.internal__453.csv │ ├── 1438042989234.2__CC-MAIN-20150728002309-00315-ip-10-236-191-2.ec2.internal__200.csv │ ├── 1438042987552.57__CC-MAIN-20150728002307-00259-ip-10-236-191-2.ec2.internal__2423.csv │ ├── 1438042986806.32__CC-MAIN-20150728002306-00163-ip-10-236-191-2.ec2.internal__55.csv │ ├── 1438042988860.88__CC-MAIN-20150728002308-00239-ip-10-236-191-2.ec2.internal__2107.csv │ ├── 1438042988924.75__CC-MAIN-20150728002308-00339-ip-10-236-191-2.ec2.internal__1863.csv │ ├── 1438042988317.67__CC-MAIN-20150728002308-00292-ip-10-236-191-2.ec2.internal__440.csv │ ├── 1438042985647.51__CC-MAIN-20150728002305-00301-ip-10-236-191-2.ec2.internal__2228.csv │ ├── 1438042990217.27__CC-MAIN-20150728002310-00064-ip-10-236-191-2.ec2.internal__1370.csv │ ├── 1438042987866.61__CC-MAIN-20150728002307-00252-ip-10-236-191-2.ec2.internal__1295.csv │ ├── 1438042990112.92__CC-MAIN-20150728002310-00240-ip-10-236-191-2.ec2.internal__1247.csv │ ├── 1438043058631.99__CC-MAIN-20150728002418-00126-ip-10-236-191-2.ec2.internal__1329.csv │ └── 1438042988317.67__CC-MAIN-20150728002308-00033-ip-10-236-191-2.ec2.internal__2355.csv │ └── valid_csv │ ├── 1438042988650.6__CC-MAIN-20150728002308-00203-ip-10-236-191-2.ec2.internal__1883.csv │ ├── 1438042990112.92__CC-MAIN-20150728002310-00244-ip-10-236-191-2.ec2.internal__470.csv │ ├── 1438043060830.93__CC-MAIN-20150728002420-00057-ip-10-236-191-2.ec2.internal__1060.csv │ ├── 1438042986806.32__CC-MAIN-20150728002306-00126-ip-10-236-191-2.ec2.internal__1540.csv │ ├── 1438042985140.15__CC-MAIN-20150728002305-00339-ip-10-236-191-2.ec2.internal__723.csv │ ├── 1438042987552.57__CC-MAIN-20150728002307-00229-ip-10-236-191-2.ec2.internal__1750.csv │ ├── 1438042989178.64__CC-MAIN-20150728002309-00069-ip-10-236-191-2.ec2.internal__120.csv │ ├── 1438042988048.90__CC-MAIN-20150728002308-00213-ip-10-236-191-2.ec2.internal__784.csv │ ├── 1438042987155.85__CC-MAIN-20150728002307-00006-ip-10-236-191-2.ec2.internal__1038.csv │ ├── 1438042987628.47__CC-MAIN-20150728002307-00335-ip-10-236-191-2.ec2.internal__1368.csv │ ├── 1438042988840.31__CC-MAIN-20150728002308-00067-ip-10-236-191-2.ec2.internal__1817.csv │ ├── 1438042989126.22__CC-MAIN-20150728002309-00181-ip-10-236-191-2.ec2.internal__1685.csv │ ├── 1438042988065.26__CC-MAIN-20150728002308-00076-ip-10-236-191-2.ec2.internal__1719.csv │ ├── 1438042988840.31__CC-MAIN-20150728002308-00310-ip-10-236-191-2.ec2.internal__630.csv │ ├── 1438042992201.62__CC-MAIN-20150728002312-00098-ip-10-236-191-2.ec2.internal__1505.csv │ ├── 1438042986444.39__CC-MAIN-20150728002306-00060-ip-10-236-191-2.ec2.internal__549.csv │ ├── 1438042989897.84__CC-MAIN-20150728002309-00095-ip-10-236-191-2.ec2.internal__1199.csv │ ├── 1438042988650.6__CC-MAIN-20150728002308-00126-ip-10-236-191-2.ec2.internal__477.csv │ ├── 1438042986444.39__CC-MAIN-20150728002306-00217-ip-10-236-191-2.ec2.internal__2206.csv │ ├── 1438042989790.89__CC-MAIN-20150728002309-00266-ip-10-236-191-2.ec2.internal__593.csv │ ├── 1438042985140.15__CC-MAIN-20150728002305-00141-ip-10-236-191-2.ec2.internal__886.csv │ ├── 1438042989018.40__CC-MAIN-20150728002309-00317-ip-10-236-191-2.ec2.internal__2.csv │ ├── 1438042985140.15__CC-MAIN-20150728002305-00185-ip-10-236-191-2.ec2.internal__576.csv │ ├── 1438042986444.39__CC-MAIN-20150728002306-00119-ip-10-236-191-2.ec2.internal__2126.csv │ ├── 1438042982502.13__CC-MAIN-20150728002302-00303-ip-10-236-191-2.ec2.internal__551.csv │ ├── 1438042986615.83__CC-MAIN-20150728002306-00049-ip-10-236-191-2.ec2.internal__1859.csv │ ├── 1438042988312.76__CC-MAIN-20150728002308-00140-ip-10-236-191-2.ec2.internal__1485.csv │ ├── 1438042987228.91__CC-MAIN-20150728002307-00257-ip-10-236-191-2.ec2.internal__622.csv │ ├── 1438042988962.66__CC-MAIN-20150728002308-00231-ip-10-236-191-2.ec2.internal__1481.csv │ ├── 1438042986806.32__CC-MAIN-20150728002306-00042-ip-10-236-191-2.ec2.internal__367.csv │ ├── 1438042988061.16__CC-MAIN-20150728002308-00295-ip-10-236-191-2.ec2.internal__1098.csv │ ├── 1438042989142.82__CC-MAIN-20150728002309-00287-ip-10-236-191-2.ec2.internal__1807.csv │ ├── 1438042987127.36__CC-MAIN-20150728002307-00308-ip-10-236-191-2.ec2.internal__1005.csv │ ├── 1438042986806.32__CC-MAIN-20150728002306-00186-ip-10-236-191-2.ec2.internal__960.csv │ ├── 1438042988840.31__CC-MAIN-20150728002308-00323-ip-10-236-191-2.ec2.internal__634.csv │ ├── 1438042990177.43__CC-MAIN-20150728002310-00003-ip-10-236-191-2.ec2.internal__2195.csv │ ├── 1438042987228.91__CC-MAIN-20150728002307-00319-ip-10-236-191-2.ec2.internal__1580.csv │ ├── 1438042988308.23__CC-MAIN-20150728002308-00218-ip-10-236-191-2.ec2.internal__2226.csv │ ├── 1438043058631.99__CC-MAIN-20150728002418-00210-ip-10-236-191-2.ec2.internal__769.csv │ ├── 1438042986357.49__CC-MAIN-20150728002306-00316-ip-10-236-191-2.ec2.internal__2351.csv │ ├── 1438042987135.9__CC-MAIN-20150728002307-00175-ip-10-236-191-2.ec2.internal__1018.csv │ ├── 1438042988860.88__CC-MAIN-20150728002308-00188-ip-10-236-191-2.ec2.internal__18.csv │ ├── 1438042988311.72__CC-MAIN-20150728002308-00175-ip-10-236-191-2.ec2.internal__1284.csv │ ├── 1438042988924.75__CC-MAIN-20150728002308-00019-ip-10-236-191-2.ec2.internal__1335.csv │ ├── 1438042986451.45__CC-MAIN-20150728002306-00229-ip-10-236-191-2.ec2.internal__463.csv │ └── 1438042988048.90__CC-MAIN-20150728002308-00117-ip-10-236-191-2.ec2.internal__1172.csv ├── exp ├── ft_cell │ ├── cell.yml │ └── cell_pred.yml ├── ft_col │ └── col.yml ├── ft_table │ ├── table.yml │ └── table_pred.yml ├── ext_feat │ └── ext_feat.yml └── pretrain │ ├── 26600K_freq.yml │ └── 26600K_mix.yml └── env └── env.yml /model/.keep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /out/.keep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /table_embedder/models/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /table_embedder/models/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /table_embedder/readers/lib/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /data/clscol.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SFIG611/tabbie/HEAD/data/clscol.npy -------------------------------------------------------------------------------- /data/clsrow.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SFIG611/tabbie/HEAD/data/clsrow.npy -------------------------------------------------------------------------------- /table_embedder/predictors/__init__.py: -------------------------------------------------------------------------------- 1 | # from .t2d_predictor import T2DPredictor 2 | 3 | -------------------------------------------------------------------------------- /table_embedder/readers/epoch_callbacks/__init__.py: -------------------------------------------------------------------------------- 1 | # from .t2d_predictor import T2DPredictor 2 | 3 | -------------------------------------------------------------------------------- /exp/ft_cell/cell.yml: -------------------------------------------------------------------------------- 1 | 2 | model_path: ./model/freq.tar.gz 3 | clscol_path: ./data/clscol.npy 4 | clsrow_path: ./data/clsrow.npy 5 | 6 | 7 | -------------------------------------------------------------------------------- /exp/ft_col/col.yml: -------------------------------------------------------------------------------- 1 | 2 | model_path: ./model/freq.tar.gz 3 | clscol_path: ./data/clscol.npy 4 | clsrow_path: ./data/clsrow.npy 5 | 6 | 7 | -------------------------------------------------------------------------------- /exp/ft_table/table.yml: -------------------------------------------------------------------------------- 1 | 2 | model_path: ./model/freq.tar.gz 3 | clscol_path: ./data/clscol.npy 4 | clsrow_path: ./data/clsrow.npy 5 | 6 | 7 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042988399.65__CC-MAIN-20150728002308-00257-ip-10-236-191-2.ec2.internal__2153.csv: -------------------------------------------------------------------------------- 1 | ,expert,grid,height 2 | sf,10%,0%,10% 3 | den,2,0,2 4 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042988399.65__CC-MAIN-20150728002308-00257-ip-10-236-191-2.ec2.internal__2153.csv: -------------------------------------------------------------------------------- 1 | ,expert,novice,total 2 | sf,10%,0%,10% 3 | den,2,0,2 4 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438043058631.99__CC-MAIN-20150728002418-00261-ip-10-236-191-2.ec2.internal__2006.csv: -------------------------------------------------------------------------------- 1 | ,expert,novice,total 2 | sf,0%,100%,100% 3 | den,0,1,1 4 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042988650.6__CC-MAIN-20150728002308-00203-ip-10-236-191-2.ec2.internal__1883.csv: -------------------------------------------------------------------------------- 1 | ,expert,novice,total 2 | sf,0%,50%,16.7% 3 | den,0,1,1 4 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438043058631.99__CC-MAIN-20150728002418-00261-ip-10-236-191-2.ec2.internal__2006.csv: -------------------------------------------------------------------------------- 1 | ,expert,novice,total 2 | sf,0%,100%,100% 3 | den,0,1,1 4 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042988650.6__CC-MAIN-20150728002308-00203-ip-10-236-191-2.ec2.internal__1883.csv: -------------------------------------------------------------------------------- 1 | ,expert,novice,nfl club 2 | sf,0%,50%,16.7% 3 | den,0,1,1 4 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042988399.65__CC-MAIN-20150728002308-00257-ip-10-236-191-2.ec2.internal__2153.csv: -------------------------------------------------------------------------------- 1 | ,expert,novice,total 2 | sf,10%,0%,10% 3 | den,2,0,2 4 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438043058631.99__CC-MAIN-20150728002418-00261-ip-10-236-191-2.ec2.internal__2006.csv: -------------------------------------------------------------------------------- 1 | ,expert,novice,total 2 | sf,0%,100%,100% 3 | den,0,1,1 4 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042988650.6__CC-MAIN-20150728002308-00203-ip-10-236-191-2.ec2.internal__1883.csv: -------------------------------------------------------------------------------- 1 | ,expert,novice,total 2 | sf,0%,50%,16.7% 3 | den,0,1,1 4 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042990609.0__CC-MAIN-20150728002310-00065-ip-10-236-191-2.ec2.internal__2037.csv: -------------------------------------------------------------------------------- 1 | ,expert,novice,total 2 | sf,14.3%,2,9.1% 3 | den,1,3.2%,1.2 4 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042991076.30__CC-MAIN-20150728002311-00041-ip-10-236-191-2.ec2.internal__1901.csv: -------------------------------------------------------------------------------- 1 | ,expert,novice,total 2 | sf,0%,63.6%,63.6% 3 | 0,den,2.7,2.7 4 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042988458.74__CC-MAIN-20150728002308-00212-ip-10-236-191-2.ec2.internal__1724.csv: -------------------------------------------------------------------------------- 1 | ,expert,novice,total 2 | sf,100%,100%,100% 3 | den,3,4,3.3 4 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042990112.92__CC-MAIN-20150728002310-00244-ip-10-236-191-2.ec2.internal__470.csv: -------------------------------------------------------------------------------- 1 | service,map,satellite 2 | emaps.bg,map, 3 | 360.bg,,satellite 4 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438043060830.93__CC-MAIN-20150728002420-00057-ip-10-236-191-2.ec2.internal__1060.csv: -------------------------------------------------------------------------------- 1 | fouls,1,2,total 2 | linfield,25,48,40 3 | george fox,6,16,22 4 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042990609.0__CC-MAIN-20150728002310-00065-ip-10-236-191-2.ec2.internal__2037.csv: -------------------------------------------------------------------------------- 1 | ,expert,novice,total 2 | sf,14.3%,3.2%,9.1% 3 | den,1,2,1.2 4 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042991076.30__CC-MAIN-20150728002311-00041-ip-10-236-191-2.ec2.internal__1901.csv: -------------------------------------------------------------------------------- 1 | ,expert,novice,total 2 | sf,0%,63.6%,63.6% 3 | den,0,2.7,2.7 4 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042988458.74__CC-MAIN-20150728002308-00212-ip-10-236-191-2.ec2.internal__1724.csv: -------------------------------------------------------------------------------- 1 | ,expert,novice,total 2 | sf,100%,100%,100% 3 | den,3,4,3.3 4 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438043060830.93__CC-MAIN-20150728002420-00057-ip-10-236-191-2.ec2.internal__1060.csv: -------------------------------------------------------------------------------- 1 | fouls,1,2,total 2 | linfield,25,15,40 3 | george fox,6,16,22 4 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042990609.0__CC-MAIN-20150728002310-00065-ip-10-236-191-2.ec2.internal__2037.csv: -------------------------------------------------------------------------------- 1 | ,expert,novice,total 2 | sf,14.3%,3.2%,9.1% 3 | den,1,2,1.2 4 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042991076.30__CC-MAIN-20150728002311-00041-ip-10-236-191-2.ec2.internal__1901.csv: -------------------------------------------------------------------------------- 1 | ,expert,novice,total 2 | sf,0%,63.6%,63.6% 3 | den,0,2.7,2.7 4 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042988458.74__CC-MAIN-20150728002308-00212-ip-10-236-191-2.ec2.internal__1724.csv: -------------------------------------------------------------------------------- 1 | ,expert,novice,total 2 | sf,100%,100%,100% 3 | den,3,4,3.3 4 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042987628.47__CC-MAIN-20150728002307-00145-ip-10-236-191-2.ec2.internal__1041.csv: -------------------------------------------------------------------------------- 1 | draw controls,1,2,total 2 | sunyit,5,7,12 3 | cazenovia,9,7,16 4 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042987628.47__CC-MAIN-20150728002307-00145-ip-10-236-191-2.ec2.internal__1041.csv: -------------------------------------------------------------------------------- 1 | draw controls,1,2,total 2 | sunyit,5,7,12 3 | cazenovia,9,7,16 4 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042990112.92__CC-MAIN-20150728002310-00244-ip-10-236-191-2.ec2.internal__470.csv: -------------------------------------------------------------------------------- 1 | service,map,satellite 2 | emaps.bg,map, 3 | 360.bg,,satellite 4 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438043060830.93__CC-MAIN-20150728002420-00057-ip-10-236-191-2.ec2.internal__1060.csv: -------------------------------------------------------------------------------- 1 | fouls,1,2,total 2 | linfield,25,15,40 3 | george fox,6,16,22 4 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042986451.45__CC-MAIN-20150728002306-00067-ip-10-236-191-2.ec2.internal__128.csv: -------------------------------------------------------------------------------- 1 | name,, 2 | moonflower market,moab,435-259-5712 3 | utah co-op,murray, 4 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042986806.32__CC-MAIN-20150728002306-00126-ip-10-236-191-2.ec2.internal__1540.csv: -------------------------------------------------------------------------------- 1 | quantity,list price 2 | 1 - 25,$3.09 3 | 26 - 99,$2.81 4 | 100+,$2.55 5 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042986451.45__CC-MAIN-20150728002306-00067-ip-10-236-191-2.ec2.internal__128.csv: -------------------------------------------------------------------------------- 1 | name,, 2 | moonflower market,moab,435-259-5712 3 | utah co-op,murray, 4 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042987628.47__CC-MAIN-20150728002307-00145-ip-10-236-191-2.ec2.internal__1041.csv: -------------------------------------------------------------------------------- 1 | draw controls,1,points,total 2 | sunyit,5,7,12 3 | cazenovia,9,7,16 4 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042986806.32__CC-MAIN-20150728002306-00126-ip-10-236-191-2.ec2.internal__1540.csv: -------------------------------------------------------------------------------- 1 | quantity,list price 2 | 1 - 25,$3.09 3 | 26 - 99,$2.81 4 | 100+,$2.55 5 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042990112.92__CC-MAIN-20150728002310-00244-ip-10-236-191-2.ec2.internal__470.csv: -------------------------------------------------------------------------------- 1 | hollister (sized),map,satellite 2 | emaps.bg,map, 3 | 360.bg,,satellite 4 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042986451.45__CC-MAIN-20150728002306-00067-ip-10-236-191-2.ec2.internal__128.csv: -------------------------------------------------------------------------------- 1 | name,, 2 | moonflower market,moab,435-259-5712 3 | utah co-op,murray, 4 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042986806.32__CC-MAIN-20150728002306-00126-ip-10-236-191-2.ec2.internal__1540.csv: -------------------------------------------------------------------------------- 1 | quantity,list price 2 | 1 - 25,$3.09 3 | 26 - 99,$2.81 4 | 100+,$2.55 5 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438043060830.93__CC-MAIN-20150728002420-00072-ip-10-236-191-2.ec2.internal__1045.csv: -------------------------------------------------------------------------------- 1 | runs short,,runs long 2 | runs narrow,,runs wide 3 | not comfy,,very comfy 4 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042990112.50__CC-MAIN-20150728002310-00303-ip-10-236-191-2.ec2.internal__1888.csv: -------------------------------------------------------------------------------- 1 | 4,,died:, 2 | born:,,cause of death:, 3 | birth place:,,profession:,cast ... 4 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438043060830.93__CC-MAIN-20150728002420-00072-ip-10-236-191-2.ec2.internal__1045.csv: -------------------------------------------------------------------------------- 1 | runs short,,runs long 2 | runs narrow,,runs wide 3 | not comfy,,very comfy 4 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438043060830.93__CC-MAIN-20150728002420-00072-ip-10-236-191-2.ec2.internal__1045.csv: -------------------------------------------------------------------------------- 1 | runs short,,runs long 2 | runs narrow,,runs wide 3 | not comfy,,very comfy 4 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042988308.23__CC-MAIN-20150728002308-00294-ip-10-236-191-2.ec2.internal__2445.csv: -------------------------------------------------------------------------------- 1 | type,1 bed,2 bed,3 bed,4 bed 2 | houses,-,2,1,1 3 | flats,-,-,-,- 4 | all,1,2,1,- 5 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438043062635.98__CC-MAIN-20150728002422-00203-ip-10-236-191-2.ec2.internal__1734.csv: -------------------------------------------------------------------------------- 1 | ,, 2 | small greeting card,12–6,postcard 3 | "4"" x 6""",tobie matthew,113662 - 4 | -------------------------------------------------------------------------------- /table_embedder/__init__.py: -------------------------------------------------------------------------------- 1 | # pylint: disable=wildcard-import 2 | from table_embedder.readers import * 3 | from table_embedder.models import * 4 | from table_embedder.predictors import * 5 | -------------------------------------------------------------------------------- /table_embedder/readers/__init__.py: -------------------------------------------------------------------------------- 1 | # from allennlp.data.token_indexers.single_id_token_indexer import SingleIdTokenIndexer 2 | # from lib.single_id_token_indexer import SingleIdTokenIndexer 3 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042981921.1__CC-MAIN-20150728002301-00294-ip-10-236-191-2.ec2.internal__444.csv: -------------------------------------------------------------------------------- 1 | goalies:,w,l,ot,sv%,gaa 2 | j. halak,38,17,8,.914,2.43 3 | c. johnson,8,4,1,.889,3.08 4 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042985140.15__CC-MAIN-20150728002305-00339-ip-10-236-191-2.ec2.internal__723.csv: -------------------------------------------------------------------------------- 1 | ,today,normal,record,7/29/2014 2 | high,30â°,35â°,n/a,32â° 3 | low,48â°,18â°,n/a,20â° 4 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042987552.57__CC-MAIN-20150728002307-00229-ip-10-236-191-2.ec2.internal__1750.csv: -------------------------------------------------------------------------------- 1 | qty,store,section 2 | 3,beaverton,mystery- a to z 3 | 1,hawthorne,mystery- a to z 4 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042989178.64__CC-MAIN-20150728002309-00069-ip-10-236-191-2.ec2.internal__120.csv: -------------------------------------------------------------------------------- 1 | passing,c-a,yds,td,int 2 | jimmy stainback,16-20,234,2,0 3 | joseph moultrie,1-1,1,0,0 4 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042988308.23__CC-MAIN-20150728002308-00294-ip-10-236-191-2.ec2.internal__2445.csv: -------------------------------------------------------------------------------- 1 | type,1 bed,2 bed,location,4 bed 2 | houses,-,2,1,1 3 | flats,-,-,-,- 4 | all,-,2,1,1 5 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042985140.15__CC-MAIN-20150728002305-00339-ip-10-236-191-2.ec2.internal__723.csv: -------------------------------------------------------------------------------- 1 | ,today,normal,record,7/29/2014 2 | high,48â°,35â°,n/a,32â° 3 | low,30â°,18â°,n/a,20â° 4 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042981921.1__CC-MAIN-20150728002301-00294-ip-10-236-191-2.ec2.internal__444.csv: -------------------------------------------------------------------------------- 1 | goalies:,w,l,ot,sv%,gaa 2 | j. halak,38,17,4,.914,2.43 3 | c. johnson,8,8,1,.889,3.08 4 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042988308.23__CC-MAIN-20150728002308-00294-ip-10-236-191-2.ec2.internal__2445.csv: -------------------------------------------------------------------------------- 1 | type,1 bed,2 bed,3 bed,4 bed 2 | houses,-,2,1,1 3 | flats,-,-,-,- 4 | all,-,2,1,1 5 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042985140.15__CC-MAIN-20150728002305-00339-ip-10-236-191-2.ec2.internal__723.csv: -------------------------------------------------------------------------------- 1 | ,today,normal,record,7/29/2014 2 | high,48â°,35â°,n/a,32â° 3 | low,30â°,18â°,n/a,20â° 4 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042987552.57__CC-MAIN-20150728002307-00229-ip-10-236-191-2.ec2.internal__1750.csv: -------------------------------------------------------------------------------- 1 | qty,store,section 2 | 3,beaverton,mystery- a to z 3 | 1,hawthorne,mystery- a to z 4 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042990112.50__CC-MAIN-20150728002310-00303-ip-10-236-191-2.ec2.internal__1888.csv: -------------------------------------------------------------------------------- 1 | also known as:,,died:, 2 | cause of death:,,born:, 3 | birth place:,,profession:,cast ... 4 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042989018.40__CC-MAIN-20150728002309-00123-ip-10-236-191-2.ec2.internal__2275.csv: -------------------------------------------------------------------------------- 1 | pos,dog,sp 2 | 1st,1 astrum,6/4 f 3 | 1st,5 whitefoot rosy,9/4 4 | 3rd,3 swift dublin,7/4 5 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042981921.1__CC-MAIN-20150728002301-00294-ip-10-236-191-2.ec2.internal__444.csv: -------------------------------------------------------------------------------- 1 | goalies:,w,decided,ot,sv%,gaa 2 | j. halak,38,17,4,.914,2.43 3 | c. johnson,8,8,1,.889,3.08 4 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042989018.40__CC-MAIN-20150728002309-00123-ip-10-236-191-2.ec2.internal__2275.csv: -------------------------------------------------------------------------------- 1 | pos,dog,sp 2 | 1st,1 astrum,6/4 f 3 | 1st,5 whitefoot rosy,9/4 4 | 3rd,3 swift dublin,7/4 5 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042987552.57__CC-MAIN-20150728002307-00229-ip-10-236-191-2.ec2.internal__1750.csv: -------------------------------------------------------------------------------- 1 | qty,description,section 2 | 3,beaverton,mystery- a to z 3 | 1,hawthorne,mystery- a to z 4 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042990112.50__CC-MAIN-20150728002310-00303-ip-10-236-191-2.ec2.internal__1888.csv: -------------------------------------------------------------------------------- 1 | also known as:,,died:, 2 | born:,,cause of death:, 3 | birth place:,,profession:,cast ... 