├── README.md ├── Chapter02 ├── sample-pdf.pdf ├── sample-one-line.pdf ├── sample-one-line.docx ├── sample-one-line.protected.pdf ├── recipe3.py ├── word.py ├── recipe6.py ├── pdf.py ├── recipe2.py ├── recipe1.py └── recipe7.py ├── datasets ├── tokens │ ├── neg │ │ ├── cv000_tok-9611.txt │ │ ├── cv008_tok-11555.txt │ │ ├── cv012_tok-26965.txt │ │ ├── cv018_tok-11502.txt │ │ ├── cv021_tok-29141.txt │ │ ├── cv024_tok-22867.txt │ │ ├── cv035_tok-22978.txt │ │ ├── cv043_tok-12173.txt │ │ ├── cv055_tok-24153.txt │ │ ├── cv056_tok-14710.txt │ │ ├── cv062_tok-12406.txt │ │ ├── cv068_tok-12683.txt │ │ ├── cv070_tok-20301.txt │ │ ├── cv077_tok-18725.txt │ │ ├── cv078_tok-21038.txt │ │ ├── cv082_tok-26375.txt │ │ ├── cv086_tok-29002.txt │ │ ├── cv101_tok-24219.txt │ │ ├── cv102_tok-26890.txt │ │ ├── cv103_tok-28381.txt │ │ ├── cv115_tok-15080.txt │ │ ├── cv116_tok-9636.txt │ │ ├── cv140_tok-20790.txt │ │ ├── cv144_tok-14311.txt │ │ ├── cv150_tok-18938.txt │ │ ├── cv157_tok-19147.txt │ │ ├── cv164_tok-10606.txt │ │ ├── cv166_tok-23172.txt │ │ ├── cv170_tok-18402.txt │ │ ├── cv176_tok-15880.txt │ │ ├── cv181_tok-29326.txt │ │ ├── cv182_tok-25803.txt │ │ ├── cv184_tok-20654.txt │ │ ├── cv185_tok-22786.txt │ │ ├── cv187_tok-29374.txt │ │ ├── cv190_tok-17313.txt │ │ ├── cv196_tok-25263.txt │ │ ├── cv202_tok-15873.txt │ │ ├── cv206_tok-15604.txt │ │ ├── cv210_tok-15092.txt │ │ ├── cv211_tok-20701.txt │ │ ├── cv218_tok-20838.txt │ │ ├── cv219_tok-11130.txt │ │ ├── cv234_tok-28890.txt │ │ ├── cv241_tok-21519.txt │ │ ├── cv248_tok-17823.txt │ │ ├── cv252_tok-28837.txt │ │ ├── cv258_tok-15032.txt │ │ ├── cv260_tok-18536.txt │ │ ├── cv261_tok-24932.txt │ │ ├── cv263_tok-24157.txt │ │ ├── cv269_tok-19393.txt │ │ ├── cv270_tok-26085.txt │ │ ├── cv273_tok-29386.txt │ │ ├── cv277_tok-13229.txt │ │ ├── cv279_tok-23947.txt │ │ ├── cv280_tok-21672.txt │ │ ├── cv283_tok-24782.txt │ │ ├── cv303_tok-11557.txt │ │ ├── cv305_tok-24131.txt │ │ ├── cv307_tok-20139.txt │ │ ├── cv328_tok-23090.txt │ │ ├── cv329_tok-17076.txt │ │ ├── cv335_tok-12547.txt │ │ ├── cv336_tok-24857.txt │ │ ├── cv338_tok-24961.txt │ │ ├── cv339_tok-26055.txt │ │ ├── cv340_tok-10533.txt │ │ ├── cv341_tok-23117.txt │ │ ├── cv346_tok-24609.txt │ │ ├── cv347_tok-16780.txt │ │ ├── cv361_tok-29119.txt │ │ ├── cv362_tok-20426.txt │ │ ├── cv363_tok-21128.txt │ │ ├── cv371_tok-18848.txt │ │ ├── cv374_tok-26964.txt │ │ ├── cv381_tok-25624.txt │ │ ├── cv382_tok-21934.txt │ │ ├── cv384_tok-25866.txt │ │ ├── cv391_tok-29447.txt │ │ ├── cv393_tok-29397.txt │ │ ├── cv406_tok-18155.txt │ │ ├── cv415_tok-28738.txt │ │ ├── cv419_tok-16024.txt │ │ ├── cv423_tok-10742.txt │ │ ├── cv424_tok-29318.txt │ │ ├── cv428_tok-20300.txt │ │ ├── cv434_tok-29273.txt │ │ ├── cv435_tok-17966.txt │ │ ├── cv438_tok-17297.txt │ │ ├── cv439_tok-21510.txt │ │ ├── cv441_tok-9002.txt │ │ ├── cv442_tok-27163.txt │ │ ├── cv447_tok-19197.txt │ │ ├── cv450_tok-13677.txt │ │ ├── cv451_tok-28707.txt │ │ ├── cv453_tok-17410.txt │ │ ├── cv456_tok-29420.txt │ │ ├── cv458_tok-19400.txt │ │ ├── cv459_tok-29432.txt │ │ ├── cv465_tok-29619.txt │ │ ├── cv469_tok-15267.txt │ │ ├── cv472_tok-11943.txt │ │ ├── cv473_tok-14810.txt │ │ ├── cv479_tok-23674.txt │ │ ├── cv481_tok-10977.txt │ │ ├── cv488_tok-13847.txt │ │ ├── cv496_tok-17126.txt │ │ ├── cv500_tok-13146.txt │ │ ├── cv505_tok-17424.txt │ │ ├── cv512_tok-28882.txt │ │ ├── cv523_tok-23339.txt │ │ ├── cv524_tok-20616.txt │ │ ├── cv528_tok-25667.txt │ │ ├── cv534_tok-12128.txt │ │ ├── cv535_tok-19937.txt │ │ ├── cv544_tok-25047.txt │ │ ├── cv553_tok-27936.txt │ │ ├── cv559_tok-17078.txt │ │ ├── cv561_tok-18471.txt │ │ ├── cv563_tok-27217.txt │ │ ├── cv574_tok-23226.txt │ │ ├── cv581_tok-29376.txt │ │ ├── cv586_tok-19488.txt │ │ ├── cv596_tok-27611.txt │ │ ├── cv598_tok-28906.txt │ │ ├── cv603_tok-18184.txt │ │ ├── cv604_tok-21195.txt │ │ ├── cv605_tok-12048.txt │ │ ├── cv608_tok-29484.txt │ │ ├── cv617_tok-24070.txt │ │ ├── cv630_tok-23300.txt │ │ ├── cv632_tok-14112.txt │ │ ├── cv639_tok-16459.txt │ │ ├── cv651_tok-28796.txt │ │ ├── cv656_tok-29675.txt │ │ ├── cv666_tok-16121.txt │ │ ├── cv668_tok-23578.txt │ │ ├── cv669_tok-12224.txt │ │ ├── cv670_tok-9891.txt │ │ ├── cv672_tok-20564.txt │ │ ├── cv675_tok-10091.txt │ │ ├── cv683_tok-11354.txt │ │ ├── cv684_tok-10190.txt │ │ ├── cv688_tok-29384.txt │ │ ├── cv690_tok-26288.txt │ │ ├── cv695_tok-21695.txt │ │ ├── cv697_tok-12765.txt │ │ ├── cv373_tok-25938.txt │ │ ├── cv452_tok-18656.txt │ │ ├── cv592_tok-10894.txt │ │ ├── cv557_tok-24760.txt │ │ ├── cv059_tok-8583.txt │ │ ├── cv239_tok-24885.txt │ │ └── cv216_tok-27832.txt │ └── pos │ │ ├── cv002_tok-12931.txt │ │ ├── cv017_tok-29801.txt │ │ ├── cv018_tok-10094.txt │ │ ├── cv019_tok-11209.txt │ │ ├── cv022_tok-17069.txt │ │ ├── cv023_tok-12160.txt │ │ ├── cv043_tok-24397.txt │ │ ├── cv044_tok-29505.txt │ │ ├── cv045_tok-29121.txt │ │ ├── cv051_tok-21020.txt │ │ ├── cv057_tok-14094.txt │ │ ├── cv063_tok-28706.txt │ │ ├── cv068_tok-12672.txt │ │ ├── cv075_tok-17788.txt │ │ ├── cv088_tok-10534.txt │ │ ├── cv099_tok-15838.txt │ │ ├── cv102_tok-21103.txt │ │ ├── cv104_tok-28425.txt │ │ ├── cv108_tok-12767.txt │ │ ├── cv109_tok-16113.txt │ │ ├── cv116_tok-9457.txt │ │ ├── cv124_tok-29590.txt │ │ ├── cv127_tok-22921.txt │ │ ├── cv131_tok-19363.txt │ │ ├── cv135_tok-18510.txt │ │ ├── cv142_tok-11890.txt │ │ ├── cv154_tok-10175.txt │ │ ├── cv156_tok-12349.txt │ │ ├── cv157_tok-29786.txt │ │ ├── cv165_tok-11425.txt │ │ ├── cv179_tok-10822.txt │ │ ├── cv188_tok-16638.txt │ │ ├── cv190_tok-29198.txt │ │ ├── cv195_tok-13683.txt │ │ ├── cv200_tok-19912.txt │ │ ├── cv204_tok-10080.txt │ │ ├── cv207_tok-10975.txt │ │ ├── cv211_tok-24353.txt │ │ ├── cv212_tok-11472.txt │ │ ├── cv219_tok-22240.txt │ │ ├── cv232_tok-18168.txt │ │ ├── cv240_tok-29525.txt │ │ ├── cv245_tok-19462.txt │ │ ├── cv247_tok-26084.txt │ │ ├── cv249_tok-18722.txt │ │ ├── cv253_tok-19526.txt │ │ ├── cv255_tok-15449.txt │ │ ├── cv256_tok-11576.txt │ │ ├── cv258_tok-25234.txt │ │ ├── cv270_tok-29235.txt │ │ ├── cv271_tok-11240.txt │ │ ├── cv273_tok-10626.txt │ │ ├── cv274_tok-12014.txt │ │ ├── cv275_tok-12167.txt │ │ ├── cv278_tok-17924.txt │ │ ├── cv280_tok-27724.txt │ │ ├── cv296_tok-11353.txt │ │ ├── cv298_tok-16139.txt │ │ ├── cv313_tok-19364.txt │ │ ├── cv324_tok-11182.txt │ │ ├── cv326_tok-28892.txt │ │ ├── cv348_tok-24201.txt │ │ ├── cv353_tok-29082.txt │ │ ├── cv354_tok-13227.txt │ │ ├── cv355_tok-11500.txt │ │ ├── cv382_tok-11565.txt │ │ ├── cv391_tok-29468.txt │ │ ├── cv395_tok-27468.txt │ │ ├── cv400_tok-11748.txt │ │ ├── cv403_tok-19027.txt │ │ ├── cv404_tok-23115.txt │ │ ├── cv408_tok-24111.txt │ │ ├── cv409_tok-11193.txt │ │ ├── cv410_tok-24246.txt │ │ ├── cv418_tok-10147.txt │ │ ├── cv426_tok-12735.txt │ │ ├── cv433_tok-16006.txt │ │ ├── cv439_tok-13632.txt │ │ ├── cv440_tok-24265.txt │ │ ├── cv442_tok-28944.txt │ │ ├── cv448_tok-25113.txt │ │ ├── cv450_tok-18817.txt │ │ ├── cv454_tok-11053.txt │ │ ├── cv466_tok-22246.txt │ │ ├── cv468_tok-11620.txt │ │ ├── cv471_tok-21022.txt │ │ ├── cv472_tok-24511.txt │ │ ├── cv487_tok-15094.txt │ │ ├── cv489_tok-23236.txt │ │ ├── cv490_tok-15448.txt │ │ ├── cv493_tok-10732.txt │ │ ├── cv494_tok-25127.txt │ │ ├── cv498_tok-28077.txt │ │ ├── cv510_tok-29540.txt │ │ ├── cv512_tok-27457.txt │ │ ├── cv516_tok-10558.txt │ │ ├── cv520_tok-13142.txt │ │ ├── cv547_tok-18643.txt │ │ ├── cv552_tok-23130.txt │ │ ├── cv553_tok-13743.txt │ │ ├── cv560_tok-11131.txt │ │ ├── cv562_tok-19381.txt │ │ ├── cv567_tok-29658.txt │ │ ├── cv581_tok-20785.txt │ │ ├── cv583_tok-19290.txt │ │ ├── cv585_tok-29721.txt │ │ ├── cv588_tok-10492.txt │ │ ├── cv589_tok-17484.txt │ │ ├── cv596_tok-29066.txt │ │ ├── cv598_tok-18159.txt │ │ ├── cv600_tok-23338.txt │ │ ├── cv609_tok-27236.txt │ │ ├── cv618_tok-23497.txt │ │ ├── cv628_tok-24095.txt │ │ ├── cv633_tok-28885.txt │ │ ├── cv634_tok-28807.txt │ │ ├── cv637_tok-9659.txt │ │ ├── cv640_tok-26304.txt │ │ ├── cv649_tok-27594.txt │ │ ├── cv650_tok-14989.txt │ │ ├── cv653_tok-10211.txt │ │ ├── cv658_tok-13091.txt │ │ ├── cv661_tok-10482.txt │ │ ├── cv670_tok-24009.txt │ │ ├── cv690_tok-23617.txt │ │ ├── cv692_tok-24295.txt │ │ ├── cv696_tok-10835.txt │ │ ├── cv365_tok-21785.txt │ │ ├── cv132_tok-5618.txt │ │ ├── cv037_tok-11720.txt │ │ ├── cv206_tok-12590.txt │ │ └── cv627_tok-14423.txt └── mix20_rand700_tokens_cleaned │ └── tokens │ ├── neg │ ├── cv000_tok-9611.txt │ ├── cv008_tok-11555.txt │ ├── cv012_tok-26965.txt │ ├── cv018_tok-11502.txt │ ├── cv021_tok-29141.txt │ ├── cv024_tok-22867.txt │ ├── cv035_tok-22978.txt │ ├── cv043_tok-12173.txt │ ├── cv055_tok-24153.txt │ ├── cv056_tok-14710.txt │ ├── cv062_tok-12406.txt │ ├── cv068_tok-12683.txt │ ├── cv070_tok-20301.txt │ ├── cv077_tok-18725.txt │ ├── cv078_tok-21038.txt │ ├── cv082_tok-26375.txt │ ├── cv086_tok-29002.txt │ ├── cv101_tok-24219.txt │ ├── cv102_tok-26890.txt │ ├── cv103_tok-28381.txt │ ├── cv115_tok-15080.txt │ ├── cv116_tok-9636.txt │ ├── cv140_tok-20790.txt │ ├── cv144_tok-14311.txt │ ├── cv150_tok-18938.txt │ ├── cv157_tok-19147.txt │ ├── cv164_tok-10606.txt │ ├── cv166_tok-23172.txt │ ├── cv170_tok-18402.txt │ ├── cv176_tok-15880.txt │ ├── cv181_tok-29326.txt │ ├── cv182_tok-25803.txt │ ├── cv184_tok-20654.txt │ ├── cv185_tok-22786.txt │ ├── cv187_tok-29374.txt │ ├── cv190_tok-17313.txt │ ├── cv196_tok-25263.txt │ ├── cv202_tok-15873.txt │ ├── cv206_tok-15604.txt │ ├── cv210_tok-15092.txt │ ├── cv211_tok-20701.txt │ ├── cv218_tok-20838.txt │ ├── cv219_tok-11130.txt │ ├── cv234_tok-28890.txt │ ├── cv241_tok-21519.txt │ ├── cv248_tok-17823.txt │ ├── cv252_tok-28837.txt │ ├── cv258_tok-15032.txt │ ├── cv260_tok-18536.txt │ ├── cv261_tok-24932.txt │ ├── cv263_tok-24157.txt │ ├── cv269_tok-19393.txt │ ├── cv270_tok-26085.txt │ ├── cv273_tok-29386.txt │ ├── cv277_tok-13229.txt │ ├── cv279_tok-23947.txt │ ├── cv280_tok-21672.txt │ ├── cv283_tok-24782.txt │ ├── cv303_tok-11557.txt │ ├── cv305_tok-24131.txt │ ├── cv307_tok-20139.txt │ ├── cv328_tok-23090.txt │ ├── cv329_tok-17076.txt │ ├── cv335_tok-12547.txt │ ├── cv336_tok-24857.txt │ ├── cv338_tok-24961.txt │ ├── cv339_tok-26055.txt │ ├── cv340_tok-10533.txt │ ├── cv341_tok-23117.txt │ ├── cv346_tok-24609.txt │ ├── cv347_tok-16780.txt │ ├── cv361_tok-29119.txt │ ├── cv362_tok-20426.txt │ ├── cv363_tok-21128.txt │ ├── cv371_tok-18848.txt │ ├── cv374_tok-26964.txt │ ├── cv381_tok-25624.txt │ ├── cv382_tok-21934.txt │ ├── cv384_tok-25866.txt │ ├── cv391_tok-29447.txt │ ├── cv393_tok-29397.txt │ ├── cv406_tok-18155.txt │ ├── cv415_tok-28738.txt │ ├── cv419_tok-16024.txt │ ├── cv423_tok-10742.txt │ ├── cv424_tok-29318.txt │ ├── cv428_tok-20300.txt │ ├── cv434_tok-29273.txt │ ├── cv435_tok-17966.txt │ ├── cv438_tok-17297.txt │ ├── cv439_tok-21510.txt │ ├── cv441_tok-9002.txt │ ├── cv442_tok-27163.txt │ ├── cv447_tok-19197.txt │ ├── cv450_tok-13677.txt │ ├── cv451_tok-28707.txt │ ├── cv453_tok-17410.txt │ ├── cv456_tok-29420.txt │ ├── cv458_tok-19400.txt │ ├── cv459_tok-29432.txt │ ├── cv465_tok-29619.txt │ ├── cv469_tok-15267.txt │ ├── cv472_tok-11943.txt │ ├── cv473_tok-14810.txt │ ├── cv479_tok-23674.txt │ ├── cv481_tok-10977.txt │ ├── cv488_tok-13847.txt │ ├── cv496_tok-17126.txt │ ├── cv500_tok-13146.txt │ ├── cv505_tok-17424.txt │ ├── cv512_tok-28882.txt │ ├── cv523_tok-23339.txt │ ├── cv524_tok-20616.txt │ ├── cv528_tok-25667.txt │ ├── cv534_tok-12128.txt │ ├── cv535_tok-19937.txt │ ├── cv544_tok-25047.txt │ ├── cv553_tok-27936.txt │ ├── cv559_tok-17078.txt │ ├── cv561_tok-18471.txt │ ├── cv563_tok-27217.txt │ ├── cv574_tok-23226.txt │ ├── cv581_tok-29376.txt │ ├── cv586_tok-19488.txt │ ├── cv596_tok-27611.txt │ ├── cv598_tok-28906.txt │ ├── cv603_tok-18184.txt │ ├── cv604_tok-21195.txt │ ├── cv605_tok-12048.txt │ ├── cv608_tok-29484.txt │ ├── cv617_tok-24070.txt │ ├── cv630_tok-23300.txt │ ├── cv632_tok-14112.txt │ ├── cv639_tok-16459.txt │ ├── cv651_tok-28796.txt │ ├── cv656_tok-29675.txt │ ├── cv666_tok-16121.txt │ ├── cv668_tok-23578.txt │ ├── cv669_tok-12224.txt │ ├── cv670_tok-9891.txt │ ├── cv672_tok-20564.txt │ ├── cv675_tok-10091.txt │ ├── cv683_tok-11354.txt │ ├── cv684_tok-10190.txt │ ├── cv688_tok-29384.txt │ ├── cv690_tok-26288.txt │ ├── cv695_tok-21695.txt │ ├── cv697_tok-12765.txt │ ├── cv373_tok-25938.txt │ ├── cv452_tok-18656.txt │ ├── cv592_tok-10894.txt │ ├── cv557_tok-24760.txt │ ├── cv059_tok-8583.txt │ ├── cv239_tok-24885.txt │ └── cv216_tok-27832.txt │ └── pos │ ├── cv002_tok-12931.txt │ ├── cv017_tok-29801.txt │ ├── cv018_tok-10094.txt │ ├── cv019_tok-11209.txt │ ├── cv022_tok-17069.txt │ ├── cv023_tok-12160.txt │ ├── cv043_tok-24397.txt │ ├── cv044_tok-29505.txt │ ├── cv045_tok-29121.txt │ ├── cv051_tok-21020.txt │ ├── cv057_tok-14094.txt │ ├── cv063_tok-28706.txt │ ├── cv068_tok-12672.txt │ ├── cv075_tok-17788.txt │ ├── cv088_tok-10534.txt │ ├── cv099_tok-15838.txt │ ├── cv102_tok-21103.txt │ ├── cv104_tok-28425.txt │ ├── cv108_tok-12767.txt │ ├── cv109_tok-16113.txt │ ├── cv116_tok-9457.txt │ ├── cv124_tok-29590.txt │ ├── cv127_tok-22921.txt │ ├── cv131_tok-19363.txt │ ├── cv135_tok-18510.txt │ ├── cv142_tok-11890.txt │ ├── cv154_tok-10175.txt │ ├── cv156_tok-12349.txt │ ├── cv157_tok-29786.txt │ ├── cv165_tok-11425.txt │ ├── cv179_tok-10822.txt │ ├── cv188_tok-16638.txt │ ├── cv190_tok-29198.txt │ ├── cv195_tok-13683.txt │ ├── cv200_tok-19912.txt │ ├── cv204_tok-10080.txt │ ├── cv207_tok-10975.txt │ ├── cv211_tok-24353.txt │ ├── cv212_tok-11472.txt │ ├── cv219_tok-22240.txt │ ├── cv232_tok-18168.txt │ ├── cv240_tok-29525.txt │ ├── cv245_tok-19462.txt │ ├── cv247_tok-26084.txt │ ├── cv249_tok-18722.txt │ ├── cv253_tok-19526.txt │ ├── cv255_tok-15449.txt │ ├── cv256_tok-11576.txt │ ├── cv258_tok-25234.txt │ ├── cv270_tok-29235.txt │ ├── cv271_tok-11240.txt │ ├── cv273_tok-10626.txt │ ├── cv274_tok-12014.txt │ ├── cv275_tok-12167.txt │ ├── cv278_tok-17924.txt │ ├── cv280_tok-27724.txt │ ├── cv296_tok-11353.txt │ ├── cv298_tok-16139.txt │ ├── cv313_tok-19364.txt │ ├── cv324_tok-11182.txt │ ├── cv326_tok-28892.txt │ ├── cv348_tok-24201.txt │ ├── cv353_tok-29082.txt │ ├── cv354_tok-13227.txt │ ├── cv355_tok-11500.txt │ ├── cv382_tok-11565.txt │ ├── cv391_tok-29468.txt │ ├── cv395_tok-27468.txt │ ├── cv400_tok-11748.txt │ ├── cv403_tok-19027.txt │ ├── cv404_tok-23115.txt │ ├── cv408_tok-24111.txt │ ├── cv409_tok-11193.txt │ ├── cv410_tok-24246.txt │ ├── cv418_tok-10147.txt │ ├── cv426_tok-12735.txt │ ├── cv433_tok-16006.txt │ ├── cv439_tok-13632.txt │ ├── cv440_tok-24265.txt │ ├── cv442_tok-28944.txt │ ├── cv448_tok-25113.txt │ ├── cv450_tok-18817.txt │ ├── cv454_tok-11053.txt │ ├── cv466_tok-22246.txt │ ├── cv468_tok-11620.txt │ ├── cv471_tok-21022.txt │ ├── cv472_tok-24511.txt │ ├── cv487_tok-15094.txt │ ├── cv489_tok-23236.txt │ ├── cv490_tok-15448.txt │ ├── cv493_tok-10732.txt │ ├── cv494_tok-25127.txt │ ├── cv498_tok-28077.txt │ ├── cv510_tok-29540.txt │ ├── cv512_tok-27457.txt │ ├── cv516_tok-10558.txt │ ├── cv520_tok-13142.txt │ ├── cv547_tok-18643.txt │ ├── cv552_tok-23130.txt │ ├── cv553_tok-13743.txt │ ├── cv560_tok-11131.txt │ ├── cv562_tok-19381.txt │ ├── cv567_tok-29658.txt │ ├── cv581_tok-20785.txt │ ├── cv583_tok-19290.txt │ ├── cv585_tok-29721.txt │ ├── cv588_tok-10492.txt │ ├── cv589_tok-17484.txt │ ├── cv596_tok-29066.txt │ ├── cv598_tok-18159.txt │ ├── cv600_tok-23338.txt │ ├── cv609_tok-27236.txt │ ├── cv618_tok-23497.txt │ ├── cv628_tok-24095.txt │ ├── cv633_tok-28885.txt │ ├── cv634_tok-28807.txt │ ├── cv637_tok-9659.txt │ ├── cv640_tok-26304.txt │ ├── cv649_tok-27594.txt │ ├── cv650_tok-14989.txt │ ├── cv653_tok-10211.txt │ ├── cv658_tok-13091.txt │ ├── cv661_tok-10482.txt │ ├── cv670_tok-24009.txt │ ├── cv690_tok-23617.txt │ ├── cv692_tok-24295.txt │ ├── cv696_tok-10835.txt │ ├── cv365_tok-21785.txt │ ├── cv132_tok-5618.txt │ ├── cv037_tok-11720.txt │ ├── cv206_tok-12590.txt │ └── cv627_tok-14423.txt ├── Chapter04 ├── recipe6.py ├── recipe5.py ├── recipe7.py ├── recipe4.py ├── recipe1.py ├── recipe3.py └── recipe2.py ├── Chapter05 ├── Exploring.py └── RecursiveCFG.py ├── Chapter06 ├── Chunker.py ├── ParsingDG.py └── SimpleChunker.py ├── Chapter07 └── NER.py ├── Chapter01 ├── recipe5.py ├── recipe1.py ├── recipe3.py ├── recipe7.py ├── recipe4.py └── recipe6.py └── Chapter03 ├── recipe2.py ├── recipe3.py ├── recipe5.py └── recipe4.py /README.md: -------------------------------------------------------------------------------- 1 | # Natural-Language-Processing-with-Python-Cookbook 2 | Natural Language Processing with Python Cookbook, published by Packt 3 | -------------------------------------------------------------------------------- /Chapter02/sample-pdf.