├── Cleaning.ipynb
├── Drawing-Conclusions-pynb.txt
├── Histogram-Practice.ipynb
├── Pandas_Functions_Formulae.xlsx
├── README.md
├── appending.ipynb
├── appending_rename.ipynb
├── assessing.ipynb
├── assessing_case2.ipynb
├── assessing_quiz.html
├── assessing_quiz.ipynb
├── cleaning_column_labels.ipynb
├── cleaning_practice.ipynb
├── conclusions-quiz-solutions.ipynb.txt
├── conclusions_groupby.ipynb
├── conclusions_query.ipynb
├── conclusions_quiz.ipynb
├── drawing_conclusions_Fuel.ipynb
├── eda_visuals.ipynb
├── eda_visuals_practise_functions.ipynb
├── exploring_visuals.ipynb
├── fix_datatypes_air_pollution.ipynb
├── fix_datatypes_cyl.ipynb
├── matplotlib_example.ipynb
├── plots-pandas.ipynb
├── plotting_type_quality.ipynb
├── query_filter.ipynb
├── reading_csv.ipynb
├── visuals_quiz.ipynb
├── wine_visualizations.ipynb
├── winequality-red.csv
├── winequality-white.csv
└── winequality_edited.csv


/Cleaning.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "metadata": {
  7 |     "collapsed": true
  8 |    },
  9 |    "outputs": [],
 10 |    "source": [
 11 |     "#import packages\n",
 12 |     "import pandas as pd\n",
 13 |     "\n",
 14 |     "#read csv document\n",
 15 |     "df = pd.read_csv('ChicagoResults.csv')"
 16 |    ]
 17 |   },
 18 |   {
 19 |    "cell_type": "code",
 20 |    "execution_count": 2,
 21 |    "metadata": {},
 22 |    "outputs": [
 23 |     {
 24 |      "name": "stdout",
 25 |      "output_type": "stream",
 26 |      "text": [
 27 |       "<class 'pandas.core.frame.DataFrame'>\n",
 28 |       "RangeIndex: 271 entries, 0 to 270\n",
 29 |       "Data columns (total 7 columns):\n",
 30 |       "year          271 non-null int64\n",
 31 |       "city          271 non-null object\n",
 32 |       "country       271 non-null object\n",
 33 |       "avg_temp      271 non-null float64\n",
 34 |       "sevenDayMA    265 non-null float64\n",
 35 |       "FiveYearMA    267 non-null float64\n",
 36 |       "TenYearMA     262 non-null float64\n",
 37 |       "dtypes: float64(4), int64(1), object(2)\n",
 38 |       "memory usage: 14.9+ KB\n"
 39 |      ]
 40 |     }
 41 |    ],
 42 |    "source": [
 43 |     "df.info()"
 44 |    ]
 45 |   },
 46 |   {
 47 |    "cell_type": "code",
 48 |    "execution_count": 4,
 49 |    "metadata": {},
 50 |    "outputs": [],
 51 |    "source": [
 52 |     "mean_FiveYearMA = df['FiveYearMA'].mean()"
 53 |    ]
 54 |   },
 55 |   {
 56 |    "cell_type": "code",
 57 |    "execution_count": 5,
 58 |    "metadata": {},
 59 |    "outputs": [
 60 |     {
 61 |      "data": {
 62 |       "text/plain": [
 63 |        "0       9.893401\n",
 64 |        "1       9.893401\n",
 65 |        "2       9.893401\n",
 66 |        "3       9.893401\n",
 67 |        "4       3.794000\n",
 68 |        "5       2.706000\n",
 69 |        "6       0.360000\n",
 70 |        "7       2.098000\n",
 71 |        "8       4.336000\n",
 72 |        "9       5.236000\n",
 73 |        "10      7.244000\n",
 74 |        "11      9.372000\n",
 75 |        "12      8.756000\n",
 76 |        "13      8.748000\n",
 77 |        "14      9.748000\n",
 78 |        "15      9.462000\n",
 79 |        "16      9.252000\n",
 80 |        "17      9.380000\n",
 81 |        "18      9.230000\n",
 82 |        "19      9.294000\n",
 83 |        "20      9.116000\n",
 84 |        "21      9.324000\n",
 85 |        "22      9.670000\n",
 86 |        "23      9.688000\n",
 87 |        "24      9.606000\n",
 88 |        "25      9.852000\n",
 89 |        "26      9.684000\n",
 90 |        "27      9.660000\n",
 91 |        "28      9.650000\n",
 92 |        "29      9.822000\n",
 93 |        "         ...    \n",
 94 |        "241    10.436000\n",
 95 |        "242    10.448000\n",
 96 |        "243    10.504000\n",
 97 |        "244    10.914000\n",
 98 |        "245    10.898000\n",
 99 |        "246    10.726000\n",
100 |        "247    11.004000\n",
101 |        "248    11.156000\n",
102 |        "249    10.796000\n",
103 |        "250    10.660000\n",
104 |        "251    10.812000\n",
105 |        "252    10.626000\n",
106 |        "253    10.222000\n",
107 |        "254    10.202000\n",
108 |        "255    10.728000\n",
109 |        "256    10.960000\n",
110 |        "257    11.064000\n",
111 |        "258    11.492000\n",
112 |        "259    11.770000\n",
113 |        "260    11.304000\n",
114 |        "261    11.148000\n",
115 |        "262    11.246000\n",
116 |        "263    11.280000\n",
117 |        "264    11.264000\n",
118 |        "265    11.216000\n",
119 |        "266    11.088000\n",
120 |        "267    11.136000\n",
121 |        "268    11.004000\n",
122 |        "269    11.278000\n",
123 |        "270    11.548000\n",
124 |        "Name: FiveYearMA, Length: 271, dtype: float64"
125 |       ]
126 |      },
127 |      "execution_count": 5,
128 |      "metadata": {},
129 |      "output_type": "execute_result"
130 |     }
131 |    ],
132 |    "source": [
133 |     "df['FiveYearMA'].fillna(mean_FiveYearMA)"
134 |    ]
135 |   },
136 |   {
137 |    "cell_type": "code",
138 |    "execution_count": 7,
139 |    "metadata": {},
140 |    "outputs": [
141 |     {
142 |      "data": {
143 |       "text/html": [
144 |        "<div>\n",
145 |        "<style>\n",
146 |        "    .dataframe thead tr:only-child th {\n",
147 |        "        text-align: right;\n",
148 |        "    }\n",
149 |        "\n",
150 |        "    .dataframe thead th {\n",
151 |        "        text-align: left;\n",
152 |        "    }\n",
153 |        "\n",
154 |        "    .dataframe tbody tr th {\n",
155 |        "        vertical-align: top;\n",
156 |        "    }\n",
157 |        "</style>\n",
158 |        "<table border=\"1\" class=\"dataframe\">\n",
159 |        "  <thead>\n",
160 |        "    <tr style=\"text-align: right;\">\n",
161 |        "      <th></th>\n",
162 |        "      <th>year</th>\n",
163 |        "      <th>city</th>\n",
164 |        "      <th>country</th>\n",
165 |        "      <th>avg_temp</th>\n",
166 |        "      <th>sevenDayMA</th>\n",
167 |        "      <th>FiveYearMA</th>\n",
168 |        "      <th>TenYearMA</th>\n",
169 |        "    </tr>\n",
170 |        "  </thead>\n",
171 |        "  <tbody>\n",
172 |        "    <tr>\n",
173 |        "      <th>0</th>\n",
174 |        "      <td>1743</td>\n",
175 |        "      <td>Chicago</td>\n",
176 |        "      <td>United States</td>\n",
177 |        "      <td>5.44</td>\n",
178 |        "      <td>NaN</td>\n",
179 |        "      <td>NaN</td>\n",
180 |        "      <td>NaN</td>\n",
181 |        "    </tr>\n",
182 |        "    <tr>\n",
183 |        "      <th>1</th>\n",
184 |        "      <td>1744</td>\n",
185 |        "      <td>Chicago</td>\n",
186 |        "      <td>United States</td>\n",
187 |        "      <td>11.73</td>\n",
188 |        "      <td>NaN</td>\n",
189 |        "      <td>NaN</td>\n",
190 |        "      <td>NaN</td>\n",
191 |        "    </tr>\n",
192 |        "    <tr>\n",
193 |        "      <th>2</th>\n",
194 |        "      <td>1745</td>\n",
195 |        "      <td>Chicago</td>\n",
196 |        "      <td>United States</td>\n",
197 |        "      <td>1.80</td>\n",
198 |        "      <td>NaN</td>\n",
199 |        "      <td>NaN</td>\n",
200 |        "      <td>NaN</td>\n",
201 |        "    </tr>\n",
202 |        "    <tr>\n",
203 |        "      <th>3</th>\n",
204 |        "      <td>1746</td>\n",
205 |        "      <td>Chicago</td>\n",
206 |        "      <td>United States</td>\n",
207 |        "      <td>0.00</td>\n",
208 |        "      <td>NaN</td>\n",
209 |        "      <td>NaN</td>\n",
210 |        "      <td>NaN</td>\n",
211 |        "    </tr>\n",
212 |        "    <tr>\n",
213 |        "      <th>4</th>\n",
214 |        "      <td>1747</td>\n",
215 |        "      <td>Chicago</td>\n",
216 |        "      <td>United States</td>\n",
217 |        "      <td>0.00</td>\n",
218 |        "      <td>NaN</td>\n",
219 |        "      <td>3.794</td>\n",
220 |        "      <td>NaN</td>\n",
221 |        "    </tr>\n",
222 |        "    <tr>\n",
223 |        "      <th>5</th>\n",
224 |        "      <td>1748</td>\n",
225 |        "      <td>Chicago</td>\n",
226 |        "      <td>United States</td>\n",
227 |        "      <td>0.00</td>\n",
228 |        "      <td>NaN</td>\n",
229 |        "      <td>2.706</td>\n",
230 |        "      <td>NaN</td>\n",
231 |        "    </tr>\n",
232 |        "    <tr>\n",
233 |        "      <th>6</th>\n",
234 |        "      <td>1749</td>\n",
235 |        "      <td>Chicago</td>\n",
236 |        "      <td>United States</td>\n",
237 |        "      <td>0.00</td>\n",
238 |        "      <td>2.710000</td>\n",
239 |        "      <td>0.360</td>\n",
240 |        "      <td>NaN</td>\n",
241 |        "    </tr>\n",
242 |        "    <tr>\n",
243 |        "      <th>7</th>\n",
244 |        "      <td>1750</td>\n",
245 |        "      <td>Chicago</td>\n",
246 |        "      <td>United States</td>\n",
247 |        "      <td>10.49</td>\n",
248 |        "      <td>3.431429</td>\n",
249 |        "      <td>2.098</td>\n",
250 |        "      <td>NaN</td>\n",
251 |        "    </tr>\n",
252 |        "    <tr>\n",
253 |        "      <th>8</th>\n",
254 |        "      <td>1751</td>\n",
255 |        "      <td>Chicago</td>\n",
256 |        "      <td>United States</td>\n",
257 |        "      <td>11.19</td>\n",
258 |        "      <td>3.354286</td>\n",
259 |        "      <td>4.336</td>\n",
260 |        "      <td>NaN</td>\n",
261 |        "    </tr>\n",
262 |        "    <tr>\n",
263 |        "      <th>9</th>\n",
264 |        "      <td>1752</td>\n",
265 |        "      <td>Chicago</td>\n",
266 |        "      <td>United States</td>\n",
267 |        "      <td>4.50</td>\n",
268 |        "      <td>3.740000</td>\n",
269 |        "      <td>5.236</td>\n",
270 |        "      <td>4.515</td>\n",
271 |        "    </tr>\n",
272 |        "    <tr>\n",
273 |        "      <th>10</th>\n",
274 |        "      <td>1753</td>\n",
275 |        "      <td>Chicago</td>\n",
276 |        "      <td>United States</td>\n",
277 |        "      <td>10.04</td>\n",
278 |        "      <td>5.174286</td>\n",
279 |        "      <td>7.244</td>\n",
280 |        "      <td>4.975</td>\n",
281 |        "    </tr>\n",
282 |        "  </tbody>\n",
283 |        "</table>\n",
284 |        "</div>"
285 |       ],
286 |       "text/plain": [
287 |        "    year     city        country  avg_temp  sevenDayMA  FiveYearMA  TenYearMA\n",
288 |        "0   1743  Chicago  United States      5.44         NaN         NaN        NaN\n",
289 |        "1   1744  Chicago  United States     11.73         NaN         NaN        NaN\n",
290 |        "2   1745  Chicago  United States      1.80         NaN         NaN        NaN\n",
291 |        "3   1746  Chicago  United States      0.00         NaN         NaN        NaN\n",
292 |        "4   1747  Chicago  United States      0.00         NaN       3.794        NaN\n",
293 |        "5   1748  Chicago  United States      0.00         NaN       2.706        NaN\n",
294 |        "6   1749  Chicago  United States      0.00    2.710000       0.360        NaN\n",
295 |        "7   1750  Chicago  United States     10.49    3.431429       2.098        NaN\n",
296 |        "8   1751  Chicago  United States     11.19    3.354286       4.336        NaN\n",
297 |        "9   1752  Chicago  United States      4.50    3.740000       5.236      4.515\n",
298 |        "10  1753  Chicago  United States     10.04    5.174286       7.244      4.975"
299 |       ]
300 |      },
301 |      "execution_count": 7,
302 |      "metadata": {},
303 |      "output_type": "execute_result"
304 |     }
305 |    ],
306 |    "source": [
307 |     "df.head(11)"
308 |    ]
309 |   },
310 |   {
311 |    "cell_type": "code",
312 |    "execution_count": 8,
313 |    "metadata": {
314 |     "collapsed": true
315 |    },
316 |    "outputs": [],
317 |    "source": [
318 |     "df['FiveYearMA'] = df['FiveYearMA'].fillna(mean_FiveYearMA)"
319 |    ]
320 |   },
321 |   {
322 |    "cell_type": "code",
323 |    "execution_count": 9,
324 |    "metadata": {
325 |     "scrolled": true
326 |    },
327 |    "outputs": [
328 |     {
329 |      "data": {
330 |       "text/html": [
331 |        "<div>\n",
332 |        "<style>\n",
333 |        "    .dataframe thead tr:only-child th {\n",
334 |        "        text-align: right;\n",
335 |        "    }\n",
336 |        "\n",
337 |        "    .dataframe thead th {\n",
338 |        "        text-align: left;\n",
339 |        "    }\n",
340 |        "\n",
341 |        "    .dataframe tbody tr th {\n",
342 |        "        vertical-align: top;\n",
343 |        "    }\n",
344 |        "</style>\n",
345 |        "<table border=\"1\" class=\"dataframe\">\n",
346 |        "  <thead>\n",
347 |        "    <tr style=\"text-align: right;\">\n",
348 |        "      <th></th>\n",
349 |        "      <th>year</th>\n",
350 |        "      <th>city</th>\n",
351 |        "      <th>country</th>\n",
352 |        "      <th>avg_temp</th>\n",
353 |        "      <th>sevenDayMA</th>\n",
354 |        "      <th>FiveYearMA</th>\n",
355 |        "      <th>TenYearMA</th>\n",
356 |        "    </tr>\n",
357 |        "  </thead>\n",
358 |        "  <tbody>\n",
359 |        "    <tr>\n",
360 |        "      <th>0</th>\n",
361 |        "      <td>1743</td>\n",
362 |        "      <td>Chicago</td>\n",
363 |        "      <td>United States</td>\n",
364 |        "      <td>5.44</td>\n",
365 |        "      <td>NaN</td>\n",
366 |        "      <td>9.893401</td>\n",
367 |        "      <td>NaN</td>\n",
368 |        "    </tr>\n",
369 |        "    <tr>\n",
370 |        "      <th>1</th>\n",
371 |        "      <td>1744</td>\n",
372 |        "      <td>Chicago</td>\n",
373 |        "      <td>United States</td>\n",
374 |        "      <td>11.73</td>\n",
375 |        "      <td>NaN</td>\n",
376 |        "      <td>9.893401</td>\n",
377 |        "      <td>NaN</td>\n",
378 |        "    </tr>\n",
379 |        "    <tr>\n",
380 |        "      <th>2</th>\n",
381 |        "      <td>1745</td>\n",
382 |        "      <td>Chicago</td>\n",
383 |        "      <td>United States</td>\n",
384 |        "      <td>1.80</td>\n",
385 |        "      <td>NaN</td>\n",
386 |        "      <td>9.893401</td>\n",
387 |        "      <td>NaN</td>\n",
388 |        "    </tr>\n",
389 |        "    <tr>\n",
390 |        "      <th>3</th>\n",
391 |        "      <td>1746</td>\n",
392 |        "      <td>Chicago</td>\n",
393 |        "      <td>United States</td>\n",
394 |        "      <td>0.00</td>\n",
395 |        "      <td>NaN</td>\n",
396 |        "      <td>9.893401</td>\n",
397 |        "      <td>NaN</td>\n",
398 |        "    </tr>\n",
399 |        "    <tr>\n",
400 |        "      <th>4</th>\n",
401 |        "      <td>1747</td>\n",
402 |        "      <td>Chicago</td>\n",
403 |        "      <td>United States</td>\n",
404 |        "      <td>0.00</td>\n",
405 |        "      <td>NaN</td>\n",
406 |        "      <td>3.794000</td>\n",
407 |        "      <td>NaN</td>\n",
408 |        "    </tr>\n",
409 |        "    <tr>\n",
410 |        "      <th>5</th>\n",
411 |        "      <td>1748</td>\n",
412 |        "      <td>Chicago</td>\n",
413 |        "      <td>United States</td>\n",
414 |        "      <td>0.00</td>\n",
415 |        "      <td>NaN</td>\n",
416 |        "      <td>2.706000</td>\n",
417 |        "      <td>NaN</td>\n",
418 |        "    </tr>\n",
419 |        "    <tr>\n",
420 |        "      <th>6</th>\n",
421 |        "      <td>1749</td>\n",
422 |        "      <td>Chicago</td>\n",
423 |        "      <td>United States</td>\n",
424 |        "      <td>0.00</td>\n",
425 |        "      <td>2.710000</td>\n",
426 |        "      <td>0.360000</td>\n",
427 |        "      <td>NaN</td>\n",