4 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042989018.40__CC-MAIN-20150728002309-00123-ip-10-236-191-2.ec2.internal__2275.csv: -------------------------------------------------------------------------------- 1 | pos,dog,sp 2 | 1st,1 astrum,6/4 f 3 | 1st,5 whitefoot rosy,9/4 4 | 3rd,3 swift dublin,7/4 5 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042989178.64__CC-MAIN-20150728002309-00069-ip-10-236-191-2.ec2.internal__120.csv: -------------------------------------------------------------------------------- 1 | passing,c-a,yds,td,int 2 | jimmy stainback,16-20,234,2,0 3 | joseph moultrie,1-1,1,0,0 4 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042986615.83__CC-MAIN-20150728002306-00051-ip-10-236-191-2.ec2.internal__1024.csv: -------------------------------------------------------------------------------- 1 | kickoff returns,no,yds,avg,lg,td 2 | mike adams,3,55,18.3,32,0 3 | daniel ricci,1,12,12.0,12,0 4 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042989178.64__CC-MAIN-20150728002309-00069-ip-10-236-191-2.ec2.internal__120.csv: -------------------------------------------------------------------------------- 1 | passing,c-a,yds,td,ports of call 2 | jimmy stainback,16-20,234,2,0 3 | joseph moultrie,1-1,1,0,0 4 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042986615.83__CC-MAIN-20150728002306-00051-ip-10-236-191-2.ec2.internal__1024.csv: -------------------------------------------------------------------------------- 1 | kickoff returns,no,yds,avg,lg,td 2 | mike adams,3,55,18.3,32,0 3 | daniel ricci,1,12,12.0,12,0 4 | -------------------------------------------------------------------------------- /exp/ft_table/table_pred.yml: -------------------------------------------------------------------------------- 1 | 2 | learn_type: 'pred' 3 | batch_size: '1' 4 | cuda_devices: [0] 5 | clscol_path: ./data/clscol.npy 6 | clsrow_path: ./data/clsrow.npy 7 | out_dir: ./data/ft_cell/debug 8 | 9 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042987127.36__CC-MAIN-20150728002307-00141-ip-10-236-191-2.ec2.internal__156.csv: -------------------------------------------------------------------------------- 1 | interception returns,no,yds,avg,lg,td 2 | casey dillon,1,33,33.0,33,0 3 | frank ruopoli,1,9,9.0,9,0 4 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042982502.13__CC-MAIN-20150728002302-00111-ip-10-236-191-2.ec2.internal__1274.csv: -------------------------------------------------------------------------------- 1 | transmission,hollister (waist - in),noveno dã­gito 2 | s/m,29 - 31,74 - 79 3 | l/xl,32 - 34,81 - 86 4 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042987127.36__CC-MAIN-20150728002307-00141-ip-10-236-191-2.ec2.internal__156.csv: -------------------------------------------------------------------------------- 1 | aslı çakır alptekin,no,yds,avg,lg,td 2 | casey dillon,1,33,33.0,33,0 3 | frank ruopoli,1,9,9.0,9,0 4 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438043062635.98__CC-MAIN-20150728002422-00203-ip-10-236-191-2.ec2.internal__1734.csv: -------------------------------------------------------------------------------- 1 | ,, 2 | small greeting card,large greeting card,postcard 3 | "4"" x 6""","5"" x 7.5""","4"" x 6""" 4 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042988048.90__CC-MAIN-20150728002308-00213-ip-10-236-191-2.ec2.internal__784.csv: -------------------------------------------------------------------------------- 1 | ,today,normal,record,8/27/2014 2 | high,93â°,91â°,105â° (1943),94â° 3 | low,72â°,70â°,57â° (1958),68â° 4 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042987127.36__CC-MAIN-20150728002307-00141-ip-10-236-191-2.ec2.internal__156.csv: -------------------------------------------------------------------------------- 1 | interception returns,no,yds,avg,lg,td 2 | casey dillon,1,33,33.0,33,0 3 | frank ruopoli,1,9,9.0,9,0 4 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438043062635.98__CC-MAIN-20150728002422-00203-ip-10-236-191-2.ec2.internal__1734.csv: -------------------------------------------------------------------------------- 1 | ,, 2 | small greeting card,large greeting card,postcard 3 | "4"" x 6""","5"" x 7.5""","4"" x 6""" 4 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042988048.90__CC-MAIN-20150728002308-00213-ip-10-236-191-2.ec2.internal__784.csv: -------------------------------------------------------------------------------- 1 | ,today,normal,record,8/27/2014 2 | high,93â°,91â°,105â° (1943),94â° 3 | low,72â°,70â°,57â° (1958),68â° 4 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042990900.28__CC-MAIN-20150728002310-00070-ip-10-236-191-2.ec2.internal__1337.csv: -------------------------------------------------------------------------------- 1 | time,3,tamil,tuesday,wednesday,thursday,friday,saturday 2 | all day,12,13,14,15,16,17,18 3 | 8:00 am,,,,,,, 4 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042988048.90__CC-MAIN-20150728002308-00213-ip-10-236-191-2.ec2.internal__784.csv: -------------------------------------------------------------------------------- 1 | ,today,normal,record,8/27/2014 2 | high,93â°,91â°,105â° (1943),94â° 3 | low,72â°,70â°,57â° (1958),68â° 4 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042990900.28__CC-MAIN-20150728002310-00251-ip-10-236-191-2.ec2.internal__2279.csv: -------------------------------------------------------------------------------- 1 | date,event,price,source 2 | 05/29/13,sale,"$2,475,000",public records 3 | 02/27/08,sale,$10,public records 4 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042987155.85__CC-MAIN-20150728002307-00006-ip-10-236-191-2.ec2.internal__1038.csv: -------------------------------------------------------------------------------- 1 | year,team,pos,g,gs,pen,penyd 2 | 1997,2tm,wr,13,wr,1,10 3 | 1996,det,9,16,16,--,-- 4 | 1995,det,wr,16,16,--,-- 5 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042989018.48__CC-MAIN-20150728002309-00112-ip-10-236-191-2.ec2.internal__1789.csv: -------------------------------------------------------------------------------- 1 | play type,statewide total 2 | straight,"$20,000" 3 | box,"$28,300" 4 | straight/box,"$20,800" 5 | combo,"$5,000" 6 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042988860.4__CC-MAIN-20150728002308-00197-ip-10-236-191-2.ec2.internal__2236.csv: -------------------------------------------------------------------------------- 1 | title,name,phone,email 2 | coach,,,not available 3 | assistant coach,,,not available 4 | manager,,,not available 5 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042990900.28__CC-MAIN-20150728002310-00251-ip-10-236-191-2.ec2.internal__2279.csv: -------------------------------------------------------------------------------- 1 | result(s),event,born,source 2 | 05/29/13,sale,"$2,475,000",public records 3 | 02/27/08,sale,$10,public records 4 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042990900.28__CC-MAIN-20150728002310-00251-ip-10-236-191-2.ec2.internal__2279.csv: -------------------------------------------------------------------------------- 1 | date,event,price,source 2 | 05/29/13,sale,"$2,475,000",public records 3 | 02/27/08,sale,$10,public records 4 | -------------------------------------------------------------------------------- /exp/ext_feat/ext_feat.yml: -------------------------------------------------------------------------------- 1 | 2 | bs: '5' 3 | max_cell_len: '300' 4 | task_type: 'pred' 5 | dump_emb: '1' 6 | cuda_devices: [2] 7 | clscol_path: ./data/clscol.npy 8 | clsrow_path: ./data/clsrow.npy 9 | 10 | 11 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042989018.48__CC-MAIN-20150728002309-00112-ip-10-236-191-2.ec2.internal__1789.csv: -------------------------------------------------------------------------------- 1 | play type,statewide total 2 | straight,"$20,000" 3 | box,"$28,300" 4 | straight/box,"$20,800" 5 | combo,"$5,000" 6 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042990900.28__CC-MAIN-20150728002310-00070-ip-10-236-191-2.ec2.internal__1337.csv: -------------------------------------------------------------------------------- 1 | time,sunday,monday,tuesday,wednesday,thursday,friday,saturday 2 | 16,12,13,14,15,all day,17,18 3 | 8:00 am,,,,,,, 4 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042986615.83__CC-MAIN-20150728002306-00051-ip-10-236-191-2.ec2.internal__1024.csv: -------------------------------------------------------------------------------- 1 | kickoff returns,no,yds,avg,lg,td 2 | mike adams,3,55,18.3,32,rolling stone 3 | daniel ricci,1,12,12.0,12,$34.00 4 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042988860.4__CC-MAIN-20150728002308-00197-ip-10-236-191-2.ec2.internal__2236.csv: -------------------------------------------------------------------------------- 1 | title,name,phone,email 2 | coach,,,not available 3 | assistant coach,,,not available 4 | manager,,,not available 5 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438043062635.98__CC-MAIN-20150728002422-00266-ip-10-236-191-2.ec2.internal__1392.csv: -------------------------------------------------------------------------------- 1 | size,age,height (in),waist,hip 2 | 2t,2,34.5 - 36.5,21,21 3 | 3t,3,36.5 - 38.5,21.5,22 4 | 4t,4,38.5 - 41.5,22-23,23 5 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042987155.85__CC-MAIN-20150728002307-00006-ip-10-236-191-2.ec2.internal__1038.csv: -------------------------------------------------------------------------------- 1 | year,team,pos,goals,gs,pen,penyd 2 | 1997,2tm,wr,13,9,1,10 3 | 1996,det,wr,16,16,--,-- 4 | 1995,det,wr,16,16,--,-- 5 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042989018.48__CC-MAIN-20150728002309-00112-ip-10-236-191-2.ec2.internal__1789.csv: -------------------------------------------------------------------------------- 1 | play type,statewide total 2 | straight,"$20,000" 3 | box,"$28,300" 4 | straight/box,"$20,800" 5 | combo,"$5,000" 6 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042990900.28__CC-MAIN-20150728002310-00070-ip-10-236-191-2.ec2.internal__1337.csv: -------------------------------------------------------------------------------- 1 | time,sunday,monday,tuesday,wednesday,thursday,friday,saturday 2 | all day,12,13,14,15,16,17,18 3 | 8:00 am,,,,,,, 4 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042988860.4__CC-MAIN-20150728002308-00197-ip-10-236-191-2.ec2.internal__2236.csv: -------------------------------------------------------------------------------- 1 | title,name,phone,email 2 | coach,,,not available 3 | assistant coach,,,not available 4 | manager,,,not available 5 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042987155.85__CC-MAIN-20150728002307-00006-ip-10-236-191-2.ec2.internal__1038.csv: -------------------------------------------------------------------------------- 1 | year,team,pos,g,gs,pen,penyd 2 | 1997,2tm,wr,13,9,1,10 3 | 1996,det,wr,16,16,--,-- 4 | 1995,det,wr,16,16,--,-- 5 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042981753.21__CC-MAIN-20150728002301-00208-ip-10-236-191-2.ec2.internal__1874.csv: -------------------------------------------------------------------------------- 1 | ,tgt,catches,yds,td 2 | dwayne bowe,3,2,17,0 3 | jamaal charles,2,2,1,0 4 | mike cox,2,2,4,0 5 | larry johnson,2,2,1,0 6 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042982502.13__CC-MAIN-20150728002302-00111-ip-10-236-191-2.ec2.internal__1274.csv: -------------------------------------------------------------------------------- 1 | hollister (s - xl),hollister (waist - in),international (waist - cm) 2 | 81 - 86,29 - 31,74 - 79 3 | l/xl,32 - 34,s/m 4 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042986625.58__CC-MAIN-20150728002306-00239-ip-10-236-191-2.ec2.internal__2767.csv: -------------------------------------------------------------------------------- 1 | type,regulations.gov 2 | special conditions no.,2015-07503 3 | rin, 4 | docket no.,faa-2015-0720 5 | fr doc.,23-263-sc 6 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042987155.85__CC-MAIN-20150728002307-00192-ip-10-236-191-2.ec2.internal__2107.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | ,,1,2,3,4,5 3 | 6,7,8,9,10,11,20 4 | 13,14,15,16,17,18,19 5 | 12,21,25,23,24,22,26 6 | 27,28,29,30,31,, 7 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042988962.66__CC-MAIN-20150728002308-00249-ip-10-236-191-2.ec2.internal__2362.csv: -------------------------------------------------------------------------------- 1 | availability,stability,weights 2 | pro d,1.0,"150 class, 151-176" 3 | x-line,0.0,"150 class, 151-176" 4 | esp,1.0,161-176 5 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042987228.91__CC-MAIN-20150728002307-00122-ip-10-236-191-2.ec2.internal__88.csv: -------------------------------------------------------------------------------- 1 | audley end bowling,overs,mdns,runs,wkts,wides,no-balls 2 | hughes,?,?,?,6,-,- 3 | keyser,?,?,?,3,-,- 4 | smart,?,?,?,1,-,- 5 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042987628.47__CC-MAIN-20150728002307-00125-ip-10-236-191-2.ec2.internal__980.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | 12,,,1,2,3,4 3 | 5,6,7,8,9,10,11 4 | ,13,14,15,16,17,18 5 | 19,27,21,22,23,24,25 6 | 26,20,28,29,30,31, 7 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438043062635.98__CC-MAIN-20150728002422-00266-ip-10-236-191-2.ec2.internal__1392.csv: -------------------------------------------------------------------------------- 1 | size,age,height (in),waist,hip 2 | 3t,2,34.5 - 36.5,21,21 3 | 2t,3,36.5 - 38.5,21.5,22 4 | 4t,4,38.5 - 41.5,22-23,23 5 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042988840.31__CC-MAIN-20150728002308-00067-ip-10-236-191-2.ec2.internal__1817.csv: -------------------------------------------------------------------------------- 1 | domain,out,in,pagerank,ip 2 | mail.mahapwd.com,0,0,6/255,115.111.58.217 3 | www.mahapwd.com,5/255,1,0,115.111.58.211 4 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042989126.22__CC-MAIN-20150728002309-00181-ip-10-236-191-2.ec2.internal__1685.csv: -------------------------------------------------------------------------------- 1 | visitor,v,home,h,location,status 2 | clarington,3,kingston,3,invista - whig, 3 | pickering,7,belleville,2,qsc rink a, 4 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042981753.21__CC-MAIN-20150728002301-00208-ip-10-236-191-2.ec2.internal__1874.csv: -------------------------------------------------------------------------------- 1 | ,tgt,catches,yds,td 2 | dwayne bowe,3,2,17,0 3 | jamaal charles,2,2,1,0 4 | mike cox,2,2,4,0 5 | larry johnson,2,2,1,0 6 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042986625.58__CC-MAIN-20150728002306-00239-ip-10-236-191-2.ec2.internal__2767.csv: -------------------------------------------------------------------------------- 1 | type,regulations.gov 2 | fr doc.,2015-07503 3 | rin, 4 | docket no.,faa-2015-0720 5 | special conditions no.,23-263-sc 6 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042987155.85__CC-MAIN-20150728002307-00192-ip-10-236-191-2.ec2.internal__2107.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | ,,1,2,3,4,5 3 | 6,7,8,9,10,11,12 4 | 13,14,15,16,17,18,19 5 | 20,21,22,23,24,25,26 6 | 27,28,29,30,31,, 7 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042988962.66__CC-MAIN-20150728002308-00249-ip-10-236-191-2.ec2.internal__2362.csv: -------------------------------------------------------------------------------- 1 | availability,stability,weights 2 | pro d,0.0,"150 class, 151-176" 3 | x-line,1.0,"150 class, 151-176" 4 | esp,1.0,161-176 5 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042989826.86__CC-MAIN-20150728002309-00179-ip-10-236-191-2.ec2.internal__2223.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | ,,,1,2,3,4 3 | 5,6,7,8,9,10,11 4 | 12,13,14,15,16,17,18 5 | 19,20,21,22,23,24,25 6 | 26,27,28,29,30,31, 7 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042987228.91__CC-MAIN-20150728002307-00122-ip-10-236-191-2.ec2.internal__88.csv: -------------------------------------------------------------------------------- 1 | audley end bowling,overs,mdns,runs,wkts,wides,no-balls 2 | hughes,?,?,?,6,-,- 3 | keyser,?,?,?,3,-,- 4 | smart,?,?,?,1,-,- 5 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042989126.22__CC-MAIN-20150728002309-00181-ip-10-236-191-2.ec2.internal__1685.csv: -------------------------------------------------------------------------------- 1 | visitor,v,home,h,location,status 2 | clarington,3,kingston,2,invista - whig, 3 | pickering,7,belleville,3,qsc rink a, 4 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042981753.21__CC-MAIN-20150728002301-00208-ip-10-236-191-2.ec2.internal__1874.csv: -------------------------------------------------------------------------------- 1 | ,tgt,catches,yds,td 2 | dwayne bowe,3,2,17,0 3 | jamaal charles,2,2,1,0 4 | mike cox,2,2,4,0 5 | larry johnson,2,2,1,0 6 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042982502.13__CC-MAIN-20150728002302-00111-ip-10-236-191-2.ec2.internal__1274.csv: -------------------------------------------------------------------------------- 1 | hollister (s - xl),hollister (waist - in),international (waist - cm) 2 | s/m,29 - 31,74 - 79 3 | l/xl,32 - 34,81 - 86 4 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042986625.58__CC-MAIN-20150728002306-00239-ip-10-236-191-2.ec2.internal__2767.csv: -------------------------------------------------------------------------------- 1 | type,regulations.gov 2 | fr doc.,2015-07503 3 | rin, 4 | docket no.,faa-2015-0720 5 | special conditions no.,23-263-sc 6 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438043062635.98__CC-MAIN-20150728002422-00266-ip-10-236-191-2.ec2.internal__1392.csv: -------------------------------------------------------------------------------- 1 | size,age,height (in),waist,hip 2 | 2t,2,34.5 - 36.5,21,21 3 | 3t,3,36.5 - 38.5,21.5,22 4 | 4t,4,38.5 - 41.5,22-23,23 5 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042987628.47__CC-MAIN-20150728002307-00335-ip-10-236-191-2.ec2.internal__1368.csv: -------------------------------------------------------------------------------- 1 | size,age,height (in),waist,hip 2 | 2t,2,34.5 - 36.5,21,21 3 | 3t,3,36.5 - 38.5,21.5,22 4 | 4t,4,38.5 - 41.5,22-23,23 5 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042988840.31__CC-MAIN-20150728002308-00067-ip-10-236-191-2.ec2.internal__1817.csv: -------------------------------------------------------------------------------- 1 | domain,out,in,pagerank,ip 2 | mail.mahapwd.com,0,0,6/255,115.111.58.217 3 | www.mahapwd.com,0,1,5/255,115.111.58.211 4 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042989126.22__CC-MAIN-20150728002309-00181-ip-10-236-191-2.ec2.internal__1685.csv: -------------------------------------------------------------------------------- 1 | visitor,v,home,h,location,status 2 | clarington,3,kingston,2,invista - whig, 3 | pickering,7,belleville,3,qsc rink a, 4 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042988250.59__CC-MAIN-20150728002308-00009-ip-10-236-191-2.ec2.internal__1805.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | ,3,,1,2,,4 3 | 5,6,7,8,9,10,11 4 | 12,13,14,15,16,17,18 5 | 19,24,21,22,23,20,25 6 | 26,27,28,29,30,31, 7 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042987628.47__CC-MAIN-20150728002307-00335-ip-10-236-191-2.ec2.internal__1368.csv: -------------------------------------------------------------------------------- 1 | size,age,height (in),waist,hip 2 | 2t,2,34.5 - 36.5,21,21 3 | 3t,3,36.5 - 38.5,21.5,29 4 | cover,4,ghw 16 nocturnal,22-23,23 5 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042988065.26__CC-MAIN-20150728002308-00076-ip-10-236-191-2.ec2.internal__1719.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | ,,,,1,2,3 3 | 4,5,6,7,8,9,17 4 | 11,12,13,14,15,16,10 5 | 18,19,20,28,22,23,24 6 | 25,26,27,21,29,30,31 7 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042988840.31__CC-MAIN-20150728002308-00310-ip-10-236-191-2.ec2.internal__630.csv: -------------------------------------------------------------------------------- 1 | record id,action,time 2 | 2009-03-03t12:03:33+00:00,add,lc|n 85145452 3 | isni|0000000028835422,add,2013-09-16t16:15:07+00:00 4 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042992201.62__CC-MAIN-20150728002312-00098-ip-10-236-191-2.ec2.internal__1505.csv: -------------------------------------------------------------------------------- 1 | #,name,yr,hometown,%,saves 2 | 0,hallie yancey,so,"wallingford, pa",0.373,47 3 | 1,mackenzie duffy,fr,"cranston, ri",0.396,76 4 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042988250.59__CC-MAIN-20150728002308-00009-ip-10-236-191-2.ec2.internal__1805.csv: -------------------------------------------------------------------------------- 1 | s,old,t,w,t,f,s 2 | ,,,1,2,3,4 3 | 5,6,7,8,9,10,11 4 | 12,13,14,15,16,17,18 5 | 19,20,21,22,23,24,25 6 | 26,27,28,29,30,31, 7 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042988840.31__CC-MAIN-20150728002308-00310-ip-10-236-191-2.ec2.internal__630.csv: -------------------------------------------------------------------------------- 1 | record id,action,time 2 | lc|n 85145452,add,2009-03-03t12:03:33+00:00 3 | isni|0000000028835422,add,2013-09-16t16:15:07+00:00 4 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042992201.62__CC-MAIN-20150728002312-00098-ip-10-236-191-2.ec2.internal__1505.csv: -------------------------------------------------------------------------------- 1 | #,name,yr,hometown,%,saves 2 | 0,hallie yancey,so,"wallingford, pa",0.373,47 3 | 1,mackenzie duffy,fr,"cranston, ri",0.396,76 4 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042987155.85__CC-MAIN-20150728002307-00192-ip-10-236-191-2.ec2.internal__2107.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | ,,1,2,3,4,5 3 | 6,7,8,9,10,11,12 4 | 13,14,15,16,17,18,19 5 | 20,21,22,23,24,25,26 6 | 27,28,29,30,31,, 7 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042988650.53__CC-MAIN-20150728002308-00168-ip-10-236-191-2.ec2.internal__1772.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | ,,,1,2,3,4 3 | 5,6,7,8,9,10,11 4 | 12,13,14,15,16,17,18 5 | 19,20,21,22,23,24,25 6 | 26,27,28,29,30,31, 7 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042988962.66__CC-MAIN-20150728002308-00249-ip-10-236-191-2.ec2.internal__2362.csv: -------------------------------------------------------------------------------- 1 | availability,stability,weights 2 | pro d,0.0,"150 class, 151-176" 3 | x-line,1.0,"150 class, 151-176" 4 | esp,1.0,161-176 5 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042989826.86__CC-MAIN-20150728002309-00179-ip-10-236-191-2.ec2.internal__2223.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | ,,,1,2,3,4 3 | 5,6,7,8,9,10,11 4 | 12,13,14,15,16,17,18 5 | 19,20,21,22,23,24,25 6 | 26,27,28,29,30,31, 7 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042987228.91__CC-MAIN-20150728002307-00122-ip-10-236-191-2.ec2.internal__88.csv: -------------------------------------------------------------------------------- 1 | audley end bowling,overs,mdns,runs,wkts,wides,no-balls 2 | hughes,?,?,?,6,-,- 3 | keyser,?,?,?,3,-,- 4 | smart,?,?,?,1,-,- 5 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042987628.47__CC-MAIN-20150728002307-00125-ip-10-236-191-2.ec2.internal__980.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | ,,,1,2,3,4 3 | 5,6,7,8,9,10,11 4 | 12,13,14,15,16,17,18 5 | 19,20,21,22,23,24,25 6 | 26,27,28,29,30,31, 7 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042988250.59__CC-MAIN-20150728002308-00009-ip-10-236-191-2.ec2.internal__1805.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | ,,,1,2,3,4 3 | 5,6,7,8,9,10,11 4 | 12,13,14,15,16,17,18 5 | 19,20,21,22,23,24,25 6 | 26,27,28,29,30,31, 7 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042988065.26__CC-MAIN-20150728002308-00076-ip-10-236-191-2.ec2.internal__1719.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | ,,,,1,2,3 3 | 4,5,6,7,8,9,10 4 | 11,12,13,14,15,16,17 5 | 18,19,20,21,22,23,24 6 | 25,26,27,28,29,30,31 7 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042988840.31__CC-MAIN-20150728002308-00310-ip-10-236-191-2.ec2.internal__630.csv: -------------------------------------------------------------------------------- 1 | record id,action,time 2 | lc|n 85145452,add,2009-03-03t12:03:33+00:00 3 | isni|0000000028835422,add,2013-09-16t16:15:07+00:00 4 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042988650.53__CC-MAIN-20150728002308-00168-ip-10-236-191-2.ec2.internal__1772.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | ,,,1,2,3,4 3 | 5,6,7,ckon-fm,9,10,11 4 | 12,13,14,15,16,17,18 5 | 19,20,21,22,23,24,25 6 | 26,27,28,242,7,31, 7 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042992543.60__CC-MAIN-20150728002312-00232-ip-10-236-191-2.ec2.internal__1998.csv: -------------------------------------------------------------------------------- 1 | version,license,api,released 2 | 0.1.1stable,mit license,11/06/2010,13/06/2010 3 | 0.1.0stable,mit license,0.1.0stable,0.1.0stable 4 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438043062635.98__CC-MAIN-20150728002422-00156-ip-10-236-191-2.ec2.internal__1687.csv: -------------------------------------------------------------------------------- 1 | period,returns (%),rank # 2 | 1 mth,-,- 3 | 3 mth,-,- 4 | 6 mth,-,- 5 | 1 year,-,- 6 | -,2 year,- 7 | 3 year,-,- 8 | 5 year,-,- 9 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042986615.83__CC-MAIN-20150728002306-00215-ip-10-236-191-2.ec2.internal__1920.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | ,,,,,,1 3 | 2,3,4,5,6,7,8 4 | 9,17,11,12,13,14,15 5 | 16,10,,19,20,21,22 6 | 23,24,25,26,27,28,29 7 | 30,,18,,,, 8 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042988061.16__CC-MAIN-20150728002308-00120-ip-10-236-191-2.ec2.internal__883.csv: -------------------------------------------------------------------------------- 1 | kickoff returns,no,yds,avg,lg,td 2 | konnor fleming,4,89,22.3,38,0 3 | tre nowaczynski,2,43,39,32,0 4 | c.j. smith,2,21.5,19.5,21,0 5 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042989891.18__CC-MAIN-20150728002309-00110-ip-10-236-191-2.ec2.internal__1467.csv: -------------------------------------------------------------------------------- 1 | age,head circumference (in),head circumference (cm) 2 | 0/6m,"16 1/2""",41.9 3 | 6/12m,"17 1/2""",44.5 4 | 12/24m,"18 1/2""",47 5 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042990217.27__CC-MAIN-20150728002310-00130-ip-10-236-191-2.ec2.internal__376.csv: -------------------------------------------------------------------------------- 1 | bio,website, 2 | ,profile views, 3 | ,age, 4 | visits,member for,"2 years, 9 months" 5 | ,seen,feb 23 at 0:05 6 | stats,location,4 7 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042989897.84__CC-MAIN-20150728002309-00095-ip-10-236-191-2.ec2.internal__1199.csv: -------------------------------------------------------------------------------- 1 | play progress,users at this level of gameplay 2 | tried it,20% 3 | played it,8% 4 | halfway,4% 5 | 4%,64% 6 | conquered it,beat it 7 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438043062635.98__CC-MAIN-20150728002422-00156-ip-10-236-191-2.ec2.internal__1687.csv: -------------------------------------------------------------------------------- 1 | continental,returns (%),rank # 2 | 1 mth,-,- 3 | 3 mth,-,- 4 | 6 mth,-,- 5 | 1 year,-,- 6 | 2 year,-,- 7 | 3 year,-,- 8 | 5 year,-,- 9 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042987628.47__CC-MAIN-20150728002307-00125-ip-10-236-191-2.ec2.internal__980.csv: -------------------------------------------------------------------------------- 1 | s,m,t,location,t,f,s 2 | ,,,1,2,3,4 3 | 5,6,7,8,9,10,11 4 | 12,13,14,15,16,17,18 5 | 19,20,21,22,23,24,25 6 | 26,27,28,29,30,31, 7 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042988650.6__CC-MAIN-20150728002308-00014-ip-10-236-191-2.ec2.internal__1639.