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/Chapter02/sample-pdf.pdf -------------------------------------------------------------------------------- /Chapter02/sample-one-line.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/Chapter02/sample-one-line.pdf -------------------------------------------------------------------------------- /Chapter02/sample-one-line.docx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/Chapter02/sample-one-line.docx -------------------------------------------------------------------------------- /Chapter02/sample-one-line.protected.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/Chapter02/sample-one-line.protected.pdf -------------------------------------------------------------------------------- /datasets/tokens/neg/cv000_tok-9611.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv000_tok-9611.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv008_tok-11555.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv008_tok-11555.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv012_tok-26965.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv012_tok-26965.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv018_tok-11502.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv018_tok-11502.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv021_tok-29141.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv021_tok-29141.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv024_tok-22867.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv024_tok-22867.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv035_tok-22978.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv035_tok-22978.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv043_tok-12173.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv043_tok-12173.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv055_tok-24153.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv055_tok-24153.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv056_tok-14710.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv056_tok-14710.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv062_tok-12406.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv062_tok-12406.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv068_tok-12683.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv068_tok-12683.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv070_tok-20301.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv070_tok-20301.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv077_tok-18725.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv077_tok-18725.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv078_tok-21038.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv078_tok-21038.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv082_tok-26375.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv082_tok-26375.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv086_tok-29002.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv086_tok-29002.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv101_tok-24219.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv101_tok-24219.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv102_tok-26890.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv102_tok-26890.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv103_tok-28381.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv103_tok-28381.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv115_tok-15080.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv115_tok-15080.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv116_tok-9636.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv116_tok-9636.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv140_tok-20790.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv140_tok-20790.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv144_tok-14311.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv144_tok-14311.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv150_tok-18938.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv150_tok-18938.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv157_tok-19147.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv157_tok-19147.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv164_tok-10606.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv164_tok-10606.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv166_tok-23172.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv166_tok-23172.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv170_tok-18402.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv170_tok-18402.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv176_tok-15880.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv176_tok-15880.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv181_tok-29326.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv181_tok-29326.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv182_tok-25803.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv182_tok-25803.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv184_tok-20654.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv184_tok-20654.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv185_tok-22786.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv185_tok-22786.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv187_tok-29374.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv187_tok-29374.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv190_tok-17313.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv190_tok-17313.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv196_tok-25263.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv196_tok-25263.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv202_tok-15873.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv202_tok-15873.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv206_tok-15604.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv206_tok-15604.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv210_tok-15092.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv210_tok-15092.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv211_tok-20701.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv211_tok-20701.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv218_tok-20838.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv218_tok-20838.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv219_tok-11130.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv219_tok-11130.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv234_tok-28890.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv234_tok-28890.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv241_tok-21519.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv241_tok-21519.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv248_tok-17823.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv248_tok-17823.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv252_tok-28837.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv252_tok-28837.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv258_tok-15032.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv258_tok-15032.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv260_tok-18536.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv260_tok-18536.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv261_tok-24932.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv261_tok-24932.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv263_tok-24157.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv263_tok-24157.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv269_tok-19393.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv269_tok-19393.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv270_tok-26085.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv270_tok-26085.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv273_tok-29386.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv273_tok-29386.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv277_tok-13229.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv277_tok-13229.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv279_tok-23947.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv279_tok-23947.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv280_tok-21672.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv280_tok-21672.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv283_tok-24782.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv283_tok-24782.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv303_tok-11557.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv303_tok-11557.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv305_tok-24131.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv305_tok-24131.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv307_tok-20139.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv307_tok-20139.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv328_tok-23090.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv328_tok-23090.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv329_tok-17076.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv329_tok-17076.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv335_tok-12547.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv335_tok-12547.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv336_tok-24857.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv336_tok-24857.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv338_tok-24961.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv338_tok-24961.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv339_tok-26055.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv339_tok-26055.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv340_tok-10533.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv340_tok-10533.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv341_tok-23117.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv341_tok-23117.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv346_tok-24609.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv346_tok-24609.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv347_tok-16780.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv347_tok-16780.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv361_tok-29119.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv361_tok-29119.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv362_tok-20426.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv362_tok-20426.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv363_tok-21128.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv363_tok-21128.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv371_tok-18848.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv371_tok-18848.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv374_tok-26964.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv374_tok-26964.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv381_tok-25624.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv381_tok-25624.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv382_tok-21934.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv382_tok-21934.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv384_tok-25866.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv384_tok-25866.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv391_tok-29447.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv391_tok-29447.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv393_tok-29397.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv393_tok-29397.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv406_tok-18155.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv406_tok-18155.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv415_tok-28738.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv415_tok-28738.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv419_tok-16024.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv419_tok-16024.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv423_tok-10742.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv423_tok-10742.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv424_tok-29318.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv424_tok-29318.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv428_tok-20300.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv428_tok-20300.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv434_tok-29273.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv434_tok-29273.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv435_tok-17966.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv435_tok-17966.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv438_tok-17297.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv438_tok-17297.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv439_tok-21510.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv439_tok-21510.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv441_tok-9002.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv441_tok-9002.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv442_tok-27163.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv442_tok-27163.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv447_tok-19197.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv447_tok-19197.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv450_tok-13677.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv450_tok-13677.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv451_tok-28707.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv451_tok-28707.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv453_tok-17410.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv453_tok-17410.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv456_tok-29420.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv456_tok-29420.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv458_tok-19400.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv458_tok-19400.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv459_tok-29432.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv459_tok-29432.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv465_tok-29619.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv465_tok-29619.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv469_tok-15267.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv469_tok-15267.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv472_tok-11943.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv472_tok-11943.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv473_tok-14810.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv473_tok-14810.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv479_tok-23674.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv479_tok-23674.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv481_tok-10977.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv481_tok-10977.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv488_tok-13847.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv488_tok-13847.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv496_tok-17126.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv496_tok-17126.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv500_tok-13146.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv500_tok-13146.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv505_tok-17424.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv505_tok-17424.