428 |        "    </tr>\n",
429 |        "    <tr>\n",
430 |        "      <th>7</th>\n",
431 |        "      <td>1750</td>\n",
432 |        "      <td>Chicago</td>\n",
433 |        "      <td>United States</td>\n",
434 |        "      <td>10.49</td>\n",
435 |        "      <td>3.431429</td>\n",
436 |        "      <td>2.098000</td>\n",
437 |        "      <td>NaN</td>\n",
438 |        "    </tr>\n",
439 |        "    <tr>\n",
440 |        "      <th>8</th>\n",
441 |        "      <td>1751</td>\n",
442 |        "      <td>Chicago</td>\n",
443 |        "      <td>United States</td>\n",
444 |        "      <td>11.19</td>\n",
445 |        "      <td>3.354286</td>\n",
446 |        "      <td>4.336000</td>\n",
447 |        "      <td>NaN</td>\n",
448 |        "    </tr>\n",
449 |        "    <tr>\n",
450 |        "      <th>9</th>\n",
451 |        "      <td>1752</td>\n",
452 |        "      <td>Chicago</td>\n",
453 |        "      <td>United States</td>\n",
454 |        "      <td>4.50</td>\n",
455 |        "      <td>3.740000</td>\n",
456 |        "      <td>5.236000</td>\n",
457 |        "      <td>4.515</td>\n",
458 |        "    </tr>\n",
459 |        "  </tbody>\n",
460 |        "</table>\n",
461 |        "</div>"
462 |       ],
463 |       "text/plain": [
464 |        "   year     city        country  avg_temp  sevenDayMA  FiveYearMA  TenYearMA\n",
465 |        "0  1743  Chicago  United States      5.44         NaN    9.893401        NaN\n",
466 |        "1  1744  Chicago  United States     11.73         NaN    9.893401        NaN\n",
467 |        "2  1745  Chicago  United States      1.80         NaN    9.893401        NaN\n",
468 |        "3  1746  Chicago  United States      0.00         NaN    9.893401        NaN\n",
469 |        "4  1747  Chicago  United States      0.00         NaN    3.794000        NaN\n",
470 |        "5  1748  Chicago  United States      0.00         NaN    2.706000        NaN\n",
471 |        "6  1749  Chicago  United States      0.00    2.710000    0.360000        NaN\n",
472 |        "7  1750  Chicago  United States     10.49    3.431429    2.098000        NaN\n",
473 |        "8  1751  Chicago  United States     11.19    3.354286    4.336000        NaN\n",
474 |        "9  1752  Chicago  United States      4.50    3.740000    5.236000      4.515"
475 |       ]
476 |      },
477 |      "execution_count": 9,
478 |      "metadata": {},
479 |      "output_type": "execute_result"
480 |     }
481 |    ],
482 |    "source": [
483 |     "df.head(10)"
484 |    ]
485 |   },
486 |   {
487 |    "cell_type": "code",
488 |    "execution_count": 11,
489 |    "metadata": {},
490 |    "outputs": [],
491 |    "source": [
492 |     "mean_TenYearMA = df['TenYearMA'].mean()"
493 |    ]
494 |   },
495 |   {
496 |    "cell_type": "code",
497 |    "execution_count": 12,
498 |    "metadata": {
499 |     "collapsed": true
500 |    },
501 |    "outputs": [],
502 |    "source": [
503 |     "df['TenYearMA'].fillna(mean_TenYearMA, inplace = True)"
504 |    ]
505 |   },
506 |   {
507 |    "cell_type": "code",
508 |    "execution_count": 13,
509 |    "metadata": {},
510 |    "outputs": [
511 |     {
512 |      "data": {
513 |       "text/html": [
514 |        "<div>\n",
515 |        "<style>\n",
516 |        "    .dataframe thead tr:only-child th {\n",
517 |        "        text-align: right;\n",
518 |        "    }\n",
519 |        "\n",
520 |        "    .dataframe thead th {\n",
521 |        "        text-align: left;\n",
522 |        "    }\n",
523 |        "\n",
524 |        "    .dataframe tbody tr th {\n",
525 |        "        vertical-align: top;\n",
526 |        "    }\n",
527 |        "</style>\n",
528 |        "<table border=\"1\" class=\"dataframe\">\n",
529 |        "  <thead>\n",
530 |        "    <tr style=\"text-align: right;\">\n",
531 |        "      <th></th>\n",
532 |        "      <th>year</th>\n",
533 |        "      <th>city</th>\n",
534 |        "      <th>country</th>\n",
535 |        "      <th>avg_temp</th>\n",
536 |        "      <th>sevenDayMA</th>\n",
537 |        "      <th>FiveYearMA</th>\n",
538 |        "      <th>TenYearMA</th>\n",
539 |        "    </tr>\n",
540 |        "  </thead>\n",
541 |        "  <tbody>\n",
542 |        "    <tr>\n",
543 |        "      <th>0</th>\n",
544 |        "      <td>1743</td>\n",
545 |        "      <td>Chicago</td>\n",
546 |        "      <td>United States</td>\n",
547 |        "      <td>5.44</td>\n",
548 |        "      <td>NaN</td>\n",
549 |        "      <td>9.893401</td>\n",
550 |        "      <td>9.949863</td>\n",
551 |        "    </tr>\n",
552 |        "    <tr>\n",
553 |        "      <th>1</th>\n",
554 |        "      <td>1744</td>\n",
555 |        "      <td>Chicago</td>\n",
556 |        "      <td>United States</td>\n",
557 |        "      <td>11.73</td>\n",
558 |        "      <td>NaN</td>\n",
559 |        "      <td>9.893401</td>\n",
560 |        "      <td>9.949863</td>\n",
561 |        "    </tr>\n",
562 |        "    <tr>\n",
563 |        "      <th>2</th>\n",
564 |        "      <td>1745</td>\n",
565 |        "      <td>Chicago</td>\n",
566 |        "      <td>United States</td>\n",
567 |        "      <td>1.80</td>\n",
568 |        "      <td>NaN</td>\n",
569 |        "      <td>9.893401</td>\n",
570 |        "      <td>9.949863</td>\n",
571 |        "    </tr>\n",
572 |        "    <tr>\n",
573 |        "      <th>3</th>\n",
574 |        "      <td>1746</td>\n",
575 |        "      <td>Chicago</td>\n",
576 |        "      <td>United States</td>\n",
577 |        "      <td>0.00</td>\n",
578 |        "      <td>NaN</td>\n",
579 |        "      <td>9.893401</td>\n",
580 |        "      <td>9.949863</td>\n",
581 |        "    </tr>\n",
582 |        "    <tr>\n",
583 |        "      <th>4</th>\n",
584 |        "      <td>1747</td>\n",
585 |        "      <td>Chicago</td>\n",
586 |        "      <td>United States</td>\n",
587 |        "      <td>0.00</td>\n",
588 |        "      <td>NaN</td>\n",
589 |        "      <td>3.794000</td>\n",
590 |        "      <td>9.949863</td>\n",
591 |        "    </tr>\n",
592 |        "    <tr>\n",
593 |        "      <th>5</th>\n",
594 |        "      <td>1748</td>\n",
595 |        "      <td>Chicago</td>\n",
596 |        "      <td>United States</td>\n",
597 |        "      <td>0.00</td>\n",
598 |        "      <td>NaN</td>\n",
599 |        "      <td>2.706000</td>\n",
600 |        "      <td>9.949863</td>\n",
601 |        "    </tr>\n",
602 |        "    <tr>\n",
603 |        "      <th>6</th>\n",
604 |        "      <td>1749</td>\n",
605 |        "      <td>Chicago</td>\n",
606 |        "      <td>United States</td>\n",
607 |        "      <td>0.00</td>\n",
608 |        "      <td>2.710000</td>\n",
609 |        "      <td>0.360000</td>\n",
610 |        "      <td>9.949863</td>\n",
611 |        "    </tr>\n",
612 |        "    <tr>\n",
613 |        "      <th>7</th>\n",
614 |        "      <td>1750</td>\n",
615 |        "      <td>Chicago</td>\n",
616 |        "      <td>United States</td>\n",
617 |        "      <td>10.49</td>\n",
618 |        "      <td>3.431429</td>\n",
619 |        "      <td>2.098000</td>\n",
620 |        "      <td>9.949863</td>\n",
621 |        "    </tr>\n",
622 |        "    <tr>\n",
623 |        "      <th>8</th>\n",
624 |        "      <td>1751</td>\n",
625 |        "      <td>Chicago</td>\n",
626 |        "      <td>United States</td>\n",
627 |        "      <td>11.19</td>\n",
628 |        "      <td>3.354286</td>\n",
629 |        "      <td>4.336000</td>\n",
630 |        "      <td>9.949863</td>\n",
631 |        "    </tr>\n",
632 |        "    <tr>\n",
633 |        "      <th>9</th>\n",
634 |        "      <td>1752</td>\n",
635 |        "      <td>Chicago</td>\n",
636 |        "      <td>United States</td>\n",
637 |        "      <td>4.50</td>\n",
638 |        "      <td>3.740000</td>\n",
639 |        "      <td>5.236000</td>\n",
640 |        "      <td>4.515000</td>\n",
641 |        "    </tr>\n",
642 |        "  </tbody>\n",
643 |        "</table>\n",
644 |        "</div>"
645 |       ],
646 |       "text/plain": [
647 |        "   year     city        country  avg_temp  sevenDayMA  FiveYearMA  TenYearMA\n",
648 |        "0  1743  Chicago  United States      5.44         NaN    9.893401   9.949863\n",
649 |        "1  1744  Chicago  United States     11.73         NaN    9.893401   9.949863\n",
650 |        "2  1745  Chicago  United States      1.80         NaN    9.893401   9.949863\n",
651 |        "3  1746  Chicago  United States      0.00         NaN    9.893401   9.949863\n",
652 |        "4  1747  Chicago  United States      0.00         NaN    3.794000   9.949863\n",
653 |        "5  1748  Chicago  United States      0.00         NaN    2.706000   9.949863\n",
654 |        "6  1749  Chicago  United States      0.00    2.710000    0.360000   9.949863\n",
655 |        "7  1750  Chicago  United States     10.49    3.431429    2.098000   9.949863\n",
656 |        "8  1751  Chicago  United States     11.19    3.354286    4.336000   9.949863\n",
657 |        "9  1752  Chicago  United States      4.50    3.740000    5.236000   4.515000"
658 |       ]
659 |      },
660 |      "execution_count": 13,
661 |      "metadata": {},
662 |      "output_type": "execute_result"
663 |     }
664 |    ],
665 |    "source": [
666 |     "df.head(10)"
667 |    ]
668 |   },
669 |   {
670 |    "cell_type": "code",
671 |    "execution_count": 14,
672 |    "metadata": {},
673 |    "outputs": [
674 |     {
675 |      "data": {
676 |       "text/plain": [
677 |        "0      False\n",
678 |        "1      False\n",
679 |        "2      False\n",
680 |        "3      False\n",
681 |        "4      False\n",
682 |        "5      False\n",
683 |        "6      False\n",
684 |        "7      False\n",
685 |        "8      False\n",
686 |        "9      False\n",
687 |        "10     False\n",
688 |        "11     False\n",
689 |        "12     False\n",
690 |        "13     False\n",
691 |        "14     False\n",
692 |        "15     False\n",
693 |        "16     False\n",
694 |        "17     False\n",
695 |        "18     False\n",
696 |        "19     False\n",
697 |        "20     False\n",
698 |        "21     False\n",
699 |        "22     False\n",
700 |        "23     False\n",
701 |        "24     False\n",
702 |        "25     False\n",
703 |        "26     False\n",
704 |        "27     False\n",
705 |        "28     False\n",
706 |        "29     False\n",
707 |        "       ...  \n",
708 |        "241    False\n",
709 |        "242    False\n",
710 |        "243    False\n",
711 |        "244    False\n",
712 |        "245    False\n",
713 |        "246    False\n",
714 |        "247    False\n",
715 |        "248    False\n",
716 |        "249    False\n",
717 |        "250    False\n",
718 |        "251    False\n",
719 |        "252    False\n",
720 |        "253    False\n",
721 |        "254    False\n",
722 |        "255    False\n",
723 |        "256    False\n",
724 |        "257    False\n",
725 |        "258    False\n",
726 |        "259    False\n",
727 |        "260    False\n",
728 |        "261    False\n",
729 |        "262    False\n",
730 |        "263    False\n",
731 |        "264    False\n",
732 |        "265    False\n",
733 |        "266    False\n",
734 |        "267    False\n",
735 |        "268    False\n",
736 |        "269    False\n",
737 |        "270    False\n",
738 |        "Length: 271, dtype: bool"
739 |       ]
740 |      },
741 |      "execution_count": 14,
742 |      "metadata": {},
743 |      "output_type": "execute_result"
744 |     }
745 |    ],
746 |    "source": [
747 |     "df.duplicated()"
748 |    ]
749 |   },
750 |   {
751 |    "cell_type": "code",
752 |    "execution_count": 15,
753 |    "metadata": {},
754 |    "outputs": [
755 |     {
756 |      "data": {
757 |       "text/plain": [
758 |        "0"
759 |       ]
760 |      },
761 |      "execution_count": 15,
762 |      "metadata": {},
763 |      "output_type": "execute_result"
764 |     }
765 |    ],
766 |    "source": [
767 |     "sum(df.duplicated())"
768 |    ]
769 |   },
770 |   {
771 |    "cell_type": "code",
772 |    "execution_count": 16,
773 |    "metadata": {
774 |     "collapsed": true
775 |    },
776 |    "outputs": [],
777 |    "source": [
778 |     "df.drop_duplicates(inplace = True)"
779 |    ]
780 |   },
781 |   {
782 |    "cell_type": "code",
783 |    "execution_count": 18,
784 |    "metadata": {},
785 |    "outputs": [
786 |     {
787 |      "name": "stdout",
788 |      "output_type": "stream",
789 |      "text": [
790 |       "<class 'pandas.core.frame.DataFrame'>\n",
791 |       "Int64Index: 271 entries, 0 to 270\n",
792 |       "Data columns (total 7 columns):\n",
793 |       "year          271 non-null int64\n",
794 |       "city          271 non-null object\n",
795 |       "country       271 non-null object\n",
796 |       "avg_temp      271 non-null float64\n",
797 |       "sevenDayMA    265 non-null float64\n",
798 |       "FiveYearMA    271 non-null float64\n",
799 |       "TenYearMA     271 non-null float64\n",
800 |       "dtypes: float64(4), int64(1), object(2)\n",
801 |       "memory usage: 16.9+ KB\n"
802 |      ]
803 |     }
804 |    ],
805 |    "source": [
806 |     "df.info(0)"
807 |    ]
808 |   },
809 |   {
810 |    "cell_type": "code",
811 |    "execution_count": 19,
812 |    "metadata": {
813 |     "collapsed": true
814 |    },
815 |    "outputs": [],
816 |    "source": [
817 |     "#df['timestamp'] = pd.to_datetime(df['timestamp'])"
818 |    ]
819 |   },
820 |   {
821 |    "cell_type": "code",
822 |    "execution_count": null,
823 |    "metadata": {
824 |     "collapsed": true
825 |    },
826 |    "outputs": [],
827 |    "source": []
828 |   }
829 |  ],
830 |  "metadata": {
831 |   "kernelspec": {
832 |    "display_name": "Python 3",
833 |    "language": "python",
834 |    "name": "python3"
835 |   },
836 |   "language_info": {
837 |    "codemirror_mode": {
838 |     "name": "ipython",
839 |     "version": 3
840 |    },
841 |    "file_extension": ".py",
842 |    "mimetype": "text/x-python",
843 |    "name": "python",
844 |    "nbconvert_exporter": "python",
845 |    "pygments_lexer": "ipython3",
846 |    "version": "3.6.2"
847 |   }
848 |  },
849 |  "nbformat": 4,
850 |  "nbformat_minor": 2
851 | }
852 | 


--------------------------------------------------------------------------------
/Drawing-Conclusions-pynb.txt:
--------------------------------------------------------------------------------
1 | import pandas as pd
2 | 


--------------------------------------------------------------------------------
/Pandas_Functions_Formulae.xlsx:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/nirupamaprv/Data-Analysis/05892f4058faf9ccc6aa90995e90d4ae7bd0bf7c/Pandas_Functions_Formulae.xlsx


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Overview
 2 | Practice Exercise from Data Analysis course of Udacity DAND
 3 | 
 4 | - .ipynb file contains code with Markdown cells from Jupyter Notebook.
 5 | - Exercises solved by self to answer questions for assignment.
 6 | - .html file is .pynb converted to web version for easy viewing
 7 | - .csv files contain data on which data analysis was conducted
 8 | 
 9 | ## Datasets and Project Summary
10 | ### Chicago temperature set
11 | - Cleaning.ipynb - Data cleaning practice
12 | - Histogram-Practice.ipynb - Practicing creating plots 
13 | - plots-pandas.ipynb - computing values for plots
14 | 
15 | ### Wine Dataset
16 | - appending.ipynb - Appending data from different datasets
17 | - appending_rename.ipynb - Appending, renaming and saving data from different datasets
18 | - assessing_quiz.ipynb - answering Quiz using pandas 
19 | - conclusions_groupby.ipynb - using groupby function to analyze quality, ratings and other Questions.