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | ,,,,,,1 3 | 2,3,4,5,6,7,8 4 | 9,10,11,12,13,14,15 5 | 16,17,18,19,20,21,22 6 | 23,24,25,26,27,28,29 7 | 30,31,,,,, 8 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042989891.18__CC-MAIN-20150728002309-00110-ip-10-236-191-2.ec2.internal__1467.csv: -------------------------------------------------------------------------------- 1 | age,head circumference (in),head circumference (cm) 2 | 0/6m,"16 1/2""",41.9 3 | 6/12m,"17 1/2""",44.5 4 | 12/24m,"18 1/2""",47 5 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042990217.27__CC-MAIN-20150728002310-00130-ip-10-236-191-2.ec2.internal__376.csv: -------------------------------------------------------------------------------- 1 | bio,website, 2 | ,location, 3 | ,age, 4 | visits,member for,"2 years, 9 months" 5 | ,seen,feb 23 at 0:05 6 | stats,profile views,4 7 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042987628.47__CC-MAIN-20150728002307-00335-ip-10-236-191-2.ec2.internal__1368.csv: -------------------------------------------------------------------------------- 1 | size,academic offices,height (in),waist,hip 2 | 2t,2,34.5 - 36.5,21,21 3 | 3t,3,36.5 - 38.5,21.5,22 4 | 4t,4,38.5 - 41.5,22-23,23 5 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042988840.31__CC-MAIN-20150728002308-00067-ip-10-236-191-2.ec2.internal__1817.csv: -------------------------------------------------------------------------------- 1 | domain,out,award streamer,pagerank,ip 2 | mail.mahapwd.com,0,0,6/255,115.111.58.217 3 | www.mahapwd.com,0,1,5/255,115.111.58.211 4 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042989897.84__CC-MAIN-20150728002309-00095-ip-10-236-191-2.ec2.internal__1199.csv: -------------------------------------------------------------------------------- 1 | play progress,users at this level of gameplay 2 | tried it,20% 3 | played it,8% 4 | halfway,4% 5 | beat it,64% 6 | conquered it,4% 7 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042992543.60__CC-MAIN-20150728002312-00232-ip-10-236-191-2.ec2.internal__1998.csv: -------------------------------------------------------------------------------- 1 | version,license,api,released 2 | 0.1.1stable,mit license,0.1.0stable,13/06/2010 3 | 0.1.0stable,mit license,0.1.0stable,11/06/2010 4 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438043062635.98__CC-MAIN-20150728002422-00156-ip-10-236-191-2.ec2.internal__1687.csv: -------------------------------------------------------------------------------- 1 | period,returns (%),rank # 2 | 1 mth,-,- 3 | 3 mth,-,- 4 | 6 mth,-,- 5 | 1 year,-,- 6 | 2 year,-,- 7 | 3 year,-,- 8 | 5 year,-,- 9 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042989891.18__CC-MAIN-20150728002309-00110-ip-10-236-191-2.ec2.internal__1467.csv: -------------------------------------------------------------------------------- 1 | age,head circumference (in),head circumference (cm) 2 | 0/6m,"16 1/2""",41.9 3 | 6/12m,"17 1/2""",44.5 4 | 12/24m,"18 1/2""",47 5 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042990217.27__CC-MAIN-20150728002310-00130-ip-10-236-191-2.ec2.internal__376.csv: -------------------------------------------------------------------------------- 1 | bio,website, 2 | ,location, 3 | ,age, 4 | visits,member for,"2 years, 9 months" 5 | ,seen,feb 23 at 0:05 6 | stats,profile views,4 7 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042992201.62__CC-MAIN-20150728002312-00098-ip-10-236-191-2.ec2.internal__1505.csv: -------------------------------------------------------------------------------- 1 | #,name,yr,hometown,%,saves 2 | 0,hallie yancey,so,"wallingford, pa",0.373,47 3 | 1,mackenzie duffy,fr,"cranston, ri",0.396,76 4 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042988310.3__CC-MAIN-20150728002308-00191-ip-10-236-191-2.ec2.internal__1723.csv: -------------------------------------------------------------------------------- 1 | gain ratio,9.0,7.9,6.8,5.6,4.7,4.2,3.6,2.9 2 | gear inches,115,101,87,71.2,60.6,4.3,45.8,37.5 3 | meters,9.2,8.1,7.0,5.7,4.8,53.2,3.7,3.0 4 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042989301.17__CC-MAIN-20150728002309-00076-ip-10-236-191-2.ec2.internal__518.csv: -------------------------------------------------------------------------------- 1 | code,result 2 | italics,italics 3 | bold,bold 4 | underline,underline 5 | strike,strike 6 | monospaced,monospaced 7 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042988650.6__CC-MAIN-20150728002308-00014-ip-10-236-191-2.ec2.internal__1639.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | ,,,9,,,1 3 | 2,3,4,5,6,7,8 4 | ,10,11,12,13,14,15 5 | 16,17,18,19,20,21,22 6 | 23,24,25,26,27,28,29 7 | 30,31,,,,, 8 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042986444.39__CC-MAIN-20150728002306-00060-ip-10-236-191-2.ec2.internal__549.csv: -------------------------------------------------------------------------------- 1 | rating,avg. dinner entrã©e 2 | $$$$$,greater than $25 3 | $$$$,$18.01 - $25 4 | $$$,$12.01 - $18 5 | $$,$7.01 - $12 6 | $,less than $7 7 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042988650.6__CC-MAIN-20150728002308-00126-ip-10-236-191-2.ec2.internal__477.csv: -------------------------------------------------------------------------------- 1 | size,ys,ym,yl 2 | chest width,"28""","31""","34""" 3 | body length (measured from highest point of shoulder),"23.125""","24.875""","27""" 4 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042988310.3__CC-MAIN-20150728002308-00191-ip-10-236-191-2.ec2.internal__1723.csv: -------------------------------------------------------------------------------- 1 | gain ratio,9.0,7.9,6.8,5.6,4.7,4.2,time,2.9 2 | gear inches,115,101,87,71.2,60.6,53.2,45.8,37.5 3 | meters,9.2,8.1,7.0,5.7,4.8,4.3,3.7,3.0 4 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042988650.53__CC-MAIN-20150728002308-00168-ip-10-236-191-2.ec2.internal__1772.csv: -------------------------------------------------------------------------------- 1 | s,nightly rate,t,w,t,titles,s 2 | ,,,1,2,3,4 3 | 5,6,7,8,9,10,11 4 | 12,13,14,15,16,17,18 5 | 19,20,21,22,23,24,25 6 | 26,27,28,29,30,31, 7 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042989301.17__CC-MAIN-20150728002309-00076-ip-10-236-191-2.ec2.internal__518.csv: -------------------------------------------------------------------------------- 1 | code,result 2 | italics,italics 3 | bold,bold 4 | underline,underline 5 | strike,strike 6 | monospaced,monospaced 7 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042986444.39__CC-MAIN-20150728002306-00060-ip-10-236-191-2.ec2.internal__549.csv: -------------------------------------------------------------------------------- 1 | rating,avg. dinner entrã©e 2 | $$$$$,greater than $25 3 | $$$$,$18.01 - $25 4 | $$$,$12.01 - $18 5 | $$,$7.01 - $12 6 | $,less than $7 7 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042988065.26__CC-MAIN-20150728002308-00076-ip-10-236-191-2.ec2.internal__1719.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,+/−,f,thrill rating 2 | ,,,,1,2,3 3 | 4,5,6,7,8,9,10 4 | 11,12,13,14,15,16,17 5 | 18,19,20,21,22,23,24 6 | 25,26,27,28,29,30,31 7 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042988650.6__CC-MAIN-20150728002308-00126-ip-10-236-191-2.ec2.internal__477.csv: -------------------------------------------------------------------------------- 1 | size,ys,ym,a 2 | chest width,"28""","31""","34""" 3 | body length (measured from highest point of shoulder),"23.125""","24.875""","27""" 4 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042989301.17__CC-MAIN-20150728002309-00076-ip-10-236-191-2.ec2.internal__518.csv: -------------------------------------------------------------------------------- 1 | code,result 2 | italics,italics 3 | bold,bold 4 | underline,underline 5 | strike,strike 6 | monospaced,monospaced 7 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042986615.83__CC-MAIN-20150728002306-00215-ip-10-236-191-2.ec2.internal__1920.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | ,,,,,,1 3 | 2,3,4,5,6,7,8 4 | 9,10,11,12,13,14,15 5 | 16,17,18,19,20,21,22 6 | 23,24,25,26,27,28,29 7 | 30,,,,,, 8 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042988061.16__CC-MAIN-20150728002308-00120-ip-10-236-191-2.ec2.internal__883.csv: -------------------------------------------------------------------------------- 1 | kickoff returns,no,yds,avg,lg,td 2 | konnor fleming,4,89,22.3,38,0 3 | tre nowaczynski,2,43,21.5,32,0 4 | c.j. smith,2,39,19.5,21,0 5 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042988650.6__CC-MAIN-20150728002308-00014-ip-10-236-191-2.ec2.internal__1639.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | ,,,,,,1 3 | 2,3,4,5,6,7,8 4 | 9,10,11,12,13,14,15 5 | 16,17,18,19,20,21,22 6 | 23,24,25,26,27,28,29 7 | 30,31,,,,, 8 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042986444.39__CC-MAIN-20150728002306-00060-ip-10-236-191-2.ec2.internal__549.csv: -------------------------------------------------------------------------------- 1 | rating,avg. dinner entrã©e 2 | $$$$$,greater than $25 3 | $$$$,$18.01 - $25 4 | $$$,$12.01 - $18 5 | $$,$7.01 - $12 6 | $,less than $7 7 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042989897.84__CC-MAIN-20150728002309-00095-ip-10-236-191-2.ec2.internal__1199.csv: -------------------------------------------------------------------------------- 1 | play progress,users at this level of gameplay 2 | tried it,20% 3 | played it,8% 4 | halfway,4% 5 | beat it,64% 6 | conquered it,4% 7 | -------------------------------------------------------------------------------- /exp/ft_cell/cell_pred.yml: -------------------------------------------------------------------------------- 1 | 2 | learn_type: 'pred' 3 | batch_size: '1' 4 | cuda_devices: [0] 5 | # out_pred_name: pred.jsonl 6 | clscol_path: ./data/clscol.npy 7 | clsrow_path: ./data/clsrow.npy 8 | # out_dir: ./data/ft_cell/debug 9 | 10 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042992543.60__CC-MAIN-20150728002312-00232-ip-10-236-191-2.ec2.internal__1998.csv: -------------------------------------------------------------------------------- 1 | version,license,peak position,released 2 | 0.1.1stable,mit license,0.1.0stable,13/06/2010 3 | 0.1.0stable,mit license,0.1.0stable,11/06/2010 4 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042988399.65__CC-MAIN-20150728002308-00127-ip-10-236-191-2.ec2.internal__1207.csv: -------------------------------------------------------------------------------- 1 | code,iata,kind,name,city,distance,bearing,airlines 2 | oagn,gzi,small,ghazni airport,,21 nm e,92, 3 | oamk,,small,mukur airport,,40 nm s,189, 4 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042986444.39__CC-MAIN-20150728002306-00217-ip-10-236-191-2.ec2.internal__2206.csv: -------------------------------------------------------------------------------- 1 | date,coach,event,position,points 2 | 21/04/2013,mtb regional a,nutcracker altura 2 at gandale (master male),9,0 3 | ,rider's total points,,,0 4 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042988310.3__CC-MAIN-20150728002308-00191-ip-10-236-191-2.ec2.internal__1723.csv: -------------------------------------------------------------------------------- 1 | gain ratio,9.0,7.9,6.8,5.6,4.7,4.2,3.6,2.9 2 | gear inches,115,101,87,71.2,60.6,53.2,45.8,37.5 3 | meters,9.2,8.1,7.0,5.7,4.8,4.3,3.7,3.0 4 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042988650.6__CC-MAIN-20150728002308-00126-ip-10-236-191-2.ec2.internal__477.csv: -------------------------------------------------------------------------------- 1 | size,ys,ym,yl 2 | chest width,"28""","31""","34""" 3 | body length (measured from highest point of shoulder),"23.125""","24.875""","27""" 4 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042988399.65__CC-MAIN-20150728002308-00127-ip-10-236-191-2.ec2.internal__1207.csv: -------------------------------------------------------------------------------- 1 | code,iata,kind,name,city,distance,bearing,airlines 2 | oagn,gzi,small,ghazni airport,,21 nm e,92, 3 | oamk,,small,mukur airport,,40 nm s,189, 4 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042986444.39__CC-MAIN-20150728002306-00217-ip-10-236-191-2.ec2.internal__2206.csv: -------------------------------------------------------------------------------- 1 | date,category,event,position,points 2 | 21/04/2013,mtb regional a,nutcracker altura 2 at gandale (master male),9,0 3 | ,rider's total points,,,0 4 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042989790.89__CC-MAIN-20150728002309-00266-ip-10-236-191-2.ec2.internal__593.csv: -------------------------------------------------------------------------------- 1 | season,team,gp,w,l,so,ga,sa,sv%,gaa,min 2 | 2002-2003,wild,11,5,6,0,25,257,.903,2.59,579 3 | ,nhl totals,50,28,18,"2,860",121,"1,483",.918,2.54,2 4 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042987034.19__CC-MAIN-20150728002307-00101-ip-10-236-191-2.ec2.internal__2095.csv: -------------------------------------------------------------------------------- 1 | per,from,to,enemy 2 | 01/07/12,khimki,torpedo,free 3 | 07/03/11,volgar,khimki,n/a 4 | 19/08/10,atyrau,volgar,n/a 5 | 01/08/09,spartak,atyrau,n/a 6 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042989018.40__CC-MAIN-20150728002309-00317-ip-10-236-191-2.ec2.internal__2.csv: -------------------------------------------------------------------------------- 1 | class year,salary 2 | bonus category,array 3 | 1,$160k 4 | 2,$170k 5 | 3,$185k 6 | 4,$210k 7 | 5,$230k 8 | 6,$250k 9 | 7,$265k 10 | 8,$280k 11 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042987034.19__CC-MAIN-20150728002307-00101-ip-10-236-191-2.ec2.internal__2095.csv: -------------------------------------------------------------------------------- 1 | per,from,to,value 2 | 01/07/12,khimki,torpedo,free 3 | 07/03/11,volgar,khimki,n/a 4 | 19/08/10,atyrau,volgar,n/a 5 | 01/08/09,spartak,atyrau,n/a 6 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042988399.65__CC-MAIN-20150728002308-00127-ip-10-236-191-2.ec2.internal__1207.csv: -------------------------------------------------------------------------------- 1 | code,iata,kind,name,city,distance,bearing,airlines 2 | oagn,gzi,small,ghazni airport,,21 nm e,92, 3 | oamk,,small,mukur airport,,40 nm s,189, 4 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042986444.39__CC-MAIN-20150728002306-00217-ip-10-236-191-2.ec2.internal__2206.csv: -------------------------------------------------------------------------------- 1 | date,category,event,position,points 2 | 21/04/2013,mtb regional a,nutcracker altura 2 at gandale (master male),9,0 3 | ,rider's total points,,,0 4 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042989790.89__CC-MAIN-20150728002309-00266-ip-10-236-191-2.ec2.internal__593.csv: -------------------------------------------------------------------------------- 1 | season,team,gp,w,l,so,ga,sa,sv%,gaa,min 2 | 2002-2003,wild,11,5,6,0,25,257,.903,2.59,579 3 | ,nhl totals,50,28,18,2,121,"1,483",.918,2.54,"2,860" 4 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042987034.19__CC-MAIN-20150728002307-00101-ip-10-236-191-2.ec2.internal__2095.csv: -------------------------------------------------------------------------------- 1 | per,from,to,value 2 | nominated,khimki,torpedo,telugu 3 | 0,volgar,khimki,n/a 4 | 19/08/10,atyrau,volgar,n/a 5 | anthony corallo,spartak,467.13,n/a 6 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042985140.15__CC-MAIN-20150728002305-00141-ip-10-236-191-2.ec2.internal__886.csv: -------------------------------------------------------------------------------- 1 | customer experience,total customer reviews 2 | positive experience,0 3 | neutral experience,0 4 | negative experience,0 5 | total customer reviews,0 6 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042989018.40__CC-MAIN-20150728002309-00317-ip-10-236-191-2.ec2.internal__2.csv: -------------------------------------------------------------------------------- 1 | class year,salary 2 | bonus category,array 3 | 1,$160k 4 | 2,$170k 5 | $185k,3 6 | 4,$210k 7 | 5,$230k 8 | 6,$250k 9 | 7,$265k 10 | 8,$280k 11 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042985647.51__CC-MAIN-20150728002305-00318-ip-10-236-191-2.ec2.internal__105.csv: -------------------------------------------------------------------------------- 1 | receiving,no,yds,avg,lg,td 2 | adam moses,4,56,14.0,31,0 3 | christian jackson,4,25,6.3,20,0 4 | mike ferraro,1,7,7.0,7,0 5 | neal mcfarland,1,5,5.0,5,0 6 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042988061.16__CC-MAIN-20150728002308-00120-ip-10-236-191-2.ec2.internal__883.csv: -------------------------------------------------------------------------------- 1 | kickoff returns,weekly growth,yds,avg,lg,progress 2 | konnor fleming,4,89,22.3,38,0 3 | tre nowaczynski,2,43,21.5,32,0 4 | c.j. smith,2,39,19.5,21,0 5 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042985140.15__CC-MAIN-20150728002305-00141-ip-10-236-191-2.ec2.internal__886.csv: -------------------------------------------------------------------------------- 1 | customer experience,total customer reviews 2 | positive experience,0 3 | neutral experience,0 4 | negative experience,0 5 | total customer reviews,0 6 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042985140.15__CC-MAIN-20150728002305-00141-ip-10-236-191-2.ec2.internal__886.csv: -------------------------------------------------------------------------------- 1 | customer experience,total customer reviews 2 | positive experience,0 3 | neutral experience,0 4 | negative experience,0 5 | total customer reviews,0 6 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042989018.40__CC-MAIN-20150728002309-00317-ip-10-236-191-2.ec2.internal__2.csv: -------------------------------------------------------------------------------- 1 | class year,salary 2 | bonus category,array 3 | 1,$160k 4 | 2,$170k 5 | 3,$185k 6 | 4,$210k 7 | 5,$230k 8 | 6,$250k 9 | 7,$265k 10 | 8,$280k 11 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042988317.67__CC-MAIN-20150728002308-00041-ip-10-236-191-2.ec2.internal__159.csv: -------------------------------------------------------------------------------- 1 | rushing,att,yds,avg,lg,td 2 | harry meisner,16,20,5.8,92,0 3 | amoh kumengisa,7,36,5.1,14,0 4 | heath haden,15,17,1.1,18,0 5 | braden urevick,1,-11,-11.0,0,0 6 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042985140.15__CC-MAIN-20150728002305-00185-ip-10-236-191-2.ec2.internal__576.csv: -------------------------------------------------------------------------------- 1 | business,contact,category 2 | ,, 3 | 1. blue nami sushi - roseville,"1465 eureka rd. #120 roseville, ca 916-787-1177","asian: southeast, japanese / sushi" 4 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042981460.12__CC-MAIN-20150728002301-00003-ip-10-236-191-2.ec2.internal__1387.csv: -------------------------------------------------------------------------------- 1 | size,us,type,china,gaa,eu,years 2 | xs,6/7,9.125,235,23,36-37,4 3 | s,7/8,9.5,245,24,38-39,5 4 | m,8/9,9.875,255,25,39-40,6 5 | l,9/10,10.375,265,26,40-41,7 6 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042986615.83__CC-MAIN-20150728002306-00215-ip-10-236-191-2.ec2.internal__1920.csv: -------------------------------------------------------------------------------- 1 | s,peak chart positions,t,w,t,champion,s 2 | ,,,,,,1 3 | 2,3,4,5,6,7,8 4 | 9,10,11,12,13,14,15 5 | 16,17,18,19,20,21,22 6 | 23,24,25,26,27,28,29 7 | 30,,,,,, 8 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042990217.27__CC-MAIN-20150728002310-00111-ip-10-236-191-2.ec2.internal__2531.csv: -------------------------------------------------------------------------------- 1 | "liberal arts and sciences, general studies and humanities",associate 2 | humanities/humanistic studies,123 3 | liberal arts and sciences/liberal studies,94 4 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042985140.15__CC-MAIN-20150728002305-00185-ip-10-236-191-2.ec2.internal__576.csv: -------------------------------------------------------------------------------- 1 | business,contact,category 2 | ,, 3 | 1. blue nami sushi - roseville,"1465 eureka rd. #120 roseville, ca 916-787-1177","asian: southeast, japanese / sushi" 4 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042985647.51__CC-MAIN-20150728002305-00318-ip-10-236-191-2.ec2.internal__105.csv: -------------------------------------------------------------------------------- 1 | receiving,no,yds,avg,lg,td 2 | adam moses,4,56,14.0,31,0 3 | christian jackson,4,25,6.3,20,0 4 | mike ferraro,1,7,7.0,7,0 5 | neal mcfarland,1,5,5.0,5,0 6 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042985140.15__CC-MAIN-20150728002305-00185-ip-10-236-191-2.ec2.internal__576.csv: -------------------------------------------------------------------------------- 1 | business,contact,category 2 | ,, 3 | 1. blue nami sushi - roseville,"1465 eureka rd. #120 roseville, ca 916-787-1177","asian: southeast, japanese / sushi" 4 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042988860.88__CC-MAIN-20150728002308-00317-ip-10-236-191-2.ec2.internal__1033.csv: -------------------------------------------------------------------------------- 1 | main crawlers,total visits 2 | ask jeeves/teoma,357 3 | baiduspider,"5,123" 4 | exabot,31 5 | googlebot,584 6 | msn bot - bingbot,0 7 | slurp inktomi (yahoo),2 8 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042989507.42__CC-MAIN-20150728002309-00037-ip-10-236-191-2.ec2.internal__1161.csv: -------------------------------------------------------------------------------- 1 | tournament,year,r2d pointsprize money,r1,r2,r3,r4,par, 2 | us pga championship,1984,€,,0,0,0,0,0 3 | lufthansa german open,1990,"€ 24,787",,70,65,69,64,-16 4 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042989891.18__CC-MAIN-20150728002309-00046-ip-10-236-191-2.ec2.internal__1544.csv: -------------------------------------------------------------------------------- 1 | date,action,by 2 | 2004-12-21 15:54:05z,created,"hansson, hans" 3 | 2010-09-07 10:14:26z,changed,"kroh, andreas" 4 | 2013-08-26 18:24:18z,changed,"kroh, andreas" 5 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042990123.20__CC-MAIN-20150728002310-00184-ip-10-236-191-2.ec2.internal__2231.csv: -------------------------------------------------------------------------------- 1 | ,,, 2 | principal investigator:,yiming li,3, 3 | principal investigator:,qinghua wang,huashan hospital/st michael's hospital, 4 | 0,zheng jiao,huashan hospital, 5 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042990112.92__CC-MAIN-20150728002310-00030-ip-10-236-191-2.ec2.internal__954.csv: -------------------------------------------------------------------------------- 1 | size,xs,s,m,l,xl,xxl 2 | neck,14-14.5,15-15.5,19-19.5,17-17.5,18-18.5,16-16.5 3 | sleeve length,32,33,34,35,36,37 4 | chest,32-35,35-38,38-41,42-45,46-49,50-53 5 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042990217.27__CC-MAIN-20150728002310-00111-ip-10-236-191-2.ec2.internal__2531.csv: -------------------------------------------------------------------------------- 1 | "liberal arts and sciences, general studies and humanities",associate 2 | humanities/humanistic studies,123 3 | liberal arts and sciences/liberal studies,94 4 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042988860.88__CC-MAIN-20150728002308-00317-ip-10-236-191-2.ec2.internal__1033.csv: -------------------------------------------------------------------------------- 1 | main crawlers,total visits 2 | ask jeeves/teoma,0 3 | baiduspider,"5,123" 4 | exabot,31 5 | googlebot,584 6 | msn bot - bingbot,357 7 | slurp inktomi (yahoo),2 8 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042989891.18__CC-MAIN-20150728002309-00046-ip-10-236-191-2.ec2.internal__1544.csv: -------------------------------------------------------------------------------- 1 | date,action,by 2 | 2004-12-21 15:54:05z,created,"hansson, hans" 3 | 2010-09-07 10:14:26z,changed,"kroh, andreas" 4 | 2013-08-26 18:24:18z,changed,"kroh, andreas" 5 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042990112.92__CC-MAIN-20150728002310-00221-ip-10-236-191-2.ec2.internal__1384.csv: -------------------------------------------------------------------------------- 1 | size,us,inches,china,japan (cm),eu,uk 2 | xs,6/7,9.125,235,23,36-37,4 3 | s,7/8,9.5,245,24,38-39,5 4 | m,8/9,9.875,255,25,39-40,6 5 | l,9/10,10.375,265,26,40-41,7 6 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042986444.39__CC-MAIN-20150728002306-00119-ip-10-236-191-2.ec2.internal__2126.csv: -------------------------------------------------------------------------------- 1 | sunday,monday,tuesday,wednesday,thursday,league,missing 2 | ,,,,1,2,3 3 | 4,5,6,7,8,9,10 4 | 11,12,13,14,15,16,17 5 | 18,19,20,21,22,23,24 6 | 25,26,27,28,29,30, 7 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042989790.89__CC-MAIN-20150728002309-00266-ip-10-236-191-2.ec2.internal__593.csv: -------------------------------------------------------------------------------- 1 | season,team,gp,w,l,so,place,sa,sv%,gaa,â· retalhuleu 2 | 2002-2003,wild,11,5,6,0,25,257,.903,2.59,579 3 | ,nhl totals,50,28,18,2,121,"1,483",.918,2.54,"2,860" 4 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042988317.67__CC-MAIN-20150728002308-00041-ip-10-236-191-2.ec2.internal__159.csv: -------------------------------------------------------------------------------- 1 | rushing,att,yds,avg,lg,td 2 | harry meisner,16,92,5.8,20,0 3 | amoh kumengisa,7,36,5.1,14,0 4 | heath haden,15,17,1.1,18,0 5 | braden urevick,1,-11,-11.0,0,0 6 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042988860.88__CC-MAIN-20150728002308-00317-ip-10-236-191-2.ec2.internal__1033.csv: -------------------------------------------------------------------------------- 1 | main crawlers,total visits 2 | ask jeeves/teoma,0 3 | baiduspider,"5,123" 4 | exabot,31 5 | googlebot,584 6 | msn bot - bingbot,357 7 | slurp inktomi (yahoo),2 8 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042989507.42__CC-MAIN-20150728002309-00037-ip-10-236-191-2.ec2.internal__1161.csv: -------------------------------------------------------------------------------- 1 | tournament,year,r2d pointsprize money,r1,r2,r3,r4,par, 2 | us pga championship,1990,€,,0,0,0,0,0 3 | lufthansa german open,1984,"€ 24,787",,70,65,69,64,-16 4 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042990112.92__CC-MAIN-20150728002310-00030-ip-10-236-191-2.ec2.internal__954.csv: -------------------------------------------------------------------------------- 1 | size,xs,s,m,l,xl,xxl 2 | neck,14-14.5,15-15.5,16-16.5,17-17.5,18-18.5,19-19.5 3 | sleeve length,32,33,34,35,36,37 4 | chest,32-35,35-38,38-41,42-45,46-49,50-53 5 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042990217.27__CC-MAIN-20150728002310-00111-ip-10-236-191-2.ec2.internal__2531.csv: -------------------------------------------------------------------------------- 1 | "liberal arts and sciences, general studies and humanities",associate 2 | humanities/humanistic studies,123 3 | liberal arts and sciences/liberal studies,94 4 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042981460.12__CC-MAIN-20150728002301-00003-ip-10-236-191-2.ec2.internal__1387.csv: -------------------------------------------------------------------------------- 1 | size,us,inches,china,japan (cm),eu,uk 2 | 6/7,xs,9.125,235,23,36-37,4 3 | s,7/8,40-41,245,24,38-39,5 4 | m,8/9,9.875,255,25,39-40,6 5 | l,9/10,10.375,265,26,9.5,7 6 