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv512_tok-28882.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv512_tok-28882.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv523_tok-23339.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv523_tok-23339.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv524_tok-20616.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv524_tok-20616.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv528_tok-25667.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv528_tok-25667.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv534_tok-12128.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv534_tok-12128.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv535_tok-19937.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv535_tok-19937.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv544_tok-25047.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv544_tok-25047.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv553_tok-27936.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv553_tok-27936.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv559_tok-17078.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv559_tok-17078.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv561_tok-18471.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv561_tok-18471.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv563_tok-27217.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv563_tok-27217.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv574_tok-23226.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv574_tok-23226.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv581_tok-29376.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv581_tok-29376.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv586_tok-19488.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv586_tok-19488.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv596_tok-27611.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv596_tok-27611.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv598_tok-28906.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv598_tok-28906.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv603_tok-18184.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv603_tok-18184.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv604_tok-21195.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv604_tok-21195.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv605_tok-12048.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv605_tok-12048.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv608_tok-29484.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv608_tok-29484.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv617_tok-24070.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv617_tok-24070.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv630_tok-23300.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv630_tok-23300.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv632_tok-14112.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv632_tok-14112.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv639_tok-16459.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv639_tok-16459.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv651_tok-28796.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv651_tok-28796.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv656_tok-29675.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv656_tok-29675.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv666_tok-16121.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv666_tok-16121.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv668_tok-23578.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv668_tok-23578.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv669_tok-12224.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv669_tok-12224.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv670_tok-9891.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv670_tok-9891.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv672_tok-20564.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv672_tok-20564.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv675_tok-10091.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv675_tok-10091.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv683_tok-11354.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv683_tok-11354.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv684_tok-10190.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv684_tok-10190.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv688_tok-29384.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv688_tok-29384.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv690_tok-26288.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv690_tok-26288.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv695_tok-21695.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv695_tok-21695.txt -------------------------------------------------------------------------------- /datasets/tokens/neg/cv697_tok-12765.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/neg/cv697_tok-12765.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv002_tok-12931.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv002_tok-12931.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv017_tok-29801.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv017_tok-29801.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv018_tok-10094.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv018_tok-10094.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv019_tok-11209.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv019_tok-11209.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv022_tok-17069.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv022_tok-17069.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv023_tok-12160.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv023_tok-12160.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv043_tok-24397.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv043_tok-24397.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv044_tok-29505.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv044_tok-29505.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv045_tok-29121.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv045_tok-29121.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv051_tok-21020.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv051_tok-21020.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv057_tok-14094.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv057_tok-14094.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv063_tok-28706.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv063_tok-28706.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv068_tok-12672.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv068_tok-12672.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv075_tok-17788.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv075_tok-17788.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv088_tok-10534.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv088_tok-10534.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv099_tok-15838.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv099_tok-15838.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv102_tok-21103.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv102_tok-21103.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv104_tok-28425.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv104_tok-28425.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv108_tok-12767.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv108_tok-12767.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv109_tok-16113.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv109_tok-16113.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv116_tok-9457.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv116_tok-9457.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv124_tok-29590.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv124_tok-29590.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv127_tok-22921.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv127_tok-22921.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv131_tok-19363.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv131_tok-19363.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv135_tok-18510.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv135_tok-18510.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv142_tok-11890.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv142_tok-11890.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv154_tok-10175.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv154_tok-10175.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv156_tok-12349.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv156_tok-12349.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv157_tok-29786.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv157_tok-29786.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv165_tok-11425.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv165_tok-11425.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv179_tok-10822.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv179_tok-10822.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv188_tok-16638.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv188_tok-16638.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv190_tok-29198.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv190_tok-29198.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv195_tok-13683.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv195_tok-13683.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv200_tok-19912.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv200_tok-19912.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv204_tok-10080.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv204_tok-10080.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv207_tok-10975.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv207_tok-10975.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv211_tok-24353.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv211_tok-24353.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv212_tok-11472.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv212_tok-11472.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv219_tok-22240.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv219_tok-22240.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv232_tok-18168.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv232_tok-18168.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv240_tok-29525.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv240_tok-29525.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv245_tok-19462.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv245_tok-19462.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv247_tok-26084.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv247_tok-26084.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv249_tok-18722.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv249_tok-18722.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv253_tok-19526.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv253_tok-19526.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv255_tok-15449.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv255_tok-15449.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv256_tok-11576.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv256_tok-11576.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv258_tok-25234.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv258_tok-25234.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv270_tok-29235.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv270_tok-29235.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv271_tok-11240.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv271_tok-11240.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv273_tok-10626.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv273_tok-10626.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv274_tok-12014.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv274_tok-12014.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv275_tok-12167.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv275_tok-12167.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv278_tok-17924.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv278_tok-17924.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv280_tok-27724.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv280_tok-27724.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv296_tok-11353.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv296_tok-11353.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv298_tok-16139.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv298_tok-16139.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv313_tok-19364.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv313_tok-19364.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv324_tok-11182.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv324_tok-11182.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv326_tok-28892.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv326_tok-28892.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv348_tok-24201.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv348_tok-24201.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv353_tok-29082.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv353_tok-29082.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv354_tok-13227.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv354_tok-13227.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv355_tok-11500.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv355_tok-11500.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv382_tok-11565.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv382_tok-11565.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv391_tok-29468.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv391_tok-29468.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv395_tok-27468.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv395_tok-27468.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv400_tok-11748.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv400_tok-11748.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv403_tok-19027.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv403_tok-19027.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv404_tok-23115.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv404_tok-23115.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv408_tok-24111.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv408_tok-24111.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv409_tok-11193.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv409_tok-11193.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv410_tok-24246.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv410_tok-24246.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv418_tok-10147.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv418_tok-10147.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv426_tok-12735.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv426_tok-12735.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv433_tok-16006.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv433_tok-16006.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv439_tok-13632.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv439_tok-13632.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv440_tok-24265.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv440_tok-24265.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv442_tok-28944.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv442_tok-28944.