20 | - conclusions_query.ipynb - drawing conclusions to Qs on ratings 
21 | - eda_visuals.ipynb - Addressing Qs on wine dataset using different plots 
22 | - eda_visuals_practise_functions.ipynb - Addressing additional Qs using different plots; Here, varying colors are used to differentiate groups
23 | - plotting_type_quality.ipynb - Creating plots with matplotlib for ratings
24 | - wine_visualizations.ipynb - Use Matplotlib to create bar charts that visualize the conclusions made with groupby and queries
25 | 
26 | ### Cancer Dataset
27 | - assessing.ipynb - inspecting datasets, data types, selecting different ranges 
28 | - cleaning_practice.ipynb - practicing data wrangling
29 | 
30 | 
31 | ### Auto Dataset for 2008 and 2018 models
32 | - assessing_case2.ipynb  - answering Quiz using pandas 
33 | - cleaning_column_labels.ipynb - data wrangling
34 | - drawing_conclusions_Fuel.ipynb - Making inferences and comparisons on fuel efficiency, improvements, classes, etc. and visualizing using histograms and pie charts
35 | - exploring_visuals.ipynb - Making inferences and comparisons using visualizations
36 | - fix_datatypes_air_pollution.ipynb - Data Wrangling
37 | fix_datatypes_cyl.ipynb - Datatypes transformation		
38 | - query_filter.ipynb - Data Wrangling
39 | 
40 | ### Other Datasets
41 | - matplotlib_example.ipynb - Practicing bar charts 
42 | - conclusions_quiz.ipynb - **Store Sales Dataset** - Analyzing sales figures and periods to determine performance and revenue
43 | - reading_csv.ipynb - **Student Scores Data**- Reading, writing and inspecting values
44 | - visuals_quiz.ipynb - **Powerplant Data** - creating plots using matplotlib and answering Quiz questions
45 | 
46 | 
47 | 


--------------------------------------------------------------------------------
/assessing_case2.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {
  6 |     "collapsed": true
  7 |    },
  8 |    "source": [
  9 |     "# Assessing\n",
 10 |     "Use the space below to explore `all_alpha_08.csv` and `all_alpha_18.csv` to answer the quiz questions below."
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 28,
 16 |    "metadata": {},
 17 |    "outputs": [
 18 |     {
 19 |      "name": "stdout",
 20 |      "output_type": "stream",
 21 |      "text": [
 22 |       "<class 'pandas.core.frame.DataFrame'>\n",
 23 |       "RangeIndex: 1611 entries, 0 to 1610\n",
 24 |       "Data columns (total 18 columns):\n",
 25 |       "Model                   1611 non-null object\n",
 26 |       "Displ                   1609 non-null float64\n",
 27 |       "Cyl                     1609 non-null float64\n",
 28 |       "Trans                   1611 non-null object\n",
 29 |       "Drive                   1611 non-null object\n",
 30 |       "Fuel                    1611 non-null object\n",
 31 |       "Cert Region             1611 non-null object\n",
 32 |       "Stnd                    1611 non-null object\n",
 33 |       "Stnd Description        1611 non-null object\n",
 34 |       "Underhood ID            1611 non-null object\n",
 35 |       "Veh Class               1611 non-null object\n",
 36 |       "Air Pollution Score     1611 non-null int64\n",
 37 |       "City MPG                1611 non-null object\n",
 38 |       "Hwy MPG                 1611 non-null object\n",
 39 |       "Cmb MPG                 1611 non-null object\n",
 40 |       "Greenhouse Gas Score    1611 non-null int64\n",
 41 |       "SmartWay                1611 non-null object\n",
 42 |       "Comb CO2                1611 non-null object\n",
 43 |       "dtypes: float64(2), int64(2), object(14)\n",
 44 |       "memory usage: 226.6+ KB\n"
 45 |      ]
 46 |     }
 47 |    ],
 48 |    "source": [
 49 |     "import pandas as pd\n",
 50 |     "\n",
 51 |     "df_18 = pd.read_csv('all_alpha_18.csv')\n",
 52 |     "df_18.info()\n"
 53 |    ]
 54 |   },
 55 |   {
 56 |    "cell_type": "code",
 57 |    "execution_count": 29,
 58 |    "metadata": {},
 59 |    "outputs": [
 60 |     {
 61 |      "name": "stdout",
 62 |      "output_type": "stream",
 63 |      "text": [
 64 |       "<class 'pandas.core.frame.DataFrame'>\n",
 65 |       "RangeIndex: 2404 entries, 0 to 2403\n",
 66 |       "Data columns (total 18 columns):\n",
 67 |       "Model                   2404 non-null object\n",
 68 |       "Displ                   2404 non-null float64\n",
 69 |       "Cyl                     2205 non-null object\n",
 70 |       "Trans                   2205 non-null object\n",
 71 |       "Drive                   2311 non-null object\n",
 72 |       "Fuel                    2404 non-null object\n",
 73 |       "Sales Area              2404 non-null object\n",
 74 |       "Stnd                    2404 non-null object\n",
 75 |       "Underhood ID            2404 non-null object\n",
 76 |       "Veh Class               2404 non-null object\n",
 77 |       "Air Pollution Score     2404 non-null object\n",
 78 |       "FE Calc Appr            2205 non-null object\n",
 79 |       "City MPG                2205 non-null object\n",
 80 |       "Hwy MPG                 2205 non-null object\n",
 81 |       "Cmb MPG                 2205 non-null object\n",
 82 |       "Unadj Cmb MPG           2205 non-null float64\n",
 83 |       "Greenhouse Gas Score    2205 non-null object\n",
 84 |       "SmartWay                2404 non-null object\n",
 85 |       "dtypes: float64(2), object(16)\n",
 86 |       "memory usage: 338.1+ KB\n"
 87 |      ]
 88 |     }
 89 |    ],
 90 |    "source": [
 91 |     "df_08 = pd.read_csv('all_alpha_08.csv')\n",
 92 |     "df_08.info()"
 93 |    ]
 94 |   },
 95 |   {
 96 |    "cell_type": "code",
 97 |    "execution_count": 30,
 98 |    "metadata": {},
 99 |    "outputs": [
100 |     {
101 |      "data": {
102 |       "text/plain": [
103 |        "0"
104 |       ]
105 |      },
106 |      "execution_count": 30,
107 |      "metadata": {},
108 |      "output_type": "execute_result"
109 |     }
110 |    ],
111 |    "source": [
112 |     "sum(df_18.duplicated())"
113 |    ]
114 |   },
115 |   {
116 |    "cell_type": "code",
117 |    "execution_count": 31,
118 |    "metadata": {},
119 |    "outputs": [
120 |     {
121 |      "data": {
122 |       "text/plain": [
123 |        "25"
124 |       ]
125 |      },
126 |      "execution_count": 31,
127 |      "metadata": {},
128 |      "output_type": "execute_result"
129 |     }
130 |    ],
131 |    "source": [
132 |     "sum(df_08.duplicated())"
133 |    ]
134 |   },
135 |   {
136 |    "cell_type": "code",
137 |    "execution_count": 32,
138 |    "metadata": {},
139 |    "outputs": [
140 |     {
141 |      "data": {
142 |       "text/plain": [
143 |        "Gasoline                1492\n",
144 |        "Ethanol/Gas               55\n",
145 |        "Diesel                    38\n",
146 |        "Gasoline/Electricity      24\n",
147 |        "Electricity                2\n",
148 |        "Name: Fuel, dtype: int64"
149 |       ]
150 |      },
151 |      "execution_count": 32,
152 |      "metadata": {},
153 |      "output_type": "execute_result"
154 |     }
155 |    ],
156 |    "source": [
157 |     "df_18.Fuel.value_counts()"
158 |    ]
159 |   },
160 |   {
161 |    "cell_type": "code",
162 |    "execution_count": 33,
163 |    "metadata": {},
164 |    "outputs": [
165 |     {
166 |      "data": {
167 |       "text/plain": [
168 |        "Gasoline       2318\n",
169 |        "ethanol/gas      72\n",
170 |        "diesel           11\n",
171 |        "CNG               2\n",
172 |        "ethanol           1\n",
173 |        "Name: Fuel, dtype: int64"
174 |       ]
175 |      },
176 |      "execution_count": 33,
177 |      "metadata": {},
178 |      "output_type": "execute_result"
179 |     }
180 |    ],
181 |    "source": [
182 |     "df_08.Fuel.value_counts()"
183 |    ]
184 |   },
185 |   {
186 |    "cell_type": "code",
187 |    "execution_count": 34,
188 |    "metadata": {},
189 |    "outputs": [
190 |     {
191 |      "data": {
192 |       "text/plain": [
193 |        "1611"
194 |       ]
195 |      },
196 |      "execution_count": 34,
197 |      "metadata": {},
198 |      "output_type": "execute_result"
199 |     }
200 |    ],
201 |    "source": [
202 |     "sum(df_18.Model.value_counts())"
203 |    ]
204 |   },
205 |   {
206 |    "cell_type": "code",
207 |    "execution_count": 35,
208 |    "metadata": {},
209 |    "outputs": [
210 |     {
211 |      "data": {
212 |       "text/html": [
213 |        "<div>\n",
214 |        "<style>\n",
215 |        "    .dataframe thead tr:only-child th {\n",
216 |        "        text-align: right;\n",
217 |        "    }\n",
218 |        "\n",
219 |        "    .dataframe thead th {\n",
220 |        "        text-align: left;\n",
221 |        "    }\n",
222 |        "\n",
223 |        "    .dataframe tbody tr th {\n",
224 |        "        vertical-align: top;\n",
225 |        "    }\n",
226 |        "</style>\n",
227 |        "<table border=\"1\" class=\"dataframe\">\n",
228 |        "  <thead>\n",
229 |        "    <tr style=\"text-align: right;\">\n",
230 |        "      <th></th>\n",
231 |        "      <th>Displ</th>\n",
232 |        "      <th>Cyl</th>\n",
233 |        "      <th>Air Pollution Score</th>\n",
234 |        "      <th>Greenhouse Gas Score</th>\n",
235 |        "    </tr>\n",
236 |        "  </thead>\n",
237 |        "  <tbody>\n",
238 |        "    <tr>\n",
239 |        "      <th>count</th>\n",
240 |        "      <td>1609.000000</td>\n",
241 |        "      <td>1609.000000</td>\n",
242 |        "      <td>1611.000000</td>\n",
243 |        "      <td>1611.000000</td>\n",
244 |        "    </tr>\n",
245 |        "    <tr>\n",
246 |        "      <th>mean</th>\n",
247 |        "      <td>3.055687</td>\n",
248 |        "      <td>5.479180</td>\n",
249 |        "      <td>3.958411</td>\n",
250 |        "      <td>4.711359</td>\n",
251 |        "    </tr>\n",
252 |        "    <tr>\n",
253 |        "      <th>std</th>\n",
254 |        "      <td>1.344574</td>\n",
255 |        "      <td>1.749121</td>\n",
256 |        "      <td>1.824303</td>\n",
257 |        "      <td>1.657429</td>\n",
258 |        "    </tr>\n",
259 |        "    <tr>\n",
260 |        "      <th>min</th>\n",
261 |        "      <td>1.200000</td>\n",
262 |        "      <td>3.000000</td>\n",
263 |        "      <td>1.000000</td>\n",
264 |        "      <td>1.000000</td>\n",
265 |        "    </tr>\n",
266 |        "    <tr>\n",
267 |        "      <th>25%</th>\n",
268 |        "      <td>2.000000</td>\n",
269 |        "      <td>4.000000</td>\n",
270 |        "      <td>3.000000</td>\n",
271 |        "      <td>4.000000</td>\n",
272 |        "    </tr>\n",
273 |        "    <tr>\n",
274 |        "      <th>50%</th>\n",
275 |        "      <td>3.000000</td>\n",
276 |        "      <td>6.000000</td>\n",
277 |        "      <td>3.000000</td>\n",
278 |        "      <td>5.000000</td>\n",
279 |        "    </tr>\n",
280 |        "    <tr>\n",
281 |        "      <th>75%</th>\n",
282 |        "      <td>3.600000</td>\n",
283 |        "      <td>6.000000</td>\n",
284 |        "      <td>5.000000</td>\n",
285 |        "      <td>6.000000</td>\n",
286 |        "    </tr>\n",
287 |        "    <tr>\n",
288 |        "      <th>max</th>\n",
289 |        "      <td>8.000000</td>\n",
290 |        "      <td>16.000000</td>\n",
291 |        "      <td>10.000000</td>\n",
292 |        "      <td>10.000000</td>\n",
293 |        "    </tr>\n",
294 |        "  </tbody>\n",
295 |        "</table>\n",
296 |        "</div>"
297 |       ],
298 |       "text/plain": [
299 |        "             Displ          Cyl  Air Pollution Score  Greenhouse Gas Score\n",
300 |        "count  1609.000000  1609.000000          1611.000000           1611.000000\n",
301 |        "mean      3.055687     5.479180             3.958411              4.711359\n",
302 |        "std       1.344574     1.749121             1.824303              1.657429\n",
303 |        "min       1.200000     3.000000             1.000000              1.000000\n",
304 |        "25%       2.000000     4.000000             3.000000              4.000000\n",
305 |        "50%       3.000000     6.000000             3.000000              5.000000\n",
306 |        "75%       3.600000     6.000000             5.000000              6.000000\n",
307 |        "max       8.000000    16.000000            10.000000             10.000000"
308 |       ]
309 |      },
310 |      "execution_count": 35,
311 |      "metadata": {},
312 |      "output_type": "execute_result"
313 |     }
314 |    ],
315 |    "source": [
316 |     "df_18.describe()"
317 |    ]
318 |   },
319 |   {
320 |    "cell_type": "code",
321 |    "execution_count": 36,
322 |    "metadata": {},
323 |    "outputs": [
324 |     {
325 |      "data": {
326 |       "text/html": [
327 |        "<div>\n",
328 |        "<style>\n",
329 |        "    .dataframe thead tr:only-child th {\n",
330 |        "        text-align: right;\n",
331 |        "    }\n",
332 |        "\n",
333 |        "    .dataframe thead th {\n",
334 |        "        text-align: left;\n",
335 |        "    }\n",
336 |        "\n",
337 |        "    .dataframe tbody tr th {\n",
338 |        "        vertical-align: top;\n",
339 |        "    }\n",
340 |        "</style>\n",
341 |        "<table border=\"1\" class=\"dataframe\">\n",
342 |        "  <thead>\n",
343 |        "    <tr style=\"text-align: right;\">\n",
344 |        "      <th></th>\n",
345 |        "      <th>Model</th>\n",
346 |        "      <th>Displ</th>\n",
347 |        "      <th>Cyl</th>\n",
348 |        "      <th>Trans</th>\n",
349 |        "      <th>Drive</th>\n",
350 |        "      <th>Fuel</th>\n",
351 |        "      <th>Cert Region</th>\n",
352 |        "      <th>Stnd</th>\n",
353 |        "      <th>Stnd Description</th>\n",
354 |        "      <th>Underhood ID</th>\n",
355 |        "      <th>Veh Class</th>\n",
356 |        "      <th>Air Pollution Score</th>\n",
357 |        "      <th>City MPG</th>\n",
358 |        "      <th>Hwy MPG</th>\n",
359 |        "      <th>Cmb MPG</th>\n",
360 |        "      <th>Greenhouse Gas Score</th>\n",
361 |        "      <th>SmartWay</th>\n",
362 |        "      <th>Comb CO2</th>\n",
363 |        "    </tr>\n",
364 |        "  </thead>\n",
365 |        "  <tbody>\n",
366 |        "    <tr>\n",
367 |        "      <th>0</th>\n",
368 |        "      <td>ACURA RDX</td>\n",
369 |        "      <td>3.5</td>\n",
370 |        "      <td>6.0</td>\n",
371 |        "      <td>SemiAuto-6</td>\n",
372 |        "      <td>2WD</td>\n",
373 |        "      <td>Gasoline</td>\n",
374 |        "      <td>FA</td>\n",
375 |        "      <td>T3B125</td>\n",
376 |        "      <td>Federal Tier 3 Bin 125</td>\n",
377 |        "      <td>JHNXT03.5GV3</td>\n",
378 |        "      <td>small SUV</td>\n",
379 |        "      <td>3</td>\n",
380 |        "      <td>20</td>\n",
381 |        "      <td>28</td>\n",
382 |        "      <td>23</td>\n",
383 |        "      <td>5</td>\n",
384 |        "      <td>No</td>\n",
385 |        "      <td>386</td>\n",
386 |        "    </tr>\n",
387 |        "    <tr>\n",
388 |        "      <th>1</th>\n",
389 |        "      <td>ACURA RDX</td>\n",
390 |        "      <td>3.5</td>\n",
391 |        "      <td>6.0</td>\n",
392 |        "      <td>SemiAuto-6</td>\n",
393 |        "      <td>2WD</td>\n",
394 |        "      <td>Gasoline</td>\n",
395 |        "      <td>CA</td>\n",
396 |        "      <td>U2</td>\n",
397 |        "      <td>California LEV-II ULEV</td>\n",
398 |        "      <td>JHNXT03.5GV3</td>\n",
399 |        "      <td>small SUV</td>\n",
400 |        "      <td>3</td>\n",
401 |        "      <td>20</td>\n",