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042982502.13__CC-MAIN-20150728002302-00303-ip-10-236-191-2.ec2.internal__551.csv: -------------------------------------------------------------------------------- 1 | team,w,l,pct,gb 2 | kansas city,60,38,.612,-- 3 | minnesota,52,.531,46,8.0 4 | detroit,48,51,.485,12.5 5 | chi white sox,47,50,.485,12.5 6 | cleveland,45,53,.459,15.0 7 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042986444.39__CC-MAIN-20150728002306-00119-ip-10-236-191-2.ec2.internal__2126.csv: -------------------------------------------------------------------------------- 1 | sunday,monday,tuesday,wednesday,thursday,friday,saturday 2 | ,,,,1,2,3 3 | 4,5,6,7,8,9,10 4 | 11,12,13,14,15,16,17 5 | 22,19,20,21,18,23,24 6 | 29,26,27,28,25,30, 7 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042989507.42__CC-MAIN-20150728002309-00037-ip-10-236-191-2.ec2.internal__1161.csv: -------------------------------------------------------------------------------- 1 | 4 br/sleeps 8,year,r2d pointsprize money,result,r2,r3,uk,par, 2 | us pga championship,1990,€,,0,0,0,0,0 3 | lufthansa german open,1984,"€ 24,787",,70,65,69,64,-16 4 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042982502.13__CC-MAIN-20150728002302-00303-ip-10-236-191-2.ec2.internal__551.csv: -------------------------------------------------------------------------------- 1 | team,w,l,pct,gb 2 | kansas city,60,38,.612,-- 3 | minnesota,52,46,.531,8.0 4 | detroit,48,51,.485,12.5 5 | chi white sox,47,50,.485,12.5 6 | cleveland,45,53,.459,15.0 7 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042986615.83__CC-MAIN-20150728002306-00049-ip-10-236-191-2.ec2.internal__1859.csv: -------------------------------------------------------------------------------- 1 | rnd,result,year,rank,score� 2 | 64,win,miles ransom��,�,6-0; 6-4 3 | 32,loss,ben hwang��,�,6-2; 7-5 4 | 2,loss,jackson murphy��,�,wo (inj)woj* 5 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042989891.18__CC-MAIN-20150728002309-00046-ip-10-236-191-2.ec2.internal__1544.csv: -------------------------------------------------------------------------------- 1 | date,action,by 2 | 2004-12-21 15:54:05z,created,"hansson, hans" 3 | 2010-09-07 10:14:26z,changed,"kroh, andreas" 4 | 2013-08-26 18:24:18z,changed,"kroh, andreas" 5 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042990112.92__CC-MAIN-20150728002310-00221-ip-10-236-191-2.ec2.internal__1384.csv: -------------------------------------------------------------------------------- 1 | size,us,inches,china,japan (cm),eu,uk 2 | xs,6/7,9.125,235,23,36-37,4 3 | s,7/8,9.5,245,24,38-39,5 4 | m,8/9,9.875,255,25,39-40,6 5 | l,9/10,10.375,265,26,40-41,7 6 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042981460.12__CC-MAIN-20150728002301-00003-ip-10-236-191-2.ec2.internal__1387.csv: -------------------------------------------------------------------------------- 1 | size,us,inches,china,japan (cm),eu,uk 2 | xs,6/7,9.125,235,23,36-37,4 3 | s,7/8,9.5,245,24,38-39,5 4 | m,8/9,9.875,255,25,39-40,6 5 | l,9/10,10.375,265,26,40-41,7 6 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042986444.39__CC-MAIN-20150728002306-00119-ip-10-236-191-2.ec2.internal__2126.csv: -------------------------------------------------------------------------------- 1 | sunday,monday,tuesday,wednesday,thursday,friday,saturday 2 | ,,,,1,2,3 3 | 4,5,6,7,8,9,10 4 | 11,12,13,14,15,16,17 5 | 18,19,20,21,22,23,24 6 | 25,26,27,28,29,30, 7 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042988924.75__CC-MAIN-20150728002308-00052-ip-10-236-191-2.ec2.internal__2363.csv: -------------------------------------------------------------------------------- 1 | ,singular,plural 2 | nominativ,das publikum,die publika 3 | genitiv,des publikums,der publika 4 | dativ,dem publikum,den publika 5 | akkusativ,das publikum,die publika 6 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042988317.67__CC-MAIN-20150728002308-00041-ip-10-236-191-2.ec2.internal__159.csv: -------------------------------------------------------------------------------- 1 | rushing,att,yds,avg,lg,queensland rwy. 2 | harry meisner,16,92,5.8,20,0 3 | amoh kumengisa,7,36,5.1,14,0 4 | heath haden,15,17,1.1,18,0 5 | braden urevick,1,-11,-11.0,0,0 6 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042988924.75__CC-MAIN-20150728002308-00052-ip-10-236-191-2.ec2.internal__2363.csv: -------------------------------------------------------------------------------- 1 | ,singular,plural 2 | nominativ,das publikum,die publika 3 | genitiv,des publikums,der publika 4 | dativ,dem publikum,den publika 5 | akkusativ,das publikum,die publika 6 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042988924.75__CC-MAIN-20150728002308-00052-ip-10-236-191-2.ec2.internal__2363.csv: -------------------------------------------------------------------------------- 1 | ,singular,plural 2 | nominativ,das publikum,die publika 3 | genitiv,des publikums,der publika 4 | dativ,dem publikum,den publika 5 | akkusativ,das publikum,die publika 6 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042982502.13__CC-MAIN-20150728002302-00303-ip-10-236-191-2.ec2.internal__551.csv: -------------------------------------------------------------------------------- 1 | team,w,l,pct,gb 2 | kansas city,60,38,.612,-- 3 | minnesota,52,46,.531,8.0 4 | detroit,48,51,.485,12.5 5 | chi white sox,47,50,.485,12.5 6 | cleveland,45,53,.459,15.0 7 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042988860.88__CC-MAIN-20150728002308-00278-ip-10-236-191-2.ec2.internal__245.csv: -------------------------------------------------------------------------------- 1 | odbc support,enabled 2 | active persistent links,0 3 | active links,0 4 | odbc library,unixodbc 5 | odbc_include,-i/usr/include 6 | -l/usr/lib64,odbc_lflags 7 | odbc_libs,-lodbc 8 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042989826.86__CC-MAIN-20150728002309-00179-ip-10-236-191-2.ec2.internal__2223.csv: -------------------------------------------------------------------------------- 1 | s,m,t,w,t,f,s 2 | ,,,1,2,missy patterson,4 3 | 5,6,7,8,9,10,11 4 | 12,13,central african republic conflict (2012–13),15,16,17,18 5 | 19,20,21,22,23,24,25 6 | 26,27,28,29,30,31, 7 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042985647.51__CC-MAIN-20150728002305-00318-ip-10-236-191-2.ec2.internal__105.csv: -------------------------------------------------------------------------------- 1 | receiving,no,yds,avg,lg,td 2 | adam moses,jr show novice jr,56,14.0,31,0 3 | christian jackson,4,25,6.3,20,150 4 | mike ferraro,1,7,7.0,7,0 5 | temp. â°c,4:07 p.m. et,5,5.0,5,1 6 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042986615.83__CC-MAIN-20150728002306-00049-ip-10-236-191-2.ec2.internal__1859.csv: -------------------------------------------------------------------------------- 1 | rnd,result,opponent��,rank,score� 2 | 64,win,ben hwang��,�,6-0; 6-4 3 | 32,loss,miles ransom��,�,6-2; 7-5 4 | 2,loss,jackson murphy��,�,wo (inj)woj* 5 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042988860.88__CC-MAIN-20150728002308-00278-ip-10-236-191-2.ec2.internal__245.csv: -------------------------------------------------------------------------------- 1 | odbc support,enabled 2 | active persistent links,0 3 | active links,0 4 | odbc library,unixodbc 5 | odbc_include,-i/usr/include 6 | odbc_lflags,-l/usr/lib64 7 | odbc_libs,-lodbc 8 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042989018.48__CC-MAIN-20150728002309-00056-ip-10-236-191-2.ec2.internal__1290.csv: -------------------------------------------------------------------------------- 1 | sock size/age,shoe size: us,shoe size: uk,shoe size: euro 2 | 0-3 mos,01,.5,16 3 | 3-6 mos,02,1,17 4 | 6-12 mos,03-04,2-3,18-19 5 | 12-18 mos,04-5,3-4,19-20 6 | 18-24 mos,6,5,22 7 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042992543.60__CC-MAIN-20150728002312-00162-ip-10-236-191-2.ec2.internal__375.csv: -------------------------------------------------------------------------------- 1 | svä“tdiena,pirmdiena,otrdiena,treå¡diena,ceturtdiena,piektdiena,g 2 | 1,2 1,3,4,5,6 2,7 3 | 8,9,10,11,12 1,13 1,14 4 | 15,16 1,17,18 1,19,20 1,21 2 5 | 22 1,23,24,25,26,27,28 1 6 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042991019.80__CC-MAIN-20150728002311-00109-ip-10-236-191-2.ec2.internal__710.csv: -------------------------------------------------------------------------------- 1 | method,1971,fee 2 | standard,5 to 7 business days*,$ 7.00 3 | express,3 business days**,$ 12.00 4 | two day,2 business days***,$ 18.00 5 | overnight,next business day***,$ 25.00 6 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042986615.83__CC-MAIN-20150728002306-00049-ip-10-236-191-2.ec2.internal__1859.csv: -------------------------------------------------------------------------------- 1 | rnd,result,opponent��,rank,score� 2 | 64,win,miles ransom��,�,6-0; 6-4 3 | 32,loss,ben hwang��,�,6-2; 7-5 4 | 2,loss,jackson murphy��,�,wo (inj)woj* 5 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042989018.48__CC-MAIN-20150728002309-00056-ip-10-236-191-2.ec2.internal__1290.csv: -------------------------------------------------------------------------------- 1 | sock size/age,shoe size: us,shoe size: uk,shoe size: euro 2 | 0-3 mos,01,.5,3-4 3 | 3-6 mos,02,1,17 4 | 6-12 mos,03-04,2-3,18-19 5 | 12-18 mos,04-5,16,19-20 6 | 18-24 mos,6,5,22 7 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042991019.80__CC-MAIN-20150728002311-00290-ip-10-236-191-2.ec2.internal__1606.csv: -------------------------------------------------------------------------------- 1 | item #,part #,item description 2 | axxrpfkssd2,axxrpcm2,intel 256mb ddr2 ecc sdram cache memory - 256mb ddr2 sdram - 240-pin 3 | 1078120,273004,intel raid ssd cache w fast path io 4 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042991019.80__CC-MAIN-20150728002311-00290-ip-10-236-191-2.ec2.internal__1606.csv: -------------------------------------------------------------------------------- 1 | item #,part #,item description 2 | 273004,axxrpcm2,intel 256mb ddr2 ecc sdram cache memory - 256mb ddr2 sdram - 240-pin 3 | 1078120,axxrpfkssd2,intel raid ssd cache w fast path io 4 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042989507.42__CC-MAIN-20150728002309-00199-ip-10-236-191-2.ec2.internal__2601.csv: -------------------------------------------------------------------------------- 1 | time,record,monday,tuesday,wednesday,thursday,friday,saturday 2 | all day,3,4,5,6,7,8,9 3 | 1:00 pm,,,,,ascp policy & advocacy monthly briefing call 03/07/2013 - 1:00pm - 2:00pm,, 4 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042990112.92__CC-MAIN-20150728002310-00030-ip-10-236-191-2.ec2.internal__954.csv: -------------------------------------------------------------------------------- 1 | size,free position shots,s,athlete,l,h,xxl 2 | neck,14-14.5,15-15.5,16-16.5,17-17.5,18-18.5,19-19.5 3 | sleeve length,32,33,34,35,36,37 4 | chest,32-35,35-38,38-41,42-45,46-49,50-53 5 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042988860.88__CC-MAIN-20150728002308-00278-ip-10-236-191-2.ec2.internal__245.csv: -------------------------------------------------------------------------------- 1 | odbc support,enabled 2 | active persistent links,0 3 | active links,0 4 | odbc library,unixodbc 5 | odbc_include,-i/usr/include 6 | odbc_lflags,-l/usr/lib64 7 | odbc_libs,-lodbc 8 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042989018.48__CC-MAIN-20150728002309-00056-ip-10-236-191-2.ec2.internal__1290.csv: -------------------------------------------------------------------------------- 1 | sock size/age,shoe size: us,shoe size: uk,shoe size: euro 2 | 0-3 mos,01,.5,16 3 | 3-6 mos,02,1,17 4 | 6-12 mos,03-04,2-3,18-19 5 | 12-18 mos,04-5,3-4,19-20 6 | 18-24 mos,6,5,22 7 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042991019.80__CC-MAIN-20150728002311-00290-ip-10-236-191-2.ec2.internal__1606.csv: -------------------------------------------------------------------------------- 1 | item #,part #,item description 2 | 273004,axxrpcm2,intel 256mb ddr2 ecc sdram cache memory - 256mb ddr2 sdram - 240-pin 3 | 1078120,axxrpfkssd2,intel raid ssd cache w fast path io 4 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042989507.42__CC-MAIN-20150728002309-00199-ip-10-236-191-2.ec2.internal__2601.csv: -------------------------------------------------------------------------------- 1 | time,sunday,monday,tuesday,wednesday,thursday,friday,saturday 2 | all day,3,4,5,6,7,8,9 3 | 1:00 pm,,,,,ascp policy & advocacy monthly briefing call 03/07/2013 - 1:00pm - 2:00pm,, 4 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042989891.18__CC-MAIN-20150728002309-00291-ip-10-236-191-2.ec2.internal__436.csv: -------------------------------------------------------------------------------- 1 | ,event,category,name,date 2 | 5,cross at the college,a race,cole sprague,9/25 3 | 30,cross crusade,category c,adrian bennett,10/16 4 | 47,battle at barlow,category c,matthew edwards,10/20 5 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042990112.92__CC-MAIN-20150728002310-00221-ip-10-236-191-2.ec2.internal__1384.csv: -------------------------------------------------------------------------------- 1 | size,us,inches,china,japan (cm),eu,uk 2 | xs,6/7,9.125,235,23,36-37,4 3 | s,1,9.5,245,5.7,38-39,wisconsin 4 | m,8/9,9.875,255,25,39-40,6 5 | 332.98,9/10,10.375,(1764–1833),26,40-41,7 6 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042992543.60__CC-MAIN-20150728002312-00162-ip-10-236-191-2.ec2.internal__375.csv: -------------------------------------------------------------------------------- 1 | svä“tdiena,pirmdiena,otrdiena,treå¡diena,ceturtdiena,piektdiena,sestdiena 2 | 1,2 1,3,4,5,6 2,17 3 | 8,9,10,11,12 1,13 1,14 4 | 15,26,7,18 1,19,20 1,21 2 5 | 22 1,23,24,25,16 1,27,28 1 6 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042981856.5__CC-MAIN-20150728002301-00062-ip-10-236-191-2.ec2.internal__1831.csv: -------------------------------------------------------------------------------- 1 | candidate,raised,spent,cash on hand,last report 2 | david valadao (r) (60% of vote),"$1,315,897","$1,181,113",ctyp152152693,"december 31, 2012" 3 | 5,"$123,905","$99,754","$14,718",3 4 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042989507.42__CC-MAIN-20150728002309-00199-ip-10-236-191-2.ec2.internal__2601.csv: -------------------------------------------------------------------------------- 1 | time,sunday,monday,tuesday,wednesday,thursday,friday,saturday 2 | 1.0.6stable,3,4,5,6,7,8,9 3 | 1:00 pm,,,,,ascp policy & advocacy monthly briefing call 03/07/2013 - 1:00pm - 2:00pm,, 4 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042989891.18__CC-MAIN-20150728002309-00291-ip-10-236-191-2.ec2.internal__436.csv: -------------------------------------------------------------------------------- 1 | ,event,category,name,eu 2 | 5,cross at the college,a race,cole sprague,10/20 3 | 30,cross crusade,category c,adrian bennett,10/16 4 | 47,battle at barlow,category c,matthew edwards,9/25 5 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042988312.76__CC-MAIN-20150728002308-00140-ip-10-236-191-2.ec2.internal__1485.csv: -------------------------------------------------------------------------------- 1 | #,player,sog,ga,saves,min 2 | 0,taylor cornelius.... *,4,-,4,45:00 3 | 1,annie stephens......,7,-,7,45:00 4 | tm,team................,1,-,1,0:00 5 | ,totals..............,12,0,12,90:00 6 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042992543.60__CC-MAIN-20150728002312-00162-ip-10-236-191-2.ec2.internal__375.csv: -------------------------------------------------------------------------------- 1 | svä“tdiena,pirmdiena,otrdiena,treå¡diena,ceturtdiena,piektdiena,sestdiena 2 | 1,2 1,3,4,5,6 2,7 3 | 8,9,10,11,12 1,13 1,14 4 | 15,16 1,17,18 1,19,20 1,21 2 5 | 22 1,23,24,25,26,27,28 1 6 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042988312.76__CC-MAIN-20150728002308-00140-ip-10-236-191-2.ec2.internal__1485.csv: -------------------------------------------------------------------------------- 1 | #,player,sog,ga,saves,min 2 | 0,taylor cornelius.... *,4,-,4,45:00 3 | 1,annie stephens......,7,-,7,45:00 4 | tm,team................,1,-,1,0:00 5 | ,totals..............,12,0,12,90:00 6 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042988051.33__CC-MAIN-20150728002308-00108-ip-10-236-191-2.ec2.internal__614.csv: -------------------------------------------------------------------------------- 1 | num,name,team,gp,g 2 | 91,"lovas, ricky",sumen,7,23 3 | 19,"stellino, jason",sumen,7,20 4 | 15,"mcgowan, nick",sumen,7,97 5 | 5,"ibarra, marty",sumen,7,13 6 | 22,"courtland, bryant",sumen,7,12 7 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042989826.86__CC-MAIN-20150728002309-00046-ip-10-236-191-2.ec2.internal__1968.csv: -------------------------------------------------------------------------------- 1 | title,price,purchase 2 | 2015 carlat self-assessment course,$377.00, 3 | antipsychotic update—january 2013 (1 credit),$14.95, 4 | antipsychotics update–february 2015 (1 credit),$14.95, 5 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042987228.91__CC-MAIN-20150728002307-00257-ip-10-236-191-2.ec2.internal__622.csv: -------------------------------------------------------------------------------- 1 | num,name,team,gp,star 2 | 10,"scheu, nikki",#4 ri,4,8 3 | 41,"mackintosh, anelle",#2 ri,4,7 4 | 56,"eden , rina",#3 ri,4,5 5 | 43,5,#1 ri,4,"roberts, hailey" 6 | 12,"squires, mary",#3 ri,4,5 7 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042988051.33__CC-MAIN-20150728002308-00108-ip-10-236-191-2.ec2.internal__614.csv: -------------------------------------------------------------------------------- 1 | name,name,pegi,gp,g 2 | 91,"lovas, ricky",sumen,7,23 3 | 19,"stellino, jason",sumen,7,20 4 | 97,"mcgowan, nick",sumen,7,15 5 | 5,"ibarra, marty",sumen,7,13 6 | 22,"courtland, bryant",sumen,7,12 7 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042989826.86__CC-MAIN-20150728002309-00046-ip-10-236-191-2.ec2.internal__1968.csv: -------------------------------------------------------------------------------- 1 | title,price,purchase 2 | 2015 carlat self-assessment course,$377.00, 3 | antipsychotic update—january 2013 (1 credit),$14.95, 4 | antipsychotics update–february 2015 (1 credit),$14.95, 5 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042989891.18__CC-MAIN-20150728002309-00291-ip-10-236-191-2.ec2.internal__436.csv: -------------------------------------------------------------------------------- 1 | ,event,category,name,date 2 | 5,cross at the college,a race,cole sprague,10/20 3 | 30,cross crusade,category c,adrian bennett,10/16 4 | 47,battle at barlow,category c,matthew edwards,9/25 5 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042989826.86__CC-MAIN-20150728002309-00046-ip-10-236-191-2.ec2.internal__1968.csv: -------------------------------------------------------------------------------- 1 | title,price,purchase 2 | 2015 carlat self-assessment course,$377.00, 3 | antipsychotic update—january 2013 (1 credit),$14.95, 4 | antipsychotics update–february 2015 (1 credit),$14.95, 5 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042987228.91__CC-MAIN-20150728002307-00257-ip-10-236-191-2.ec2.internal__622.csv: -------------------------------------------------------------------------------- 1 | num,name,team,gp,star 2 | 10,"scheu, nikki",#4 ri,4,8 3 | 41,"mackintosh, anelle",#2 ri,4,7 4 | 56,"eden , rina",#3 ri,4,5 5 | 43,"roberts, hailey",#1 ri,4,5 6 | 12,"squires, mary",#3 ri,4,5 7 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042986444.39__CC-MAIN-20150728002306-00031-ip-10-236-191-2.ec2.internal__523.csv: -------------------------------------------------------------------------------- 1 | num,name,team,gp,pts 2 | 91,"lovas, ricky",sumen,7,39 3 | 19,"stellino, jason",sumen,7,25 4 | 97,"mcgowan, nick",sumen,7,27 5 | 22,"courtland, bryant",sumen,7,34 6 | 5,"ibarra, marty",sumen,7,24 7 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042988065.26__CC-MAIN-20150728002308-00287-ip-10-236-191-2.ec2.internal__1557.csv: -------------------------------------------------------------------------------- 1 | per,shf,avg,toi,ev tot,pp tot,sh tot 2 | 1,00:00,00:40,06:04,06:04,9,00:00 3 | 2,7,00:54,06:21,00:00,00:00,06:21 4 | 3,11,00:29,05:26,03:57,00:00,01:29 5 | tot,27,00:39,17:51,16:22,00:00,01:29 6 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042988051.33__CC-MAIN-20150728002308-00270-ip-10-236-191-2.ec2.internal__770.csv: -------------------------------------------------------------------------------- 1 | method,estimated delivery time,fee 2 | standard,5 to 7 business days*,$ 7.00 3 | express,3 business days**,$ 12.00 4 | two day,2 business days***,$ 18.00 5 | overnight,next business day***,$ 25.00 6 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042991019.80__CC-MAIN-20150728002311-00109-ip-10-236-191-2.ec2.internal__710.csv: -------------------------------------------------------------------------------- 1 | method,estimated delivery time,fee 2 | standard,5 to 7 business days*,$ 7.00 3 | express,3 business days**,$ 12.00 4 | two day,2 business days***,$ 18.00 5 | overnight,next business day***,$ 25.00 6 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042986444.39__CC-MAIN-20150728002306-00031-ip-10-236-191-2.ec2.internal__523.csv: -------------------------------------------------------------------------------- 1 | num,name,team,gp,pts 2 | 91,"lovas, ricky",sumen,7,39 3 | 19,"stellino, jason",sumen,7,34 4 | 97,"mcgowan, nick",sumen,7,27 5 | 22,"courtland, bryant",sumen,7,25 6 | 5,"ibarra, marty",sumen,7,24 7 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042989234.2__CC-MAIN-20150728002309-00204-ip-10-236-191-2.ec2.internal__253.csv: -------------------------------------------------------------------------------- 1 | 9,title 2 | jill h. allor,committee co-chair 3 | r. kenton denny,committee co-chair 4 | earl cheek,committee member 5 | teresa buchanan,committee member 6 | nathan gottfiried,dean's representative 7 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042990123.20__CC-MAIN-20150728002310-00184-ip-10-236-191-2.ec2.internal__2231.csv: -------------------------------------------------------------------------------- 1 | ,,, 2 | principal investigator:,yiming li,huashan hospital, 3 | principal investigator:,qinghua wang,huashan hospital/st michael's hospital, 4 | principal investigator:,zheng jiao,huashan hospital, 5 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042988051.33__CC-MAIN-20150728002308-00270-ip-10-236-191-2.ec2.internal__770.csv: -------------------------------------------------------------------------------- 1 | founded,estimated delivery time,bb 2 | standard,5 to 7 business days*,$ 7.00 3 | express,3 business days**,$ 12.00 4 | two day,2 business days***,$ 18.00 5 | overnight,next business day***,$ 25.00 6 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042986444.39__CC-MAIN-20150728002306-00031-ip-10-236-191-2.ec2.internal__523.csv: -------------------------------------------------------------------------------- 1 | num,name,team,gp,pts 2 | 91,"lovas, ricky",sumen,7,39 3 | 19,"stellino, jason",sumen,7,34 4 | 97,"mcgowan, nick",sumen,7,27 5 | 22,"courtland, bryant",sumen,7,25 6 | 5,"ibarra, marty",sumen,7,24 7 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042988051.33__CC-MAIN-20150728002308-00108-ip-10-236-191-2.ec2.internal__614.csv: -------------------------------------------------------------------------------- 1 | num,name,team,gp,g 2 | 91,"lovas, ricky",sumen,7,23 3 | 19,"stellino, jason",sumen,7,20 4 | 97,"mcgowan, nick",sumen,7,15 5 | 5,"ibarra, marty",sumen,7,13 6 | 22,"courtland, bryant",sumen,7,12 7 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042988065.26__CC-MAIN-20150728002308-00287-ip-10-236-191-2.ec2.internal__1557.csv: -------------------------------------------------------------------------------- 1 | per,shf,avg,toi,ev tot,pp tot,sh tot 2 | 1,9,00:40,06:04,06:04,00:00,00:00 3 | 2,7,00:54,06:21,06:21,00:00,00:00 4 | 3,11,00:29,05:26,03:57,00:00,01:29 5 | tot,27,00:39,17:51,16:22,00:00,01:29 6 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042989234.2__CC-MAIN-20150728002309-00204-ip-10-236-191-2.ec2.internal__253.csv: -------------------------------------------------------------------------------- 1 | advisor name,title 2 | jill h. allor,committee co-chair 3 | r. kenton denny,committee co-chair 4 | earl cheek,committee member 5 | teresa buchanan,committee member 6 | nathan gottfiried,erika zuchold 7 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042987775.70__CC-MAIN-20150728002307-00015-ip-10-236-191-2.ec2.internal__437.csv: -------------------------------------------------------------------------------- 1 | ,monday–saturday 2 | 10:00 am,2 3 | 11:00 am,journey to space 3d 4 | noon,prehistoric planet 3d 5 | heliokles ii,great white shark 3d 6 | 3:00 pm,journey to space 3d 7 | 14.19,prehistoric planet 3d 8 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042989042.37__CC-MAIN-20150728002309-00074-ip-10-236-191-2.ec2.internal__2439.csv: -------------------------------------------------------------------------------- 1 | location,local time 2 | euskirchen (germany - north rhine-westphalia),"sunday, august 2, 2015 at 12:35:02 pm" 3 | herisau (switzerland - appenzell ausserrhoden),"sunday, august 2, 2015 at 12:35:02 pm" 4 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042987228.91__CC-MAIN-20150728002307-00257-ip-10-236-191-2.ec2.internal__622.csv: -------------------------------------------------------------------------------- 1 | num,name,team,gp,wind direction 2 | 10,"scheu, nikki",#4 ri,4,8 3 | 41,"mackintosh, anelle",#2 ri,4,7 4 | 56,"eden , rina",#3 ri,4,5 5 | 43,"roberts, hailey",#1 ri,4,5 6 | 12,"squires, mary",#3 ri,4,5 7 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042988962.66__CC-MAIN-20150728002308-00231-ip-10-236-191-2.ec2.internal__1481.csv: -------------------------------------------------------------------------------- 1 | nickname,height (in),height (cm),weight (lbs),pf 2 | 12m,"26-29""",66-73.7,17-22 lbs,7.7-9.9 kgs 3 | 18m,"29-31""",73.7-78.7,22-27 lbs,9.9-12.2 kgs 4 | 24m,"31-33""",78.7-83.8,27-30 lbs,12.2-13.6 kgs 5 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042990123.20__CC-MAIN-20150728002310-00184-ip-10-236-191-2.ec2.internal__2231.csv: -------------------------------------------------------------------------------- 1 | ,,, 2 | principal investigator:,yiming li,huashan hospital, 3 | principal investigator:,qinghua wang,huashan hospital/st michael's hospital, 4 | principal investigator:,zheng jiao,huashan hospital, 5 