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv448_tok-25113.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv448_tok-25113.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv450_tok-18817.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv450_tok-18817.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv454_tok-11053.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv454_tok-11053.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv466_tok-22246.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv466_tok-22246.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv468_tok-11620.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv468_tok-11620.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv471_tok-21022.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv471_tok-21022.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv472_tok-24511.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv472_tok-24511.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv487_tok-15094.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv487_tok-15094.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv489_tok-23236.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv489_tok-23236.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv490_tok-15448.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv490_tok-15448.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv493_tok-10732.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv493_tok-10732.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv494_tok-25127.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv494_tok-25127.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv498_tok-28077.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv498_tok-28077.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv510_tok-29540.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv510_tok-29540.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv512_tok-27457.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv512_tok-27457.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv516_tok-10558.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv516_tok-10558.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv520_tok-13142.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv520_tok-13142.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv547_tok-18643.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv547_tok-18643.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv552_tok-23130.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv552_tok-23130.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv553_tok-13743.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv553_tok-13743.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv560_tok-11131.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv560_tok-11131.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv562_tok-19381.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv562_tok-19381.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv567_tok-29658.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv567_tok-29658.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv581_tok-20785.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv581_tok-20785.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv583_tok-19290.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv583_tok-19290.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv585_tok-29721.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv585_tok-29721.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv588_tok-10492.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv588_tok-10492.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv589_tok-17484.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv589_tok-17484.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv596_tok-29066.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv596_tok-29066.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv598_tok-18159.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv598_tok-18159.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv600_tok-23338.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv600_tok-23338.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv609_tok-27236.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv609_tok-27236.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv618_tok-23497.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv618_tok-23497.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv628_tok-24095.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv628_tok-24095.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv633_tok-28885.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv633_tok-28885.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv634_tok-28807.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv634_tok-28807.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv637_tok-9659.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv637_tok-9659.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv640_tok-26304.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv640_tok-26304.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv649_tok-27594.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv649_tok-27594.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv650_tok-14989.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv650_tok-14989.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv653_tok-10211.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv653_tok-10211.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv658_tok-13091.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv658_tok-13091.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv661_tok-10482.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv661_tok-10482.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv670_tok-24009.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv670_tok-24009.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv690_tok-23617.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv690_tok-23617.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv692_tok-24295.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv692_tok-24295.txt -------------------------------------------------------------------------------- /datasets/tokens/pos/cv696_tok-10835.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/tokens/pos/cv696_tok-10835.txt -------------------------------------------------------------------------------- /Chapter04/recipe6.py: -------------------------------------------------------------------------------- 1 | import re 2 | 3 | raw = "I am big! It's the pictures that got small." 4 | print(re.split(r' +', raw)) 5 | 6 | print(re.split(r'\W+', raw)) 7 | 8 | print(re.findall(r'\w+|\S\w*', raw)) -------------------------------------------------------------------------------- /Chapter04/recipe5.py: -------------------------------------------------------------------------------- 1 | import re 2 | 3 | street = '21 Ramkrishna Road' 4 | print(re.sub('Road', 'Rd', street)) 5 | 6 | text = 'Diwali is a festival of light, Holi is a festival of color!' 7 | print(re.findall(r"\b\w{5}\b", text)) -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv000_tok-9611.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv000_tok-9611.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv008_tok-11555.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv008_tok-11555.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv012_tok-26965.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv012_tok-26965.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv018_tok-11502.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv018_tok-11502.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv021_tok-29141.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv021_tok-29141.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv024_tok-22867.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv024_tok-22867.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv035_tok-22978.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv035_tok-22978.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv043_tok-12173.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv043_tok-12173.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv055_tok-24153.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv055_tok-24153.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv056_tok-14710.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv056_tok-14710.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv062_tok-12406.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv062_tok-12406.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv068_tok-12683.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv068_tok-12683.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv070_tok-20301.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv070_tok-20301.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv077_tok-18725.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv077_tok-18725.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv078_tok-21038.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv078_tok-21038.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv082_tok-26375.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv082_tok-26375.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv086_tok-29002.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv086_tok-29002.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv101_tok-24219.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv101_tok-24219.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv102_tok-26890.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv102_tok-26890.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv103_tok-28381.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv103_tok-28381.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv115_tok-15080.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv115_tok-15080.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv116_tok-9636.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv116_tok-9636.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv140_tok-20790.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv140_tok-20790.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv144_tok-14311.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv144_tok-14311.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv150_tok-18938.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv150_tok-18938.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv157_tok-19147.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv157_tok-19147.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv164_tok-10606.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv164_tok-10606.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv166_tok-23172.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv166_tok-23172.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv170_tok-18402.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv170_tok-18402.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv176_tok-15880.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv176_tok-15880.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv181_tok-29326.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv181_tok-29326.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv182_tok-25803.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv182_tok-25803.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv184_tok-20654.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv184_tok-20654.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv185_tok-22786.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv185_tok-22786.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv187_tok-29374.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv187_tok-29374.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv190_tok-17313.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv190_tok-17313.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv196_tok-25263.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv196_tok-25263.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv202_tok-15873.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv202_tok-15873.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv206_tok-15604.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv206_tok-15604.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv210_tok-15092.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv210_tok-15092.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv211_tok-20701.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv211_tok-20701.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv218_tok-20838.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv218_tok-20838.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv219_tok-11130.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv219_tok-11130.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv234_tok-28890.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv234_tok-28890.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv241_tok-21519.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv241_tok-21519.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv248_tok-17823.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv248_tok-17823.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv252_tok-28837.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv252_tok-28837.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv258_tok-15032.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv258_tok-15032.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv260_tok-18536.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv260_tok-18536.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv261_tok-24932.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv261_tok-24932.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv263_tok-24157.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv263_tok-24157.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv269_tok-19393.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv269_tok-19393.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv270_tok-26085.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv270_tok-26085.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv273_tok-29386.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv273_tok-29386.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv277_tok-13229.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv277_tok-13229.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv279_tok-23947.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv279_tok-23947.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv280_tok-21672.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv280_tok-21672.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv283_tok-24782.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv283_tok-24782.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv303_tok-11557.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv303_tok-11557.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv305_tok-24131.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv305_tok-24131.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv307_tok-20139.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv307_tok-20139.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv328_tok-23090.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv328_tok-23090.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv329_tok-17076.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv329_tok-17076.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv335_tok-12547.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv335_tok-12547.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv336_tok-24857.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv336_tok-24857.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv338_tok-24961.