402 |        "      <td>28</td>\n",
403 |        "      <td>23</td>\n",
404 |        "      <td>5</td>\n",
405 |        "      <td>No</td>\n",
406 |        "      <td>386</td>\n",
407 |        "    </tr>\n",
408 |        "    <tr>\n",
409 |        "      <th>2</th>\n",
410 |        "      <td>ACURA RDX</td>\n",
411 |        "      <td>3.5</td>\n",
412 |        "      <td>6.0</td>\n",
413 |        "      <td>SemiAuto-6</td>\n",
414 |        "      <td>4WD</td>\n",
415 |        "      <td>Gasoline</td>\n",
416 |        "      <td>FA</td>\n",
417 |        "      <td>T3B125</td>\n",
418 |        "      <td>Federal Tier 3 Bin 125</td>\n",
419 |        "      <td>JHNXT03.5GV3</td>\n",
420 |        "      <td>small SUV</td>\n",
421 |        "      <td>3</td>\n",
422 |        "      <td>19</td>\n",
423 |        "      <td>27</td>\n",
424 |        "      <td>22</td>\n",
425 |        "      <td>4</td>\n",
426 |        "      <td>No</td>\n",
427 |        "      <td>402</td>\n",
428 |        "    </tr>\n",
429 |        "    <tr>\n",
430 |        "      <th>3</th>\n",
431 |        "      <td>ACURA RDX</td>\n",
432 |        "      <td>3.5</td>\n",
433 |        "      <td>6.0</td>\n",
434 |        "      <td>SemiAuto-6</td>\n",
435 |        "      <td>4WD</td>\n",
436 |        "      <td>Gasoline</td>\n",
437 |        "      <td>CA</td>\n",
438 |        "      <td>U2</td>\n",
439 |        "      <td>California LEV-II ULEV</td>\n",
440 |        "      <td>JHNXT03.5GV3</td>\n",
441 |        "      <td>small SUV</td>\n",
442 |        "      <td>3</td>\n",
443 |        "      <td>19</td>\n",
444 |        "      <td>27</td>\n",
445 |        "      <td>22</td>\n",
446 |        "      <td>4</td>\n",
447 |        "      <td>No</td>\n",
448 |        "      <td>402</td>\n",
449 |        "    </tr>\n",
450 |        "    <tr>\n",
451 |        "      <th>4</th>\n",
452 |        "      <td>ACURA TLX</td>\n",
453 |        "      <td>2.4</td>\n",
454 |        "      <td>4.0</td>\n",
455 |        "      <td>AMS-8</td>\n",
456 |        "      <td>2WD</td>\n",
457 |        "      <td>Gasoline</td>\n",
458 |        "      <td>CA</td>\n",
459 |        "      <td>L3ULEV125</td>\n",
460 |        "      <td>California LEV-III ULEV125</td>\n",
461 |        "      <td>JHNXV02.4WH3</td>\n",
462 |        "      <td>small car</td>\n",
463 |        "      <td>3</td>\n",
464 |        "      <td>23</td>\n",
465 |        "      <td>33</td>\n",
466 |        "      <td>27</td>\n",
467 |        "      <td>6</td>\n",
468 |        "      <td>No</td>\n",
469 |        "      <td>330</td>\n",
470 |        "    </tr>\n",
471 |        "  </tbody>\n",
472 |        "</table>\n",
473 |        "</div>"
474 |       ],
475 |       "text/plain": [
476 |        "       Model  Displ  Cyl       Trans Drive      Fuel Cert Region       Stnd  \\\n",
477 |        "0  ACURA RDX    3.5  6.0  SemiAuto-6   2WD  Gasoline          FA     T3B125   \n",
478 |        "1  ACURA RDX    3.5  6.0  SemiAuto-6   2WD  Gasoline          CA         U2   \n",
479 |        "2  ACURA RDX    3.5  6.0  SemiAuto-6   4WD  Gasoline          FA     T3B125   \n",
480 |        "3  ACURA RDX    3.5  6.0  SemiAuto-6   4WD  Gasoline          CA         U2   \n",
481 |        "4  ACURA TLX    2.4  4.0       AMS-8   2WD  Gasoline          CA  L3ULEV125   \n",
482 |        "\n",
483 |        "             Stnd Description  Underhood ID  Veh Class  Air Pollution Score  \\\n",
484 |        "0      Federal Tier 3 Bin 125  JHNXT03.5GV3  small SUV                    3   \n",
485 |        "1      California LEV-II ULEV  JHNXT03.5GV3  small SUV                    3   \n",
486 |        "2      Federal Tier 3 Bin 125  JHNXT03.5GV3  small SUV                    3   \n",
487 |        "3      California LEV-II ULEV  JHNXT03.5GV3  small SUV                    3   \n",
488 |        "4  California LEV-III ULEV125  JHNXV02.4WH3  small car                    3   \n",
489 |        "\n",
490 |        "  City MPG Hwy MPG Cmb MPG  Greenhouse Gas Score SmartWay Comb CO2  \n",
491 |        "0       20      28      23                     5       No      386  \n",
492 |        "1       20      28      23                     5       No      386  \n",
493 |        "2       19      27      22                     4       No      402  \n",
494 |        "3       19      27      22                     4       No      402  \n",
495 |        "4       23      33      27                     6       No      330  "
496 |       ]
497 |      },
498 |      "execution_count": 36,
499 |      "metadata": {},
500 |      "output_type": "execute_result"
501 |     }
502 |    ],
503 |    "source": [
504 |     "df_18.head()"
505 |    ]
506 |   },
507 |   {
508 |    "cell_type": "code",
509 |    "execution_count": 37,
510 |    "metadata": {},
511 |    "outputs": [
512 |     {
513 |      "data": {
514 |       "text/html": [
515 |        "<div>\n",
516 |        "<style>\n",
517 |        "    .dataframe thead tr:only-child th {\n",
518 |        "        text-align: right;\n",
519 |        "    }\n",
520 |        "\n",
521 |        "    .dataframe thead th {\n",
522 |        "        text-align: left;\n",
523 |        "    }\n",
524 |        "\n",
525 |        "    .dataframe tbody tr th {\n",
526 |        "        vertical-align: top;\n",
527 |        "    }\n",
528 |        "</style>\n",
529 |        "<table border=\"1\" class=\"dataframe\">\n",
530 |        "  <thead>\n",
531 |        "    <tr style=\"text-align: right;\">\n",
532 |        "      <th></th>\n",
533 |        "      <th>Displ</th>\n",
534 |        "      <th>Unadj Cmb MPG</th>\n",
535 |        "    </tr>\n",
536 |        "  </thead>\n",
537 |        "  <tbody>\n",
538 |        "    <tr>\n",
539 |        "      <th>count</th>\n",
540 |        "      <td>2404.000000</td>\n",
541 |        "      <td>2205.000000</td>\n",
542 |        "    </tr>\n",
543 |        "    <tr>\n",
544 |        "      <th>mean</th>\n",
545 |        "      <td>3.748918</td>\n",
546 |        "      <td>23.916104</td>\n",
547 |        "    </tr>\n",
548 |        "    <tr>\n",
549 |        "      <th>std</th>\n",
550 |        "      <td>1.335785</td>\n",
551 |        "      <td>6.366170</td>\n",
552 |        "    </tr>\n",
553 |        "    <tr>\n",
554 |        "      <th>min</th>\n",
555 |        "      <td>1.300000</td>\n",
556 |        "      <td>10.018400</td>\n",
557 |        "    </tr>\n",
558 |        "    <tr>\n",
559 |        "      <th>25%</th>\n",
560 |        "      <td>2.500000</td>\n",
561 |        "      <td>19.113900</td>\n",
562 |        "    </tr>\n",
563 |        "    <tr>\n",
564 |        "      <th>50%</th>\n",
565 |        "      <td>3.500000</td>\n",
566 |        "      <td>23.921300</td>\n",
567 |        "    </tr>\n",
568 |        "    <tr>\n",
569 |        "      <th>75%</th>\n",
570 |        "      <td>4.800000</td>\n",
571 |        "      <td>27.869300</td>\n",
572 |        "    </tr>\n",
573 |        "    <tr>\n",
574 |        "      <th>max</th>\n",
575 |        "      <td>8.400000</td>\n",
576 |        "      <td>65.777800</td>\n",
577 |        "    </tr>\n",
578 |        "  </tbody>\n",
579 |        "</table>\n",
580 |        "</div>"
581 |       ],
582 |       "text/plain": [
583 |        "             Displ  Unadj Cmb MPG\n",
584 |        "count  2404.000000    2205.000000\n",
585 |        "mean      3.748918      23.916104\n",
586 |        "std       1.335785       6.366170\n",
587 |        "min       1.300000      10.018400\n",
588 |        "25%       2.500000      19.113900\n",
589 |        "50%       3.500000      23.921300\n",
590 |        "75%       4.800000      27.869300\n",
591 |        "max       8.400000      65.777800"
592 |       ]
593 |      },
594 |      "execution_count": 37,
595 |      "metadata": {},
596 |      "output_type": "execute_result"
597 |     }
598 |    ],
599 |    "source": [
600 |     "df_08.describe()\n"
601 |    ]
602 |   },
603 |   {
604 |    "cell_type": "code",
605 |    "execution_count": 38,
606 |    "metadata": {},
607 |    "outputs": [
608 |     {
609 |      "data": {
610 |       "text/plain": [
611 |        "2205"
612 |       ]
613 |      },
614 |      "execution_count": 38,
615 |      "metadata": {},
616 |      "output_type": "execute_result"
617 |     }
618 |    ],
619 |    "source": [
620 |     "sum(df_08.Cyl.value_counts())"
621 |    ]
622 |   },
623 |   {
624 |    "cell_type": "code",
625 |    "execution_count": 39,
626 |    "metadata": {},
627 |    "outputs": [
628 |     {
629 |      "data": {
630 |       "text/plain": [
631 |        "Model                   436\n",
632 |        "Displ                    47\n",
633 |        "Cyl                       8\n",
634 |        "Trans                    14\n",
635 |        "Drive                     2\n",
636 |        "Fuel                      5\n",
637 |        "Sales Area                3\n",
638 |        "Stnd                     12\n",
639 |        "Underhood ID            343\n",
640 |        "Veh Class                 9\n",
641 |        "Air Pollution Score      13\n",
642 |        "FE Calc Appr              2\n",
643 |        "City MPG                 39\n",
644 |        "Hwy MPG                  43\n",
645 |        "Cmb MPG                  38\n",
646 |        "Unadj Cmb MPG           721\n",
647 |        "Greenhouse Gas Score     20\n",
648 |        "SmartWay                  2\n",
649 |        "dtype: int64"
650 |       ]
651 |      },
652 |      "execution_count": 39,
653 |      "metadata": {},
654 |      "output_type": "execute_result"
655 |     }
656 |    ],
657 |    "source": [
658 |     "df_08.nunique()"
659 |    ]
660 |   },
661 |   {
662 |    "cell_type": "code",
663 |    "execution_count": 40,
664 |    "metadata": {},
665 |    "outputs": [
666 |     {
667 |      "data": {
668 |       "text/plain": [
669 |        "Model                   367\n",
670 |        "Displ                    36\n",
671 |        "Cyl                       7\n",
672 |        "Trans                    26\n",
673 |        "Drive                     2\n",
674 |        "Fuel                      5\n",
675 |        "Cert Region               2\n",
676 |        "Stnd                     19\n",
677 |        "Stnd Description         19\n",
678 |        "Underhood ID            230\n",
679 |        "Veh Class                 9\n",
680 |        "Air Pollution Score       6\n",
681 |        "City MPG                 58\n",
682 |        "Hwy MPG                  62\n",
683 |        "Cmb MPG                  57\n",
684 |        "Greenhouse Gas Score     10\n",
685 |        "SmartWay                  3\n",
686 |        "Comb CO2                299\n",
687 |        "dtype: int64"
688 |       ]
689 |      },
690 |      "execution_count": 40,
691 |      "metadata": {},
692 |      "output_type": "execute_result"
693 |     }
694 |    ],
695 |    "source": [
696 |     "df_18.nunique()"
697 |    ]
698 |   },
699 |   {
700 |    "cell_type": "code",
701 |    "execution_count": null,
702 |    "metadata": {
703 |     "collapsed": true
704 |    },
705 |    "outputs": [],
706 |    "source": []
707 |   },
708 |   {
709 |    "cell_type": "code",
710 |    "execution_count": null,
711 |    "metadata": {
712 |     "collapsed": true
713 |    },
714 |    "outputs": [],
715 |    "source": []
716 |   },
717 |   {
718 |    "cell_type": "code",
719 |    "execution_count": null,
720 |    "metadata": {
721 |     "collapsed": true
722 |    },
723 |    "outputs": [],
724 |    "source": []
725 |   }
726 |  ],
727 |  "metadata": {
728 |   "kernelspec": {
729 |    "display_name": "Python 3",
730 |    "language": "python",
731 |    "name": "python3"
732 |   },
733 |   "language_info": {
734 |    "codemirror_mode": {
735 |     "name": "ipython",
736 |     "version": 3
737 |    },
738 |    "file_extension": ".py",
739 |    "mimetype": "text/x-python",
740 |    "name": "python",
741 |    "nbconvert_exporter": "python",
742 |    "pygments_lexer": "ipython3",
743 |    "version": "3.6.1"
744 |   }
745 |  },
746 |  "nbformat": 4,
747 |  "nbformat_minor": 2
748 | }
749 | 


--------------------------------------------------------------------------------
/assessing_quiz.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {},
  6 |    "source": [
  7 |     "# Assessing\n",
  8 |     "Use the space below to explore `winequality-red.csv` and `winequality-white.csv` to answer the quiz questions below.\n",
  9 |     "\n",
 10 |     "Assessing Data\n",
 11 |     "Using Pandas, explore winequality-red.csv and winequality-white.csv in the Jupyter notebook below to answer quiz questions below the notebook about these characteristics of the datasets:\n",
 12 |     "\n",
 13 |     "number of samples in each dataset\n",
 14 |     "number of columns in each dataset\n",
 15 |     "features with missing values\n",
 16 |     "duplicate rows in the white wine dataset\n",
 17 |     "number of unique values for quality in each dataset\n",
 18 |     "mean density of the red wine dataset\n",
 19 |     "This data was originally taken from here:\n",
 20 |     "https://archive.ics.uci.edu/ml/datasets/Wine+Quality"
 21 |    ]
 22 |   },
 23 |   {
 24 |    "cell_type": "code",
 25 |    "execution_count": 1,
 26 |    "metadata": {
 27 |     "collapsed": true
 28 |    },
 29 |    "outputs": [],
 30 |    "source": [
 31 |     "import pandas as pd\n",
 32 |     "# maptplotlib inline\n",
 33 |     "\n",
 34 |     "df_red = pd.read_csv('winequality-red.csv', sep = ';')\n",
 35 |     "df_white = pd.read_csv('winequality-white.csv',sep = ';')"
 36 |    ]
 37 |   },
 38 |   {
 39 |    "cell_type": "code",
 40 |    "execution_count": 2,
 41 |    "metadata": {},
 42 |    "outputs": [
 43 |     {
 44 |      "name": "stdout",
 45 |      "output_type": "stream",
 46 |      "text": [
 47 |       "<class 'pandas.core.frame.DataFrame'>\n",
 48 |       "RangeIndex: 1599 entries, 0 to 1598\n",
 49 |       "Data columns (total 12 columns):\n",
 50 |       "fixed acidity           1599 non-null float64\n",
 51 |       "volatile acidity        1599 non-null float64\n",
 52 |       "citric acid             1599 non-null float64\n",
 53 |       "residual sugar          1599 non-null float64\n",
 54 |       "chlorides               1599 non-null float64\n",
 55 |       "free sulfur dioxide     1599 non-null float64\n",
 56 |       "total sulfur dioxide    1599 non-null float64\n",
 57 |       "density                 1599 non-null float64\n",
 58 |       "pH                      1599 non-null float64\n",
 59 |       "sulphates               1599 non-null float64\n",
 60 |       "alcohol                 1599 non-null float64\n",
 61 |       "quality                 1599 non-null int64\n",
 62 |       "dtypes: float64(11), int64(1)\n",
 63 |       "memory usage: 150.0 KB\n",
 64 |       "<class 'pandas.core.frame.DataFrame'>\n",
 65 |       "RangeIndex: 4898 entries, 0 to 4897\n",
 66 |       "Data columns (total 12 columns):\n",
 67 |       "fixed acidity           4898 non-null float64\n",
 68 |       "volatile acidity        4898 non-null float64\n",
 69 |       "citric acid             4898 non-null float64\n",
 70 |       "residual sugar          4898 non-null float64\n",
 71 |       "chlorides               4898 non-null float64\n",
 72 |       "free sulfur dioxide     4898 non-null float64\n",
 73 |       "total sulfur dioxide    4898 non-null float64\n",
 74 |       "density                 4898 non-null float64\n",
 75 |       "pH                      4898 non-null float64\n",
 76 |       "sulphates               4898 non-null float64\n",
 77 |       "alcohol                 4898 non-null float64\n",
 78 |       "quality                 4898 non-null int64\n",
 79 |       "dtypes: float64(11), int64(1)\n",
 80 |       "memory usage: 459.3 KB\n"