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042988051.33__CC-MAIN-20150728002308-00270-ip-10-236-191-2.ec2.internal__770.csv: -------------------------------------------------------------------------------- 1 | method,estimated delivery time,fee 2 | standard,5 to 7 business days*,$ 7.00 3 | express,3 business days**,$ 12.00 4 | two day,2 business days***,$ 18.00 5 | overnight,next business day***,$ 25.00 6 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042991019.80__CC-MAIN-20150728002311-00109-ip-10-236-191-2.ec2.internal__710.csv: -------------------------------------------------------------------------------- 1 | method,estimated delivery time,fee 2 | standard,5 to 7 business days*,$ 7.00 3 | express,3 business days**,$ 12.00 4 | two day,2 business days***,$ 18.00 5 | overnight,next business day***,$ 25.00 6 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042989331.34__CC-MAIN-20150728002309-00143-ip-10-236-191-2.ec2.internal__1055.csv: -------------------------------------------------------------------------------- 1 | #,player,gp,g,a,tp 2 | 1.,adam pawlick (f),56,32,34,0 3 | 2.,corey banfield (f),.500,t18m 9/13,41,61 4 | 3.,matt gingera (f),22,34,24,58 5 | 4.,7–39,54,12,45,57 6 | 5.,matt whitehead (f),n-up-a29,6,35,56 7 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042986806.32__CC-MAIN-20150728002306-00186-ip-10-236-191-2.ec2.internal__960.csv: -------------------------------------------------------------------------------- 1 | features,trial,premium 2 | fix your dll errors,fix 1 dll error,1 3 | fix your registry errors,fix 15 registry errors,fix unlimited registry errors 4 | semarang,free download now,from $29.95* buy premium 5 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042988065.26__CC-MAIN-20150728002308-00287-ip-10-236-191-2.ec2.internal__1557.csv: -------------------------------------------------------------------------------- 1 | per,shf,avg,opponents in the final,ev tot,pp tot,ff 2 | 1,9,00:40,06:04,06:04,00:00,00:00 3 | 2,7,00:54,06:21,06:21,00:00,00:00 4 | 3,11,00:29,05:26,03:57,00:00,01:29 5 | tot,27,00:39,17:51,16:22,00:00,01:29 6 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042989042.37__CC-MAIN-20150728002309-00074-ip-10-236-191-2.ec2.internal__2439.csv: -------------------------------------------------------------------------------- 1 | popular vote,local time 2 | euskirchen (germany - north rhine-westphalia),"sunday, august 2, 2015 at 12:35:02 pm" 3 | herisau (switzerland - appenzell ausserrhoden),"sunday, august 2, 2015 at 12:35:02 pm" 4 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042989331.34__CC-MAIN-20150728002309-00098-ip-10-236-191-2.ec2.internal__350.csv: -------------------------------------------------------------------------------- 1 | school level,school 2 | primary school,washington elementary 3 | primary school,lincoln plus high 4 | middle school,herbert hoover middle 5 | middle school,lincoln plus high 6 | high school,lincoln plus high 7 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042989234.2__CC-MAIN-20150728002309-00204-ip-10-236-191-2.ec2.internal__253.csv: -------------------------------------------------------------------------------- 1 | advisor name,title 2 | jill h. allor,committee co-chair 3 | r. kenton denny,committee co-chair 4 | earl cheek,committee member 5 | teresa buchanan,committee member 6 | nathan gottfiried,dean's representative 7 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042989331.34__CC-MAIN-20150728002309-00143-ip-10-236-191-2.ec2.internal__1055.csv: -------------------------------------------------------------------------------- 1 | #,player,gp,g,a,tp 2 | 1.,adam pawlick (f),56,32,34,66 3 | 2.,corey banfield (f),47,20,41,61 4 | 3.,matt gingera (f),53,34,24,58 5 | 4.,ryan salvis (f),54,12,45,57 6 | 5.,matt whitehead (f),56,21,35,56 7 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042987402.78__CC-MAIN-20150728002307-00143-ip-10-236-191-2.ec2.internal__1993.csv: -------------------------------------------------------------------------------- 1 | games,age,city,sport,event,team,noc,rank,medal, 2 | 1960 summer,26,roma,rowing,men's coxless fours,italy,ita,2,silver, 3 | 1968 summer,34,ciudad de mã©xico,rowing,men's coxless fours,italy,ita,3,bronze, 4 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042989042.37__CC-MAIN-20150728002309-00074-ip-10-236-191-2.ec2.internal__2439.csv: -------------------------------------------------------------------------------- 1 | location,local time 2 | euskirchen (germany - north rhine-westphalia),"sunday, august 2, 2015 at 12:35:02 pm" 3 | herisau (switzerland - appenzell ausserrhoden),"sunday, august 2, 2015 at 12:35:02 pm" 4 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042988962.66__CC-MAIN-20150728002308-00231-ip-10-236-191-2.ec2.internal__1481.csv: -------------------------------------------------------------------------------- 1 | age,height (in),height (cm),weight (lbs),weight (kgs) 2 | 12m,"26-29""",66-73.7,17-22 lbs,7.7-9.9 kgs 3 | 18m,"29-31""",73.7-78.7,22-27 lbs,9.9-12.2 kgs 4 | 24m,"31-33""",78.7-83.8,27-30 lbs,12.2-13.6 kgs 5 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042988650.6__CC-MAIN-20150728002308-00168-ip-10-236-191-2.ec2.internal__2261.csv: -------------------------------------------------------------------------------- 1 | availability,stability,weights 2 | millennium (stnd),straight,"150 class, 160-175" 3 | quantum,straight,"150 class, 160-175" 4 | sirius,straight,"150 class, 151-175" 5 | sirius dyed,straight,"150 class, 160-175" 6 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042989018.40__CC-MAIN-20150728002309-00178-ip-10-236-191-2.ec2.internal__1420.csv: -------------------------------------------------------------------------------- 1 | compare,item/cat #,type,length,width,height, 2 | compare,contractor bag 48-55-3530,storage & tool belts,"26.5""","13""","14""", 3 | compare,bodygripâ® router carrying case 48-55-5615,storage & tool belts,,,, 4 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042989331.34__CC-MAIN-20150728002309-00098-ip-10-236-191-2.ec2.internal__350.csv: -------------------------------------------------------------------------------- 1 | school level,school 2 | primary school,washington elementary 3 | primary school,lincoln plus high 4 | middle school,herbert hoover middle 5 | middle school,lincoln plus high 6 | high school,lincoln plus high 7 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042988962.66__CC-MAIN-20150728002308-00231-ip-10-236-191-2.ec2.internal__1481.csv: -------------------------------------------------------------------------------- 1 | age,height (in),height (cm),weight (lbs),weight (kgs) 2 | 12m,"26-29""",66-73.7,17-22 lbs,7.7-9.9 kgs 3 | 18m,"29-31""",73.7-78.7,22-27 lbs,9.9-12.2 kgs 4 | grêmio,"31-33""",78.7-83.8,27-30 lbs,12.2-13.6 kgs 5 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042987402.78__CC-MAIN-20150728002307-00143-ip-10-236-191-2.ec2.internal__1993.csv: -------------------------------------------------------------------------------- 1 | run 1 (sg),age,city,sport,event,team,noc,rank,medal, 2 | 1960 summer,26,roma,rowing,men's coxless fours,italy,ita,2,silver, 3 | 1968 summer,34,ciudad de mã©xico,rowing,men's coxless fours,italy,ita,3,bronze, 4 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042988650.6__CC-MAIN-20150728002308-00168-ip-10-236-191-2.ec2.internal__2261.csv: -------------------------------------------------------------------------------- 1 | availability,stability,weights 2 | millennium (stnd),straight,"150 class, 160-175" 3 | quantum,straight,"150 class, 160-175" 4 | sirius,straight,"150 class, 151-175" 5 | sirius dyed,straight,"150 class, 160-175" 6 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042989018.40__CC-MAIN-20150728002309-00178-ip-10-236-191-2.ec2.internal__1420.csv: -------------------------------------------------------------------------------- 1 | compare,item/cat #,type,length,width,height, 2 | compare,contractor bag 48-55-3530,storage & tool belts,"26.5""","13""","14""", 3 | compare,bodygripâ® router carrying case 48-55-5615,storage & tool belts,,,, 4 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042989018.40__CC-MAIN-20150728002309-00178-ip-10-236-191-2.ec2.internal__1420.csv: -------------------------------------------------------------------------------- 1 | compare,item/cat #,type,length,width,height, 2 | compare,contractor bag 48-55-3530,storage & tool belts,"26.5""","13""","14""", 3 | compare,bodygripâ® router carrying case 48-55-5615,storage & tool belts,,,, 4 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042989331.34__CC-MAIN-20150728002309-00098-ip-10-236-191-2.ec2.internal__350.csv: -------------------------------------------------------------------------------- 1 | school level,school 2 | primary school,washington elementary 3 | primary school,lincoln plus high 4 | middle school,herbert hoover middle 5 | middle school,lincoln plus high 6 | high school,lincoln plus high 7 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042986615.83__CC-MAIN-20150728002306-00084-ip-10-236-191-2.ec2.internal__747.csv: -------------------------------------------------------------------------------- 1 | ,,,,, 2 | assists,games,record,113,season,over/under 3 | 0-4,19.00,6w v 13 l,32.00%,40.20%,-8.20% 4 | 5-9 assists,54.00,21w 32 l,38.80%,40.20%,2.0 5 | 10-14 assists,9.00,6w v 3 l,67.00%,40.20%,kelly versteeg 6 | ,,,,, 7 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042987402.78__CC-MAIN-20150728002307-00143-ip-10-236-191-2.ec2.internal__1993.csv: -------------------------------------------------------------------------------- 1 | games,age,city,sport,event,team,noc,rank,medal, 2 | 1960 summer,26,roma,rowing,tannis slimmon,italy,ita,2,silver, 3 | 1968 summer,34,ciudad de mã©xico,rowing,men's coxless fours,los angeles clippers,ita,3,bronze, 4 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042986806.32__CC-MAIN-20150728002306-00042-ip-10-236-191-2.ec2.internal__367.csv: -------------------------------------------------------------------------------- 1 | duration,w,l,era,g,gs,sv,ip,h,er,bb,so,whip 2 | last 7 games,1,1,5.63,7,7,0,40.0,46,25,9,30,1.38 3 | last 15 games,112.0,4,5.21,15,15,0,1.42,103,50,20,72,86.1 4 | last 30 games,4,8,5.38,19,19,0,4,134,67,24,94,1.41 5 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042988061.16__CC-MAIN-20150728002308-00295-ip-10-236-191-2.ec2.internal__1098.csv: -------------------------------------------------------------------------------- 1 | #,player,gp,g,a,tp 2 | 1.,dylan strome (f),68,45,84,129 3 | 2.,mitchell marner (f),63,44,82,126 4 | joseph blandisi (f),connor mcdavid (f),47,44,76,120 5 | 4.,3.,68,60,52,112 6 | 5.,christian dvorak (f),66,41,68,109 7 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042989331.34__CC-MAIN-20150728002309-00143-ip-10-236-191-2.ec2.internal__1055.csv: -------------------------------------------------------------------------------- 1 | #,player,gp,100+,a,nationality 2 | 1.,adam pawlick (f),56,32,34,66 3 | 2.,corey banfield (f),47,20,41,61 4 | 3.,matt gingera (f),53,34,24,58 5 | 4.,ryan salvis (f),54,12,45,57 6 | 5.,matt whitehead (f),56,21,35,56 7 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042987775.70__CC-MAIN-20150728002307-00015-ip-10-236-191-2.ec2.internal__437.csv: -------------------------------------------------------------------------------- 1 | ,monday–saturday 2 | 10:00 am,great white shark 3d 3 | 11:00 am,journey to space 3d 4 | noon,prehistoric planet 3d 5 | 2:00 pm,great white shark 3d 6 | 3:00 pm,journey to space 3d 7 | 4:00 pm,prehistoric planet 3d 8 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042987775.70__CC-MAIN-20150728002307-00015-ip-10-236-191-2.ec2.internal__437.csv: -------------------------------------------------------------------------------- 1 | ,monday–saturday 2 | 10:00 am,great white shark 3d 3 | 11:00 am,journey to space 3d 4 | noon,prehistoric planet 3d 5 | 2:00 pm,great white shark 3d 6 | 3:00 pm,journey to space 3d 7 | 4:00 pm,prehistoric planet 3d 8 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042988650.6__CC-MAIN-20150728002308-00168-ip-10-236-191-2.ec2.internal__2261.csv: -------------------------------------------------------------------------------- 1 | availability,stability,weights 2 | millennium (stnd),straight,"150 class, 160-175" 3 | quantum,straight,"150 class, 160-175" 4 | sirius,straight,"150 class, 151-175" 5 | sirius dyed,straight,"150 class, 160-175" 6 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042986806.32__CC-MAIN-20150728002306-00042-ip-10-236-191-2.ec2.internal__367.csv: -------------------------------------------------------------------------------- 1 | duration,w,l,era,g,gs,sv,ip,h,er,bb,so,whip 2 | last 7 games,1,1,5.63,7,7,0,40.0,46,25,9,30,1.38 3 | last 15 games,4,4,5.21,15,15,0,86.1,103,50,20,72,1.42 4 | last 30 games,4,8,5.38,19,19,0,112.0,134,67,24,94,1.41 5 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042986423.95__CC-MAIN-20150728002306-00337-ip-10-236-191-2.ec2.internal__484.csv: -------------------------------------------------------------------------------- 1 | ,s,m,l,xl 2 | size,8,10-12,14-16,18 3 | chest,27,28-30,31-33,34 4 | waist,26-27,24-25,23.5,28 5 | 24.5,arm/sleeve from center back neck,26-27.5,28.5-30,31 6 | neck,12,12.5-13,13.5-14,14.5 7 | length,22.75,25,27.25,29.5 8 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042987228.91__CC-MAIN-20150728002307-00306-ip-10-236-191-2.ec2.internal__1005.csv: -------------------------------------------------------------------------------- 1 | ,application,bulb size, 2 | ,front fog,h11,see bulbs 3 | ,sidelight,501,see bulbs 4 | ,front indicator,382,see bulbs 5 | ,side indicator,-, 6 | ,interior,-,- 7 | ,drl,-,- 8 | ,dashboard,-,- 9 | ,cornering,-,- 10 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042988051.33__CC-MAIN-20150728002308-00259-ip-10-236-191-2.ec2.internal__541.csv: -------------------------------------------------------------------------------- 1 | first name,last name,suffix,covered official position (if applicable),new 2 | john,colbert,,schedule c employee dept. of labor 1996-2001,jim 3 | lee,foley,iii,, 4 | ,sourwine,,pro. staff memb. sen. approps comm 1975-2007, 5 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438043062635.98__CC-MAIN-20150728002422-00195-ip-10-236-191-2.ec2.internal__742.csv: -------------------------------------------------------------------------------- 1 | lunes,maã±ana,tarde,noche 2 | martes,maã±ana,tarde,noche 3 | miã©rcoles,maã±ana,tarde,noche 4 | jueves,maã±ana,tarde,noche 5 | viernes,maã±ana,tarde,noche 6 | sã¡bado,maã±ana,tarde,noche 7 | domingo,maã±ana,tarde,noche 8 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042986423.95__CC-MAIN-20150728002306-00337-ip-10-236-191-2.ec2.internal__484.csv: -------------------------------------------------------------------------------- 1 | ,s,county,l,xl 2 | size,8,10-12,14-16,18 3 | chest,27,28-30,31-33,34 4 | waist,23.5,24-25,26-27,28 5 | arm/sleeve from center back neck,24.5,26-27.5,28.5-30,31 6 | neck,12,12.5-13,13.5-14,14.5 7 | length,22.75,25,27.25,29.5 8 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042986615.83__CC-MAIN-20150728002306-00084-ip-10-236-191-2.ec2.internal__747.csv: -------------------------------------------------------------------------------- 1 | ,,,,, 2 | assists,games,record,percentage,season,over/under 3 | 0-4,19.00,6w v 13 l,32.00%,40.20%,-8.20% 4 | 5-9 assists,54.00,21w 32 l,38.80%,40.20%,-1.40% 5 | 10-14 assists,9.00,6w v 3 l,67.00%,40.20%,26.80% 6 | ,,,,, 7 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042987228.91__CC-MAIN-20150728002307-00306-ip-10-236-191-2.ec2.internal__1005.csv: -------------------------------------------------------------------------------- 1 | ,application,bulb size, 2 | ,front fog,h11,see bulbs 3 | ,sidelight,501,see bulbs 4 | ,front indicator,382,see bulbs 5 | ,side indicator,-, 6 | ,interior,-,- 7 | ,drl,-,- 8 | ,dashboard,-,- 9 | ,cornering,-,- 10 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042988051.33__CC-MAIN-20150728002308-00259-ip-10-236-191-2.ec2.internal__541.csv: -------------------------------------------------------------------------------- 1 | first name,last name,dates,covered official position (if applicable),new 2 | john,colbert,,schedule c employee dept. of labor 1996-2001, 3 | lee,foley,iii,, 4 | jim,sourwine,,pro. staff memb. sen. approps comm 1975-2007, 5 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438043062635.98__CC-MAIN-20150728002422-00195-ip-10-236-191-2.ec2.internal__742.csv: -------------------------------------------------------------------------------- 1 | lunes,maã±ana,tarde,noche 2 | martes,maã±ana,tarde,noche 3 | miã©rcoles,maã±ana,tarde,noche 4 | jueves,maã±ana,tarde,noche 5 | viernes,maã±ana,tarde,noche 6 | sã¡bado,maã±ana,tarde,noche 7 | domingo,maã±ana,tarde,noche 8 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042986423.95__CC-MAIN-20150728002306-00337-ip-10-236-191-2.ec2.internal__484.csv: -------------------------------------------------------------------------------- 1 | ,s,m,l,xl 2 | size,8,10-12,14-16,18 3 | chest,27,28-30,31-33,34 4 | waist,23.5,24-25,26-27,28 5 | arm/sleeve from center back neck,24.5,26-27.5,28.5-30,31 6 | neck,12,12.5-13,13.5-14,14.5 7 | length,22.75,25,27.25,29.5 8 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042986615.83__CC-MAIN-20150728002306-00084-ip-10-236-191-2.ec2.internal__747.csv: -------------------------------------------------------------------------------- 1 | ,,,,, 2 | assists,games,record,percentage,season,over/under 3 | 0-4,19.00,6w v 13 l,32.00%,40.20%,-8.20% 4 | 5-9 assists,54.00,21w 32 l,38.80%,40.20%,-1.40% 5 | 10-14 assists,9.00,6w v 3 l,67.00%,40.20%,26.80% 6 | ,,,,, 7 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042987228.91__CC-MAIN-20150728002307-00306-ip-10-236-191-2.ec2.internal__1005.csv: -------------------------------------------------------------------------------- 1 | ,application,bulb size, 2 | ,front fog,h11,see bulbs 3 | ,sidelight,501,see bulbs 4 | ,front indicator,382,see bulbs 5 | ,side indicator,-, 6 | ,interior,-,- 7 | ,drl,-,- 8 | ,dashboard,-,- 9 | ,cornering,-,- 10 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438043062635.98__CC-MAIN-20150728002422-00195-ip-10-236-191-2.ec2.internal__742.csv: -------------------------------------------------------------------------------- 1 | lunes,maã±ana,tarde,noche 2 | martes,maã±ana,tarde,noche 3 | miã©rcoles,maã±ana,tarde,noche 4 | jueves,maã±ana,tarde,noche 5 | viernes,maã±ana,tarde,noche 6 | sã¡bado,maã±ana,tarde,noche 7 | domingo,maã±ana,tarde,noche 8 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042988061.16__CC-MAIN-20150728002308-00295-ip-10-236-191-2.ec2.internal__1098.csv: -------------------------------------------------------------------------------- 1 | #,player,gp,g,a,tp 2 | 1.,dylan strome (f),68,45,84,129 3 | 2.,mitchell marner (f),63,44,82,126 4 | 3.,connor mcdavid (f),47,44,76,120 5 | 4.,joseph blandisi (f),68,52,60,112 6 | 5.,christian dvorak (f),66,41,68,109 7 | -------------------------------------------------------------------------------- /env/env.yml: -------------------------------------------------------------------------------- 1 | name: table_emb_dev 2 | channels: 3 | - defaults 4 | dependencies: 5 | - python=3.6 6 | - numpy 7 | - pip 8 | - pandas 9 | - pip: 10 | - allennlp==1.0 11 | - pytorch_pretrained_bert 12 | - pyyaml 13 | - cython 14 | - pandas 15 | - tqdm 16 | - jinja2 17 | 18 | 19 | 20 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042989142.82__CC-MAIN-20150728002309-00287-ip-10-236-191-2.ec2.internal__1807.csv: -------------------------------------------------------------------------------- 1 | name,occupation,birth,death,known for 2 | raf vallone,actor,18-sep-1916,24-dec-1994,south pacific 3 | alida valli,actor,31-may-1921,22-apr-2006,the third man 4 | rossano brazzi,actor,17-feb-1916,31-oct-2002,the greek tycoon 5 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042986806.32__CC-MAIN-20150728002306-00042-ip-10-236-191-2.ec2.internal__367.csv: -------------------------------------------------------------------------------- 1 | yds rush,time,deaths,era,g,gs,sv,zip,h,er,bb,so,score 2 | last 7 games,1,1,5.63,7,7,0,40.0,46,25,9,30,1.38 3 | last 15 games,4,4,5.21,15,15,0,86.1,103,50,20,72,1.42 4 | last 30 games,4,8,5.38,19,19,0,112.0,134,67,24,94,1.41 5 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042988051.33__CC-MAIN-20150728002308-00259-ip-10-236-191-2.ec2.internal__541.csv: -------------------------------------------------------------------------------- 1 | first name,last name,suffix,covered official position (if applicable),new 2 | john,colbert,,schedule c employee dept. of labor 1996-2001, 3 | lee,foley,iii,, 4 | jim,sourwine,,pro. staff memb. sen. approps comm 1975-2007, 5 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042989510.73__CC-MAIN-20150728002309-00063-ip-10-236-191-2.ec2.internal__1159.csv: -------------------------------------------------------------------------------- 1 | ,gp,gs,min/g,fg/g,pct,3pt/g,pct,ft/g,pct,ppg 2 | 2013-14,2,-,6.5,1.0-2.0,50.0,0.0-0.0,-,3.5-4.0,87.5,5.5 3 | 2014-15,4,-,2.0,0.2-0.2,100.0,0.0-0.0,-,0.0-0.2,0.0,0.5 4 | total,6,-,3.5,0.5-0.8,60.0,0.0-0.0,-,1.2-1.5,77.8,2.2 5 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042989142.82__CC-MAIN-20150728002309-00287-ip-10-236-191-2.ec2.internal__1807.csv: -------------------------------------------------------------------------------- 1 | name,occupation,birth,death,known for 2 | rossano brazzi,actor,18-sep-1916,24-dec-1994,south pacific 3 | alida valli,actor,31-may-1921,22-apr-2006,the third man 4 | raf vallone,actor,17-feb-1916,31-oct-2002,the greek tycoon 5 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042990603.54__CC-MAIN-20150728002310-00257-ip-10-236-191-2.ec2.internal__130.csv: -------------------------------------------------------------------------------- 1 | definition/meaning,word/phrase 2 | final game of a double header,nightcap 3 | joist that receives the end of a header in floor or roof framing in order to leave an opening for a staircase or chimney etc.,"trimmer , trimmer joist" 4 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042987174.71__CC-MAIN-20150728002307-00249-ip-10-236-191-2.ec2.internal__1312.csv: -------------------------------------------------------------------------------- 1 | ,this school,state average 2 | white,91%,89% 3 | asian or asian/pacific islander,7%,3% 4 | hispanic,3%,4% 5 | two or more races,0%,2% 6 | hawaiian native/pacific islander,0%,0% 7 | american indian/alaska native,0%,0% 8 | black,0%,2% 9 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042990603.54__CC-MAIN-20150728002310-00257-ip-10-236-191-2.ec2.internal__130.csv: -------------------------------------------------------------------------------- 1 | definition/meaning,word/phrase 2 | final game of a double header,nightcap 3 | joist that receives the end of a header in floor or roof framing in order to leave an opening for a staircase or chimney etc.,"trimmer , trimmer joist" 4 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042981856.5__CC-MAIN-20150728002301-00062-ip-10-236-191-2.ec2.internal__1831.csv: -------------------------------------------------------------------------------- 1 | candidate,raised,album,cash on hand,last report 2 | david valadao (r) (60% of vote),"$1,315,897","$1,181,113","$134,784","december 31, 2012" 3 | john hernandez (d) (40% of vote),"$123,905","$99,754","$14,718","november 26, 2012" 4 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042987127.36__CC-MAIN-20150728002307-00308-ip-10-236-191-2.ec2.internal__1005.csv: -------------------------------------------------------------------------------- 1 | nottinghamshire bowling,f,mdns,runs,wkts,wides,no-balls 2 | guttridge,23,6,61,0,-,- 3 | attewell,46,21,81,4,-,- 4 | brown,25,19,56,0,-,- 5 | jones,21,4,82,3,-,- 6 | dench,8,1,26,0,-,- 7 | dixon,12,5,20,1,-,- 8 | daft,2.2,1,2,2,-,- 9 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042989142.82__CC-MAIN-20150728002309-00287-ip-10-236-191-2.ec2.internal__1807.csv: -------------------------------------------------------------------------------- 1 | name,occupation,birth,death,chart positions 2 | rossano brazzi,actor,18-sep-1916,24-dec-1994,south pacific 3 | alida valli,actor,31-may-1921,22-apr-2006,the third man 4 | raf vallone,actor,17-feb-1916,31-oct-2002,the greek tycoon 5 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042990603.54__CC-MAIN-20150728002310-00257-ip-10-236-191-2.ec2.internal__130.csv: -------------------------------------------------------------------------------- 1 | definition/meaning,word/phrase 2 | final game of a double header,nightcap 3 | joist that receives the end of a header in floor or roof framing in order to leave an opening for a staircase or chimney etc.,"trimmer , trimmer joist" 4 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042981856.5__CC-MAIN-20150728002301-00062-ip-10-236-191-2.ec2.internal__1831.csv: -------------------------------------------------------------------------------- 1 | candidate,raised,spent,cash on hand,last report 2 | david valadao (r) (60% of vote),"$1,315,897","$1,181,113","$134,784","december 31, 2012" 3 | john hernandez (d) (40% of vote),"$123,905","$99,754","$14,718","november 26, 2012" 4 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042987174.71__CC-MAIN-20150728002307-00249-ip-10-236-191-2.ec2.internal__1312.csv: -------------------------------------------------------------------------------- 1 | ,this school,state average 2 | white,91%,89% 3 | 7%,asian or asian/pacific islander,3% 4 | hispanic,3%,4% 5 | two or more races,0%,2% 6 | hawaiian native/pacific islander,0%,0% 7 | american indian/alaska native,0%,0% 8 | black,0%,2% 9 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042989018.48__CC-MAIN-20150728002309-00040-ip-10-236-191-2.ec2.internal__1358.