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv338_tok-24961.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv339_tok-26055.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv339_tok-26055.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv340_tok-10533.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv340_tok-10533.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv341_tok-23117.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv341_tok-23117.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv346_tok-24609.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv346_tok-24609.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv347_tok-16780.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv347_tok-16780.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv361_tok-29119.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv361_tok-29119.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv362_tok-20426.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv362_tok-20426.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv363_tok-21128.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv363_tok-21128.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv371_tok-18848.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv371_tok-18848.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv374_tok-26964.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv374_tok-26964.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv381_tok-25624.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv381_tok-25624.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv382_tok-21934.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv382_tok-21934.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv384_tok-25866.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv384_tok-25866.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv391_tok-29447.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv391_tok-29447.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv393_tok-29397.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv393_tok-29397.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv406_tok-18155.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv406_tok-18155.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv415_tok-28738.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv415_tok-28738.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv419_tok-16024.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv419_tok-16024.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv423_tok-10742.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv423_tok-10742.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv424_tok-29318.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv424_tok-29318.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv428_tok-20300.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv428_tok-20300.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv434_tok-29273.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv434_tok-29273.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv435_tok-17966.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv435_tok-17966.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv438_tok-17297.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv438_tok-17297.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv439_tok-21510.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv439_tok-21510.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv441_tok-9002.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv441_tok-9002.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv442_tok-27163.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv442_tok-27163.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv447_tok-19197.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv447_tok-19197.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv450_tok-13677.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv450_tok-13677.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv451_tok-28707.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv451_tok-28707.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv453_tok-17410.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv453_tok-17410.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv456_tok-29420.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv456_tok-29420.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv458_tok-19400.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv458_tok-19400.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv459_tok-29432.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv459_tok-29432.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv465_tok-29619.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv465_tok-29619.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv469_tok-15267.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv469_tok-15267.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv472_tok-11943.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv472_tok-11943.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv473_tok-14810.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv473_tok-14810.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv479_tok-23674.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv479_tok-23674.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv481_tok-10977.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv481_tok-10977.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv488_tok-13847.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv488_tok-13847.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv496_tok-17126.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv496_tok-17126.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv500_tok-13146.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv500_tok-13146.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv505_tok-17424.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv505_tok-17424.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv512_tok-28882.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv512_tok-28882.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv523_tok-23339.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv523_tok-23339.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv524_tok-20616.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv524_tok-20616.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv528_tok-25667.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv528_tok-25667.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv534_tok-12128.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv534_tok-12128.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv535_tok-19937.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv535_tok-19937.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv544_tok-25047.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv544_tok-25047.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv553_tok-27936.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv553_tok-27936.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv559_tok-17078.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv559_tok-17078.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv561_tok-18471.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv561_tok-18471.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv563_tok-27217.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv563_tok-27217.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv574_tok-23226.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv574_tok-23226.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv581_tok-29376.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv581_tok-29376.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv586_tok-19488.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv586_tok-19488.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv596_tok-27611.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv596_tok-27611.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv598_tok-28906.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv598_tok-28906.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv603_tok-18184.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv603_tok-18184.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv604_tok-21195.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv604_tok-21195.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv605_tok-12048.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv605_tok-12048.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv608_tok-29484.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv608_tok-29484.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv617_tok-24070.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv617_tok-24070.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv630_tok-23300.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv630_tok-23300.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv632_tok-14112.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv632_tok-14112.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv639_tok-16459.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv639_tok-16459.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv651_tok-28796.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv651_tok-28796.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv656_tok-29675.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv656_tok-29675.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv666_tok-16121.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv666_tok-16121.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv668_tok-23578.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv668_tok-23578.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv669_tok-12224.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv669_tok-12224.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv670_tok-9891.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv670_tok-9891.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv672_tok-20564.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv672_tok-20564.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv675_tok-10091.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv675_tok-10091.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv683_tok-11354.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv683_tok-11354.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv684_tok-10190.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv684_tok-10190.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv688_tok-29384.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv688_tok-29384.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv690_tok-26288.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv690_tok-26288.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv695_tok-21695.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv695_tok-21695.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv697_tok-12765.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv697_tok-12765.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv002_tok-12931.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv002_tok-12931.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv017_tok-29801.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv017_tok-29801.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv018_tok-10094.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv018_tok-10094.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv019_tok-11209.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv019_tok-11209.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv022_tok-17069.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv022_tok-17069.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv023_tok-12160.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv023_tok-12160.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv043_tok-24397.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv043_tok-24397.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv044_tok-29505.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv044_tok-29505.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv045_tok-29121.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv045_tok-29121.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv051_tok-21020.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv051_tok-21020.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv057_tok-14094.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv057_tok-14094.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv063_tok-28706.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv063_tok-28706.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv068_tok-12672.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv068_tok-12672.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv075_tok-17788.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv075_tok-17788.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv088_tok-10534.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv088_tok-10534.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv099_tok-15838.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv099_tok-15838.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv102_tok-21103.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv102_tok-21103.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv104_tok-28425.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv104_tok-28425.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv108_tok-12767.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv108_tok-12767.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv109_tok-16113.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv109_tok-16113.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv116_tok-9457.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv116_tok-9457.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv124_tok-29590.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv124_tok-29590.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv127_tok-22921.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv127_tok-22921.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv131_tok-19363.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv131_tok-19363.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv135_tok-18510.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv135_tok-18510.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv142_tok-11890.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv142_tok-11890.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv154_tok-10175.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv154_tok-10175.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv156_tok-12349.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv156_tok-12349.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv157_tok-29786.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv157_tok-29786.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv165_tok-11425.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv165_tok-11425.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv179_tok-10822.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv179_tok-10822.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv188_tok-16638.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv188_tok-16638.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv190_tok-29198.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv190_tok-29198.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv195_tok-13683.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv195_tok-13683.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv200_tok-19912.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv200_tok-19912.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv204_tok-10080.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv204_tok-10080.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv207_tok-10975.