 81 |      ]
 82 |     }
 83 |    ],
 84 |    "source": [
 85 |     "df_red.info()\n",
 86 |     "df_white.info()"
 87 |    ]
 88 |   },
 89 |   {
 90 |    "cell_type": "code",
 91 |    "execution_count": 3,
 92 |    "metadata": {},
 93 |    "outputs": [
 94 |     {
 95 |      "data": {
 96 |       "text/html": [
 97 |        "<div>\n",
 98 |        "<style>\n",
 99 |        "    .dataframe thead tr:only-child th {\n",
100 |        "        text-align: right;\n",
101 |        "    }\n",
102 |        "\n",
103 |        "    .dataframe thead th {\n",
104 |        "        text-align: left;\n",
105 |        "    }\n",
106 |        "\n",
107 |        "    .dataframe tbody tr th {\n",
108 |        "        vertical-align: top;\n",
109 |        "    }\n",
110 |        "</style>\n",
111 |        "<table border=\"1\" class=\"dataframe\">\n",
112 |        "  <thead>\n",
113 |        "    <tr style=\"text-align: right;\">\n",
114 |        "      <th></th>\n",
115 |        "      <th>fixed acidity</th>\n",
116 |        "      <th>volatile acidity</th>\n",
117 |        "      <th>citric acid</th>\n",
118 |        "      <th>residual sugar</th>\n",
119 |        "      <th>chlorides</th>\n",
120 |        "      <th>free sulfur dioxide</th>\n",
121 |        "      <th>total sulfur dioxide</th>\n",
122 |        "      <th>density</th>\n",
123 |        "      <th>pH</th>\n",
124 |        "      <th>sulphates</th>\n",
125 |        "      <th>alcohol</th>\n",
126 |        "      <th>quality</th>\n",
127 |        "    </tr>\n",
128 |        "  </thead>\n",
129 |        "  <tbody>\n",
130 |        "    <tr>\n",
131 |        "      <th>0</th>\n",
132 |        "      <td>7.4</td>\n",
133 |        "      <td>0.70</td>\n",
134 |        "      <td>0.00</td>\n",
135 |        "      <td>1.9</td>\n",
136 |        "      <td>0.076</td>\n",
137 |        "      <td>11.0</td>\n",
138 |        "      <td>34.0</td>\n",
139 |        "      <td>0.9978</td>\n",
140 |        "      <td>3.51</td>\n",
141 |        "      <td>0.56</td>\n",
142 |        "      <td>9.4</td>\n",
143 |        "      <td>5</td>\n",
144 |        "    </tr>\n",
145 |        "    <tr>\n",
146 |        "      <th>1</th>\n",
147 |        "      <td>7.8</td>\n",
148 |        "      <td>0.88</td>\n",
149 |        "      <td>0.00</td>\n",
150 |        "      <td>2.6</td>\n",
151 |        "      <td>0.098</td>\n",
152 |        "      <td>25.0</td>\n",
153 |        "      <td>67.0</td>\n",
154 |        "      <td>0.9968</td>\n",
155 |        "      <td>3.20</td>\n",
156 |        "      <td>0.68</td>\n",
157 |        "      <td>9.8</td>\n",
158 |        "      <td>5</td>\n",
159 |        "    </tr>\n",
160 |        "    <tr>\n",
161 |        "      <th>2</th>\n",
162 |        "      <td>7.8</td>\n",
163 |        "      <td>0.76</td>\n",
164 |        "      <td>0.04</td>\n",
165 |        "      <td>2.3</td>\n",
166 |        "      <td>0.092</td>\n",
167 |        "      <td>15.0</td>\n",
168 |        "      <td>54.0</td>\n",
169 |        "      <td>0.9970</td>\n",
170 |        "      <td>3.26</td>\n",
171 |        "      <td>0.65</td>\n",
172 |        "      <td>9.8</td>\n",
173 |        "      <td>5</td>\n",
174 |        "    </tr>\n",
175 |        "    <tr>\n",
176 |        "      <th>3</th>\n",
177 |        "      <td>11.2</td>\n",
178 |        "      <td>0.28</td>\n",
179 |        "      <td>0.56</td>\n",
180 |        "      <td>1.9</td>\n",
181 |        "      <td>0.075</td>\n",
182 |        "      <td>17.0</td>\n",
183 |        "      <td>60.0</td>\n",
184 |        "      <td>0.9980</td>\n",
185 |        "      <td>3.16</td>\n",
186 |        "      <td>0.58</td>\n",
187 |        "      <td>9.8</td>\n",
188 |        "      <td>6</td>\n",
189 |        "    </tr>\n",
190 |        "    <tr>\n",
191 |        "      <th>4</th>\n",
192 |        "      <td>7.4</td>\n",
193 |        "      <td>0.70</td>\n",
194 |        "      <td>0.00</td>\n",
195 |        "      <td>1.9</td>\n",
196 |        "      <td>0.076</td>\n",
197 |        "      <td>11.0</td>\n",
198 |        "      <td>34.0</td>\n",
199 |        "      <td>0.9978</td>\n",
200 |        "      <td>3.51</td>\n",
201 |        "      <td>0.56</td>\n",
202 |        "      <td>9.4</td>\n",
203 |        "      <td>5</td>\n",
204 |        "    </tr>\n",
205 |        "  </tbody>\n",
206 |        "</table>\n",
207 |        "</div>"
208 |       ],
209 |       "text/plain": [
210 |        "   fixed acidity  volatile acidity  citric acid  residual sugar  chlorides  \\\n",
211 |        "0            7.4              0.70         0.00             1.9      0.076   \n",
212 |        "1            7.8              0.88         0.00             2.6      0.098   \n",
213 |        "2            7.8              0.76         0.04             2.3      0.092   \n",
214 |        "3           11.2              0.28         0.56             1.9      0.075   \n",
215 |        "4            7.4              0.70         0.00             1.9      0.076   \n",
216 |        "\n",
217 |        "   free sulfur dioxide  total sulfur dioxide  density    pH  sulphates  \\\n",
218 |        "0                 11.0                  34.0   0.9978  3.51       0.56   \n",
219 |        "1                 25.0                  67.0   0.9968  3.20       0.68   \n",
220 |        "2                 15.0                  54.0   0.9970  3.26       0.65   \n",
221 |        "3                 17.0                  60.0   0.9980  3.16       0.58   \n",
222 |        "4                 11.0                  34.0   0.9978  3.51       0.56   \n",
223 |        "\n",
224 |        "   alcohol  quality  \n",
225 |        "0      9.4        5  \n",
226 |        "1      9.8        5  \n",
227 |        "2      9.8        5  \n",
228 |        "3      9.8        6  \n",
229 |        "4      9.4        5  "
230 |       ]
231 |      },
232 |      "execution_count": 3,
233 |      "metadata": {},
234 |      "output_type": "execute_result"
235 |     }
236 |    ],
237 |    "source": [
238 |     "df_red.head()"
239 |    ]
240 |   },
241 |   {
242 |    "cell_type": "code",
243 |    "execution_count": 4,
244 |    "metadata": {},
245 |    "outputs": [
246 |     {
247 |      "data": {
248 |       "text/plain": [
249 |        "240"
250 |       ]
251 |      },
252 |      "execution_count": 4,
253 |      "metadata": {},
254 |      "output_type": "execute_result"
255 |     }
256 |    ],
257 |    "source": [
258 |     "#number of duplicate rows\n",
259 |     "sum(df_red.duplicated())"
260 |    ]
261 |   },
262 |   {
263 |    "cell_type": "code",
264 |    "execution_count": 5,
265 |    "metadata": {},
266 |    "outputs": [
267 |     {
268 |      "data": {
269 |       "text/plain": [
270 |        "937"
271 |       ]
272 |      },
273 |      "execution_count": 5,
274 |      "metadata": {},
275 |      "output_type": "execute_result"
276 |     }
277 |    ],
278 |    "source": [
279 |     "#number of duplicate rows\n",
280 |     "sum(df_white.duplicated())"
281 |    ]
282 |   },
283 |   {
284 |    "cell_type": "code",
285 |    "execution_count": 7,
286 |    "metadata": {},
287 |    "outputs": [
288 |     {
289 |      "name": "stdout",
290 |      "output_type": "stream",
291 |      "text": [
292 |       "Unique values of quality for red wine are 6\n",
293 |       "unique values of quality for white wine are 7\n"
294 |      ]
295 |     }
296 |    ],
297 |    "source": [
298 |     "#number of unique values of quality\n",
299 |     "print(\"Unique values of quality for red wine are {}\".format(len(df_red.quality.unique())))\n",
300 |     "print(\"unique values of quality for white wine are {}\".format(len(df_white.quality.unique())))"
301 |    ]
302 |   },
303 |   {
304 |    "cell_type": "code",
305 |    "execution_count": 8,
306 |    "metadata": {},
307 |    "outputs": [
308 |     {
309 |      "data": {
310 |       "text/plain": [
311 |        "0.9967466791744833"
312 |       ]
313 |      },
314 |      "execution_count": 8,
315 |      "metadata": {},
316 |      "output_type": "execute_result"
317 |     }
318 |    ],
319 |    "source": [
320 |     "df_red['density'].mean()"
321 |    ]
322 |   },
323 |   {
324 |    "cell_type": "markdown",
325 |    "metadata": {},
326 |    "source": [
327 |     "# Questions and Answers to Quiz\n",
328 |     "\n",
329 |     "Answers derived by code calculations provided above\n",
330 |     "\n",
331 |     "- How many samples of red wine are there? 1599\n",
332 |     "- How many samples of white wine are there? 4898\n",
333 |     "- How many columns are in each dataset? 12\n",
334 |     "- Which features have missing values? None of these features have missing values\n",
335 |     "- How many duplicate rows are in the white wine dataset? 937\n",
336 |     "- Are duplicate rows in these datasets significant/ need to be dropped? Not necessarily\n",
337 |     "- How many unique values of quality are in the red wine dataset? 6\n",
338 |     "- How many unique values of quality are in the white wine dataset? 7\n",
339 |     "- What is the mean density in the red wine dataset? 0.996747\n",
340 |     "\n",
341 |     "\n"
342 |    ]
343 |   },
344 |   {
345 |    "cell_type": "code",
346 |    "execution_count": null,
347 |    "metadata": {
348 |     "collapsed": true
349 |    },
350 |    "outputs": [],
351 |    "source": []
352 |   }
353 |  ],
354 |  "metadata": {
355 |   "kernelspec": {
356 |    "display_name": "Python 3",
357 |    "language": "python",
358 |    "name": "python3"
359 |   },
360 |   "language_info": {
361 |    "codemirror_mode": {
362 |     "name": "ipython",
363 |     "version": 3
364 |    },
365 |    "file_extension": ".py",
366 |    "mimetype": "text/x-python",
367 |    "name": "python",
368 |    "nbconvert_exporter": "python",
369 |    "pygments_lexer": "ipython3",
370 |    "version": "3.6.2"
371 |   }
372 |  },
373 |  "nbformat": 4,
374 |  "nbformat_minor": 2
375 | }
376 | 


--------------------------------------------------------------------------------
/cleaning_column_labels.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {},
  6 |    "source": [
  7 |     "# Cleaning Column Labels\n",
  8 |     "Use `all_alpha_08.csv` and `all_alpha_18.csv`"
  9 |    ]
 10 |   },
 11 |   {
 12 |    "cell_type": "code",
 13 |    "execution_count": 1,
 14 |    "metadata": {
 15 |     "collapsed": true
 16 |    },
 17 |    "outputs": [],
 18 |    "source": [
 19 |     "import pandas as pd"
 20 |    ]
 21 |   },
 22 |   {
 23 |    "cell_type": "code",
 24 |    "execution_count": 2,
 25 |    "metadata": {
 26 |     "collapsed": true
 27 |    },
 28 |    "outputs": [],
 29 |    "source": [
 30 |     "# load datasets\n",
 31 |     "\n",
 32 |     "df_08 = pd.read_csv('all_alpha_08.csv')\n",
 33 |     "df_18 = pd.read_csv('all_alpha_18.csv')"
 34 |    ]
 35 |   },
 36 |   {
 37 |    "cell_type": "code",
 38 |    "execution_count": 3,
 39 |    "metadata": {},
 40 |    "outputs": [
 41 |     {
 42 |      "data": {
 43 |       "text/html": [
 44 |        "<div>\n",
 45 |        "<style>\n",
 46 |        "    .dataframe thead tr:only-child th {\n",
 47 |        "        text-align: right;\n",
 48 |        "    }\n",
 49 |        "\n",
 50 |        "    .dataframe thead th {\n",
 51 |        "        text-align: left;\n",
 52 |        "    }\n",
 53 |        "\n",
 54 |        "    .dataframe tbody tr th {\n",
 55 |        "        vertical-align: top;\n",
 56 |        "    }\n",
 57 |        "</style>\n",
 58 |        "<table border=\"1\" class=\"dataframe\">\n",
 59 |        "  <thead>\n",
 60 |        "    <tr style=\"text-align: right;\">\n",
 61 |        "      <th></th>\n",
 62 |        "      <th>Model</th>\n",
 63 |        "      <th>Displ</th>\n",
 64 |        "      <th>Cyl</th>\n",
 65 |        "      <th>Trans</th>\n",
 66 |        "      <th>Drive</th>\n",
 67 |        "      <th>Fuel</th>\n",
 68 |        "      <th>Sales Area</th>\n",
 69 |        "      <th>Stnd</th>\n",
 70 |        "      <th>Underhood ID</th>\n",
 71 |        "      <th>Veh Class</th>\n",
 72 |        "      <th>Air Pollution Score</th>\n",
 73 |        "      <th>FE Calc Appr</th>\n",
 74 |        "      <th>City MPG</th>\n",
 75 |        "      <th>Hwy MPG</th>\n",
 76 |        "      <th>Cmb MPG</th>\n",
 77 |        "      <th>Unadj Cmb MPG</th>\n",
 78 |        "      <th>Greenhouse Gas Score</th>\n",
 79 |        "      <th>SmartWay</th>\n",
 80 |        "    </tr>\n",
 81 |        "  </thead>\n",
 82 |        "  <tbody>\n",
 83 |        "    <tr>\n",
 84 |        "      <th>0</th>\n",
 85 |        "      <td>ACURA MDX</td>\n",
 86 |        "      <td>3.7</td>\n",
 87 |        "      <td>(6 cyl)</td>\n",
 88 |        "      <td>Auto-S5</td>\n",
 89 |        "      <td>4WD</td>\n",
 90 |        "      <td>Gasoline</td>\n",
 91 |        "      <td>CA</td>\n",
 92 |        "      <td>U2</td>\n",
 93 |        "      <td>8HNXT03.7PKR</td>\n",
 94 |        "      <td>SUV</td>\n",
 95 |        "      <td>7</td>\n",
 96 |        "      <td>Drv</td>\n",
 97 |        "      <td>15</td>\n",
 98 |        "      <td>20</td>\n",
 99 |        "      <td>17</td>\n",
100 |        "      <td>22.0527</td>\n",
101 |        "      <td>4</td>\n",
102 |        "      <td>no</td>\n",
103 |        "    </tr>\n",
104 |        "  </tbody>\n",
105 |        "</table>\n",
106 |        "</div>"
107 |       ],
108 |       "text/plain": [
109 |        "       Model  Displ      Cyl    Trans Drive      Fuel Sales Area Stnd  \\\n",
110 |        "0  ACURA MDX    3.7  (6 cyl)  Auto-S5   4WD  Gasoline         CA   U2   \n",
111 |        "\n",
112 |        "   Underhood ID Veh Class Air Pollution Score FE Calc Appr City MPG Hwy MPG  \\\n",
113 |        "0  8HNXT03.7PKR       SUV                   7          Drv       15      20   \n",
114 |        "\n",
115 |        "  Cmb MPG  Unadj Cmb MPG Greenhouse Gas Score SmartWay  \n",
116 |        "0      17        22.0527                    4       no  "
117 |       ]
118 |      },
119 |      "execution_count": 3,
120 |      "metadata": {},
121 |      "output_type": "execute_result"
122 |     }
123 |    ],
124 |    "source": [
125 |     "# view 2008 dataset\n",
126 |     "df_08.head(1)"
127 |    ]
128 |   },
129 |   {
130 |    "cell_type": "code",
131 |    "execution_count": 4,
132 |    "metadata": {},
133 |    "outputs": [
134 |     {
135 |      "data": {
136 |       "text/html": [
137 |        "<div>\n",
138 |        "<style>\n",
139 |        "    .dataframe thead tr:only-child th {\n",
140 |        "        text-align: right;\n",
141 |        "    }\n",
142 |        "\n",
143 |        "    .dataframe thead th {\n",
144 |        "        text-align: left;\n",
145 |        "    }\n",
146 |        "\n",
147 |        "    .dataframe tbody tr th {\n",
148 |        "        vertical-align: top;\n",
149 |        "    }\n",
150 |        "</style>\n",
151 |        "<table border=\"1\" class=\"dataframe\">\n",
152 |        "  <thead>\n",
153 |        "    <tr style=\"text-align: right;\">\n",
154 |        "      <th></th>\n",
155 |        "      <th>Model</th>\n",
156 |        "      <th>Displ</th>\n",
157 |        "      <th>Cyl</th>\n",
158 |        "      <th>Trans</th>\n",
159 |        "      <th>Drive</th>\n",
160 |        "      <th>Fuel</th>\n",
161 |        "      <th>Cert Region</th>\n",
162 |        "      <th>Stnd</th>\n",
163 |        "      <th>Stnd Description</th>\n",
164 |        "      <th>Underhood ID</th>\n",
165 |        "      <th>Veh Class</th>\n",
166 |        "      <th>Air Pollution Score</th>\n",
167 |        "      <th>City MPG</th>\n",
168 |        "      <th>Hwy MPG</th>\n",
169 |        "      <th>Cmb MPG</th>\n",
170 |        "      <th>Greenhouse Gas Score</th>\n",