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | 17,"chorus, silent roles: people" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | 0:00,2004 5 | specific doctor:,"doctor’s name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042987127.36__CC-MAIN-20150728002307-00308-ip-10-236-191-2.ec2.internal__1005.csv: -------------------------------------------------------------------------------- 1 | nottinghamshire bowling,overs,mdns,runs,wkts,wides,no-balls 2 | guttridge,23,6,61,0,-,- 3 | attewell,46,21,81,4,-,- 4 | brown,12,19,56,0,-,- 5 | dench,21,5,82,3,-,- 6 | jones,8,1,26,0,-,- 7 | dixon,25,4,20,1,-,- 8 | daft,2.2,1,2,2,-,- 9 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042989510.73__CC-MAIN-20150728002309-00063-ip-10-236-191-2.ec2.internal__1159.csv: -------------------------------------------------------------------------------- 1 | ,gp,gs,precipitation,fg/g,pct,3pt/g,pct,ft/g,women,ppg 2 | 2013-14,2,-,6.5,1.0-2.0,50.0,0.0-0.0,-,3.5-4.0,87.5,5.5 3 | 2014-15,4,-,2.0,0.2-0.2,100.0,0.0-0.0,-,0.0-0.2,0.0,0.5 4 | total,6,-,3.5,0.5-0.8,60.0,0.0-0.0,-,1.2-1.5,77.8,2.2 5 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042986806.32__CC-MAIN-20150728002306-00186-ip-10-236-191-2.ec2.internal__960.csv: -------------------------------------------------------------------------------- 1 | mpg,trial,premium 2 | fix your dll errors,fix 1 dll error,fix unlimited dll errors 3 | fix your registry errors,fix 15 registry errors,fix unlimited registry errors 4 | cost of dll-files fixer,free download now,from $29.95* buy premium 5 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042987174.71__CC-MAIN-20150728002307-00249-ip-10-236-191-2.ec2.internal__1312.csv: -------------------------------------------------------------------------------- 1 | ,this school,state average 2 | white,91%,89% 3 | asian or asian/pacific islander,7%,3% 4 | hispanic,3%,4% 5 | two or more races,0%,2% 6 | hawaiian native/pacific islander,0%,0% 7 | american indian/alaska native,0%,0% 8 | black,0%,2% 9 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042987127.36__CC-MAIN-20150728002307-00308-ip-10-236-191-2.ec2.internal__1005.csv: -------------------------------------------------------------------------------- 1 | nottinghamshire bowling,overs,mdns,runs,wkts,wides,no-balls 2 | guttridge,23,6,61,0,-,- 3 | attewell,46,21,81,4,-,- 4 | brown,25,19,56,0,-,- 5 | jones,21,4,82,3,-,- 6 | dench,8,1,26,0,-,- 7 | dixon,12,5,20,1,-,- 8 | daft,2.2,1,2,2,-,- 9 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042986806.32__CC-MAIN-20150728002306-00186-ip-10-236-191-2.ec2.internal__960.csv: -------------------------------------------------------------------------------- 1 | features,trial,premium 2 | fix your dll errors,fix 1 dll error,fix unlimited dll errors 3 | fix your registry errors,fix 15 registry errors,fix unlimited registry errors 4 | cost of dll-files fixer,free download now,from $29.95* buy premium 5 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042988930.94__CC-MAIN-20150728002308-00013-ip-10-236-191-2.ec2.internal__1079.csv: -------------------------------------------------------------------------------- 1 | pos,team,pld,gd,pts 2 | 1,birmingham,0,0,0 3 | 6,bolton,0,0,0 4 | 3,blackburn,0,0,0 5 | 4,brentford,0,0,0 6 | 5,brighton,0,0,0 7 | 2,derby,0,0,0 8 | 7,burnley,0,0,0 9 | 8,cardiff,0,0,0 10 | 9,charlton,0,0,0 11 | 10,bristol city,0,0,0 12 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438043062723.96__CC-MAIN-20150728002422-00214-ip-10-236-191-2.ec2.internal__833.csv: -------------------------------------------------------------------------------- 1 | ,gp,gs,mpg,off/g,def/g,reb/g,pf/g,dq/g,ast/g,to/g,a/to,stl/g,blk/g 2 | 2012-13,20,-,4.6,0.2,0.4,0.5,0.3,0.0,0.2,0.2,0.1,0.2,0.0 3 | 2013-14,8,-,0.0,1.0,0.3,0.4,0.5,0.0,0.4,4.1,0.8,0.0,3.1 4 | total,28,-,0.5,0.1,0.3,0.5,0.3,0.0,0.2,0.3,0.9,0.1,0.0 5 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042988311.72__CC-MAIN-20150728002308-00230-ip-10-236-191-2.ec2.internal__1981.csv: -------------------------------------------------------------------------------- 1 | ,x-small,small,medium,large,x-large,2x-large 2 | chest (in),"33-34""","35-37""","38-40""","41-43""","44-46""","47-49""" 3 | waist (in),"28""","30""","32-33""","33-34""","36""","38""" 4 | sleeve length (in),"32""","33""","34""","35""","36""","36""" 5 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042988930.94__CC-MAIN-20150728002308-00013-ip-10-236-191-2.ec2.internal__1079.csv: -------------------------------------------------------------------------------- 1 | pos,team,pld,gd,pts 2 | 1,birmingham,0,0,0 3 | 2,blackburn,0,0,0 4 | 3,bolton,0,0,0 5 | 4,brentford,0,0,0 6 | 5,brighton,0,0,0 7 | 6,bristol city,0,0,0 8 | 7,burnley,0,0,0 9 | 8,cardiff,0,0,0 10 | 9,charlton,0,0,0 11 | 10,derby,0,0,0 12 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042988458.74__CC-MAIN-20150728002308-00210-ip-10-236-191-2.ec2.internal__1149.csv: -------------------------------------------------------------------------------- 1 | pressure vessels constructed in accordance with:,minimum,maximum 2 | code paragraphs u-68 and u-69,110%,125% 3 | "code paragraphs u-200, through 1974 edition",100%,110% 4 | api-asme code,100%,110% 5 | dot cylinders,as required by dot regulations, 6 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042988930.94__CC-MAIN-20150728002308-00013-ip-10-236-191-2.ec2.internal__1079.csv: -------------------------------------------------------------------------------- 1 | pos,team,pld,gd,pts 2 | 1,birmingham,0,0,0 3 | 2,blackburn,0,0,0 4 | 3,bolton,0,0,0 5 | 4,brentford,0,0,0 6 | 5,brighton,0,0,0 7 | 6,bristol city,0,0,0 8 | 7,burnley,0,0,0 9 | 8,cardiff,0,0,0 10 | 9,charlton,0,0,0 11 | 10,derby,0,0,0 12 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438043062723.96__CC-MAIN-20150728002422-00214-ip-10-236-191-2.ec2.internal__833.csv: -------------------------------------------------------------------------------- 1 | ,gp,gs,mpg,off/g,def/g,reb/g,pf/g,dq/g,ast/g,to/g,a/to,stl/g,blk/g 2 | 2012-13,20,-,4.6,0.2,0.4,0.5,0.3,0.0,0.2,0.2,1.0,0.2,0.0 3 | 2013-14,8,-,3.1,0.1,0.3,0.4,0.5,0.0,0.4,0.5,0.8,0.0,0.0 4 | total,28,-,4.1,0.1,0.3,0.5,0.3,0.0,0.2,0.3,0.9,0.1,0.0 5 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042988458.74__CC-MAIN-20150728002308-00210-ip-10-236-191-2.ec2.internal__1149.csv: -------------------------------------------------------------------------------- 1 | pressure vessels constructed in accordance with:,minimum,maximum 2 | code paragraphs u-68 and u-69,110%,125% 3 | "code paragraphs u-200, through 1974 edition",100%,110% 4 | api-asme code,100%,110% 5 | dot cylinders,as required by dot regulations, 6 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438043062723.96__CC-MAIN-20150728002422-00214-ip-10-236-191-2.ec2.internal__833.csv: -------------------------------------------------------------------------------- 1 | ,gp,gs,mpg,off/g,def/g,reb/g,pf/g,dq/g,ast/g,to/g,position,stl/g,blk/g 2 | 2012-13,20,-,4.6,0.2,0.4,0.5,0.3,0.0,0.2,0.2,1.0,0.2,0.0 3 | 2013-14,8,-,3.1,0.1,0.3,0.4,0.5,0.0,0.4,0.5,0.8,0.0,0.0 4 | total,28,-,4.1,0.1,0.3,0.5,0.3,0.0,0.2,0.3,0.9,0.1,0.0 5 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042989178.64__CC-MAIN-20150728002309-00150-ip-10-236-191-2.ec2.internal__362.csv: -------------------------------------------------------------------------------- 1 | business,s,m,t,w,t,f,s 2 | "go to week of jan 27, 2013",27,28,29,30,31,1,2 3 | "go to week of feb 3, 2013",3,4,5,6,7,8,9 4 | "go to week of feb 10, 2013",10,11,12,13,14,15,16 5 | ,17,18,19,20,21,22,23 6 | "go to week of feb 24, 2013",24,25,26,27,28,1,2 7 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042988311.72__CC-MAIN-20150728002308-00230-ip-10-236-191-2.ec2.internal__1981.csv: -------------------------------------------------------------------------------- 1 | ,x-small,small,medium,large,x-large,2x-large 2 | chest (in),"33-34""","35-37""","38-40""","41-43""","44-46""","47-49""" 3 | waist (in),"28""","30""","32-33""","33-34""","36""","38""" 4 | sleeve length (in),"32""","33""","34""","35""","36""","36""" 5 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042988458.74__CC-MAIN-20150728002308-00210-ip-10-236-191-2.ec2.internal__1149.csv: -------------------------------------------------------------------------------- 1 | pressure vessels constructed in accordance with:,minimum,maximum 2 | code paragraphs u-68 and u-69,110%,125% 3 | "code paragraphs u-200, through 1974 edition",100%,110% 4 | api-asme code,100%,110% 5 | dot cylinders,as required by dot regulations, 6 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042988311.72__CC-MAIN-20150728002308-00230-ip-10-236-191-2.ec2.internal__1981.csv: -------------------------------------------------------------------------------- 1 | ,x-small,small,medium,large,x-large,2x-large 2 | chest (in),"33-34""","35-37""","38-40""",5,"44-46""","47-49""" 3 | waist (in),"28""","30""","32-33""","33-34""","36""","38""" 4 | sleeve length (in),"32""","33""","34""","35""",shanghai smg,larysa mykhas 5 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042989178.64__CC-MAIN-20150728002309-00150-ip-10-236-191-2.ec2.internal__362.csv: -------------------------------------------------------------------------------- 1 | week selector,s,m,t,w,t,f,s 2 | "go to week of jan 27, 2013",27,28,29,30,31,1,2 3 | "go to week of feb 3, 2013",3,4,5,6,7,8,9 4 | "go to week of feb 10, 2013",10,11,12,13,14,15,16 5 | ,17,18,19,20,21,22,2 6 | "go to week of feb 24, 2013",24,25,26,27,28,1,23 7 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042989178.64__CC-MAIN-20150728002309-00150-ip-10-236-191-2.ec2.internal__362.csv: -------------------------------------------------------------------------------- 1 | week selector,s,m,t,w,t,f,s 2 | "go to week of jan 27, 2013",27,28,29,30,31,1,2 3 | "go to week of feb 3, 2013",3,4,5,6,7,8,9 4 | "go to week of feb 10, 2013",10,11,12,13,14,15,16 5 | ,17,18,19,20,21,22,23 6 | "go to week of feb 24, 2013",24,25,26,27,28,1,2 7 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042981460.12__CC-MAIN-20150728002301-00202-ip-10-236-191-2.ec2.internal__2064.csv: -------------------------------------------------------------------------------- 1 | method name,description 2 | _,translates a string into the current language 3 | sprintf,passes a string thru an sprintf 4 | printf,passes a string thru an printf 5 | script,translate a string into the current language and stores it in the javascript language store. 6 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042990177.43__CC-MAIN-20150728002310-00003-ip-10-236-191-2.ec2.internal__2195.csv: -------------------------------------------------------------------------------- 1 | release,number,set,japanese name,rarity 2 | 2008-10-18,1,duelist pack: yusei,DUELIST PACK —é?Šæ˜Ÿç·¨â€”,ultra rare 3 | 2012-08-11,de04-jp158,duelist edition volume 4,デュエリストエディション ï¼¶ï½?luï½?e 4,secret rare 4 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042981460.12__CC-MAIN-20150728002301-00202-ip-10-236-191-2.ec2.internal__2064.csv: -------------------------------------------------------------------------------- 1 | method name,description 2 | _,translates a string into the current language 3 | sprintf,passes a string thru an sprintf 4 | printf,passes a string thru an printf 5 | script,translate a string into the current language and stores it in the javascript language store. 6 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042989234.2__CC-MAIN-20150728002309-00315-ip-10-236-191-2.ec2.internal__200.csv: -------------------------------------------------------------------------------- 1 | name,last modified,size,gp 2 | parent directory,,,directory 3 | zenbuild,2009-jan-01 10:20:05,1.2k,application/octet-stream 4 | build-thoggen.sh,2009-jan-01 10:19:43,10.7k,application/octet-stream 5 | thoggen-0.7.1.tar.gz,2008-jun-12 15:47:39,917.8k,application/x-gzip 6 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042990112.92__CC-MAIN-20150728002310-00222-ip-10-236-191-2.ec2.internal__22.csv: -------------------------------------------------------------------------------- 1 | ,full program grid 2 | 7:00 pm,cbs evening news with scott pelley 3 | 7:30 pm,entertainment tonight 4 | 8:00 pm,2 broke girls 5 | the odd couple,8:30 pm 6 | 9:00 pm,scorpion 7 | 9:59 pm,ncis: los angeles 8 | 11:00 pm,eyewitness news at 11 9 | 11:35 pm,scorpion 10 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042988065.26__CC-MAIN-20150728002308-00173-ip-10-236-191-2.ec2.internal__453.csv: -------------------------------------------------------------------------------- 1 | vehicle numbers,model name,manufacturer,body,chassis,engine,gearbox equipment,year of get,year of remove,photos, 2 | unknown ?,fiat doblã²,technical,technical equipment,,,,2013,-,no photo,1/1 3 | unknown ?,jelcz 317,technical,technical equipment,,,,2013,-,no photo,1/1 4 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042989234.2__CC-MAIN-20150728002309-00315-ip-10-236-191-2.ec2.internal__200.csv: -------------------------------------------------------------------------------- 1 | name,last modified,size,type 2 | parent directory,,,directory 3 | zenbuild,1.2k,2009-jan-01 10:20:05,application/octet-stream 4 | build-thoggen.sh,2009-jan-01 10:19:43,10.7k,application/octet-stream 5 | thoggen-0.7.1.tar.gz,2008-jun-12 15:47:39,917.8k,application/x-gzip 6 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042989510.73__CC-MAIN-20150728002309-00063-ip-10-236-191-2.ec2.internal__1159.csv: -------------------------------------------------------------------------------- 1 | ,gp,gs,min/g,fg/g,pct,3pt/g,pct,ft/g,pct,ppg 2 | 2013-14,2,-,6.5,"""come home to five"" (sezairi sezali & sylvia ratonel)",50.0,0.0-0.0,-,1923,87.5,5.5 3 | 2014-15,4,-,2.0,0.2-0.2,100.0,0.0-0.0,-,0.0-0.2,0.0,0.5 4 | total,6,-,3.5,0.5-0.8,60.0,0.0-0.0,-,1.2-1.5,77.8,2.2 5 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042989897.84__CC-MAIN-20150728002309-00300-ip-10-236-191-2.ec2.internal__309.csv: -------------------------------------------------------------------------------- 1 | microfiche part no.,9,new exchange unit part no.,bosch part no.,year,marju 2 | 93 45 216,02 73 532,93 62 617,0 280 800 054,1982-86,b201 na 3 | 75 36 915,02 73 524,75 36 915,0 280 800 070,1987-88,b201 na 4 | 93 62 617,02 73 532,93 62 617,0 280 800 054,1982-84,b201 turbo 5 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042990112.92__CC-MAIN-20150728002310-00222-ip-10-236-191-2.ec2.internal__22.csv: -------------------------------------------------------------------------------- 1 | ,full program grid 2 | 7:00 pm,cbs evening news with scott pelley 3 | 7:30 pm,entertainment tonight 4 | 8:00 pm,2 broke girls 5 | 8:30 pm,the odd couple 6 | 9:00 pm,scorpion 7 | 9:59 pm,ncis: los angeles 8 | 11:00 pm,eyewitness news at 11 9 | 11:35 pm,scorpion 10 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042988065.26__CC-MAIN-20150728002308-00173-ip-10-236-191-2.ec2.internal__453.csv: -------------------------------------------------------------------------------- 1 | vehicle numbers,model name,manufacturer,body,attendance,engine,gearbox equipment,year of get,year of remove,silver, 2 | unknown ?,fiat doblã²,technical,technical equipment,,,,2013,-,no photo,1/1 3 | unknown ?,jelcz 317,technical,technical equipment,,,,2013,-,no photo,1/1 4 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042988840.31__CC-MAIN-20150728002308-00323-ip-10-236-191-2.ec2.internal__634.csv: -------------------------------------------------------------------------------- 1 | record id,action,time 2 | lc|no 98077809,add,2009-03-03t12:03:38+00:00 3 | bne|xx1047876,add,2009-06-15t11:42:44+00:00 4 | dnb|140433597,add,2014-01-15t05:38:27+00:00 5 | isni|0000000059273928,add,2014-05-14t22:19:01+00:00 6 | sudoc|171617096,add,2014-08-28t14:36:24+00:00 7 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042990177.43__CC-MAIN-20150728002310-00003-ip-10-236-191-2.ec2.internal__2195.csv: -------------------------------------------------------------------------------- 1 | release,number,set,japanese name,rarity 2 | 2008-10-18,dp08-jp016,duelist pack: yusei,DUELIST PACK —é?Šæ˜Ÿç·¨â€”,ultra rare 3 | 2012-08-11,de04-jp158,duelist edition volume 4,デュエリストエディション ï¼¶ï½?luï½?e 4,secret rare 4 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042990112.92__CC-MAIN-20150728002310-00222-ip-10-236-191-2.ec2.internal__22.csv: -------------------------------------------------------------------------------- 1 | ,full program grid 2 | 7:00 pm,cbs evening news with scott pelley 3 | 7:30 pm,entertainment tonight 4 | 8:00 pm,2 broke girls 5 | 8:30 pm,the odd couple 6 | 9:00 pm,scorpion 7 | 9:59 pm,ncis: los angeles 8 | 11:00 pm,eyewitness news at 11 9 | 11:35 pm,scorpion 10 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042981460.12__CC-MAIN-20150728002301-00202-ip-10-236-191-2.ec2.internal__2064.csv: -------------------------------------------------------------------------------- 1 | method name,description 2 | _,translates a string into the current language 3 | sprintf,passes a string thru an sprintf 4 | printf,passes a string thru an printf 5 | script,translate a string into the current language and stores it in the javascript language store. 6 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042988065.26__CC-MAIN-20150728002308-00173-ip-10-236-191-2.ec2.internal__453.csv: -------------------------------------------------------------------------------- 1 | vehicle numbers,model name,manufacturer,body,chassis,engine,gearbox equipment,year of get,year of remove,photos, 2 | unknown ?,fiat doblã²,technical,technical equipment,,,,2013,-,no photo,1/1 3 | unknown ?,jelcz 317,technical,technical equipment,,,,2013,-,no photo,1/1 4 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042989234.2__CC-MAIN-20150728002309-00315-ip-10-236-191-2.ec2.internal__200.csv: -------------------------------------------------------------------------------- 1 | name,last modified,size,type 2 | parent directory,,,directory 3 | zenbuild,2009-jan-01 10:20:05,1.2k,application/octet-stream 4 | build-thoggen.sh,2009-jan-01 10:19:43,10.7k,application/octet-stream 5 | thoggen-0.7.1.tar.gz,2008-jun-12 15:47:39,917.8k,application/x-gzip 6 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042988840.31__CC-MAIN-20150728002308-00323-ip-10-236-191-2.ec2.internal__634.csv: -------------------------------------------------------------------------------- 1 | record id,action,time 2 | lc|no 98077809,isni|0000000059273928,2009-03-03t12:03:38+00:00 3 | bne|xx1047876,add,2009-06-15t11:42:44+00:00 4 | dnb|140433597,add,2014-01-15t05:38:27+00:00 5 | add,add,2014-05-14t22:19:01+00:00 6 | sudoc|171617096,add,2014-08-28t14:36:24+00:00 7 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042989142.82__CC-MAIN-20150728002309-00099-ip-10-236-191-2.ec2.internal__2068.csv: -------------------------------------------------------------------------------- 1 | list,rank,result,vendor,total cores,rmax (tflops),rpeak (tflops),power (kw) 2 | 11/2006,298,"bladecenter hs20 cluster, xeon em64t 3.6 ghz, gig-ethernet",ibm,966,3.6,7.0,158.00 3 | 06/2006,187,"bladecenter hs20 cluster, xeon em64t 3.6 ghz, gig-ethernet",ibm,966,3.6,7.0,158.00 4 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042989142.82__CC-MAIN-20150728002309-00099-ip-10-236-191-2.ec2.internal__2068.csv: -------------------------------------------------------------------------------- 1 | list,rank,system,vendor,total cores,rmax (tflops),rpeak (tflops),power (kw) 2 | 11/2006,298,"bladecenter hs20 cluster, xeon em64t 3.6 ghz, gig-ethernet",ibm,966,3.6,7.0,158.00 3 | 06/2006,187,"bladecenter hs20 cluster, xeon em64t 3.6 ghz, gig-ethernet",ibm,966,3.6,7.0,158.00 4 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042988840.31__CC-MAIN-20150728002308-00323-ip-10-236-191-2.ec2.internal__634.csv: -------------------------------------------------------------------------------- 1 | record id,action,time 2 | lc|no 98077809,add,2009-03-03t12:03:38+00:00 3 | bne|xx1047876,add,2009-06-15t11:42:44+00:00 4 | dnb|140433597,add,2014-01-15t05:38:27+00:00 5 | isni|0000000059273928,add,2014-05-14t22:19:01+00:00 6 | sudoc|171617096,add,2014-08-28t14:36:24+00:00 7 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042990177.43__CC-MAIN-20150728002310-00003-ip-10-236-191-2.ec2.internal__2195.csv: -------------------------------------------------------------------------------- 1 | release,number,set,japanese name,rarity 2 | 2008-10-18,dp08-jp016,duelist pack: yusei,DUELIST PACK —é?Šæ˜Ÿç·¨â€”,ultra rare 3 | 2012-08-11,de04-jp158,duelist edition volume 4,デュエリストエディション ï¼¶ï½?luï½?e 4,secret rare 4 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042982502.13__CC-MAIN-20150728002302-00239-ip-10-236-191-2.ec2.internal__685.csv: -------------------------------------------------------------------------------- 1 | ,date,location,batter,opposing pitcher,throws,inning,outs,score diff,runners,result 2 | ,07/29/62,sportsman's park,chris cannizzaro,ernie broglio,r,2,2,"mets, -1","1st, 2nd",strikeout 3 | ,07/29/62,sportsman's park,chris cannizzaro,ernie broglio,r,5,0,tie,none,pitcher to first base 4 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042991076.30__CC-MAIN-20150728002311-00254-ip-10-236-191-2.ec2.internal__35.csv: -------------------------------------------------------------------------------- 1 | select type,table,type,possible keys,key,key len,ref,rows,extra 2 | simple,user,ref,"content_user_id,user_id",content_user_id,81,"const,const",1,using where; using temporary; using filesort 3 | simple,moderator_content,eq_ref,primary,primary,4,tfnforum.moderator_content.user_id,1, 4 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042991076.30__CC-MAIN-20150728002311-00254-ip-10-236-191-2.ec2.internal__35.csv: -------------------------------------------------------------------------------- 1 | select type,table,type,possible keys,key,key len,notes,rows,extra 2 | simple,moderator_content,ref,"content_user_id,user_id",content_user_id,81,"const,const",1,using where; using temporary; using filesort 3 | simple,user,eq_ref,primary,primary,4,tfnforum.moderator_content.user_id,1, 4 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042988061.16__CC-MAIN-20150728002308-00295-ip-10-236-191-2.ec2.internal__1098.csv: -------------------------------------------------------------------------------- 1 | #,player,casas de apuestas,"canada census mother tongue - beauharnois, quebec",a,tp 2 | 1.,dylan strome (f),68,45,84,129 3 | 2.,mitchell marner (f),63,44,82,126 4 | 3.,connor mcdavid (f),47,44,76,120 5 | 4.,joseph blandisi (f),68,52,60,112 6 | 5.,christian dvorak (f),66,41,68,109 7 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042991076.30__CC-MAIN-20150728002311-00254-ip-10-236-191-2.ec2.internal__35.csv: -------------------------------------------------------------------------------- 1 | select type,table,type,possible keys,key,key len,ref,rows,extra 2 | simple,moderator_content,ref,"content_user_id,user_id",content_user_id,81,"const,const",1,using where; using temporary; using filesort 3 | simple,user,eq_ref,primary,primary,4,tfnforum.moderator_content.user_id,1, 4 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042986148.56__CC-MAIN-20150728002306-00235-ip-10-236-191-2.ec2.internal__1751.csv: -------------------------------------------------------------------------------- 1 | arrive,dreary,labor 2 | beckon,effort,loom 3 | bide,enjoy,lurid 4 | fault,escape,money 5 | calm,exist,navy 6 | campaign,boisterous,plan 7 | challenge,fiction,race 8 | cork,focus,rail 9 | cull,fulfill,rhyme 10 | curious,gems,snort 11 | danger,grim,talk 12 | doorway,yore,holy 13 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042982502.13__CC-MAIN-20150728002302-00239-ip-10-236-191-2.ec2.internal__685.csv: -------------------------------------------------------------------------------- 1 | ,date,location,sl. no.,opposing pitcher,throws,inning,outs,score diff,runners,local time 2 | ,07/29/62,sportsman's park,chris cannizzaro,ernie broglio,r,2,2,"mets, -1","1st, 2nd",pitcher to first base 3 | ,07/29/62,sportsman's park,chris cannizzaro,ernie broglio,r,5,0,tie,none,strikeout 4 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042986148.56__CC-MAIN-20150728002306-00235-ip-10-236-191-2.ec2.internal__1751.csv: -------------------------------------------------------------------------------- 1 | arrive,dreary,labor 2 | beckon,effort,loom 3 | bide,enjoy,lurid 4 | boisterous,escape,money 5 | calm,exist,navy 6 | campaign,fault,plan 7 | challenge,fiction,race 8 | cork,focus,rail 9 | cull,fulfill,rhyme 10 | curious,gems,snort 11 | danger,grim,talk 12 | doorway,holy,yore 13 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042982502.13__CC-MAIN-20150728002302-00239-ip-10-236-191-2.ec2.internal__685.csv: -------------------------------------------------------------------------------- 1 | ,date,location,batter,opposing pitcher,throws,inning,outs,score diff,runners,result 2 | ,07/29/62,sportsman's park,chris cannizzaro,ernie broglio,r,2,2,"mets, -1","1st, 2nd",pitcher to first base 3 | ,07/29/62,sportsman's park,chris cannizzaro,ernie broglio,r,5,0,tie,none,strikeout 4 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042986148.56__CC-MAIN-20150728002306-00235-ip-10-236-191-2.ec2.internal__1751.csv: -------------------------------------------------------------------------------- 1 | arrive,dreary,labor 2 | beckon,effort,loom 3 | bide,enjoy,lurid 4 | boisterous,escape,money 5 | calm,exist,navy 6 | campaign,fault,plan 7 | challenge,fiction,race 8 | cork,focus,rail 9 | cull,fulfill,rhyme 10 | curious,gems,snort 11 | danger,grim,talk 12 | doorway,holy,yore 13 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042987228.91__CC-MAIN-20150728002307-00319-ip-10-236-191-2.ec2.internal__1580.csv: -------------------------------------------------------------------------------- 1 | pitching,ip,h,r,er,bb,so,hr,era,bf,pit,str,ctct,sts,stl,gb,fb,ld,unk,gsc 2 | "john thomson, w (8-11)",8.1,10,5,5,1,5,1,4.80,35,130,87,57,12,18,10,19,5,0,47 3 | jaime cerda,0.2,1,0,0,0,0,0,3.26,3,6,5,4,1,0,2,1,1,0, 4 | team totals,9,11,5,5,1,5,1,5.00,38,136,92,61,13,18,12,20,6,0,47 5 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042988930.94__CC-MAIN-20150728002308-00259-ip-10-236-191-2.ec2.internal__1515.csv: -------------------------------------------------------------------------------- 1 | design,,, 2 | device type,tablet,android (2.3), 3 | os,ios (2.x),smart phone, 4 | dimensions,4.30 x 2.40 x 0.33 inches (109 x 61 x 8 mm),4.04 x 2.43 x 0.46 inches (102.6 x 61.6 x 11.8 mm), 5 | weight,4.05 oz (115 g) the average is 12.6 oz (360 g),4.20 oz (119 g) the average is 5 oz (144 g), 6 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042988930.94__CC-MAIN-20150728002308-00259-ip-10-236-191-2.ec2.internal__1515.csv: -------------------------------------------------------------------------------- 1 | design,,, 2 | device type,tablet,smart phone, 3 | os,ios (2.x),android (2.3), 4 | dimensions,4.30 x 2.40 x 0.33 inches (109 x 61 x 8 mm),4.04 x 2.43 x 0.46 inches (102.6 x 61.6 x 11.8 mm), 5 | weight,4.05 oz (115 g) the average is 12.6 oz (360 g),4.20 oz (119 g) the average is 5 oz (144 g), 6 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042989897.84__CC-MAIN-20150728002309-00300-ip-10-236-191-2.ec2.internal__309.csv: -------------------------------------------------------------------------------- 1 | microfiche part no.,old exchange unit part no.,new exchange unit part no.,bosch part no.,year,notes 2 | 93 45 216,02 73 532,93 62 617,0 280 800 054,1982-86,b201 na 3 | 75 36 915,02 73 524,0 280 800 070,75 36 915,1987-88,b201 na 4 | 93 62 617,02 73 532,93 62 617,0 280 800 054,1982-84,b201 turbo 5 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042988930.94__CC-MAIN-20150728002308-00259-ip-10-236-191-2.ec2.internal__1515.csv: -------------------------------------------------------------------------------- 1 | design,,, 2 | device type,tablet,smart phone, 3 | os,ios (2.x),android (2.3), 4 | dimensions,4.30 x 2.40 x 0.33 inches (109 x 61 x 8 mm),4.04 x 2.43 x 0.46 inches (102.6 x 61.6 x 11.8 mm), 5 | weight,4.05 oz (115 g) the average is 12.6 oz (360 g),4.20 oz (119 g) the average is 5 oz (144 g), 6 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042989897.84__CC-MAIN-20150728002309-00300-ip-10-236-191-2.ec2.internal__309.csv: -------------------------------------------------------------------------------- 1 | microfiche part no.,old exchange unit part no.,new exchange unit part no.,bosch part no.,year,notes 2 | 93 45 216,02 73 532,93 62 617,0 280 800 054,1982-86,b201 na 3 | 75 36 915,02 73 524,75 36 915,0 280 800 070,1987-88,b201 na 4 | 93 62 617,02 73 532,93 62 617,0 280 800 054,1982-84,b201 turbo 5 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042987552.57__CC-MAIN-20150728002307-00259-ip-10-236-191-2.ec2.internal__2423.csv: -------------------------------------------------------------------------------- 1 | name,price,change,% chg, 2 | epicentre …,0.199,+0.049,+32.67%,epicentre holdings ltd 3 | t t j hold …,0.45,+0.09,+25.00%,t t j holdings ltd 4 | abterra lt …,0.65,+16.07%,+0.09,abterra ltd 5 | ta corp lt …,0.295,+0.035,+13.46%,ta corp ltd 6 | $ ix bioph …,0.445,+0.050,+12.66%,$ ix biopharma 7 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042987552.57__CC-MAIN-20150728002307-00259-ip-10-236-191-2.ec2.internal__2423.csv: -------------------------------------------------------------------------------- 1 | name,price,change,% chg, 2 | epicentre …,0.199,+0.049,+32.67%,epicentre holdings ltd 3 | t t j hold …,0.45,+0.09,+25.00%,t t j holdings ltd 4 | abterra lt …,0.65,+0.09,+16.07%,abterra ltd 5 | ta corp lt …,0.295,+0.035,+13.46%,ta corp ltd 6 | $ ix bioph …,0.445,+0.050,+12.66%,$ ix biopharma 7 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042987228.91__CC-MAIN-20150728002307-00319-ip-10-236-191-2.ec2.internal__1580.csv: -------------------------------------------------------------------------------- 1 | network,ip,h,r,er,bb,size,chart (1997–99),era,bf,pit,str,ctct,sts,stl,gb,fb,year,unk,gsc 2 | "john thomson, w (8-11)",8.1,10,5,5,1,5,1,4.80,35,130,87,57,12,18,10,19,5,0,47 3 | jaime cerda,0.2,1,0,0,0,0,0,3.26,3,6,5,4,1,0,2,1,1,0, 4 | team totals,9,11,5,5,1,5,1,5.00,38,136,92,61,13,18,12,20,6,0,47 5 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042987552.57__CC-MAIN-20150728002307-00259-ip-10-236-191-2.ec2.internal__2423.csv: -------------------------------------------------------------------------------- 1 | name,price,change,% chg, 2 | epicentre …,0.199,+0.049,+32.67%,epicentre holdings ltd 3 | t t j hold …,0.45,+0.09,+25.00%,t t j holdings ltd 4 | abterra lt …,0.65,+0.09,+16.07%,abterra ltd 5 | ta corp lt …,0.295,+0.035,+13.46%,ta corp ltd 6 | $ ix bioph …,0.445,+0.050,+12.66%,$ ix biopharma 7 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042987155.85__CC-MAIN-20150728002307-00318-ip-10-236-191-2.ec2.internal__2644.csv: -------------------------------------------------------------------------------- 1 | ,bkn,cle 2 | points/game,94.2,95.5 3 | assists/game,-6.2,-9.0 4 | fastbreak pts/gm,11.1,14.1 5 | pts in paint/gm,38.5,40.4 6 | avg score margin,21.0,21.0 7 | total rebounds/gm,49.5,49.5 8 | off rebound %,47.5%,47.2% 9 | effective fg %,26.1%,24.2% 10 | fta/fga,0.284,0.312 11 | turnover %,13.0%,13.1% 12 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042989331.34__CC-MAIN-20150728002309-00335-ip-10-236-191-2.ec2.internal__2086.csv: -------------------------------------------------------------------------------- 1 | highmaul bosses,first seen kill,score 2 | kargath bladefist mythic,7 months ago,696.84 3 | the butcher heroic,8 months ago, 4 | brackenspore heroic,8 months ago, 5 | tectus heroic,8 months ago, 6 | twin ogron mythic,ko'ragh heroic,657.90 7 | 6 months ago,8 months ago, 8 | imperator mar'gok heroic,7 months ago, 9 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042988308.23__CC-MAIN-20150728002308-00218-ip-10-236-191-2.ec2.internal__2226.csv: -------------------------------------------------------------------------------- 1 | susan blakeslee,female passenger,guest star 2 | toby huss,rikki / pirate rats,guest star 3 | john rubano,ratatat / pirate rats,guest star 4 | nick bakay,pirate rats / furry demon,pirate rats / furry demon 5 | richard horvitz,recurring role,recurring role 6 | charlie brissette,background singer,recurring role 7 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042987155.85__CC-MAIN-20150728002307-00318-ip-10-236-191-2.ec2.internal__2644.csv: -------------------------------------------------------------------------------- 1 | ,bkn,cle 2 | points/game,94.2,95.5 3 | avg score margin,-6.2,-9.0 4 | fastbreak pts/gm,11.1,14.1 5 | pts in paint/gm,38.5,40.4 6 | assists/game,21.0,21.0 7 | total rebounds/gm,49.5,49.5 8 | effective fg %,47.5%,47.2% 9 | off rebound %,26.1%,24.2% 10 | fta/fga,0.284,0.312 11 | turnover %,13.0%,13.1% 12 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042989331.34__CC-MAIN-20150728002309-00335-ip-10-236-191-2.ec2.internal__2086.csv: -------------------------------------------------------------------------------- 1 | highmaul bosses,first seen kill,score 2 | kargath bladefist mythic,7 months ago,696.84 3 | the butcher heroic,8 months ago, 4 | brackenspore heroic,8 months ago, 5 | tectus heroic,8 months ago, 6 | twin ogron mythic,6 months ago,657.90 7 | ko'ragh heroic,8 months ago, 8 | imperator mar'gok heroic,7 months ago, 9 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042988308.23__CC-MAIN-20150728002308-00218-ip-10-236-191-2.ec2.internal__2226.csv: -------------------------------------------------------------------------------- 1 | susan blakeslee,female passenger,guest star 2 | toby huss,rikki / pirate rats,guest star 3 | john rubano,ratatat / pirate rats,guest star 4 | nick bakay,pirate rats / furry demon,recurring role 5 | richard horvitz,pirate rats / furry demon,recurring role 6 | charlie brissette,background singer,recurring role 7 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042987155.85__CC-MAIN-20150728002307-00318-ip-10-236-191-2.ec2.internal__2644.csv: -------------------------------------------------------------------------------- 1 | ,bkn,cle 2 | points/game,94.2,95.5 3 | avg score margin,-6.2,-9.0 4 | fastbreak pts/gm,11.1,14.1 5 | pts in paint/gm,38.5,40.4 6 | assists/game,21.0,21.0 7 | total rebounds/gm,49.5,49.5 8 | effective fg %,47.5%,47.2% 9 | off rebound %,26.1%,24.2% 10 | fta/fga,0.284,0.312 11 | turnover %,13.0%,13.1% 12 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042988308.23__CC-MAIN-20150728002308-00218-ip-10-236-191-2.ec2.internal__2226.csv: -------------------------------------------------------------------------------- 1 | susan blakeslee,female passenger,guest star 2 | toby huss,rikki / pirate rats,guest star 3 | john rubano,ratatat / pirate rats,guest star 4 | nick bakay,pirate rats / furry demon,recurring role 5 | richard horvitz,pirate rats / furry demon,recurring role 6 | charlie brissette,background singer,recurring role 7 | -------------------------------------------------------------------------------- /exp/pretrain/26600K_freq.yml: -------------------------------------------------------------------------------- 1 | 2 | task_type: 'pred' 3 | batch_size: '1' 4 | max_cell_len: '300' 5 | pred_path: ./data/pretrain/sample.jsonl 6 | model_path: ./model/freq.tar.gz 7 | out_dir: ./out/ 8 | out_pred_name: pred_sample.jsonl 9 | cuda_devices: [0] 10 | 11 | clscol_path: ./data/clscol.npy 12 | clsrow_path: ./data/clsrow.npy 13 | bert_vocab_path: ./data/bert-base-uncased-vocab.txt 14 | 15 | 16 | 17 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042986806.32__CC-MAIN-20150728002306-00163-ip-10-236-191-2.ec2.internal__55.csv: -------------------------------------------------------------------------------- 1 | currã­culo,componentes curriculares,% por componentes,% por currã­culo 2 | ,lã­ngua portuguesa,71, 3 | ,inglãªs,64, 4 | acadã©mico,histã³ria,24,65 5 | ,geografia,57, 6 | ,matemã¡tica,57, 7 | ,46,79, 8 | ,educaã§ã£o visual,25, 9 | nã£o acadã©mico,educaã§ã£o fã­sica,0,24 10 | ,educaã§ã£o tecnolã³gica,36, 11 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042989331.34__CC-MAIN-20150728002309-00335-ip-10-236-191-2.ec2.internal__2086.csv: -------------------------------------------------------------------------------- 1 | highmaul bosses,first seen kill,score 2 | kargath bladefist mythic,7 months ago,696.84 3 | the butcher heroic,8 months ago, 4 | brackenspore heroic,8 months ago, 5 | tectus heroic,8 months ago, 6 | twin ogron mythic,6 months ago,657.90 7 | ko'ragh heroic,8 months ago, 8 | imperator mar'gok heroic,7 months ago, 9 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042988312.76__CC-MAIN-20150728002308-00140-ip-10-236-191-2.ec2.internal__1485.csv: -------------------------------------------------------------------------------- 1 | #,player,sog,ga,saves,min 2 | 0,taylor cornelius.... *,4,-,4,45:00 3 | february 23,overwatch blizzard apuesta por un fps competitivo que une la adrenalina de los juegos de disparos con las habilidades mã¡gicas de cualquier moba.,7,-,7,45:00 4 | tm,team................,1,-,1,7 5 | ,totals..............,12,0,12,90:00 6 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042988924.75__CC-MAIN-20150728002308-00019-ip-10-236-191-2.ec2.internal__1335.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,68-30 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor's name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438043058631.99__CC-MAIN-20150728002418-00210-ip-10-236-191-2.ec2.internal__769.csv: -------------------------------------------------------------------------------- 1 | ,px | in | cm,credits 2 | small,"857 x 900 11.9"" x 12.5"" (72 dpi) 30.2 x 31.8 (72 dpi)",1 3 | medium,"1523 x 1600 5.1"" x 5.3"" (300 dpi) 13 x 13.5 (300 dpi)",2 4 | large,"2362 x 2480 7.9"" x 8.3"" (300 dpi) 20.1 x 21.1 (300 dpi)",4 5 | extended license,"2362 x 2480 7.9"" x 8.3"" (300 dpi) 20.1 x 21.1 (300 dpi)",50 6 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042992201.62__CC-MAIN-20150728002312-00292-ip-10-236-191-2.ec2.internal__2128.csv: -------------------------------------------------------------------------------- 1 | vettore,codici di volo,franchigia bagaglio,peso massimo,home team 2 | comair,ba6200-6449,1 collo piã¹ 1 borsetta borsa per il laptop per adulti e bambini,7kg,"56cm x 36cm x 23cm (22in x 35,56cm x 22,86cm) 45cm x 36cm x 20cm (18in x 14in x 8in)" 3 | sun-air,ba8200-8299,1 collo,6kg,45cm x 36cm x 20cm (18in x 14in x 8in) 4 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438043058631.99__CC-MAIN-20150728002418-00210-ip-10-236-191-2.ec2.internal__769.csv: -------------------------------------------------------------------------------- 1 | ,px | in | cm,credits 2 | small,"857 x 900 11.9"" x 12.5"" (72 dpi) 30.2 x 31.8 (72 dpi)",1 3 | medium,"1523 x 1600 5.1"" x 5.3"" (300 dpi) 13 x 13.5 (300 dpi)",2 4 | large,"2362 x 2480 7.9"" x 8.3"" (300 dpi) 20.1 x 21.1 (300 dpi)",4 5 | extended license,"2362 x 2480 7.9"" x 8.3"" (300 dpi) 20.1 x 21.1 (300 dpi)",50 6 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438043058631.99__CC-MAIN-20150728002418-00210-ip-10-236-191-2.ec2.internal__769.csv: -------------------------------------------------------------------------------- 1 | ,px | in | cm,credits 2 | small,"857 x 900 11.9"" x 12.5"" (72 dpi) 30.2 x 31.8 (72 dpi)",1 3 | medium,"1523 x 1600 5.1"" x 5.3"" (300 dpi) 13 x 13.5 (300 dpi)",2 4 | large,"2362 x 2480 7.9"" x 8.3"" (300 dpi) 20.1 x 21.1 (300 dpi)",4 5 | extended license,"2362 x 2480 7.9"" x 8.3"" (300 dpi) 20.1 x 21.1 (300 dpi)",50 6 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042988860.88__CC-MAIN-20150728002308-00239-ip-10-236-191-2.ec2.internal__2107.csv: -------------------------------------------------------------------------------- 1 | #,date & time,match,venue,result 2 | 1,"15 aug,2000 6:30 pm gmt",aus vs sa,"telstra dome, melbourne - victoria",australia won by 94 runs 3 | 2,"17 aug,2000 6:30 pm gmt",sa vs aus,"telstra dome, melbourne - victoria",match tied 4 | 3,"19 aug,2000 6:30 pm gmt",19,"telstra dome, melbourne - victoria",south africa won by 8 runs 5 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042987228.91__CC-MAIN-20150728002307-00319-ip-10-236-191-2.ec2.internal__1580.csv: -------------------------------------------------------------------------------- 1 | pitching,ip,h,r,er,bb,so,hr,era,bf,pit,str,ctct,sts,stl,gb,fb,ld,unk,gsc 2 | "john thomson, w (8-11)",8.1,10,5,5,1,5,1,4.80,35,130,34,on,12,18,10,19,5,0,42 3 | jaime cerda,raymond schouten,1,0,0,0,0,0,3.26,"6,521",6,4–2,felix sanchez,1,0,2,1,1,0, 4 | team totals,9,11,5,5,1,5,1,26-095,38,altref. church,92,61,13,18,12,20,6,0,47 5 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042986806.32__CC-MAIN-20150728002306-00163-ip-10-236-191-2.ec2.internal__55.csv: -------------------------------------------------------------------------------- 1 | currã­culo,componentes curriculares,% por componentes,% por currã­culo 2 | ,lã­ngua portuguesa,71, 3 | ,inglãªs,64, 4 | acadã©mico,histã³ria,64,65 5 | ,geografia,57, 6 | ,matemã¡tica,57, 7 | ,ciãªncias naturais,79, 8 | ,educaã§ã£o visual,36, 9 | nã£o acadã©mico,educaã§ã£o fã­sica,0,24 10 | ,educaã§ã£o tecnolã³gica,36, 11 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042986806.32__CC-MAIN-20150728002306-00163-ip-10-236-191-2.ec2.internal__55.csv: -------------------------------------------------------------------------------- 1 | currã­culo,componentes curriculares,% por componentes,% por currã­culo 2 | ,lã­ngua portuguesa,71, 3 | ,inglãªs,64, 4 | acadã©mico,histã³ria,64,65 5 | ,geografia,57, 6 | ,matemã¡tica,57, 7 | ,ciãªncias naturais,79, 8 | ,educaã§ã£o visual,36, 9 | nã£o acadã©mico,educaã§ã£o fã­sica,0,24 10 | ,educaã§ã£o tecnolã³gica,36, 11 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042988860.88__CC-MAIN-20150728002308-00239-ip-10-236-191-2.ec2.internal__2107.csv: -------------------------------------------------------------------------------- 1 | #,class and type,match,venue,result 2 | 1,"15 aug,2000 6:30 pm gmt",aus vs sa,"telstra dome, melbourne - victoria",australia won by 94 runs 3 | 2,"17 aug,2000 6:30 pm gmt",sa vs aus,"telstra dome, melbourne - victoria",match tied 4 | 3,"19 aug,2000 6:30 pm gmt",sa vs aus,"telstra dome, melbourne - victoria",south africa won by 8 runs 5 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042988860.88__CC-MAIN-20150728002308-00239-ip-10-236-191-2.ec2.internal__2107.csv: -------------------------------------------------------------------------------- 1 | #,date & time,match,venue,result 2 | 1,"15 aug,2000 6:30 pm gmt",aus vs sa,"telstra dome, melbourne - victoria",australia won by 94 runs 3 | 2,"17 aug,2000 6:30 pm gmt",sa vs aus,"telstra dome, melbourne - victoria",match tied 4 | 3,"19 aug,2000 6:30 pm gmt",sa vs aus,"telstra dome, melbourne - victoria",south africa won by 8 runs 5 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042992201.62__CC-MAIN-20150728002312-00292-ip-10-236-191-2.ec2.internal__2128.csv: -------------------------------------------------------------------------------- 1 | vettore,codici di volo,franchigia bagaglio,peso massimo,restrizioni relative alle dimensioni 2 | comair,ba6200-6449,1 collo piã¹ 1 borsetta borsa per il laptop per adulti e bambini,7kg,"56cm x 36cm x 23cm (22in x 35,56cm x 22,86cm) 45cm x 36cm x 20cm (18in x 14in x 8in)" 3 | 1 collo,ba8200-8299,sun-air,6kg,45cm x 36cm x 20cm (18in x 14in x 8in) 4 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042992201.62__CC-MAIN-20150728002312-00292-ip-10-236-191-2.ec2.internal__2128.csv: -------------------------------------------------------------------------------- 1 | vettore,codici di volo,franchigia bagaglio,peso massimo,restrizioni relative alle dimensioni 2 | comair,ba6200-6449,1 collo piã¹ 1 borsetta borsa per il laptop per adulti e bambini,7kg,"56cm x 36cm x 23cm (22in x 35,56cm x 22,86cm) 45cm x 36cm x 20cm (18in x 14in x 8in)" 3 | sun-air,ba8200-8299,1 collo,6kg,45cm x 36cm x 20cm (18in x 14in x 8in) 4 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042989142.82__CC-MAIN-20150728002309-00099-ip-10-236-191-2.ec2.internal__2068.csv: -------------------------------------------------------------------------------- 1 | list,rank,system,vendor,total cores,rmax (tflops),rpeak (tflops),power (kw) 2 | 11/2006,298,"bladecenter hs20 cluster, xeon em64t 3.6 ghz, gig-ethernet",27,75,1,expired request for comments – trade act participant report,158.00 3 | 06/2006,187,"bladecenter hs20 cluster, xeon em64t 3.6 ghz, gig-ethernet",bill passed - house (276 - 140),14,3.6,7.0,158.00 4 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042987135.9__CC-MAIN-20150728002307-00175-ip-10-236-191-2.ec2.internal__1018.csv: -------------------------------------------------------------------------------- 1 | hat size,adjustable one size,one size 2 | adult head size (inches),21 1/4 - 24 1/2,21 - 23 1/2 3 | adult hat size,6 5/8 - 7 3/4,6 1/2 - 7 1/2 4 | youth head size (inches),,19 3/4 - 22 5 | youth hat size,,6 1/4 - 6 7/8 6 | 9,,19 - 20 1/2 7 | toddler hat size,,2t - 4t 8 | infant head size (inches),,17 1/4 - 19 9 | infant hat size,,0 - 18 months 10 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042988924.75__CC-MAIN-20150728002308-00339-ip-10-236-191-2.ec2.internal__1863.csv: -------------------------------------------------------------------------------- 1 | p,team,pld,pts 2 | 1,10,new york cosmos,20 3 | 2,tampa bay rowdies,10,19 4 | 3,14,10,carolina railhawks 5 | 4,minnesota united fc,10,14 6 | 5,indy eleven,10,13 7 | 6,jacksonville armada,10,12 8 | 7,san antonio scorpions,12,10 9 | 8,fort lauderdale strikers,10,11 10 | 9,ottawa fury fc,10,11 11 | 10,fc edmonton,10,9 12 | 11,atlanta silverbacks,10,8 13 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042988924.75__CC-MAIN-20150728002308-00339-ip-10-236-191-2.ec2.internal__1863.csv: -------------------------------------------------------------------------------- 1 | p,date,pld,pts 2 | 1,new york cosmos,10,20 3 | 2,tampa bay rowdies,10,19 4 | 3,carolina railhawks,10,14 5 | 4,minnesota united fc,10,14 6 | 5,indy eleven,10,13 7 | 6,jacksonville armada,10,12 8 | 7,san antonio scorpions,10,12 9 | 8,fort lauderdale strikers,10,11 10 | 9,ottawa fury fc,10,11 11 | 10,fc edmonton,10,9 12 | 11,atlanta silverbacks,10,8 13 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042988924.75__CC-MAIN-20150728002308-00339-ip-10-236-191-2.ec2.internal__1863.csv: -------------------------------------------------------------------------------- 1 | p,team,pld,pts 2 | 1,new york cosmos,10,20 3 | 2,tampa bay rowdies,10,19 4 | 3,carolina railhawks,10,14 5 | 4,minnesota united fc,10,14 6 | 5,indy eleven,10,13 7 | 6,jacksonville armada,10,12 8 | 7,san antonio scorpions,10,12 9 | 8,fort lauderdale strikers,10,11 10 | 9,ottawa fury fc,10,11 11 | 10,fc edmonton,10,9 12 | 11,atlanta silverbacks,10,8 13 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042988317.67__CC-MAIN-20150728002308-00292-ip-10-236-191-2.ec2.internal__440.csv: -------------------------------------------------------------------------------- 1 | ù?ø§ùŠù„‌ù‡ø§,ù…ø¬ù…ùˆø¹ù‡ù…ø´ø§ù‡ø¯ù‡ ù‡ù…ù‡ ù?ø§ùŠù„‌ù‡ø§ 2 | 30225,ù?ûŒù„ù… movie 3 | 24688,ø³ø±ûŒø§ù„ tv series 4 | 438,short films 5 | 19,ù…ø±ø§ø³ù… ø¢ú©ø§ø¯ù…ûŒ academy show 6 | 259,ø§ù†ûŒù…ù‡ anime persian sub 7 | 49,øªø±ûŒù„ø± trailer 8 | 45,ù†ø±ù… ø§ù?ø²ø§ø± software 9 | 40,ø¢ù…ùˆø²ø´ pdf 10 | 594,ù…øªù?ø±ù‚ù‡ 11 | 29,ù…ø³øªù†ø¯ documentary 12 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042988317.67__CC-MAIN-20150728002308-00292-ip-10-236-191-2.ec2.internal__440.csv: -------------------------------------------------------------------------------- 1 | ù?ø§ùŠù„‌ù‡ø§,ù…ø¬ù…ùˆø¹ù‡ù…ø´ø§ù‡ø¯ù‡ ù‡ù…ù‡ ù?ø§ùŠù„‌ù‡ø§ 2 | 30225,ù?ûŒù„ù… movie 3 | 24688,ø³ø±ûŒø§ù„ tv series 4 | 49,short films 5 | 19,ù…ø±ø§ø³ù… ø¢ú©ø§ø¯ù…ûŒ academy show 6 | 259,ø§ù†ûŒù…ù‡ anime persian sub 7 | 438,øªø±ûŒù„ø± trailer 8 | 45,ù†ø±ù… ø§ù?ø²ø§ø± software 9 | 40,ø¢ù…ùˆø²ø´ pdf 10 | 594,ù…øªù?ø±ù‚ù‡ 11 | 29,ù…ø³øªù†ø¯ documentary 12 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042988317.67__CC-MAIN-20150728002308-00292-ip-10-236-191-2.ec2.internal__440.csv: -------------------------------------------------------------------------------- 1 | ù?ø§ùŠù„‌ù‡ø§,ù…ø¬ù…ùˆø¹ù‡ù…ø´ø§ù‡ø¯ù‡ ù‡ù…ù‡ ù?ø§ùŠù„‌ù‡ø§ 2 | 30225,ù?ûŒù„ù… movie 3 | 24688,ø³ø±ûŒø§ù„ tv series 4 | 49,short films 5 | 19,ù…ø±ø§ø³ù… ø¢ú©ø§ø¯ù…ûŒ academy show 6 | 259,ø§ù†ûŒù…ù‡ anime persian sub 7 | 438,øªø±ûŒù„ø± trailer 8 | 45,ù†ø±ù… ø§ù?ø²ø§ø± software 9 | 40,ø¢ù…ùˆø²ø´ pdf 10 | 594,ù…øªù?ø±ù‚ù‡ 11 | 29,ù…ø³øªù†ø¯ documentary 12 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042990112.50__CC-MAIN-20150728002310-00124-ip-10-236-191-2.ec2.internal__1282.csv: -------------------------------------------------------------------------------- 1 | us,inches,eu,uk,japan (cm),china 2 | 5,8.625,35,2.5,25.5,220 3 | 5.5,8.875,35.5,3,22,225 4 | 6,9,36,3.5,22.5,230 5 | 6.5,9.625,37,4,23,235 6 | 7,9.25,37.5,6.5,26,240 7 | 7.5,9.375,38.5,5,24,245 8 | 11,9.5,39,5.5,24.5,250 9 | 8.5,9.125,39.5,6,25,255 10 | 9,9.875,40,4.5,21.5,260 11 | 9.5,10,40.5,7,23.5,265 12 | 10,10.25,41,7.5,26.5,270 13 | 8,10.5,43,8.5,27,280 14 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042990112.50__CC-MAIN-20150728002310-00124-ip-10-236-191-2.ec2.internal__1282.csv: -------------------------------------------------------------------------------- 1 | us,inches,new,uk,japan (cm),china 2 | 5,8.625,35,2.5,21.5,220 3 | 5.5,8.875,35.5,3,22,225 4 | 6,9,36,3.5,22.5,230 5 | 6.5,9.125,37,4,23,235 6 | 7,9.25,37.5,4.5,23.5,240 7 | 7.5,9.375,38.5,5,24,245 8 | 8,9.5,39,5.5,24.5,250 9 | 8.5,9.625,39.5,6,25,255 10 | 9,9.875,40,6.5,25.5,260 11 | 9.5,10,40.5,7,26,265 12 | 10,10.25,41,7.5,26.5,270 13 | 11,10.5,43,8.5,27,280 14 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042985647.51__CC-MAIN-20150728002305-00301-ip-10-236-191-2.ec2.internal__2228.csv: -------------------------------------------------------------------------------- 1 | us,inches,eu,uk,japan (cm),china 2 | 5,8.625,35,2.5,21.5,220 3 | 5.5,8.875,35.5,3,22,225 4 | 6,9,36,3.5,22.5,230 5 | 6.5,9.125,37,4,23,235 6 | 7,9.25,37.5,4.5,23.5,240 7 | 7.5,9.375,38.5,5,24,245 8 | 8,9.5,39,5.5,24.5,250 9 | 8.5,9.625,39.5,6,25,255 10 | 9,9.875,40,6.5,25.5,260 11 | 9.5,10,40.5,7,26,265 12 | 10,10.25,41,7.5,26.5,270 13 | 11,10.5,43,8.5,27,280 14 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042990217.27__CC-MAIN-20150728002310-00064-ip-10-236-191-2.ec2.internal__1370.csv: -------------------------------------------------------------------------------- 1 | 6,inches,eu,uk,japan (cm),china 2 | 5,8.625,35,2.5,21.5,220 3 | 5.5,8.875,35.5,3,22,225 4 | 6,9,36,3.5,22.5,230 5 | 6.5,9.125,37,4,23,235 6 | 7,9.25,37.5,4.5,23.5,240 7 | 7.5,9.375,38.5,5,24,245 8 | 8,9.5,39,5.5,24.5,250 9 | 8.5,9.625,39.5,6,25,255 10 | 9,9.875,40,6.5,25.5,260 11 | 9.5,10,40.5,7,26,265 12 | 10,10.25,41,7.5,26.5,270 13 | 11,10.5,43,8.5,27,280 14 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042985647.51__CC-MAIN-20150728002305-00301-ip-10-236-191-2.ec2.internal__2228.csv: -------------------------------------------------------------------------------- 1 | us,inches,eu,uk,japan (cm),china 2 | 5,8.625,35,5,26.5,220 3 | 5.5,10.5,35.5,3,22,225 4 | 6,9,36,3.5,22.5,230 5 | 6.5,9.125,37,4,23,235 6 | 7,9.25,37.5,4.5,23.5,240 7 | 7.5,9.375,38.5,2.5,24,245 8 | 8,9.5,39,5.5,24.5,250 9 | 8.5,9.625,41,6,25,255 10 | 9,9.875,40,6.5,25.5,260 11 | 9.5,10,40.5,7,26,265 12 | 10,10.25,39.5,7.5,21.5,270 13 | 11,8.875,43,8.5,27,280 14 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042990217.27__CC-MAIN-20150728002310-00064-ip-10-236-191-2.ec2.internal__1370.csv: -------------------------------------------------------------------------------- 1 | us,inches,eu,uk,japan (cm),china 2 | 5,8.625,35,2.5,21.5,220 3 | 5.5,8.875,35.5,12,22,225 4 | 6,virginia,36,3.5,22.5,230 5 | 6.5,9.125,37,4,23,235 6 | 7,9.25,37.5,4.5,4,240 7 | 7.5,9.375,38.5,5,24,245 8 | 8,9.5,39,5.5,24.5,250 9 | 8.5,9.625,39.5,6,25,255 10 | 9,الضار,40,6.5,25.5,260 11 | 9.5,10,40.5,7,26,82–66 12 | 10,10.25,41,7.5,26.5,270 13 | 11,10.5,43,8.5,3,x 14 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042990112.50__CC-MAIN-20150728002310-00124-ip-10-236-191-2.ec2.internal__1282.csv: -------------------------------------------------------------------------------- 1 | us,inches,eu,uk,japan (cm),china 2 | 5,8.625,35,2.5,21.5,220 3 | 5.5,8.875,35.5,3,22,225 4 | 6,9,36,3.5,22.5,230 5 | 6.5,9.125,37,4,23,235 6 | 7,9.25,37.5,4.5,23.5,240 7 | 7.5,9.375,38.5,5,24,245 8 | 8,9.5,39,5.5,24.5,250 9 | 8.5,9.625,39.5,6,25,255 10 | 9,9.875,40,6.5,25.5,260 11 | 9.5,10,40.5,7,26,265 12 | 10,10.25,41,7.5,26.5,270 13 | 11,10.5,43,8.5,27,280 14 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042985647.51__CC-MAIN-20150728002305-00301-ip-10-236-191-2.ec2.internal__2228.csv: -------------------------------------------------------------------------------- 1 | us,inches,eu,uk,japan (cm),china 2 | 5,8.625,35,2.5,21.5,220 3 | 5.5,8.875,35.5,3,22,225 4 | 6,9,36,3.5,22.5,230 5 | 6.5,9.125,37,4,23,235 6 | 7,9.25,37.5,4.5,23.5,240 7 | 7.5,9.375,38.5,5,24,245 8 | 8,9.5,39,5.5,24.5,250 9 | 8.5,9.625,39.5,6,25,255 10 | 9,9.875,40,6.5,25.5,260 11 | 9.5,10,40.5,7,26,265 12 | 10,10.25,41,7.5,26.5,270 13 | 11,10.5,43,8.5,27,280 14 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042990217.27__CC-MAIN-20150728002310-00064-ip-10-236-191-2.ec2.internal__1370.csv: -------------------------------------------------------------------------------- 1 | us,inches,eu,uk,japan (cm),china 2 | 5,8.625,35,2.5,21.5,220 3 | 5.5,8.875,35.5,3,22,225 4 | 6,9,36,3.5,22.5,230 5 | 6.5,9.125,37,4,23,235 6 | 7,9.25,37.5,4.5,23.5,240 7 | 7.5,9.375,38.5,5,24,245 8 | 8,9.5,39,5.5,24.5,250 9 | 8.5,9.625,39.5,6,25,255 10 | 9,9.875,40,6.5,25.5,260 11 | 9.5,10,40.5,7,26,265 12 | 10,10.25,41,7.5,26.5,270 13 | 11,10.5,43,8.5,27,280 14 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042988065.26__CC-MAIN-20150728002308-00033-ip-10-236-191-2.ec2.internal__865.csv: -------------------------------------------------------------------------------- 1 | ð¢ð¸ð¿ ñ?