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv207_tok-10975.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv211_tok-24353.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv211_tok-24353.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv212_tok-11472.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv212_tok-11472.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv219_tok-22240.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv219_tok-22240.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv232_tok-18168.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv232_tok-18168.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv240_tok-29525.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv240_tok-29525.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv245_tok-19462.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv245_tok-19462.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv247_tok-26084.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv247_tok-26084.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv249_tok-18722.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv249_tok-18722.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv253_tok-19526.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv253_tok-19526.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv255_tok-15449.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv255_tok-15449.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv256_tok-11576.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv256_tok-11576.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv258_tok-25234.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv258_tok-25234.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv270_tok-29235.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv270_tok-29235.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv271_tok-11240.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv271_tok-11240.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv273_tok-10626.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv273_tok-10626.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv274_tok-12014.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv274_tok-12014.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv275_tok-12167.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv275_tok-12167.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv278_tok-17924.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv278_tok-17924.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv280_tok-27724.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv280_tok-27724.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv296_tok-11353.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv296_tok-11353.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv298_tok-16139.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv298_tok-16139.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv313_tok-19364.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv313_tok-19364.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv324_tok-11182.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv324_tok-11182.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv326_tok-28892.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv326_tok-28892.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv348_tok-24201.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv348_tok-24201.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv353_tok-29082.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv353_tok-29082.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv354_tok-13227.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv354_tok-13227.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv355_tok-11500.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv355_tok-11500.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv382_tok-11565.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv382_tok-11565.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv391_tok-29468.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv391_tok-29468.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv395_tok-27468.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv395_tok-27468.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv400_tok-11748.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv400_tok-11748.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv403_tok-19027.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv403_tok-19027.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv404_tok-23115.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv404_tok-23115.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv408_tok-24111.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv408_tok-24111.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv409_tok-11193.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv409_tok-11193.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv410_tok-24246.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv410_tok-24246.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv418_tok-10147.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv418_tok-10147.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv426_tok-12735.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv426_tok-12735.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv433_tok-16006.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv433_tok-16006.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv439_tok-13632.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv439_tok-13632.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv440_tok-24265.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv440_tok-24265.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv442_tok-28944.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv442_tok-28944.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv448_tok-25113.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv448_tok-25113.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv450_tok-18817.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv450_tok-18817.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv454_tok-11053.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv454_tok-11053.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv466_tok-22246.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv466_tok-22246.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv468_tok-11620.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv468_tok-11620.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv471_tok-21022.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv471_tok-21022.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv472_tok-24511.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv472_tok-24511.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv487_tok-15094.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv487_tok-15094.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv489_tok-23236.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv489_tok-23236.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv490_tok-15448.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv490_tok-15448.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv493_tok-10732.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv493_tok-10732.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv494_tok-25127.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv494_tok-25127.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv498_tok-28077.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv498_tok-28077.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv510_tok-29540.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv510_tok-29540.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv512_tok-27457.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv512_tok-27457.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv516_tok-10558.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv516_tok-10558.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv520_tok-13142.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv520_tok-13142.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv547_tok-18643.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv547_tok-18643.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv552_tok-23130.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv552_tok-23130.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv553_tok-13743.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv553_tok-13743.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv560_tok-11131.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv560_tok-11131.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv562_tok-19381.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv562_tok-19381.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv567_tok-29658.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv567_tok-29658.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv581_tok-20785.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv581_tok-20785.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv583_tok-19290.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv583_tok-19290.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv585_tok-29721.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv585_tok-29721.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv588_tok-10492.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv588_tok-10492.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv589_tok-17484.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv589_tok-17484.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv596_tok-29066.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv596_tok-29066.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv598_tok-18159.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv598_tok-18159.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv600_tok-23338.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv600_tok-23338.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv609_tok-27236.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv609_tok-27236.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv618_tok-23497.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv618_tok-23497.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv628_tok-24095.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv628_tok-24095.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv633_tok-28885.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv633_tok-28885.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv634_tok-28807.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv634_tok-28807.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv637_tok-9659.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv637_tok-9659.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv640_tok-26304.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv640_tok-26304.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv649_tok-27594.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv649_tok-27594.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv650_tok-14989.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv650_tok-14989.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv653_tok-10211.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv653_tok-10211.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv658_tok-13091.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv658_tok-13091.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv661_tok-10482.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv661_tok-10482.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv670_tok-24009.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv670_tok-24009.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv690_tok-23617.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv690_tok-23617.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv692_tok-24295.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv692_tok-24295.txt -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv696_tok-10835.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PacktPublishing/Natural-Language-Processing-with-Python-Cookbook/HEAD/datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv696_tok-10835.txt -------------------------------------------------------------------------------- /Chapter02/recipe3.py: -------------------------------------------------------------------------------- 1 | import pdf 2 | 3 | pdfFile = 'sample-one-line.pdf' 4 | pdfFileEncrypted = 'sample-one-line.protected.pdf' 5 | 6 | print('PDF 1: \n',pdf.getTextPDF(pdfFile)) 7 | print('PDF 2: \n',pdf.getTextPDF(pdfFileEncrypted,'tuffy')) -------------------------------------------------------------------------------- /Chapter02/word.py: -------------------------------------------------------------------------------- 1 | import docx 2 | 3 | def getTextWord(wordFileName): 4 | doc = docx.Document(wordFileName) 5 | fullText = [] 6 | for para in doc.paragraphs: 7 | fullText.append(para.text) 8 | return '\n'.join(fullText) -------------------------------------------------------------------------------- /Chapter05/Exploring.py: -------------------------------------------------------------------------------- 1 | import nltk 2 | simpleSentence = "Bangalore is the capital of Karnataka." 3 | wordsInSentence = nltk.word_tokenize(simpleSentence) 4 | print(wordsInSentence) 5 | partsOfSpeechTags = nltk.pos_tag(wordsInSentence) 6 | print(partsOfSpeechTags) 7 | -------------------------------------------------------------------------------- /Chapter02/recipe6.py: -------------------------------------------------------------------------------- 1 | import feedparser 2 | 3 | myFeed = feedparser.parse("http://feeds.mashable.com/Mashable") 4 | print('Feed Title :', myFeed['feed']['title']) 5 | print('Number of posts :', len(myFeed.entries)) 6 | post = myFeed.entries[0] 7 | print('Post Title :',post.title) 8 | content = post.content[0].value 9 | print('Raw content :\n',content) -------------------------------------------------------------------------------- /Chapter06/Chunker.py: -------------------------------------------------------------------------------- 1 | import nltk 2 | 3 | text = "Lalbagh Botanical Gardens is a well known botanical garden in Bengaluru, India." 4 | sentences = nltk.sent_tokenize(text) 5 | for sentence in sentences: 6 | words = nltk.word_tokenize(sentence) 7 | tags = nltk.pos_tag(words) 8 | chunks = nltk.ne_chunk(tags) 9 | print(chunks) 10 | -------------------------------------------------------------------------------- /Chapter07/NER.py: -------------------------------------------------------------------------------- 1 | import nltk 2 | 3 | def sampleNE(): 4 | sent = nltk.corpus.treebank.tagged_sents()[0] 5 | print(nltk.ne_chunk(sent)) 6 | 7 | def sampleNE2(): 8 | sent = nltk.corpus.treebank.tagged_sents()[0] 9 | print(nltk.ne_chunk(sent, binary=True)) 10 | 11 | if __name__ == '__main__': 12 | sampleNE() 13 | sampleNE2() 14 | -------------------------------------------------------------------------------- /Chapter04/recipe7.py: -------------------------------------------------------------------------------- 1 | import re 2 | 3 | def stem(word): 4 | splits = re.findall(r'^(.*?)(ing|ly|ed|ious|ies|ive|es|s|ment)?$', word) 5 | stem = splits[0][0] 6 | return stem 7 | 8 | raw = "Keep your friends close, but your enemies closer." 