171 |        "      <th>SmartWay</th>\n",
172 |        "      <th>Comb CO2</th>\n",
173 |        "    </tr>\n",
174 |        "  </thead>\n",
175 |        "  <tbody>\n",
176 |        "    <tr>\n",
177 |        "      <th>0</th>\n",
178 |        "      <td>ACURA RDX</td>\n",
179 |        "      <td>3.5</td>\n",
180 |        "      <td>6.0</td>\n",
181 |        "      <td>SemiAuto-6</td>\n",
182 |        "      <td>2WD</td>\n",
183 |        "      <td>Gasoline</td>\n",
184 |        "      <td>FA</td>\n",
185 |        "      <td>T3B125</td>\n",
186 |        "      <td>Federal Tier 3 Bin 125</td>\n",
187 |        "      <td>JHNXT03.5GV3</td>\n",
188 |        "      <td>small SUV</td>\n",
189 |        "      <td>3</td>\n",
190 |        "      <td>20</td>\n",
191 |        "      <td>28</td>\n",
192 |        "      <td>23</td>\n",
193 |        "      <td>5</td>\n",
194 |        "      <td>No</td>\n",
195 |        "      <td>386</td>\n",
196 |        "    </tr>\n",
197 |        "  </tbody>\n",
198 |        "</table>\n",
199 |        "</div>"
200 |       ],
201 |       "text/plain": [
202 |        "       Model  Displ  Cyl       Trans Drive      Fuel Cert Region    Stnd  \\\n",
203 |        "0  ACURA RDX    3.5  6.0  SemiAuto-6   2WD  Gasoline          FA  T3B125   \n",
204 |        "\n",
205 |        "         Stnd Description  Underhood ID  Veh Class  Air Pollution Score  \\\n",
206 |        "0  Federal Tier 3 Bin 125  JHNXT03.5GV3  small SUV                    3   \n",
207 |        "\n",
208 |        "  City MPG Hwy MPG Cmb MPG  Greenhouse Gas Score SmartWay Comb CO2  \n",
209 |        "0       20      28      23                     5       No      386  "
210 |       ]
211 |      },
212 |      "execution_count": 4,
213 |      "metadata": {},
214 |      "output_type": "execute_result"
215 |     }
216 |    ],
217 |    "source": [
218 |     "# view 2018 dataset\n",
219 |     "df_18.head(1)"
220 |    ]
221 |   },
222 |   {
223 |    "cell_type": "markdown",
224 |    "metadata": {},
225 |    "source": [
226 |     "### Drop Extraneous Columns"
227 |    ]
228 |   },
229 |   {
230 |    "cell_type": "code",
231 |    "execution_count": 5,
232 |    "metadata": {},
233 |    "outputs": [
234 |     {
235 |      "data": {
236 |       "text/html": [
237 |        "<div>\n",
238 |        "<style>\n",
239 |        "    .dataframe thead tr:only-child th {\n",
240 |        "        text-align: right;\n",
241 |        "    }\n",
242 |        "\n",
243 |        "    .dataframe thead th {\n",
244 |        "        text-align: left;\n",
245 |        "    }\n",
246 |        "\n",
247 |        "    .dataframe tbody tr th {\n",
248 |        "        vertical-align: top;\n",
249 |        "    }\n",
250 |        "</style>\n",
251 |        "<table border=\"1\" class=\"dataframe\">\n",
252 |        "  <thead>\n",
253 |        "    <tr style=\"text-align: right;\">\n",
254 |        "      <th></th>\n",
255 |        "      <th>Model</th>\n",
256 |        "      <th>Displ</th>\n",
257 |        "      <th>Cyl</th>\n",
258 |        "      <th>Trans</th>\n",
259 |        "      <th>Drive</th>\n",
260 |        "      <th>Fuel</th>\n",
261 |        "      <th>Sales Area</th>\n",
262 |        "      <th>Veh Class</th>\n",
263 |        "      <th>Air Pollution Score</th>\n",
264 |        "      <th>City MPG</th>\n",
265 |        "      <th>Hwy MPG</th>\n",
266 |        "      <th>Cmb MPG</th>\n",
267 |        "      <th>Greenhouse Gas Score</th>\n",
268 |        "      <th>SmartWay</th>\n",
269 |        "    </tr>\n",
270 |        "  </thead>\n",
271 |        "  <tbody>\n",
272 |        "    <tr>\n",
273 |        "      <th>0</th>\n",
274 |        "      <td>ACURA MDX</td>\n",
275 |        "      <td>3.7</td>\n",
276 |        "      <td>(6 cyl)</td>\n",
277 |        "      <td>Auto-S5</td>\n",
278 |        "      <td>4WD</td>\n",
279 |        "      <td>Gasoline</td>\n",
280 |        "      <td>CA</td>\n",
281 |        "      <td>SUV</td>\n",
282 |        "      <td>7</td>\n",
283 |        "      <td>15</td>\n",
284 |        "      <td>20</td>\n",
285 |        "      <td>17</td>\n",
286 |        "      <td>4</td>\n",
287 |        "      <td>no</td>\n",
288 |        "    </tr>\n",
289 |        "  </tbody>\n",
290 |        "</table>\n",
291 |        "</div>"
292 |       ],
293 |       "text/plain": [
294 |        "       Model  Displ      Cyl    Trans Drive      Fuel Sales Area Veh Class  \\\n",
295 |        "0  ACURA MDX    3.7  (6 cyl)  Auto-S5   4WD  Gasoline         CA       SUV   \n",
296 |        "\n",
297 |        "  Air Pollution Score City MPG Hwy MPG Cmb MPG Greenhouse Gas Score SmartWay  \n",
298 |        "0                   7       15      20      17                    4       no  "
299 |       ]
300 |      },
301 |      "execution_count": 5,
302 |      "metadata": {},
303 |      "output_type": "execute_result"
304 |     }
305 |    ],
306 |    "source": [
307 |     "# drop columns from 2008 dataset\n",
308 |     "df_08.drop(['Stnd', 'Underhood ID', 'FE Calc Appr', 'Unadj Cmb MPG'], axis=1, inplace=True)\n",
309 |     "\n",
310 |     "# confirm changes\n",
311 |     "df_08.head(1)"
312 |    ]
313 |   },
314 |   {
315 |    "cell_type": "code",
316 |    "execution_count": 6,
317 |    "metadata": {},
318 |    "outputs": [
319 |     {
320 |      "data": {
321 |       "text/html": [
322 |        "<div>\n",
323 |        "<style>\n",
324 |        "    .dataframe thead tr:only-child th {\n",
325 |        "        text-align: right;\n",
326 |        "    }\n",
327 |        "\n",
328 |        "    .dataframe thead th {\n",
329 |        "        text-align: left;\n",
330 |        "    }\n",
331 |        "\n",
332 |        "    .dataframe tbody tr th {\n",
333 |        "        vertical-align: top;\n",
334 |        "    }\n",
335 |        "</style>\n",
336 |        "<table border=\"1\" class=\"dataframe\">\n",
337 |        "  <thead>\n",
338 |        "    <tr style=\"text-align: right;\">\n",
339 |        "      <th></th>\n",
340 |        "      <th>Model</th>\n",
341 |        "      <th>Displ</th>\n",
342 |        "      <th>Cyl</th>\n",
343 |        "      <th>Trans</th>\n",
344 |        "      <th>Drive</th>\n",
345 |        "      <th>Fuel</th>\n",
346 |        "      <th>Cert Region</th>\n",
347 |        "      <th>Veh Class</th>\n",
348 |        "      <th>Air Pollution Score</th>\n",
349 |        "      <th>City MPG</th>\n",
350 |        "      <th>Hwy MPG</th>\n",
351 |        "      <th>Cmb MPG</th>\n",
352 |        "      <th>Greenhouse Gas Score</th>\n",
353 |        "      <th>SmartWay</th>\n",
354 |        "    </tr>\n",
355 |        "  </thead>\n",
356 |        "  <tbody>\n",
357 |        "    <tr>\n",
358 |        "      <th>0</th>\n",
359 |        "      <td>ACURA RDX</td>\n",
360 |        "      <td>3.5</td>\n",
361 |        "      <td>6.0</td>\n",
362 |        "      <td>SemiAuto-6</td>\n",
363 |        "      <td>2WD</td>\n",
364 |        "      <td>Gasoline</td>\n",
365 |        "      <td>FA</td>\n",
366 |        "      <td>small SUV</td>\n",
367 |        "      <td>3</td>\n",
368 |        "      <td>20</td>\n",
369 |        "      <td>28</td>\n",
370 |        "      <td>23</td>\n",
371 |        "      <td>5</td>\n",
372 |        "      <td>No</td>\n",
373 |        "    </tr>\n",
374 |        "    <tr>\n",
375 |        "      <th>1</th>\n",
376 |        "      <td>ACURA RDX</td>\n",
377 |        "      <td>3.5</td>\n",
378 |        "      <td>6.0</td>\n",
379 |        "      <td>SemiAuto-6</td>\n",
380 |        "      <td>2WD</td>\n",
381 |        "      <td>Gasoline</td>\n",
382 |        "      <td>CA</td>\n",
383 |        "      <td>small SUV</td>\n",
384 |        "      <td>3</td>\n",
385 |        "      <td>20</td>\n",
386 |        "      <td>28</td>\n",
387 |        "      <td>23</td>\n",
388 |        "      <td>5</td>\n",
389 |        "      <td>No</td>\n",
390 |        "    </tr>\n",
391 |        "    <tr>\n",
392 |        "      <th>2</th>\n",
393 |        "      <td>ACURA RDX</td>\n",
394 |        "      <td>3.5</td>\n",
395 |        "      <td>6.0</td>\n",
396 |        "      <td>SemiAuto-6</td>\n",
397 |        "      <td>4WD</td>\n",
398 |        "      <td>Gasoline</td>\n",
399 |        "      <td>FA</td>\n",
400 |        "      <td>small SUV</td>\n",
401 |        "      <td>3</td>\n",
402 |        "      <td>19</td>\n",
403 |        "      <td>27</td>\n",
404 |        "      <td>22</td>\n",
405 |        "      <td>4</td>\n",
406 |        "      <td>No</td>\n",
407 |        "    </tr>\n",
408 |        "    <tr>\n",
409 |        "      <th>3</th>\n",
410 |        "      <td>ACURA RDX</td>\n",
411 |        "      <td>3.5</td>\n",
412 |        "      <td>6.0</td>\n",
413 |        "      <td>SemiAuto-6</td>\n",
414 |        "      <td>4WD</td>\n",
415 |        "      <td>Gasoline</td>\n",
416 |        "      <td>CA</td>\n",
417 |        "      <td>small SUV</td>\n",
418 |        "      <td>3</td>\n",
419 |        "      <td>19</td>\n",
420 |        "      <td>27</td>\n",
421 |        "      <td>22</td>\n",
422 |        "      <td>4</td>\n",
423 |        "      <td>No</td>\n",
424 |        "    </tr>\n",
425 |        "    <tr>\n",
426 |        "      <th>4</th>\n",
427 |        "      <td>ACURA TLX</td>\n",
428 |        "      <td>2.4</td>\n",
429 |        "      <td>4.0</td>\n",
430 |        "      <td>AMS-8</td>\n",
431 |        "      <td>2WD</td>\n",
432 |        "      <td>Gasoline</td>\n",
433 |        "      <td>CA</td>\n",
434 |        "      <td>small car</td>\n",
435 |        "      <td>3</td>\n",
436 |        "      <td>23</td>\n",
437 |        "      <td>33</td>\n",
438 |        "      <td>27</td>\n",
439 |        "      <td>6</td>\n",
440 |        "      <td>No</td>\n",
441 |        "    </tr>\n",
442 |        "  </tbody>\n",
443 |        "</table>\n",
444 |        "</div>"
445 |       ],
446 |       "text/plain": [
447 |        "       Model  Displ  Cyl       Trans Drive      Fuel Cert Region  Veh Class  \\\n",
448 |        "0  ACURA RDX    3.5  6.0  SemiAuto-6   2WD  Gasoline          FA  small SUV   \n",
449 |        "1  ACURA RDX    3.5  6.0  SemiAuto-6   2WD  Gasoline          CA  small SUV   \n",
450 |        "2  ACURA RDX    3.5  6.0  SemiAuto-6   4WD  Gasoline          FA  small SUV   \n",
451 |        "3  ACURA RDX    3.5  6.0  SemiAuto-6   4WD  Gasoline          CA  small SUV   \n",
452 |        "4  ACURA TLX    2.4  4.0       AMS-8   2WD  Gasoline          CA  small car   \n",
453 |        "\n",
454 |        "   Air Pollution Score City MPG Hwy MPG Cmb MPG  Greenhouse Gas Score SmartWay  \n",
455 |        "0                    3       20      28      23                     5       No  \n",
456 |        "1                    3       20      28      23                     5       No  \n",
457 |        "2                    3       19      27      22                     4       No  \n",
458 |        "3                    3       19      27      22                     4       No  \n",
459 |        "4                    3       23      33      27                     6       No  "
460 |       ]
461 |      },
462 |      "execution_count": 6,
463 |      "metadata": {},
464 |      "output_type": "execute_result"
465 |     }
466 |    ],
467 |    "source": [
468 |     "# drop columns from 2018 dataset\n",
469 |     "df_18.drop(['Stnd', 'Stnd Description', 'Underhood ID', 'Comb CO2'], axis=1, inplace=True)\n",
470 |     "\n",
471 |     "# confirm changes\n",
472 |     "df_18.head()"
473 |    ]
474 |   },
475 |   {
476 |    "cell_type": "markdown",
477 |    "metadata": {},
478 |    "source": [
479 |     "### Rename Columns"
480 |    ]
481 |   },
482 |   {
483 |    "cell_type": "code",
484 |    "execution_count": 17,
485 |    "metadata": {
486 |     "scrolled": false
487 |    },
488 |    "outputs": [
489 |     {
490 |      "data": {
491 |       "text/html": [
492 |        "<div>\n",
493 |        "<style>\n",
494 |        "    .dataframe thead tr:only-child th {\n",
495 |        "        text-align: right;\n",
496 |        "    }\n",
497 |        "\n",
498 |        "    .dataframe thead th {\n",
499 |        "        text-align: left;\n",
500 |        "    }\n",
501 |        "\n",
502 |        "    .dataframe tbody tr th {\n",
503 |        "        vertical-align: top;\n",
504 |        "    }\n",
505 |        "</style>\n",
506 |        "<table border=\"1\" class=\"dataframe\">\n",
507 |        "  <thead>\n",
508 |        "    <tr style=\"text-align: right;\">\n",
509 |        "      <th></th>\n",
510 |        "      <th>model</th>\n",
511 |        "      <th>displ</th>\n",
512 |        "      <th>cyl</th>\n",
513 |        "      <th>trans</th>\n",
514 |        "      <th>drive</th>\n",
515 |        "      <th>fuel</th>\n",
516 |        "      <th>Cert Region</th>\n",
517 |        "      <th>veh_class</th>\n",
518 |        "      <th>air_pollution_score</th>\n",
519 |        "      <th>city_mpg</th>\n",
520 |        "      <th>hwy_mpg</th>\n",
521 |        "      <th>cmb_mpg</th>\n",
522 |        "      <th>greenhouse_gas_score</th>\n",
523 |        "      <th>smartway</th>\n",
524 |        "    </tr>\n",
525 |        "  </thead>\n",
526 |        "  <tbody>\n",
527 |        "    <tr>\n",
528 |        "      <th>0</th>\n",
529 |        "      <td>ACURA MDX</td>\n",
530 |        "      <td>3.7</td>\n",
531 |        "      <td>(6 cyl)</td>\n",
532 |        "      <td>Auto-S5</td>\n",
533 |        "      <td>4WD</td>\n",
534 |        "      <td>Gasoline</td>\n",
535 |        "      <td>CA</td>\n",
536 |        "      <td>SUV</td>\n",
537 |        "      <td>7</td>\n",
538 |        "      <td>15</td>\n",
539 |        "      <td>20</td>\n",
540 |        "      <td>17</td>\n",
541 |        "      <td>4</td>\n",
542 |        "      <td>no</td>\n",
543 |        "    </tr>\n",
544 |        "  </tbody>\n",
545 |        "</table>\n",
546 |        "</div>"
547 |       ],
548 |       "text/plain": [
549 |        "       model  displ      cyl    trans drive      fuel Cert Region veh_class  \\\n",
550 |        "0  ACURA MDX    3.7  (6 cyl)  Auto-S5   4WD  Gasoline          CA       SUV   \n",
551 |        "\n",
552 |        "  air_pollution_score city_mpg hwy_mpg cmb_mpg greenhouse_gas_score smartway  \n",
553 |        "0                   7       15      20      17                    4       no  "
554 |       ]
555 |      },
556 |      "execution_count": 17,
557 |      "metadata": {},
558 |      "output_type": "execute_result"
559 |     }
560 |    ],
561 |    "source": [
562 |     "# rename Sales Area to Cert Region\n",
563 |     "names_cols = list(df_08.columns.values)\n",
564 |     "names_cols[6] = 'Cert Region'\n",
565 |     "df_08.columns = names_cols\n",
566 |     "\n",
567 |     "# confirm changes\n",
568 |     "df_08.head(1)"
569 |    ]
570 |   },
571 |   {
572 |    "cell_type": "code",
573 |    "execution_count": 18,
574 |    "metadata": {},
575 |    "outputs": [
576 |     {
577 |      "data": {
578 |       "text/html": [
579 |        "<div>\n",
580 |        "<style>\n",
581 |        "    .dataframe thead tr:only-child th {\n",
582 |        "        text-align: right;\n",
583 |        "    }\n",
584 |        "\n",
585 |        "    .dataframe thead th {\n",
586 |        "        text-align: left;\n",
587 |        "    }\n",
588 |        "\n",
589 |        "    .dataframe tbody tr th {\n",
590 |        "        vertical-align: top;\n",
591 |        "    }\n",
592 |        "</style>\n",
593 |        "<table border=\"1\" class=\"dataframe\">\n",
594 |        "  <thead>\n",
595 |        "    <tr style=\"text-align: right;\">\n",
596 |        "      <th></th>\n",
597 |        "      <th>model</th>\n",
598 |        "      <th>displ</th>\n",
599 |        "      <th>cyl</th>\n",