ñ‚ð°ð¸,ðœð°ðºñ?ð¸ð¼ñƒð¼, 2 | 40.67,+,ðŸð¾ðºð°ð¶ð¸ ñ†ðµð½ð¸ 3 | ð•ð´ð¸ð½ð¸ñ‡ð½ð° ñ?ñ‚ð°ñ?,,ðŸð¾ðºð°ð¶ð¸ ñ†ðµð½ð¸ 4 | 23.8,,ðŸð¾ðºð°ð¶ð¸ ñ†ðµð½ð¸ 5 | ð”ð²ð¾ð¹ð½ð° ñ?ñ‚ð°ñ?,,ðŸð¾ðºð°ð¶ð¸ ñ†ðµð½ð¸ 6 | ð¢ñ€ð¾ð¹ð½ð° ñ?ñ‚ð°ñ?,,ðŸð¾ðºð°ð¶ð¸ ñ†ðµð½ð¸ 7 | ð”ð²ð¾ð¹ð½ð° ñ?ñ‚ð°ñ? ñ? 2 ð¾ñ‚ð´ðµð»ð½ð¸ ð»ðµð³ð»ð°,,ðŸð¾ðºð°ð¶ð¸ ñ†ðµð½ð¸ 8 | ð”ð²ð¾ð¹ð½ð° ñ?ñ‚ð°ñ?,,ðŸð¾ðºð°ð¶ð¸ ñ†ðµð½ð¸ 9 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042986357.49__CC-MAIN-20150728002306-00316-ip-10-236-191-2.ec2.internal__2351.csv: -------------------------------------------------------------------------------- 1 | ,name,album,lã¤nge,preis, 2 | 4,nothing else matters,metallica,6:28,"1,29 €",in itunes ansehen 3 | 2,whiskey in the jar,garage inc.,5:04,"1,29 €",in itunes ansehen 4 | 3,enter sandman,metallica,5:31,"1,29 €",in itunes ansehen 5 | 1,the unforgiven,metallica,7:56,"1,29 €",in itunes ansehen 6 | 5,the day that never comes,death magnetic,6:27,"1,29 €",in itunes ansehen 7 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042987135.9__CC-MAIN-20150728002307-00175-ip-10-236-191-2.ec2.internal__1018.csv: -------------------------------------------------------------------------------- 1 | hat size,adjustable one size,one size 2 | adult head size (inches),21 1/4 - 24 1/2,21 - 23 1/2 3 | adult hat size,6 5/8 - 7 3/4,6 1/2 - 7 1/2 4 | youth head size (inches),,19 3/4 - 22 5 | youth hat size,,6 1/4 - 6 7/8 6 | toddler head size (inches),,19 - 20 1/2 7 | toddler hat size,,2t - 4t 8 | infant head size (inches),,17 1/4 - 19 9 | infant hat size,,0 - 18 months 10 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042986357.49__CC-MAIN-20150728002306-00316-ip-10-236-191-2.ec2.internal__2351.csv: -------------------------------------------------------------------------------- 1 | ,name,album,lã¤nge,preis, 2 | 1,nothing else matters,metallica,6:28,"1,29 €",in itunes ansehen 3 | 2,whiskey in the jar,garage inc.,5:04,"1,29 €",in itunes ansehen 4 | 3,enter sandman,metallica,5:31,"1,29 €",in itunes ansehen 5 | 4,the unforgiven,metallica,6:27,"1,29 €",in itunes ansehen 6 | 5,the day that never comes,death magnetic,7:56,"1,29 €",in itunes ansehen 7 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042987135.9__CC-MAIN-20150728002307-00175-ip-10-236-191-2.ec2.internal__1018.csv: -------------------------------------------------------------------------------- 1 | hat size,adjustable one size,one size 2 | adult head size (inches),21 1/4 - 24 1/2,21 - 23 1/2 3 | adult hat size,6 5/8 - 7 3/4,6 1/2 - 7 1/2 4 | youth head size (inches),,19 3/4 - 22 5 | youth hat size,,6 1/4 - 6 7/8 6 | toddler head size (inches),,19 - 20 1/2 7 | toddler hat size,,2t - 4t 8 | infant head size (inches),,17 1/4 - 19 9 | infant hat size,,0 - 18 months 10 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042986357.49__CC-MAIN-20150728002306-00316-ip-10-236-191-2.ec2.internal__2351.csv: -------------------------------------------------------------------------------- 1 | ,name,album,lã¤nge,1983 – 1997, 2 | 1,nothing else matters,metallica,6:28,"1,29 €",in itunes ansehen 3 | 2,whiskey in the jar,garage inc.,5:04,"1,29 €",in itunes ansehen 4 | 3,enter sandman,metallica,5:31,"1,29 €",in itunes ansehen 5 | 4,the unforgiven,metallica,6:27,"1,29 €",in itunes ansehen 6 | 5,the day that never comes,death magnetic,7:56,"1,29 €",in itunes ansehen 7 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042988250.59__CC-MAIN-20150728002308-00240-ip-10-236-191-2.ec2.internal__817.csv: -------------------------------------------------------------------------------- 1 | ,px | in | cm,credits 2 | small,"900 x 600 12.5"" x 8.3"" (72 dpi) 31.8 x 21.1 (72 dpi)",1 3 | medium,"1600 x 1066 5.3"" x 3.6"" (300 dpi) 13.5 x 9.1 (300 dpi)",x-large 4 | large,"2800 x 1866 9.3"" x 6.2"" (300 dpi) 23.6 x 15.7 (300 dpi)",4 5 | 2,"5616 x 3744 18.7"" x 12.5"" (300 dpi) 47.5 x 31.8 (300 dpi)",6 6 | extended license,"5616 x 3744 18.7"" x 12.5"" (300 dpi) 47.5 x 31.8 (300 dpi)",50 7 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042986451.45__CC-MAIN-20150728002306-00229-ip-10-236-191-2.ec2.internal__463.csv: -------------------------------------------------------------------------------- 1 | ,name,artist,time,price, 2 | ,ë§?ì?´ì•¼ i’m saying,november,3:50,, 3 | ,love is…,park jang hyeon (박장현) & park hyeon gyu (박현규),3:36,, 4 | ,모먼트 moment,changmin(창민),4:04,, 5 | ,1908,vixx ken (켄),3:21,, 6 | ,ë‘? 사람 (two person),park jang hyun (박장현) [bromance],4:29,, 7 | ,아랫입술 물고 (biting my lower lip),"sung by esna (ì—?스나, 윤빛나ë?¼)",3:43,, 8 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042988250.59__CC-MAIN-20150728002308-00240-ip-10-236-191-2.ec2.internal__817.csv: -------------------------------------------------------------------------------- 1 | ,px | in | cm,credits 2 | small,"900 x 600 12.5"" x 8.3"" (72 dpi) 31.8 x 21.1 (72 dpi)",1 3 | medium,"1600 x 1066 5.3"" x 3.6"" (300 dpi) 13.5 x 9.1 (300 dpi)",2 4 | large,"2800 x 1866 9.3"" x 6.2"" (300 dpi) 23.6 x 15.7 (300 dpi)",4 5 | x-large,"5616 x 3744 18.7"" x 12.5"" (300 dpi) 47.5 x 31.8 (300 dpi)",6 6 | extended license,"5616 x 3744 18.7"" x 12.5"" (300 dpi) 47.5 x 31.8 (300 dpi)",50 7 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042988250.59__CC-MAIN-20150728002308-00240-ip-10-236-191-2.ec2.internal__817.csv: -------------------------------------------------------------------------------- 1 | ,px | in | cm,credits 2 | small,"900 x 600 12.5"" x 8.3"" (72 dpi) 31.8 x 21.1 (72 dpi)",1 3 | medium,"1600 x 1066 5.3"" x 3.6"" (300 dpi) 13.5 x 9.1 (300 dpi)",2 4 | large,"2800 x 1866 9.3"" x 6.2"" (300 dpi) 23.6 x 15.7 (300 dpi)",4 5 | x-large,"5616 x 3744 18.7"" x 12.5"" (300 dpi) 47.5 x 31.8 (300 dpi)",6 6 | extended license,"5616 x 3744 18.7"" x 12.5"" (300 dpi) 47.5 x 31.8 (300 dpi)",50 7 | -------------------------------------------------------------------------------- /exp/pretrain/26600K_mix.yml: -------------------------------------------------------------------------------- 1 | 2 | task_type: 'pred' 3 | batch_size: '1' 4 | max_cell_len: '300' 5 | pred_path: ./data/pretrain/sample.jsonl 6 | # pred_path: ./data/ft_cell/data_jsonl/test.jsonl 7 | model_path: ./model/mix.tar.gz 8 | out_dir: ./out/ 9 | out_pred_name: pred_sample.jsonl 10 | # out_pred_name: out_test.jsonl 11 | cuda_devices: [0] 12 | 13 | clscol_path: ./data/clscol.npy 14 | clsrow_path: ./data/clsrow.npy 15 | bert_vocab_path: ./data/bert-base-uncased-vocab.txt 16 | 17 | 18 | 19 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042988311.72__CC-MAIN-20150728002308-00175-ip-10-236-191-2.ec2.internal__1284.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | couples only,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor’s name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042988860.88__CC-MAIN-20150728002308-00188-ip-10-236-191-2.ec2.internal__18.csv: -------------------------------------------------------------------------------- 1 | season,league,record,placement 2 | 2014-2015,adriatic league liga aba,12-14,8th 3 | 2014-2015,eurocup,3-7,36th 4 | 2014-2015,hungarian nbia,14-3,1st 5 | 2013-2014,adriatic league liga aba,8-17,12th 6 | 2013-2014,eurochallenge,10-7,4th 7 | 2013-2014,hungarian nbia,18-1,1st 8 | 2012-2013,adriatic league liga aba,9-17,13th 9 | 2012-2013,eurochallenge,6-6,9th 10 | 2012-2013,hungarian nbia,15-8,2nd 11 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042988860.88__CC-MAIN-20150728002308-00188-ip-10-236-191-2.ec2.internal__18.csv: -------------------------------------------------------------------------------- 1 | season,league,record,placement 2 | 2014-2015,adriatic league liga aba,12-14,8th 3 | 2014-2015,eurocup,3-7,36th 4 | 2014-2015,hungarian nbia,14-3,1st 5 | 2013-2014,adriatic league liga aba,8-17,12th 6 | 2013-2014,eurochallenge,10-7,4th 7 | 2013-2014,hungarian nbia,18-1,1st 8 | 2012-2013,adriatic league liga aba,9-17,13th 9 | 2012-2013,eurochallenge,6-6,9th 10 | 2012-2013,hungarian nbia,15-8,2nd 11 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042988860.88__CC-MAIN-20150728002308-00188-ip-10-236-191-2.ec2.internal__18.csv: -------------------------------------------------------------------------------- 1 | season,league,record,placement 2 | 2014-2015,adriatic league liga aba,12-14,8th 3 | 2014-2015,eurocup,general urquiza,36th 4 | 2014-2015,hungarian nbia,14-3,1st 5 | 2013-2014,adriatic league liga aba,8-17,12th 6 | 3,eurochallenge,10-7,4th 7 | 2013-2014,hungarian nbia,18-1,1st 8 | 2012-2013,adriatic league liga aba,9-17,13th 9 | 2012-2013,eurochallenge,6-6,9th 10 | 2012-2013,hungarian nbia,15-8,2nd 11 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042986423.95__CC-MAIN-20150728002306-00124-ip-10-236-191-2.ec2.internal__1089.csv: -------------------------------------------------------------------------------- 1 | start date,end date,crn,title,sec,course title,units,days,hours,bldg/rm,fee,instructor 2 | 09/10/2013,10/15/2013,42465,hrx 951,01,strategic hr management,1.0,t,18:30 - 21:30,sac 1102,$395,j vigneau 3 | 10/22/2013,11/12/2013,42466,hrx 953,01,benchmarks and trends,1.0,t,18:30 - 21:30,sac1 1104,$285,j vigneau 4 | 11/19/2013,12/10/2013,42467,hrx 955,01,hr practices,1.0,t,18:30 - 21:30,sac1 1104,$285,j vigneau 5 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042986423.95__CC-MAIN-20150728002306-00124-ip-10-236-191-2.ec2.internal__1089.csv: -------------------------------------------------------------------------------- 1 | start date,end date,crn,dept,sec,course title,units,days,hours,bldg/rm,fee,instructor 2 | 09/10/2013,10/15/2013,42465,hrx 951,01,strategic hr management,1.0,t,18:30 - 21:30,sac 1102,$395,j vigneau 3 | 10/22/2013,11/12/2013,42466,hrx 953,01,benchmarks and trends,1.0,t,18:30 - 21:30,sac1 1104,$285,j vigneau 4 | 11/19/2013,12/10/2013,42467,hrx 955,01,hr practices,1.0,t,18:30 - 21:30,sac1 1104,$285,j vigneau 5 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042990217.27__CC-MAIN-20150728002310-00075-ip-10-236-191-2.ec2.internal__1439.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor's name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042989331.34__CC-MAIN-20150728002309-00246-ip-10-236-191-2.ec2.internal__1255.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor’s name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042990217.27__CC-MAIN-20150728002310-00075-ip-10-236-191-2.ec2.internal__1439.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | "practice or hospital name (e.g. ""pinnacle hospital"")","specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,doctors by their medical specialty: 5 | specific doctor:,"doctor's name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042987866.61__CC-MAIN-20150728002307-00252-ip-10-236-191-2.ec2.internal__1295.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor's name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042988317.67__CC-MAIN-20150728002308-00033-ip-10-236-191-2.ec2.internal__2355.csv: -------------------------------------------------------------------------------- 1 | ð¿ð°ð´ðµð¶,ðµð´. ñ‡.,ð¼ð½. ñ‡. 2 | ð˜ð¼.,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ñŒ,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ð¸ 3 | ð .,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ð¸,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ðµð¹ 4 | ð”.,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ð¸,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ñ?ð¼ 5 | ð’.,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ñŒ,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ð¸ 6 | ð¢ð².,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ñŒñŽ,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ñ?ð¼ð¸ 7 | ðŸñ€.,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ð¸,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ñ?ñ… 8 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438042990112.92__CC-MAIN-20150728002310-00240-ip-10-236-191-2.ec2.internal__1247.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor's name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_cell/train_csv/1438043058631.99__CC-MAIN-20150728002418-00126-ip-10-236-191-2.ec2.internal__1329.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor's name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042989018.48__CC-MAIN-20150728002309-00040-ip-10-236-191-2.ec2.internal__1358.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor’s name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042989331.34__CC-MAIN-20150728002309-00246-ip-10-236-191-2.ec2.internal__1255.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor’s name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042988317.67__CC-MAIN-20150728002308-00033-ip-10-236-191-2.ec2.internal__2355.csv: -------------------------------------------------------------------------------- 1 | ð¿ð°ð´ðµð¶,ðµð´. ñ‡.,ð¼ð½. ñ‡. 2 | ð˜ð¼.,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ñŒ,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ð¸ 3 | ð .,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ð¸,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ðµð¹ 4 | ð”.,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ð¸,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ñ?ð¼ 5 | ð’.,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ñŒ,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ð¸ 6 | ð¢ð².,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ñŒñŽ,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ñ?ð¼ð¸ 7 | ðŸñ€.,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ð¸,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ñ?ñ… 8 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042990112.92__CC-MAIN-20150728002310-00240-ip-10-236-191-2.ec2.internal__1247.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor's name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438043058631.99__CC-MAIN-20150728002418-00126-ip-10-236-191-2.ec2.internal__1329.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor's name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042988311.72__CC-MAIN-20150728002308-00175-ip-10-236-191-2.ec2.internal__1284.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor’s name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042988924.75__CC-MAIN-20150728002308-00019-ip-10-236-191-2.ec2.internal__1335.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor's name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042989018.48__CC-MAIN-20150728002309-00040-ip-10-236-191-2.ec2.internal__1358.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor’s name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042989331.34__CC-MAIN-20150728002309-00246-ip-10-236-191-2.ec2.internal__1255.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor’s name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042990217.27__CC-MAIN-20150728002310-00075-ip-10-236-191-2.ec2.internal__1439.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor's name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042987866.61__CC-MAIN-20150728002307-00252-ip-10-236-191-2.ec2.internal__1295.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor's name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042990112.92__CC-MAIN-20150728002310-00240-ip-10-236-191-2.ec2.internal__1247.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor's name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438043058631.99__CC-MAIN-20150728002418-00126-ip-10-236-191-2.ec2.internal__1329.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor's name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042988311.72__CC-MAIN-20150728002308-00175-ip-10-236-191-2.ec2.internal__1284.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor’s name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042988924.75__CC-MAIN-20150728002308-00019-ip-10-236-191-2.ec2.internal__1335.csv: -------------------------------------------------------------------------------- 1 | to find:,enter: 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor's name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_table/train_csv/1438042988317.67__CC-MAIN-20150728002308-00033-ip-10-236-191-2.ec2.internal__2355.csv: -------------------------------------------------------------------------------- 1 | ð¿ð°ð´ðµð¶,ðµð´. ñ‡.,ð¼ð½. ñ‡. 2 | ð˜ð¼.,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ñŒ,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ð¸ 3 | ð .,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ð¸,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ðµð¹ 4 | ð”.,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ð¸,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ñ?ð¼ 5 | ð’.,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ñŒ,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ð¸ 6 | ð¢ð².,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ñŒñŽ,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ñ?ð¼ð¸ 7 | ðŸñ€.,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ð¸,ð½ðµð²ð¸ð½ð¾ì?ð²ð½ð¾ñ?ñ‚ñ?ñ… 8 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042986451.45__CC-MAIN-20150728002306-00229-ip-10-236-191-2.ec2.internal__463.csv: -------------------------------------------------------------------------------- 1 | ,name,artist,time,price, 2 | ,ë§?ì?´ì•¼ i’m saying,lee hongki (ì?´í™?기),3:50,, 3 | ,love is…,park jang hyeon (박장현) & park hyeon gyu (박현규),3:36,, 4 | ,모먼트 moment,changmin(창민),4:04,, 5 | ,in the name of love,vixx ken (켄),3:21,, 6 | ,ë‘? 사람 (two person),park jang hyun (박장현) [bromance],4:29,, 7 | ,아랫입술 물고 (biting my lower lip),"sung by esna (ì—?스나, 윤빛나ë?¼)",3:43,, 8 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042985647.51__CC-MAIN-20150728002305-00269-ip-10-236-191-2.ec2.internal__1236.csv: -------------------------------------------------------------------------------- 1 | us,uk,europe,6 2 | 6,5.5,38.5,24 3 | 6.5,6,39,24.5 4 | 7,6,40,25 5 | 7.5,6.5,40.5,25.5 6 | 8,7,41,26 7 | 8.5,7.5,42,26.5 8 | 9,8,42.5,27 9 | 9.5,8.5,43,27.5 10 | 10,9,44,28 11 | 10.5,9.5,44.5,28.5 12 | 11,10,45,29 13 | 11.5,10.5,45.5,29.5 14 | 12,11,46,30 15 | 12.5,11.5,47,30.5 16 | 13,12,47.5,31 17 | 13.5,12.5,48,31.5 18 | 14,13,48.5,32 19 | 15,14,49.5,33 20 | 16,15,50.5,34 21 | 16.5,15.5,51,34.5 22 | 17,16,51.5,35 23 | -------------------------------------------------------------------------------- /data/ft_col/train_csv/1438042987866.61__CC-MAIN-20150728002307-00252-ip-10-236-191-2.ec2.internal__1295.csv: -------------------------------------------------------------------------------- 1 | to find:,name on the register 2 | doctors with experience in your treatment:,"health condition (e.g. ""rheumatoid arthritis"") medical procedure (e.g. ""total knee replacement"")" 3 | doctors by their medical specialty:,"specialty name (e.g. ""orthopedic surgery"")" 4 | group practice or hospital:,"practice or hospital name (e.g. ""pinnacle hospital"")" 5 | specific doctor:,"doctor's name (e.g. ""dr. smith"" or ""john smith"")" 6 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042985647.51__CC-MAIN-20150728002305-00269-ip-10-236-191-2.ec2.internal__1236.csv: -------------------------------------------------------------------------------- 1 | us,uk,europe,cm 2 | 6,5.5,38.5,24 3 | 6.5,6,39,24.5 4 | 7,6,40,25 5 | 7.5,6.5,40.5,25.5 6 | 8,7,41,26 7 | 8.5,7.5,42,26.5 8 | 9,8,42.5,27 9 | 9.5,8.5,43,27.5 10 | 10,9,44,28 11 | 10.5,9.5,44.5,28.5 12 | 11,10,45,29 13 | 11.5,10.5,45.5,29.5 14 | 12,11,46,30 15 | 12.5,11.5,47,30.5 16 | 13,12,47.5,31 17 | 13.5,12.5,48,31.5 18 | 14,13,48.5,32 19 | 15,14,49.5,33 20 | 16,15,50.5,34 21 | 16.5,15.5,51,34.5 22 | 17,16,51.5,35 23 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042986451.45__CC-MAIN-20150728002306-00229-ip-10-236-191-2.ec2.internal__463.csv: -------------------------------------------------------------------------------- 1 | ,name,artist,time,shelia burrell, 2 | ,ë§?ì?´ì•¼ i’m saying,lee hongki (ì?´í™?기),3:50,, 3 | ,love is…,park jang hyeon (박장현) & park hyeon gyu (박현규),3:36,, 4 | ,모먼트 moment,changmin(창민),4:04,, 5 | ,in the name of love,vixx ken (켄),3:21,, 6 | ,ë‘? 사람 (two person),park jang hyun (박장현) [bromance],4:29,, 7 | ,아랫입술 물고 (biting my lower lip),"sung by esna (ì—?스나, 윤빛나ë?¼)",3:43,, 8 | -------------------------------------------------------------------------------- /data/ft_col/valid_csv/1438042988048.90__CC-MAIN-20150728002308-00117-ip-10-236-191-2.ec2.internal__1172.csv: -------------------------------------------------------------------------------- 1 | snp id,clin,chr 03 pos,sequence context,pf,type,maf 2 | rs12813,--,"50,258,640(+)",ggagg(g/t)gggca,,utr-variant-3-prime, 3 | rs12895,--,"50,259,042(-)",cagca(a/g)aggga,,utr-variant-3-prime, 4 | rs15488,--,"50,259,294(-)",catgt(a/c/g/t)aaaaa,,utr-variant-3-prime, 5 | rs762707,--,"50,252,421(-)",tcctc(a/c/g/t)gagta,,"synonymous-codon, reference, utr-variant-5-prime", 6 | rs916025,--,"50,239,810(-)",cagtg(c/t)accaa,,intron-variant, 7 | -------------------------------------------------------------------------------- /data/ft_cell/valid_csv/1438042988048.90__CC-MAIN-20150728002308-00117-ip-10-236-191-2.ec2.internal__1172.csv: -------------------------------------------------------------------------------- 1 | snp id,clin,chr 03 pos,sequence context,aa info,type,maf 2 | rs12813,--,"50,258,640(+)",ggagg(g/t)gggca,,"synonymous-codon, reference, utr-variant-5-prime", 3 | rs12895,--,"50,259,042(-)",cagca(a/g)aggga,,utr-variant-3-prime, 4 | rs15488,--,"50,259,294(-)",catgt(a/c/g/t)aaaaa,,intron-variant, 5 | rs762707,--,"50,252,421(-)",tcctc(a/c/g/t)gagta,,utr-variant-3-prime, 6 | rs916025,--,"50,239,810(-)",cagtg(c/t)accaa,,utr-variant-3-prime, 7 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042990217.27__CC-MAIN-20150728002310-00322-ip-10-236-191-2.ec2.internal__2306.csv: -------------------------------------------------------------------------------- 1 | time,interest,offer,visit,recruited by 2 | alabama,committed (05/11/2012),offered,none, 3 | auburn,none,offered,none, 4 | georgetown,none,offered,none, 5 | georgia,none,offered,none, 6 | kentucky,none,,none, 7 | marquette,none,,none, 8 | miami (fl),none,offered,none, 9 | mississippi,none,offered,none, 10 | mississippi st.,none,offered,none, 11 | n. carolina,none,,none, 12 | stanford,none,,none, 13 | vanderbilt,none,offered,none, 14 | -------------------------------------------------------------------------------- /data/ft_table/valid_csv/1438042988048.90__CC-MAIN-20150728002308-00117-ip-10-236-191-2.ec2.internal__1172.csv: -------------------------------------------------------------------------------- 1 | snp id,clin,chr 03 pos,sequence context,aa info,type,maf 2 | rs12813,--,"50,258,640(+)",ggagg(g/t)gggca,,utr-variant-3-prime, 3 | rs12895,--,"50,259,042(-)",cagca(a/g)aggga,,utr-variant-3-prime, 4 | rs15488,--,"50,259,294(-)",catgt(a/c/g/t)aaaaa,,utr-variant-3-prime, 5 | rs762707,--,"50,252,421(-)",tcctc(a/c/g/t)gagta,,"synonymous-codon, reference, utr-variant-5-prime", 6 | rs916025,--,"50,239,810(-)",cagtg(c/t)accaa,,intron-variant, 7 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042989234.2__CC-MAIN-20150728002309-00282-ip-10-236-191-2.ec2.internal__1016.csv: -------------------------------------------------------------------------------- 1 | ,new car,old car 2 | model,nissan altima,plymouth voyager/grand voyager 2wd 3 | drive train and engine,"2.5l, 4 cyl, automatic (variable gear ratios), fwd, regular","3.3l, 6 cyl, automatic 4-spd, fwd, (ffs), regular" 4 | price,"$22,740",model year 5 | "$3,500",2009,1996 6 | combined fuel economy,26 mpg,18 mpg 7 | vin,1n4al21e29n,1p4gp44rxtb176911 8 | odometer reading,-------,139874 9 | vehicle category,passenger car,category 1 truck 10 | -------------------------------------------------------------------------------- /data/ft_cell/test_csv/1438042990217.27__CC-MAIN-20150728002310-00322-ip-10-236-191-2.ec2.internal__2306.csv: -------------------------------------------------------------------------------- 1 | school,interest,offer,visit,recruited by 2 | none,none,offered,committed (05/11/2012), 3 | auburn,none,offered,vanderbilt, 4 | none,none,offered,alabama, 5 | georgia,none,offered,none, 6 | kentucky,none,,none, 7 | marquette,none,,georgetown, 8 | miami (fl),none,offered,none, 9 | mississippi,none,offered,none, 10 | mississippi st.,none,offered,none, 11 | n. carolina,none,,none, 12 | stanford,none,,none, 13 | none,none,offered,none, 14 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042988065.26__CC-MAIN-20150728002308-00033-ip-10-236-191-2.ec2.internal__865.csv: -------------------------------------------------------------------------------- 1 | s,ðœð°ðºñ?ð¸ð¼ñƒð¼, 2 | ð¤ð°ð¼ð¸ð»ð½ð° ñ?ñ‚ð°ñ? ñ? ð±ð°ð»ðºð¾ð½,+,ðŸð¾ðºð°ð¶ð¸ ñ†ðµð½ð¸ 3 | ð•ð´ð¸ð½ð¸ñ‡ð½ð° ñ?ñ‚ð°ñ?,,ðŸð¾ðºð°ð¶ð¸ ñ†ðµð½ð¸ 4 | ð”ð²ð¾ð¹ð½ð° ñ?ñ‚ð°ñ? ñ? 2 ð¾ñ‚ð´ðµð»ð½ð¸ ð»ðµð³ð»ð°,,ðŸð¾ðºð°ð¶ð¸ ñ†ðµð½ð¸ 5 | ð”ð²ð¾ð¹ð½ð° ñ?ñ‚ð°ñ?,,ðŸð¾ðºð°ð¶ð¸ ñ†ðµð½ð¸ 6 | ð¢ñ€ð¾ð¹ð½ð° ñ?ñ‚ð°ñ?,,ðŸð¾ðºð°ð¶ð¸ ñ†ðµð½ð¸ 7 | ð”ð²ð¾ð¹ð½ð° ñ?ñ‚ð°ñ? ñ? 2 ð¾ñ‚ð´ðµð»ð½ð¸ ð»ðµð³ð»ð°,,ðŸð¾ðºð°ð¶ð¸ ñ†ðµð½ð¸ 8 | ð”ð²ð¾ð¹ð½ð° ñ?ñ‚ð°ñ?,,ðŸð¾ðºð°ð¶ð¸ ñ†ðµð½ð¸ 9 | -------------------------------------------------------------------------------- /data/ft_col/test_csv/1438042989234.2__CC-MAIN-20150728002309-00282-ip-10-236-191-2.ec2.internal__1016.csv: -------------------------------------------------------------------------------- 1 | ,new car,old car 2 | model,nissan altima,plymouth voyager/grand voyager 2wd 3 | drive train and engine,"2.5l, 4 cyl, automatic (variable gear ratios), fwd, regular","3.3l, 6 cyl, automatic 4-spd, fwd, (ffs), regular" 4 | price,"$22,740","$3,500" 5 | model year,2009,1996 6 | combined fuel economy,26 mpg,18 mpg 7 | vin,1n4al21e29n,1p4gp44rxtb176911 8 | odometer reading,-------,139874 9 | vehicle category,passenger car,category 1 truck 10 | -------------------------------------------------------------------------------- /data/ft_table/test_csv/1438042989234.2__CC-MAIN-20150728002309-00282-ip-10-236-191-2.ec2.internal__1016.csv: -------------------------------------------------------------------------------- 1 | ,new car,old car 2 | model,nissan altima,plymouth voyager/grand voyager 2wd 3 | drive train and engine,"2.5l, 4 cyl, automatic (variable gear ratios), fwd, regular","3.3l, 6 cyl, automatic 4-spd, fwd, (ffs), regular" 4 | price,"$22,740","$3,500" 5 | model year,2009,1996 6 | combined fuel economy,26 mpg,18 mpg 7 | vin,1n4al21e29n,1p4gp44rxtb176911 8 | odometer reading,-------,139874 9 | vehicle category,passenger car,category 1 truck 10 | --------------------------------------------------------------------------------