9 | tokens = re.findall(r'\w+|\S\w*', raw) 10 | print(tokens) 11 | 12 | for t in tokens: 13 | print("'"+stem(t)+"'") -------------------------------------------------------------------------------- /Chapter06/ParsingDG.py: -------------------------------------------------------------------------------- 1 | import nltk 2 | 3 | grammar = nltk.grammar.DependencyGrammar.fromstring(""" 4 | 'savings' -> 'small' 5 | 'yield' -> 'savings' 6 | 'gains' -> 'large' 7 | 'yield' -> 'gains' 8 | """) 9 | 10 | sentence = 'small savings yield large gains' 11 | dp = nltk.parse.ProjectiveDependencyParser(grammar) 12 | for t in sorted(dp.parse(sentence.split())): 13 | print(t) 14 | t.draw() 15 | -------------------------------------------------------------------------------- /Chapter02/pdf.py: -------------------------------------------------------------------------------- 1 | from PyPDF2 import PdfFileReader 2 | 3 | def getTextPDF(pdfFileName, password = ''): 4 | pdf_file = open(pdfFileName, 'rb') 5 | read_pdf = PdfFileReader(pdf_file) 6 | if password != '': 7 | read_pdf.decrypt(password) 8 | text = [] 9 | for i in range(0,read_pdf.getNumPages()): 10 | text.append(read_pdf.getPage(i).extractText()) 11 | return '\n'.join(text) -------------------------------------------------------------------------------- /datasets/tokens/pos/cv365_tok-21785.txt: -------------------------------------------------------------------------------- 1 | all of my film reviews are archived at http : //us . imdb . com/m/reviews_by ? justin + felix this review has been submitted to the shrubbery http : //www . theshrubbery . com any comments about this review ? e-mail me at justinfelix@yahoo . comscreen story by kevin yagher and andrew kevin walker . inspired by the short story the legend of sleepy hollow by washington irving . 2 | -------------------------------------------------------------------------------- /Chapter01/recipe5.py: -------------------------------------------------------------------------------- 1 | from nltk.corpus import wordnet as wn 2 | 3 | chair = 'bat' 4 | 5 | chair_synsets = wn.synsets(chair) 6 | print('Synsets/Senses of Chair :', chair_synsets, '\n\n') 7 | 8 | for synset in chair_synsets: 9 | print(synset, ': ') 10 | print('Definition: ', synset.definition()) 11 | print('Lemmas/Synonymous words: ', synset.lemma_names()) 12 | print('Example: ', synset.examples(), '\n') 13 | -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv365_tok-21785.txt: -------------------------------------------------------------------------------- 1 | all of my film reviews are archived at http : //us . imdb . com/m/reviews_by ? justin + felix this review has been submitted to the shrubbery http : //www . theshrubbery . com any comments about this review ? e-mail me at justinfelix@yahoo . comscreen story by kevin yagher and andrew kevin walker . inspired by the short story the legend of sleepy hollow by washington irving . 2 | -------------------------------------------------------------------------------- /Chapter02/recipe2.py: -------------------------------------------------------------------------------- 1 | str = 'NLTK Dolly Python' 2 | print('Substring ends at:',str[:4]) 3 | 4 | print('Substring starts from:',str[11:] ) 5 | print('Substring :',str[5:10]) 6 | print('Substring fancy:', str[-12:-7]) 7 | 8 | if 'NLTK' in str: 9 | print('found NLTK') 10 | 11 | replaced = str.replace('Dolly', 'Dorothy') 12 | print('Replaced String:', replaced) 13 | 14 | print('Accessing each character:') 15 | for s in replaced: 16 | print(s) -------------------------------------------------------------------------------- /Chapter01/recipe1.py: -------------------------------------------------------------------------------- 1 | from nltk.corpus import reuters 2 | 3 | files = reuters.fileids() 4 | print(files) 5 | 6 | words16097 = reuters.words(['test/16097']) 7 | print(words16097) 8 | 9 | words20 = reuters.words(['test/16097'])[:20] 10 | print(words20) 11 | 12 | 13 | reutersGenres = reuters.categories() 14 | print(reutersGenres) 15 | 16 | 17 | for w in reuters.words(categories=['bop','cocoa']): 18 | print(w+' ',end='') 19 | if(w is '.'): 20 | print() 21 | -------------------------------------------------------------------------------- /datasets/tokens/neg/cv373_tok-25938.txt: -------------------------------------------------------------------------------- 1 | filmcritic . com presents a review from staff member james brundage . you can find the review with full credits at http : //filmcritic . com/misc/emporium . nsf/2a460f93626cd4678625624c007f2b46/c97ebb11df0b98398825694f005571d7 ? opendocument he is duncan macleod of the clan macleod . he's been pimpin' it since he was born in the village of glennfillan in 15somethingsomething , and he continues to pimp it in modern day . he is immortal and he cannot die . 2 | -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv373_tok-25938.txt: -------------------------------------------------------------------------------- 1 | filmcritic . com presents a review from staff member james brundage . you can find the review with full credits at http : //filmcritic . com/misc/emporium . nsf/2a460f93626cd4678625624c007f2b46/c97ebb11df0b98398825694f005571d7 ? opendocument he is duncan macleod of the clan macleod . he's been pimpin' it since he was born in the village of glennfillan in 15somethingsomething , and he continues to pimp it in modern day . he is immortal and he cannot die . 2 | -------------------------------------------------------------------------------- /Chapter02/recipe1.py: -------------------------------------------------------------------------------- 1 | namesList = ['Tuffy','Ali','Nysha','Tim' ] 2 | sentence = 'My dog sleeps on sofa' 3 | 4 | names = ';'.join(namesList) 5 | print(type(names), ':', names) 6 | wordList = sentence.split(' ') 7 | print((type(wordList)), ':', wordList) 8 | 9 | additionExample = 'ganehsa' + 'ganesha' + 'ganesha' 10 | multiplicationExample = 'ganesha' * 2 11 | print('Text Additions :', additionExample) 12 | print('Text Multiplication :', multiplicationExample) 13 | 14 | str = 'Python NLTK' 15 | print(str[1]) 16 | print(str[-3]) -------------------------------------------------------------------------------- /Chapter06/SimpleChunker.py: -------------------------------------------------------------------------------- 1 | import nltk 2 | 3 | text = "Ravi is the CEO of a Company. He is very powerful public speaker also." 4 | 5 | grammar = '\n'.join([ 6 | 'NP: {
*}', 7 | 'NP: {*}', 8 | 'NP: {+}', 9 | ]) 10 | 11 | sentences = nltk.sent_tokenize(text) 12 | 13 | for sentence in sentences: 14 | words = nltk.word_tokenize(sentence) 15 | tags = nltk.pos_tag(words) 16 | chunkparser = nltk.RegexpParser(grammar) 17 | result = chunkparser.parse(tags) 18 | print(result) 19 | -------------------------------------------------------------------------------- /Chapter01/recipe3.py: -------------------------------------------------------------------------------- 1 | import nltk 2 | from nltk.corpus import brown 3 | 4 | print(brown.categories()) 5 | 6 | genres = ['fiction', 'humor', 'romance'] 7 | whwords = ['what', 'which', 'how', 'why', 'when', 'where', 'who'] 8 | 9 | 10 | for i in range(0,len(genres)): 11 | genre = genres[i] 12 | print() 13 | print("Analysing '"+ genre + "' wh words") 14 | genre_text = brown.words(categories = genre) 15 | fdist = nltk.FreqDist(genre_text) 16 | for wh in whwords: 17 | print(wh + ':', fdist[wh], end=' ') 18 | -------------------------------------------------------------------------------- /datasets/tokens/pos/cv132_tok-5618.txt: -------------------------------------------------------------------------------- 1 | quaid stars as a man who has taken up the proffesion of dragonslayer after he feels he is betrayed by a dragon early in the movie . he runs into the last dragon in existence , and there is a genuinely amusing battle between the two which results in a standoff where quaid is in the dragons mouth , but has his sword pointed at the dragons brain . eventually , they decide to call a truce , and they work out a deal . since he is the last dragon , he will pretend to die and quaid will be able to get paid for it . 2 | -------------------------------------------------------------------------------- /Chapter01/recipe7.py: -------------------------------------------------------------------------------- 1 | from nltk.corpus import wordnet as wn 2 | type = 'n' 3 | 4 | synsets = wn.all_synsets(type) 5 | 6 | lemmas = [] 7 | for synset in synsets: 8 | for lemma in synset.lemmas(): 9 | lemmas.append(lemma.name()) 10 | 11 | print(len(lemmas)) 12 | lemmas = set(lemmas) 13 | print('Total distinct lemmas: ', len(lemmas)) 14 | 15 | count = 0 16 | for lemma in lemmas: 17 | count = count + len(wn.synsets(lemma, type)) 18 | 19 | print('Total senses :',count) 20 | print('Average Polysemy of ', type,': ' , count/len(lemmas)) -------------------------------------------------------------------------------- /datasets/tokens/neg/cv452_tok-18656.txt: -------------------------------------------------------------------------------- 1 | these are words that could be used to describe the emotions of john sayles' characters in his latest , limbo . but no , i use them to describe myself after sitting through his latest little exercise in indie egomania . i can forgive many things . but using some hackneyed , whacked-out , screwed-up * non * -ending on a movie is unforgivable . i walked a half-mile in the rain and sat through two hours of typical , plodding sayles melodrama to get cheated by a complete and total copout finale . does sayles think he's roger corman ? 2 | -------------------------------------------------------------------------------- /datasets/tokens/neg/cv592_tok-10894.txt: -------------------------------------------------------------------------------- 1 | michael dequina mrbrown@ucla . edu | michael_jordan@geocities . com | mj23@the18thhole . com mrbrown@michaeljordanfan . com | mj23@michaeljordanfan . com mrbrown23@juno . com | mrbrown@iname . com | mst3k@digicron . com visit mr . brown's movie site at http : //members . tripod . com/~mrbrown/ personal page : http : //members . tripod . com/~mrbrown/home . html michael jordan beyond the court : http : //www . geocities . com/colosseum/field/2302/ a michael jordan fan's heartbreak : http : //members . tripod . com/~mj23/mj . html 2 | -------------------------------------------------------------------------------- /Chapter04/recipe4.py: -------------------------------------------------------------------------------- 1 | import re 2 | 3 | url= "http://www.telegraph.co.uk/formula-1/2017/10/28/mexican-grand-prix-2017-time-does-start-tv-channel-odds-lewis1/2017/05/12/" 4 | date_regex = '/(\d{4})/(\d{1,2})/(\d{1,2})/' 5 | 6 | print("Date found in the URL :", re.findall(date_regex, url)) 7 | 8 | 9 | def is_allowed_specific_char(string): 10 | charRe = re.compile(r'[^a-zA-Z0-9.]') 11 | string = charRe.search(string) 12 | return not bool(string) 13 | 14 | print(is_allowed_specific_char("ABCDEFabcdef123450.")) 15 | print(is_allowed_specific_char("*&%@#!}{")) -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv132_tok-5618.txt: -------------------------------------------------------------------------------- 1 | quaid stars as a man who has taken up the proffesion of dragonslayer after he feels he is betrayed by a dragon early in the movie . he runs into the last dragon in existence , and there is a genuinely amusing battle between the two which results in a standoff where quaid is in the dragons mouth , but has his sword pointed at the dragons brain . eventually , they decide to call a truce , and they work out a deal . since he is the last dragon , he will pretend to die and quaid will be able to get paid for it . 2 | -------------------------------------------------------------------------------- /datasets/tokens/neg/cv557_tok-24760.txt: -------------------------------------------------------------------------------- 1 | filmcritic . com presents two reviews from staff members james brundage and max messier . you can find the reviews with full credits at http : //www . filmcritic . com/misc/emporium . nsf/2a460f93626cd4678625624c007f2b46/f4f3233798557e33882568e800788faa ? opendocument editor's note : rarely have to so divergent reviews for one movie crossed my desk on the same day . to wit , we present a unique experience for filmcritic . com -- something of a " he said , he said " -- two looks at mission : impossible 2 , from two of our most vocal critics . -cn 2 | -------------------------------------------------------------------------------- /Chapter01/recipe4.py: -------------------------------------------------------------------------------- 1 | import nltk 2 | from nltk.corpus import webtext 3 | print(webtext.fileids()) 4 | 5 | fileid = 'singles.txt' 6 | wbt_words = webtext.words(fileid) 7 | fdist = nltk.FreqDist(wbt_words) 8 | 9 | print('Count of the maximum appearing word "',fdist.max(),'" : ', fdist[fdist.max()]) 10 | print('Total Number of distinct tokens in the bag : ', fdist.N()) 11 | print('Following are the most common 10 words in the bag') 12 | print(fdist.most_common(10)) 13 | print('Frequency Distribution on Personal Advertisements') 14 | print(fdist.tabulate()) 15 | fdist.plot(cumulative=True) -------------------------------------------------------------------------------- /Chapter01/recipe6.py: -------------------------------------------------------------------------------- 1 | from nltk.corpus import wordnet as wn 2 | 3 | woman = wn.synset('woman.n.01') 4 | bed = wn.synset('bed.n.01') 5 | 6 | print(woman.hypernyms()) 7 | woman_paths = woman.hypernym_paths() 8 | 9 | for idx, path in enumerate(woman_paths): 10 | print('\n\nHypernym Path :', idx + 1) 11 | for synset in path: 12 | print(synset.name(), ', ', end='') 13 | 14 | 15 | 16 | types_of_beds = bed.hyponyms() 17 | print('\n\nTypes of beds(Hyponyms): ', types_of_beds) 18 | 19 | print(sorted(set(lemma.name() for synset in types_of_beds for lemma in synset.lemmas()))) -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv452_tok-18656.txt: -------------------------------------------------------------------------------- 1 | these are words that could be used to describe the emotions of john sayles' characters in his latest , limbo . but no , i use them to describe myself after sitting through his latest little exercise in indie egomania . i can forgive many things . but using some hackneyed , whacked-out , screwed-up * non * -ending on a movie is unforgivable . i walked a half-mile in the rain and sat through two hours of typical , plodding sayles melodrama to get cheated by a complete and total copout finale . does sayles think he's roger corman ? 2 | -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv592_tok-10894.txt: -------------------------------------------------------------------------------- 1 | michael dequina mrbrown@ucla . edu | michael_jordan@geocities . com | mj23@the18thhole . com mrbrown@michaeljordanfan . com | mj23@michaeljordanfan . com mrbrown23@juno . com | mrbrown@iname . com | mst3k@digicron . com visit mr . brown's movie site at http : //members . tripod . com/~mrbrown/ personal page : http : //members . tripod . com/~mrbrown/home . html michael jordan beyond the court : http : //www . geocities . com/colosseum/field/2302/ a michael jordan fan's heartbreak : http : //members . tripod . com/~mj23/mj . html 2 | -------------------------------------------------------------------------------- /datasets/tokens/pos/cv037_tok-11720.txt: -------------------------------------------------------------------------------- 1 | starring : val kilmer ( bruce wayne/batman ) , jim carrey ( edward nygma/the riddler ) , tommy lee jones ( harvey dent/two-face ) , chris o'donnell ( dick grayson/robin ) , nicole kidman ( dr . chase meridian ) , michael gough ( alfred pennyworth ) , pat hingle ( commissioner gordon ) , drew barrymore ( sugar ) , debi mazar ( spice ) directed by : joel schumacher , written by : lee batchler & janet scott batchler and akiva goldsman , based on characters created by bob kane rated pg-13 by the mpaa for violence , strong language , and a sexual implication or two 2 | -------------------------------------------------------------------------------- /Chapter02/recipe7.py: -------------------------------------------------------------------------------- 1 | from bs4 import BeautifulSoup 2 | 3 | html_doc = open('sample-html.html', 'r').read() 4 | soup = BeautifulSoup(html_doc, 'html.parser') 5 | 6 | print('Full text HTML Stripped:') 7 | print(soup.get_text()) 8 | 9 | print('Accessing the tag :', end=' ') 10 | print(soup.title) 11 | 12 | print('Accessing the text of <H1> tag :', end=' ') 13 | print(soup.h1.string) 14 | 15 | print('Accessing property of <img> tag :', end=' ') 16 | print(soup.img['alt']) 17 | 18 | print('\nAccessing all occurences of the <p> tag :') 19 | for p in soup.find_all('p'): 20 | print(p.string) -------------------------------------------------------------------------------- /datasets/tokens/neg/cv059_tok-8583.txt: -------------------------------------------------------------------------------- 1 | the winner ( live - 1997 ) starring vincent d'onofrio , rebecca demornay , delroy lindo , frank whaley , michael madsen , billy bob thornton screenplay by wendy riss , based on her stage play a darker purpose . produced by ken schwenker directed by alex cox running time : 92 minutes note : some may consider portions of the following text to be spoilers . be forewarned . -------------------------------------------------------------to assess alex cox's film the winner as a loser would be so indolent . it would be derisive . it would be glib . it would be dismissive . 