600 |        "      <th>trans</th>\n",
601 |        "      <th>drive</th>\n",
602 |        "      <th>fuel</th>\n",
603 |        "      <th>cert_region</th>\n",
604 |        "      <th>veh_class</th>\n",
605 |        "      <th>air_pollution_score</th>\n",
606 |        "      <th>city_mpg</th>\n",
607 |        "      <th>hwy_mpg</th>\n",
608 |        "      <th>cmb_mpg</th>\n",
609 |        "      <th>greenhouse_gas_score</th>\n",
610 |        "      <th>smartway</th>\n",
611 |        "    </tr>\n",
612 |        "  </thead>\n",
613 |        "  <tbody>\n",
614 |        "    <tr>\n",
615 |        "      <th>0</th>\n",
616 |        "      <td>ACURA MDX</td>\n",
617 |        "      <td>3.7</td>\n",
618 |        "      <td>(6 cyl)</td>\n",
619 |        "      <td>Auto-S5</td>\n",
620 |        "      <td>4WD</td>\n",
621 |        "      <td>Gasoline</td>\n",
622 |        "      <td>CA</td>\n",
623 |        "      <td>SUV</td>\n",
624 |        "      <td>7</td>\n",
625 |        "      <td>15</td>\n",
626 |        "      <td>20</td>\n",
627 |        "      <td>17</td>\n",
628 |        "      <td>4</td>\n",
629 |        "      <td>no</td>\n",
630 |        "    </tr>\n",
631 |        "  </tbody>\n",
632 |        "</table>\n",
633 |        "</div>"
634 |       ],
635 |       "text/plain": [
636 |        "       model  displ      cyl    trans drive      fuel cert_region veh_class  \\\n",
637 |        "0  ACURA MDX    3.7  (6 cyl)  Auto-S5   4WD  Gasoline          CA       SUV   \n",
638 |        "\n",
639 |        "  air_pollution_score city_mpg hwy_mpg cmb_mpg greenhouse_gas_score smartway  \n",
640 |        "0                   7       15      20      17                    4       no  "
641 |       ]
642 |      },
643 |      "execution_count": 18,
644 |      "metadata": {},
645 |      "output_type": "execute_result"
646 |     }
647 |    ],
648 |    "source": [
649 |     "# replace spaces with underscores and lowercase labels for 2008 dataset\n",
650 |     "df_08.rename(columns=lambda x: x.strip().lower().replace(\" \", \"_\"), inplace=True)\n",
651 |     "\n",
652 |     "# confirm changes\n",
653 |     "df_08.head(1)"
654 |    ]
655 |   },
656 |   {
657 |    "cell_type": "code",
658 |    "execution_count": 19,
659 |    "metadata": {},
660 |    "outputs": [
661 |     {
662 |      "data": {
663 |       "text/html": [
664 |        "<div>\n",
665 |        "<style>\n",
666 |        "    .dataframe thead tr:only-child th {\n",
667 |        "        text-align: right;\n",
668 |        "    }\n",
669 |        "\n",
670 |        "    .dataframe thead th {\n",
671 |        "        text-align: left;\n",
672 |        "    }\n",
673 |        "\n",
674 |        "    .dataframe tbody tr th {\n",
675 |        "        vertical-align: top;\n",
676 |        "    }\n",
677 |        "</style>\n",
678 |        "<table border=\"1\" class=\"dataframe\">\n",
679 |        "  <thead>\n",
680 |        "    <tr style=\"text-align: right;\">\n",
681 |        "      <th></th>\n",
682 |        "      <th>model</th>\n",
683 |        "      <th>displ</th>\n",
684 |        "      <th>cyl</th>\n",
685 |        "      <th>trans</th>\n",
686 |        "      <th>drive</th>\n",
687 |        "      <th>fuel</th>\n",
688 |        "      <th>cert_region</th>\n",
689 |        "      <th>veh_class</th>\n",
690 |        "      <th>air_pollution_score</th>\n",
691 |        "      <th>city_mpg</th>\n",
692 |        "      <th>hwy_mpg</th>\n",
693 |        "      <th>cmb_mpg</th>\n",
694 |        "      <th>greenhouse_gas_score</th>\n",
695 |        "      <th>smartway</th>\n",
696 |        "    </tr>\n",
697 |        "  </thead>\n",
698 |        "  <tbody>\n",
699 |        "    <tr>\n",
700 |        "      <th>0</th>\n",
701 |        "      <td>ACURA RDX</td>\n",
702 |        "      <td>3.5</td>\n",
703 |        "      <td>6.0</td>\n",
704 |        "      <td>SemiAuto-6</td>\n",
705 |        "      <td>2WD</td>\n",
706 |        "      <td>Gasoline</td>\n",
707 |        "      <td>FA</td>\n",
708 |        "      <td>small SUV</td>\n",
709 |        "      <td>3</td>\n",
710 |        "      <td>20</td>\n",
711 |        "      <td>28</td>\n",
712 |        "      <td>23</td>\n",
713 |        "      <td>5</td>\n",
714 |        "      <td>No</td>\n",
715 |        "    </tr>\n",
716 |        "  </tbody>\n",
717 |        "</table>\n",
718 |        "</div>"
719 |       ],
720 |       "text/plain": [
721 |        "       model  displ  cyl       trans drive      fuel cert_region  veh_class  \\\n",
722 |        "0  ACURA RDX    3.5  6.0  SemiAuto-6   2WD  Gasoline          FA  small SUV   \n",
723 |        "\n",
724 |        "   air_pollution_score city_mpg hwy_mpg cmb_mpg  greenhouse_gas_score smartway  \n",
725 |        "0                    3       20      28      23                     5       No  "
726 |       ]
727 |      },
728 |      "execution_count": 19,
729 |      "metadata": {},
730 |      "output_type": "execute_result"
731 |     }
732 |    ],
733 |    "source": [
734 |     "# replace spaces with underscores and lowercase labels for 2018 dataset\n",
735 |     "df_18.rename(columns=lambda x: x.strip().lower().replace(\" \", \"_\"), inplace=True)\n",
736 |     "\n",
737 |     "# confirm changes\n",
738 |     "df_18.head(1)"
739 |    ]
740 |   },
741 |   {
742 |    "cell_type": "code",
743 |    "execution_count": 20,
744 |    "metadata": {},
745 |    "outputs": [
746 |     {
747 |      "data": {
748 |       "text/plain": [
749 |        "array([ True,  True,  True,  True,  True,  True,  True,  True,  True,\n",
750 |        "        True,  True,  True,  True,  True], dtype=bool)"
751 |       ]
752 |      },
753 |      "execution_count": 20,
754 |      "metadata": {},
755 |      "output_type": "execute_result"
756 |     }
757 |    ],
758 |    "source": [
759 |     "# confirm column labels for 2008 and 2018 datasets are identical\n",
760 |     "df_08.columns == df_18.columns"
761 |    ]
762 |   },
763 |   {
764 |    "cell_type": "code",
765 |    "execution_count": 21,
766 |    "metadata": {},
767 |    "outputs": [
768 |     {
769 |      "data": {
770 |       "text/plain": [
771 |        "True"
772 |       ]
773 |      },
774 |      "execution_count": 21,
775 |      "metadata": {},
776 |      "output_type": "execute_result"
777 |     }
778 |    ],
779 |    "source": [
780 |     "# make sure they're all identical like this\n",
781 |     "(df_08.columns == df_18.columns).all()"
782 |    ]
783 |   },
784 |   {
785 |    "cell_type": "code",
786 |    "execution_count": 22,
787 |    "metadata": {
788 |     "collapsed": true
789 |    },
790 |    "outputs": [],
791 |    "source": [
792 |     "# save new datasets for next section\n",
793 |     "df_08.to_csv('data_08.csv', index=False)\n",
794 |     "df_18.to_csv('data_18.csv', index=False)"
795 |    ]
796 |   },
797 |   {
798 |    "cell_type": "code",
799 |    "execution_count": null,
800 |    "metadata": {
801 |     "collapsed": true
802 |    },
803 |    "outputs": [],
804 |    "source": []
805 |   }
806 |  ],
807 |  "metadata": {
808 |   "kernelspec": {
809 |    "display_name": "Python 3",
810 |    "language": "python",
811 |    "name": "python3"
812 |   },
813 |   "language_info": {
814 |    "codemirror_mode": {
815 |     "name": "ipython",
816 |     "version": 3
817 |    },
818 |    "file_extension": ".py",
819 |    "mimetype": "text/x-python",
820 |    "name": "python",
821 |    "nbconvert_exporter": "python",
822 |    "pygments_lexer": "ipython3",
823 |    "version": "3.6.1"
824 |   }
825 |  },
826 |  "nbformat": 4,
827 |  "nbformat_minor": 2
828 | }
829 | 


--------------------------------------------------------------------------------
/cleaning_practice.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {},
  6 |    "source": [
  7 |     "# Cleaning Practice\n",
  8 |     "Let's first practice handling missing values and duplicate data with `cancer_data_means.csv`."
  9 |    ]
 10 |   },
 11 |   {
 12 |    "cell_type": "code",
 13 |    "execution_count": 2,
 14 |    "metadata": {},
 15 |    "outputs": [
 16 |     {
 17 |      "name": "stdout",
 18 |      "output_type": "stream",
 19 |      "text": [
 20 |       "<class 'pandas.core.frame.DataFrame'>\n",
 21 |       "RangeIndex: 569 entries, 0 to 568\n",
 22 |       "Data columns (total 11 columns):\n",
 23 |       "id                     569 non-null int64\n",
 24 |       "diagnosis              569 non-null object\n",
 25 |       "radius_mean            569 non-null float64\n",
 26 |       "texture_mean           548 non-null float64\n",
 27 |       "perimeter_mean         569 non-null float64\n",
 28 |       "area_mean              569 non-null float64\n",
 29 |       "smoothness_mean        521 non-null float64\n",
 30 |       "compactness_mean       569 non-null float64\n",
 31 |       "concavity_mean         569 non-null float64\n",
 32 |       "concave_points_mean    569 non-null float64\n",
 33 |       "symmetry_mean          504 non-null float64\n",
 34 |       "dtypes: float64(9), int64(1), object(1)\n",
 35 |       "memory usage: 49.0+ KB\n"
 36 |      ]
 37 |     }
 38 |    ],
 39 |    "source": [
 40 |     "# import pandas and load cancer data\n",
 41 |     "import pandas as pd\n",
 42 |     "\n",
 43 |     "df_cancer = pd.read_csv('cancer_data_means.csv')\n",
 44 |     "\n",
 45 |     "# check which columns have missing values with info()\n",
 46 |     "df_cancer.info()"
 47 |    ]
 48 |   },
 49 |   {
 50 |    "cell_type": "code",
 51 |    "execution_count": 3,
 52 |    "metadata": {},
 53 |    "outputs": [
 54 |     {
 55 |      "name": "stdout",
 56 |      "output_type": "stream",
 57 |      "text": [
 58 |       "<class 'pandas.core.frame.DataFrame'>\n",
 59 |       "RangeIndex: 569 entries, 0 to 568\n",
 60 |       "Data columns (total 11 columns):\n",
 61 |       "id                     569 non-null int64\n",
 62 |       "diagnosis              569 non-null object\n",
 63 |       "radius_mean            569 non-null float64\n",
 64 |       "texture_mean           569 non-null float64\n",
 65 |       "perimeter_mean         569 non-null float64\n",
 66 |       "area_mean              569 non-null float64\n",
 67 |       "smoothness_mean        521 non-null float64\n",
 68 |       "compactness_mean       569 non-null float64\n",
 69 |       "concavity_mean         569 non-null float64\n",
 70 |       "concave_points_mean    569 non-null float64\n",
 71 |       "symmetry_mean          504 non-null float64\n",
 72 |       "dtypes: float64(9), int64(1), object(1)\n",
 73 |       "memory usage: 49.0+ KB\n"
 74 |      ]
 75 |     }
 76 |    ],
 77 |    "source": [
 78 |     "# use means to fill in missing values\n",
 79 |     "mean_texture = df_cancer['texture_mean'].mean()\n",
 80 |     "df_cancer['texture_mean'].fillna(mean_texture, inplace = True)\n",
 81 |     "\n",
 82 |     "# confirm your correction with info()\n",
 83 |     "df_cancer.info(0)"
 84 |    ]
 85 |   },
 86 |   {
 87 |    "cell_type": "code",
 88 |    "execution_count": 4,
 89 |    "metadata": {},
 90 |    "outputs": [
 91 |     {
 92 |      "name": "stdout",
 93 |      "output_type": "stream",
 94 |      "text": [
 95 |       "<class 'pandas.core.frame.DataFrame'>\n",
 96 |       "RangeIndex: 569 entries, 0 to 568\n",
 97 |       "Data columns (total 11 columns):\n",
 98 |       "id                     569 non-null int64\n",
 99 |       "diagnosis              569 non-null object\n",
100 |       "radius_mean            569 non-null float64\n",
101 |       "texture_mean           569 non-null float64\n",
102 |       "perimeter_mean         569 non-null float64\n",
103 |       "area_mean              569 non-null float64\n",
104 |       "smoothness_mean        569 non-null float64\n",
105 |       "compactness_mean       569 non-null float64\n",
106 |       "concavity_mean         569 non-null float64\n",
107 |       "concave_points_mean    569 non-null float64\n",
108 |       "symmetry_mean          504 non-null float64\n",
109 |       "dtypes: float64(9), int64(1), object(1)\n",
110 |       "memory usage: 49.0+ KB\n"
111 |      ]
112 |     }
113 |    ],
114 |    "source": [
115 |     "# use means to fill in missing values\n",
116 |     "#convert for smoothness_mean\n",
117 |     "mean_smoothness = df_cancer['smoothness_mean'].mean()\n",
118 |     "df_cancer['smoothness_mean'].fillna(mean_smoothness, inplace = True)\n",
119 |     "\n",
120 |     "# confirm your correction with info()\n",
121 |     "df_cancer.info(0)"
122 |    ]
123 |   },
124 |   {
125 |    "cell_type": "code",
126 |    "execution_count": 5,
127 |    "metadata": {},
128 |    "outputs": [
129 |     {
130 |      "name": "stdout",
131 |      "output_type": "stream",
132 |      "text": [
133 |       "<class 'pandas.core.frame.DataFrame'>\n",
134 |       "RangeIndex: 569 entries, 0 to 568\n",
135 |       "Data columns (total 11 columns):\n",
136 |       "id                     569 non-null int64\n",
137 |       "diagnosis              569 non-null object\n",
138 |       "radius_mean            569 non-null float64\n",
139 |       "texture_mean           569 non-null float64\n",
140 |       "perimeter_mean         569 non-null float64\n",
141 |       "area_mean              569 non-null float64\n",
142 |       "smoothness_mean        569 non-null float64\n",
143 |       "compactness_mean       569 non-null float64\n",
144 |       "concavity_mean         569 non-null float64\n",
145 |       "concave_points_mean    569 non-null float64\n",
146 |       "symmetry_mean          569 non-null float64\n",
147 |       "dtypes: float64(9), int64(1), object(1)\n",
148 |       "memory usage: 49.0+ KB\n"
149 |      ]
150 |     }
151 |    ],
152 |    "source": [
153 |     "# use means to fill in missing values\n",
154 |     "#convert for symmetry_mean\n",
155 |     "mean_symmetry = df_cancer['symmetry_mean'].mean()\n",
156 |     "df_cancer['symmetry_mean'].fillna(mean_symmetry, inplace = True)\n",
157 |     "\n",
158 |     "# confirm your correction with info()\n",
159 |     "df_cancer.info(0)"
160 |    ]
161 |   },
162 |   {
163 |    "cell_type": "code",
164 |    "execution_count": 8,
165 |    "metadata": {},
166 |    "outputs": [
167 |     {
168 |      "data": {
169 |       "text/plain": [
170 |        "5"
171 |       ]
172 |      },
173 |      "execution_count": 8,
174 |      "metadata": {},
175 |      "output_type": "execute_result"
176 |     }
177 |    ],
178 |    "source": [
179 |     "# check for duplicates in the data\n",
180 |     "sum(df_cancer.duplicated())"
181 |    ]
182 |   },
183 |   {
184 |    "cell_type": "code",
185 |    "execution_count": 10,
186 |    "metadata": {},
187 |    "outputs": [],
188 |    "source": [
189 |     "# drop duplicates\n",
190 |     "df_cancer.drop_duplicates(inplace = True)"
191 |    ]
192 |   },
193 |   {
194 |    "cell_type": "code",
195 |    "execution_count": 11,
196 |    "metadata": {},
197 |    "outputs": [
198 |     {
199 |      "data": {
200 |       "text/plain": [
201 |        "0"
202 |       ]
203 |      },
204 |      "execution_count": 11,
205 |      "metadata": {},
206 |      "output_type": "execute_result"
207 |     }
208 |    ],
209 |    "source": [
210 |     "# confirm correction by rechecking for duplicates in the data\n",
211 |     "sum(df_cancer.duplicated())"
212 |    ]
213 |   },
214 |   {
215 |    "cell_type": "markdown",
216 |    "metadata": {},
217 |    "source": [
218 |     "## Renaming Columns\n",
219 |     "Since we also previously changed our dataset to only include means of tumor features, the \"_mean\" at the end of each feature seems unnecessary. It just takes extra time to type in our analysis later. Let's come up with a list of new labels to assign to our columns."