2 | -------------------------------------------------------------------------------- /datasets/tokens/pos/cv206_tok-12590.txt: -------------------------------------------------------------------------------- 1 | starring : matthew broderick ( dr . niko " nick " tatopoulos ) , maria pitillo ( audrey timmonds ) , jean reno ( philippe roache ) , hank azaria ( victor " animal " palotti ) , harry shearer ( charles caiman ) , kevin dunn ( colonel hicks ) , arabella field ( lucy palotti ) , doug savant ( sergeant o'neal ) , vicki lewis ( dr . elsie chapman ) , michael lerner ( mayor ebert ) , lorry goldman ( gene ) , and godzilla as himself directed by : roland emmerich , written by : dean devlin & roland emmerichrated pg-13 for violence , mild profanity , and mild sexual innuendo 2 | -------------------------------------------------------------------------------- /Chapter03/recipe2.py: -------------------------------------------------------------------------------- 1 | from nltk import PorterStemmer, LancasterStemmer, word_tokenize 2 | 3 | raw = "My name is Maximus Decimus Meridius, commander of the Armies of the North, General of the Felix Legions and loyal servant to the true emperor, Marcus Aurelius. Father to a murdered son, husband to a murdered wife. And I will have my vengeance, in this life or the next." 4 | tokens = word_tokenize(raw) 5 | 6 | porter = PorterStemmer() 7 | pStems = [porter.stem(t) for t in tokens] 8 | print(pStems) 9 | 10 | lancaster = LancasterStemmer() 11 | lStems = [lancaster.stem(t) for t in tokens] 12 | print(lStems) -------------------------------------------------------------------------------- /datasets/tokens/pos/cv627_tok-14423.txt: -------------------------------------------------------------------------------- 1 | 1939 , g , 222 minutes [3 hours , 42 minutes] starring : viven leigh ( katherine scarlett o'hara-hamilton-kennedy-butler ) , clark gable ( captain rhett butler ) , olivia de havilland ( melanie wilkes ) , leslie howard ( ashley wilkes ) ; written by sidney howard ; produced by david o . selznik ; directed by victor fleming ; based on the novel by margaret mitchell . seen july 8 , 1998 at the crossgates cinema 18 , ( albany , ny ) , theater #7 , at 8 : 15 p . m . with my mom using hoyts cinema cash . [theater rating : * * * 1/2 : very good sound , picture , and seats] 2 | -------------------------------------------------------------------------------- /Chapter03/recipe3.py: -------------------------------------------------------------------------------- 1 | from nltk import word_tokenize, PorterStemmer, WordNetLemmatizer 2 | 3 | raw = "My name is Maximus Decimus Meridius, commander of the armies of the north, General of the Felix legions and loyal servant to the true emperor, Marcus Aurelius. Father to a murdered son, husband to a murdered wife. And I will have my vengeance, in this life or the next." 4 | tokens = word_tokenize(raw) 5 | 6 | porter = PorterStemmer() 7 | stems = [porter.stem(t) for t in tokens] 8 | print(stems) 9 | 10 | lemmatizer = WordNetLemmatizer() 11 | lemmas = [lemmatizer.lemmatize(t) for t in tokens] 12 | print(lemmas) -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv557_tok-24760.txt: -------------------------------------------------------------------------------- 1 | filmcritic . com presents two reviews from staff members james brundage and max messier . you can find the reviews with full credits at http : //www . filmcritic . com/misc/emporium . nsf/2a460f93626cd4678625624c007f2b46/f4f3233798557e33882568e800788faa ? opendocument editor's note : rarely have to so divergent reviews for one movie crossed my desk on the same day . to wit , we present a unique experience for filmcritic . com -- something of a " he said , he said " -- two looks at mission : impossible 2 , from two of our most vocal critics . -cn 2 | -------------------------------------------------------------------------------- /datasets/tokens/neg/cv239_tok-24885.txt: -------------------------------------------------------------------------------- 1 | the following review contains some harsh language . . . but what did you expect when you clicked on this title ? * * * cast : kristen holly smith , danica sheridan , alex boling , michael dotson , sonya hensley , janet krajeski , sabrina lu , dionysius burbano , calvin grant , jeff b . harmon written and directed by : jeff b . harmon running time : 97 minutes " the thought of losing you makes me all vomity inside . " --- blatz balinski ( danica sheridan ) laments the fact that her lesbian lover , april ( kristen holly smith ) , has just received a telegram from her ex-fiance . 2 | -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv037_tok-11720.txt: -------------------------------------------------------------------------------- 1 | starring : val kilmer ( bruce wayne/batman ) , jim carrey ( edward nygma/the riddler ) , tommy lee jones ( harvey dent/two-face ) , chris o'donnell ( dick grayson/robin ) , nicole kidman ( dr . chase meridian ) , michael gough ( alfred pennyworth ) , pat hingle ( commissioner gordon ) , drew barrymore ( sugar ) , debi mazar ( spice ) directed by : joel schumacher , written by : lee batchler & janet scott batchler and akiva goldsman , based on characters created by bob kane rated pg-13 by the mpaa for violence , strong language , and a sexual implication or two 2 | -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv059_tok-8583.txt: -------------------------------------------------------------------------------- 1 | the winner ( live - 1997 ) starring vincent d'onofrio , rebecca demornay , delroy lindo , frank whaley , michael madsen , billy bob thornton screenplay by wendy riss , based on her stage play a darker purpose . produced by ken schwenker directed by alex cox running time : 92 minutes note : some may consider portions of the following text to be spoilers . be forewarned . -------------------------------------------------------------to assess alex cox's film the winner as a loser would be so indolent . it would be derisive . it would be glib . it would be dismissive . 2 | -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv206_tok-12590.txt: -------------------------------------------------------------------------------- 1 | starring : matthew broderick ( dr . niko " nick " tatopoulos ) , maria pitillo ( audrey timmonds ) , jean reno ( philippe roache ) , hank azaria ( victor " animal " palotti ) , harry shearer ( charles caiman ) , kevin dunn ( colonel hicks ) , arabella field ( lucy palotti ) , doug savant ( sergeant o'neal ) , vicki lewis ( dr . elsie chapman ) , michael lerner ( mayor ebert ) , lorry goldman ( gene ) , and godzilla as himself directed by : roland emmerich , written by : dean devlin & roland emmerichrated pg-13 for violence , mild profanity , and mild sexual innuendo 2 | -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/pos/cv627_tok-14423.txt: -------------------------------------------------------------------------------- 1 | 1939 , g , 222 minutes [3 hours , 42 minutes] starring : viven leigh ( katherine scarlett o'hara-hamilton-kennedy-butler ) , clark gable ( captain rhett butler ) , olivia de havilland ( melanie wilkes ) , leslie howard ( ashley wilkes ) ; written by sidney howard ; produced by david o . selznik ; directed by victor fleming ; based on the novel by margaret mitchell . seen july 8 , 1998 at the crossgates cinema 18 , ( albany , ny ) , theater #7 , at 8 : 15 p . m . with my mom using hoyts cinema cash . [theater rating : * * * 1/2 : very good sound , picture , and seats] 2 | -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv239_tok-24885.txt: -------------------------------------------------------------------------------- 1 | the following review contains some harsh language . . . but what did you expect when you clicked on this title ? * * * cast : kristen holly smith , danica sheridan , alex boling , michael dotson , sonya hensley , janet krajeski , sabrina lu , dionysius burbano , calvin grant , jeff b . harmon written and directed by : jeff b . harmon running time : 97 minutes " the thought of losing you makes me all vomity inside . " --- blatz balinski ( danica sheridan ) laments the fact that her lesbian lover , april ( kristen holly smith ) , has just received a telegram from her ex-fiance . 2 | -------------------------------------------------------------------------------- /Chapter03/recipe5.py: -------------------------------------------------------------------------------- 1 | from nltk.metrics.distance import edit_distance 2 | 3 | def my_edit_distance(str1, str2): 4 | m= len(str1) + 1 5 | n= len(str2) + 1 6 | 7 | table = {} 8 | for i in range(m): table[i,0]=i 9 | for j in range(n): table[0,j]=j 10 | 11 | for i in range(1, m): 12 | for j in range(1, n): 13 | cost = 0 if str1[i - 1] == str2[j - 1] else 1 14 | table[i,j] = min(table[i, j-1]+1, table[i-1, j]+1, table[i-1, j-1]+cost) 15 | 16 | return table[i,j] 17 | 18 | print("Our Algorithm :",my_edit_distance("hand", "and")) 19 | print("NLTK Algorithm :",edit_distance("hand", "and")) -------------------------------------------------------------------------------- /Chapter04/recipe1.py: -------------------------------------------------------------------------------- 1 | import re 2 | def text_match(text, patterns): 3 | if re.search(patterns, text): 4 | return 'Found a match!' 5 | else: 6 | return('Not matched!') 7 | 8 | print(text_match("ac", "ab?")) 9 | print(text_match("abc", "ab?")) 10 | print(text_match("abbc", "ab?")) 11 | 12 | print(text_match("ac", "ab*")) 13 | print(text_match("abc", "ab*")) 14 | print(text_match("abbc", "ab*")) 15 | 16 | print(text_match("ac", "ab+")) 17 | print(text_match("abc", "ab+")) 18 | print(text_match("abbc", "ab+")) 19 | 20 | print(text_match("abbc", "ab{2}")) 21 | print(text_match("aabbbbbbc", "ab{3,5}?")) -------------------------------------------------------------------------------- /Chapter03/recipe4.py: -------------------------------------------------------------------------------- 1 | import nltk 2 | from nltk.corpus import gutenberg 3 | print(gutenberg.fileids()) 4 | 5 | gb_words = gutenberg.words('bible-kjv.txt') 6 | words_filtered = [e.lower() for e in gb_words if len(e) >= 3] 7 | stopwords = nltk.corpus.stopwords.words('english') 8 | words = [w for w in words_filtered if w.lower() not in stopwords] 9 | 10 | fdist = nltk.FreqDist(words) 11 | fdist2 = nltk.FreqDist(gb_words) 12 | 13 | 14 | print('Following are the most common 10 words in the bag') 15 | print(fdist2.most_common(10)) 16 | print('Following are the most common 10 words in the bag minus the stopwords') 17 | print(fdist.most_common(10)) 18 | fdist.plot() -------------------------------------------------------------------------------- /Chapter05/RecursiveCFG.py: -------------------------------------------------------------------------------- 1 | import nltk 2 | import string 3 | from nltk.parse.generate import generate 4 | 5 | productions = [ 6 | "ROOT -> WORD", 7 | "WORD -> ' '" 8 | ] 9 | 10 | alphabets = list(string.digits) 11 | 12 | for alphabet in alphabets: 13 | productions.append("WORD -> '{w}' WORD '{w}'".format(w=alphabet)) 14 | 15 | grammarString = "\n".join(productions) 16 | 17 | grammar = nltk.CFG.fromstring(grammarString) 18 | 19 | print(grammar) 20 | 21 | for sentence in generate(grammar, n=5, depth=5): 22 | palindrome = "".join(sentence).replace(" ", "") 23 | print("Palindrome : {}, Size : {}".format(palindrome, len(palindrome))) 24 | -------------------------------------------------------------------------------- /Chapter04/recipe3.py: -------------------------------------------------------------------------------- 1 | import re 2 | 3 | #search for literal strings in sentence 4 | patterns = [ 'Tuffy', 'Pie', 'Loki' ] 5 | text = 'Tuffy eats pie, Loki eats peas!' 6 | for pattern in patterns: 7 | print('Searching for "%s" in "%s" ->' % (pattern, text),) 8 | if re.search(pattern, text): 9 | print('Found!') 10 | else: 11 | print('Not Found!') 12 | 13 | #search a substring and find it's location too 14 | 15 | text = 'Diwali is a festival of lights, Holi is a festival of colors!' 16 | pattern = 'festival' 17 | for match in re.finditer(pattern, text): 18 | s = match.start() 19 | e = match.end() 20 | print('Found "%s" at %d:%d' % (text[s:e], s, e)) -------------------------------------------------------------------------------- /datasets/tokens/neg/cv216_tok-27832.txt: -------------------------------------------------------------------------------- 1 | annie wilson ( cate blanchett ) , a widow who struggles to raise her children in a small town in georgia is asked for help by local authorities in solving the case of a missing woman . annie is something of a psychic , she has involuntary bouts with the supernatural where she can see the past and the future and physically feel the actions happenning to her she envisions . her " gift " leads to the arrest of a nasty wife beater who may or may not have killed the pretty rich girl found in the swamp on his property . in an ultra conservative backwoods town will her testimony based on her psychic visions hold up in court ? do they even have the right man ? 2 | -------------------------------------------------------------------------------- /Chapter04/recipe2.py: -------------------------------------------------------------------------------- 1 | import re 2 | 3 | def text_match(text, patterns): 4 | if re.search(patterns, text): 5 | return 'Found a match!' 6 | else: 7 | return('Not matched!') 8 | 9 | print("Pattern to test start and end with") 10 | print(text_match("abbc", "^a.*c$")) 11 | 12 | print("Begin with a word") 13 | print(text_match("Tuffy eats pie, Loki eats peas!", "^\w+")) 14 | 15 | print("End with a word and optional punctuation") 16 | print(text_match("Tuffy eats pie, Loki eats peas!", "\w+\S*?$")) 17 | 18 | print("Finding a word which contains character, not start or end of the word") 19 | print(text_match("Tuffy eats pie, Loki eats peas!", "\Bu\B")) -------------------------------------------------------------------------------- /datasets/mix20_rand700_tokens_cleaned/tokens/neg/cv216_tok-27832.txt: -------------------------------------------------------------------------------- 1 | annie wilson ( cate blanchett ) , a widow who struggles to raise her children in a small town in georgia is asked for help by local authorities in solving the case of a missing woman . annie is something of a psychic , she has involuntary bouts with the supernatural where she can see the past and the future and physically feel the actions happenning to her she envisions . her " gift " leads to the arrest of a nasty wife beater who may or may not have killed the pretty rich girl found in the swamp on his property . in an ultra conservative backwoods town will her testimony based on her psychic visions hold up in court ? do they even have the right man ? 2 | --------------------------------------------------------------------------------