220 |    ]
221 |   },
222 |   {
223 |    "cell_type": "code",
224 |    "execution_count": 13,
225 |    "metadata": {},
226 |    "outputs": [
227 |     {
228 |      "data": {
229 |       "text/plain": [
230 |        "['id',\n",
231 |        " 'diagnosis',\n",
232 |        " 'radius',\n",
233 |        " 'texture',\n",
234 |        " 'perimeter',\n",
235 |        " 'area',\n",
236 |        " 'smoothness',\n",
237 |        " 'compactness',\n",
238 |        " 'concavity',\n",
239 |        " 'concave_points',\n",
240 |        " 'symmetry']"
241 |       ]
242 |      },
243 |      "execution_count": 13,
244 |      "metadata": {},
245 |      "output_type": "execute_result"
246 |     }
247 |    ],
248 |    "source": [
249 |     "# remove \"_mean\" from column names\n",
250 |     "new_labels = []\n",
251 |     "for col in df_cancer.columns:\n",
252 |     "    if '_mean' in col:\n",
253 |     "        new_labels.append(col[:-5])  # exclude last 6 characters\n",
254 |     "    else:\n",
255 |     "        new_labels.append(col)\n",
256 |     "\n",
257 |     "# new labels for our columns\n",
258 |     "new_labels"
259 |    ]
260 |   },
261 |   {
262 |    "cell_type": "code",
263 |    "execution_count": 14,
264 |    "metadata": {},
265 |    "outputs": [
266 |     {
267 |      "data": {
268 |       "text/html": [
269 |        "<div>\n",
270 |        "<style>\n",
271 |        "    .dataframe thead tr:only-child th {\n",
272 |        "        text-align: right;\n",
273 |        "    }\n",
274 |        "\n",
275 |        "    .dataframe thead th {\n",
276 |        "        text-align: left;\n",
277 |        "    }\n",
278 |        "\n",
279 |        "    .dataframe tbody tr th {\n",
280 |        "        vertical-align: top;\n",
281 |        "    }\n",
282 |        "</style>\n",
283 |        "<table border=\"1\" class=\"dataframe\">\n",
284 |        "  <thead>\n",
285 |        "    <tr style=\"text-align: right;\">\n",
286 |        "      <th></th>\n",
287 |        "      <th>id</th>\n",
288 |        "      <th>diagnosis</th>\n",
289 |        "      <th>radius</th>\n",
290 |        "      <th>texture</th>\n",
291 |        "      <th>perimeter</th>\n",
292 |        "      <th>area</th>\n",
293 |        "      <th>smoothness</th>\n",
294 |        "      <th>compactness</th>\n",
295 |        "      <th>concavity</th>\n",
296 |        "      <th>concave_points</th>\n",
297 |        "      <th>symmetry</th>\n",
298 |        "    </tr>\n",
299 |        "  </thead>\n",
300 |        "  <tbody>\n",
301 |        "    <tr>\n",
302 |        "      <th>0</th>\n",
303 |        "      <td>842302</td>\n",
304 |        "      <td>M</td>\n",
305 |        "      <td>17.99</td>\n",
306 |        "      <td>19.293431</td>\n",
307 |        "      <td>122.80</td>\n",
308 |        "      <td>1001.0</td>\n",
309 |        "      <td>0.118400</td>\n",
310 |        "      <td>0.27760</td>\n",
311 |        "      <td>0.3001</td>\n",
312 |        "      <td>0.14710</td>\n",
313 |        "      <td>0.2419</td>\n",
314 |        "    </tr>\n",
315 |        "    <tr>\n",
316 |        "      <th>1</th>\n",
317 |        "      <td>842517</td>\n",
318 |        "      <td>M</td>\n",
319 |        "      <td>20.57</td>\n",
320 |        "      <td>17.770000</td>\n",
321 |        "      <td>132.90</td>\n",
322 |        "      <td>1326.0</td>\n",
323 |        "      <td>0.084740</td>\n",
324 |        "      <td>0.07864</td>\n",
325 |        "      <td>0.0869</td>\n",
326 |        "      <td>0.07017</td>\n",
327 |        "      <td>0.1812</td>\n",
328 |        "    </tr>\n",
329 |        "    <tr>\n",
330 |        "      <th>2</th>\n",
331 |        "      <td>84300903</td>\n",
332 |        "      <td>M</td>\n",
333 |        "      <td>19.69</td>\n",
334 |        "      <td>21.250000</td>\n",
335 |        "      <td>130.00</td>\n",
336 |        "      <td>1203.0</td>\n",
337 |        "      <td>0.109600</td>\n",
338 |        "      <td>0.15990</td>\n",
339 |        "      <td>0.1974</td>\n",
340 |        "      <td>0.12790</td>\n",
341 |        "      <td>0.2069</td>\n",
342 |        "    </tr>\n",
343 |        "    <tr>\n",
344 |        "      <th>3</th>\n",
345 |        "      <td>84348301</td>\n",
346 |        "      <td>M</td>\n",
347 |        "      <td>11.42</td>\n",
348 |        "      <td>20.380000</td>\n",
349 |        "      <td>77.58</td>\n",
350 |        "      <td>386.1</td>\n",
351 |        "      <td>0.096087</td>\n",
352 |        "      <td>0.28390</td>\n",
353 |        "      <td>0.2414</td>\n",
354 |        "      <td>0.10520</td>\n",
355 |        "      <td>0.2597</td>\n",
356 |        "    </tr>\n",
357 |        "    <tr>\n",
358 |        "      <th>4</th>\n",
359 |        "      <td>84358402</td>\n",
360 |        "      <td>M</td>\n",
361 |        "      <td>20.29</td>\n",
362 |        "      <td>14.340000</td>\n",
363 |        "      <td>135.10</td>\n",
364 |        "      <td>1297.0</td>\n",
365 |        "      <td>0.100300</td>\n",
366 |        "      <td>0.13280</td>\n",
367 |        "      <td>0.1980</td>\n",
368 |        "      <td>0.10430</td>\n",
369 |        "      <td>0.1809</td>\n",
370 |        "    </tr>\n",
371 |        "  </tbody>\n",
372 |        "</table>\n",
373 |        "</div>"
374 |       ],
375 |       "text/plain": [
376 |        "         id diagnosis  radius    texture  perimeter    area  smoothness  \\\n",
377 |        "0    842302         M   17.99  19.293431     122.80  1001.0    0.118400   \n",
378 |        "1    842517         M   20.57  17.770000     132.90  1326.0    0.084740   \n",
379 |        "2  84300903         M   19.69  21.250000     130.00  1203.0    0.109600   \n",
380 |        "3  84348301         M   11.42  20.380000      77.58   386.1    0.096087   \n",
381 |        "4  84358402         M   20.29  14.340000     135.10  1297.0    0.100300   \n",
382 |        "\n",
383 |        "   compactness  concavity  concave_points  symmetry  \n",
384 |        "0      0.27760     0.3001         0.14710    0.2419  \n",
385 |        "1      0.07864     0.0869         0.07017    0.1812  \n",
386 |        "2      0.15990     0.1974         0.12790    0.2069  \n",
387 |        "3      0.28390     0.2414         0.10520    0.2597  \n",
388 |        "4      0.13280     0.1980         0.10430    0.1809  "
389 |       ]
390 |      },
391 |      "execution_count": 14,
392 |      "metadata": {},
393 |      "output_type": "execute_result"
394 |     }
395 |    ],
396 |    "source": [
397 |     "# assign new labels to columns in dataframe\n",
398 |     "df_cancer.columns = new_labels\n",
399 |     "\n",
400 |     "# display first few rows of dataframe to confirm changes\n",
401 |     "df_cancer.head()"
402 |    ]
403 |   },
404 |   {
405 |    "cell_type": "code",
406 |    "execution_count": 16,
407 |    "metadata": {
408 |     "collapsed": true
409 |    },
410 |    "outputs": [],
411 |    "source": [
412 |     "# save this for later\n",
413 |     "df_cancer.to_csv('cancer_data_edited.csv', index=False)"
414 |    ]
415 |   },
416 |   {
417 |    "cell_type": "code",
418 |    "execution_count": null,
419 |    "metadata": {
420 |     "collapsed": true
421 |    },
422 |    "outputs": [],
423 |    "source": []
424 |   }
425 |  ],
426 |  "metadata": {
427 |   "kernelspec": {
428 |    "display_name": "Python 3",
429 |    "language": "python",
430 |    "name": "python3"
431 |   },
432 |   "language_info": {
433 |    "codemirror_mode": {
434 |     "name": "ipython",
435 |     "version": 3
436 |    },
437 |    "file_extension": ".py",
438 |    "mimetype": "text/x-python",
439 |    "name": "python",
440 |    "nbconvert_exporter": "python",
441 |    "pygments_lexer": "ipython3",
442 |    "version": "3.6.1"
443 |   }
444 |  },
445 |  "nbformat": 4,
446 |  "nbformat_minor": 2
447 | }
448 | 


--------------------------------------------------------------------------------
/conclusions_groupby.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {},
  6 |    "source": [
  7 |     "# Drawing Conclusions Using Groupby"
  8 |    ]
  9 |   },
 10 |   {
 11 |    "cell_type": "code",
 12 |    "execution_count": 3,
 13 |    "metadata": {
 14 |     "collapsed": true
 15 |    },
 16 |    "outputs": [],
 17 |    "source": [
 18 |     "#Import packages\n",
 19 |     "import pandas as pd\n",
 20 |     "import numpy as np\n",
 21 |     "from matplotlib import pyplot as plt\n",
 22 |     "import matplotlib\n",
 23 |     "% matplotlib inline"
 24 |    ]
 25 |   },
 26 |   {
 27 |    "cell_type": "code",
 28 |    "execution_count": 4,
 29 |    "metadata": {},
 30 |    "outputs": [
 31 |     {
 32 |      "name": "stdout",
 33 |      "output_type": "stream",
 34 |      "text": [
 35 |       "<class 'pandas.core.frame.DataFrame'>\n",
 36 |       "RangeIndex: 6497 entries, 0 to 6496\n",
 37 |       "Data columns (total 13 columns):\n",
 38 |       "fixed_acidity           6497 non-null float64\n",
 39 |       "volatile_acidity        6497 non-null float64\n",
 40 |       "citric_acid             6497 non-null float64\n",
 41 |       "residual_sugar          6497 non-null float64\n",
 42 |       "chlorides               6497 non-null float64\n",
 43 |       "free_sulfur_dioxide     6497 non-null float64\n",
 44 |       "total_sulfur_dioxide    6497 non-null float64\n",
 45 |       "density                 6497 non-null float64\n",
 46 |       "pH                      6497 non-null float64\n",
 47 |       "sulphates               6497 non-null float64\n",
 48 |       "alcohol                 6497 non-null float64\n",
 49 |       "quality                 6497 non-null int64\n",
 50 |       "color                   6497 non-null object\n",
 51 |       "dtypes: float64(11), int64(1), object(1)\n",
 52 |       "memory usage: 659.9+ KB\n"
 53 |      ]
 54 |     }
 55 |    ],
 56 |    "source": [
 57 |     "# Load `winequality_edited.csv`\n",
 58 |     "wine_df = pd.read_csv('winequality_edited.csv')\n",
 59 |     "wine_df.info()"
 60 |    ]
 61 |   },
 62 |   {
 63 |    "cell_type": "markdown",
 64 |    "metadata": {
 65 |     "collapsed": true
 66 |    },
 67 |    "source": [
 68 |     "### Is a certain type of wine associated with higher quality?"
 69 |    ]
 70 |   },
 71 |   {
 72 |    "cell_type": "code",
 73 |    "execution_count": 5,
 74 |    "metadata": {},
 75 |    "outputs": [
 76 |     {
 77 |      "data": {
 78 |       "text/plain": [
 79 |        "color\n",
 80 |        "red      5.636023\n",
 81 |        "white    5.877909\n",
 82 |        "Name: quality, dtype: float64"
 83 |       ]
 84 |      },
 85 |      "execution_count": 5,
 86 |      "metadata": {},
 87 |      "output_type": "execute_result"
 88 |     }
 89 |    ],
 90 |    "source": [
 91 |     "# Find the mean quality of each wine type (red and white) with groupby\n",
 92 |     "wine_df.groupby('color')['quality'].mean()"
 93 |    ]
 94 |   },
 95 |   {
 96 |    "cell_type": "markdown",
 97 |    "metadata": {},
 98 |    "source": [
 99 |     "### What level of acidity receives the highest average rating?"
100 |    ]
101 |   },
102 |   {
103 |    "cell_type": "code",
104 |    "execution_count": 7,
105 |    "metadata": {},
106 |    "outputs": [
107 |     {
108 |      "data": {
109 |       "text/html": [
110 |        "<div>\n",
111 |        "<style>\n",
112 |        "    .dataframe thead tr:only-child th {\n",
113 |        "        text-align: right;\n",
114 |        "    }\n",
115 |        "\n",
116 |        "    .dataframe thead th {\n",
117 |        "        text-align: left;\n",
118 |        "    }\n",
119 |        "\n",
120 |        "    .dataframe tbody tr th {\n",
121 |        "        vertical-align: top;\n",
122 |        "    }\n",
123 |        "</style>\n",
124 |        "<table border=\"1\" class=\"dataframe\">\n",
125 |        "  <thead>\n",
126 |        "    <tr style=\"text-align: right;\">\n",
127 |        "      <th></th>\n",
128 |        "      <th>fixed_acidity</th>\n",
129 |        "      <th>volatile_acidity</th>\n",
130 |        "      <th>citric_acid</th>\n",
131 |        "      <th>residual_sugar</th>\n",
132 |        "      <th>chlorides</th>\n",
133 |        "      <th>free_sulfur_dioxide</th>\n",
134 |        "      <th>total_sulfur_dioxide</th>\n",
135 |        "      <th>density</th>\n",
136 |        "      <th>pH</th>\n",
137 |        "      <th>sulphates</th>\n",
138 |        "      <th>alcohol</th>\n",
139 |        "      <th>quality</th>\n",
140 |        "    </tr>\n",
141 |        "  </thead>\n",
142 |        "  <tbody>\n",
143 |        "    <tr>\n",
144 |        "      <th>count</th>\n",
145 |        "      <td>6497.000000</td>\n",
146 |        "      <td>6497.000000</td>\n",
147 |        "      <td>6497.000000</td>\n",
148 |        "      <td>6497.000000</td>\n",
149 |        "      <td>6497.000000</td>\n",
150 |        "      <td>6497.000000</td>\n",
151 |        "      <td>6497.000000</td>\n",
152 |        "      <td>6497.000000</td>\n",
153 |        "      <td>6497.000000</td>\n",
154 |        "      <td>6497.000000</td>\n",
155 |        "      <td>6497.000000</td>\n",
156 |        "      <td>6497.000000</td>\n",
157 |        "    </tr>\n",
158 |        "    <tr>\n",
159 |        "      <th>mean</th>\n",
160 |        "      <td>7.215307</td>\n",
161 |        "      <td>0.339666</td>\n",
162 |        "      <td>0.318633</td>\n",
163 |        "      <td>5.443235</td>\n",
164 |        "      <td>0.056034</td>\n",
165 |        "      <td>30.525319</td>\n",
166 |        "      <td>115.744574</td>\n",
167 |        "      <td>0.994697</td>\n",
168 |        "      <td>3.218501</td>\n",
169 |        "      <td>0.531268</td>\n",
170 |        "      <td>10.491801</td>\n",
171 |        "      <td>5.818378</td>\n",
172 |        "    </tr>\n",
173 |        "    <tr>\n",
174 |        "      <th>std</th>\n",
175 |        "      <td>1.296434</td>\n",
176 |        "      <td>0.164636</td>\n",
177 |        "      <td>0.145318</td>\n",
178 |        "      <td>4.757804</td>\n",
179 |        "      <td>0.035034</td>\n",
180 |        "      <td>17.749400</td>\n",
181 |        "      <td>56.521855</td>\n",
182 |        "      <td>0.002999</td>\n",
183 |        "      <td>0.160787</td>\n",
184 |        "      <td>0.148806</td>\n",
185 |        "      <td>1.192712</td>\n",
186 |        "      <td>0.873255</td>\n",
187 |        "    </tr>\n",
188 |        "    <tr>\n",
189 |        "      <th>min</th>\n",
190 |        "      <td>3.800000</td>\n",
191 |        "      <td>0.080000</td>\n",
192 |        "      <td>0.000000</td>\n",
193 |        "      <td>0.600000</td>\n",
194 |        "      <td>0.009000</td>\n",
195 |        "      <td>1.000000</td>\n",
196 |        "      <td>6.000000</td>\n",
197 |        "      <td>0.987110</td>\n",
198 |        "      <td>2.720000</td>\n",
199 |        "      <td>0.220000</td>\n",
200 |        "      <td>8.000000</td>\n",
201 |        "      <td>3.000000</td>\n",
202 |        "    </tr>\n",
203 |        "    <tr>\n",
204 |        "      <th>25%</th>\n",
205 |        "      <td>6.400000</td>\n",
206 |        "      <td>0.230000</td>\n",
207 |        "      <td>0.250000</td>\n",
208 |        "      <td>1.800000</td>\n",
209 |        "      <td>0.038000</td>\n",
210 |        "      <td>17.000000</td>\n",
211 |        "      <td>77.000000</td>\n",
212 |        "      <td>0.992340</td>\n",
213 |        "      <td>3.110000</td>\n",
214 |        "      <td>0.430000</td>\n",
215 |        "      <td>9.500000</td>\n",
216 |        "      <td>5.000000</td>\n",
217 |        "    </tr>\n",
218 |        "    <tr>\n",
219 |        "      <th>50%</th>\n",
220 |        "      <td>7.000000</td>\n",
221 |        "      <td>0.290000</td>\n",
222 |        "      <td>0.310000</td>\n",
223 |        "      <td>3.000000</td>\n",
224 |        "      <td>0.047000</td>\n",
225 |        "      <td>29.000000</td>\n",
226 |        "      <td>118.000000</td>\n",
227 |        "      <td>0.994890</td>\n",
228 |        "      <td>3.210000</td>\n",
229 |        "      <td>0.510000</td>\n",
230 |        "      <td>10.300000</td>\n",
231 |        "      <td>6.000000</td>\n",
232 |        "    </tr>\n",
233 |        "    <tr>\n",
234 |        "      <th>75%</th>\n",
235 |        "      <td>7.700000</td>\n",
236 |        "      <td>0.400000</td>\n",
237 |        "      <td>0.390000</td>\n",
238 |        "      <td>8.100000</td>\n",
239 |        "      <td>0.065000</td>\n",
240 |        "      <td>41.000000</td>\n",
241 |        "      <td>156.000000</td>\n",
242 |        "      <td>0.996990</td>\n",
243 |        "      <td>3.320000</td>\n",
244 |        "      <td>0.600000</td>\n",
245 |        "      <td>11.300000</td>\n",
246 |        "      <td>6.000000</td>\n",
247 |        "    </tr>\n",
248 |        "    <tr>\n",
249 |        "      <th>max</th>\n",
250 |        "      <td>15.900000</td>\n",
251 |        "      <td>1.580000</td>\n",
252 |        "      <td>1.660000</td>\n",
253 |        "      <td>65.800000</td>\n",
254 |        "      <td>0.611000</td>\n",
255 |        "      <td>289.000000</td>\n",
256 |        "      <td>440.000000</td>\n",
257 |        "      <td>1.038980</td>\n",
258 |        "      <td>4.010000</td>\n",
259 |        "      <td>2.000000</td>\n",
260 |        "      <td>14.900000</td>\n",
261 |        "      <td>9.000000</td>\n",
262 |        "    </tr>\n",
263 |        "  </tbody>\n",
264 |        "</table>\n",
265 |        "</div>"
266 |       ],
267 |       "text/plain": [
268 |        "       fixed_acidity  volatile_acidity  citric_acid  residual_sugar  \\\n",
269 |        "count    6497.000000       6497.000000  6497.000000     6497.000000   \n",
270 |        "mean        7.215307          0.339666     0.318633        5.443235   \n",
271 |        "std         1.296434          0.164636     0.145318        4.757804   \n",
272 |        "min         3.800000          0.080000     0.000000        0.600000   \n",
273 |        "25%         6.400000          0.230000     0.250000        1.800000   \n",
274 |        "50%         7.000000          0.290000     0.310000        3.000000   \n",
275 |        "75%         7.700000          0.400000     0.390000        8.100000   \n",
276 |        "max        15.900000          1.580000     1.660000       65.800000   \n",
277 |        "\n",
278 |        "         chlorides  free_sulfur_dioxide  total_sulfur_dioxide      density  \\\n",
279 |        "count  6497.000000          6497.000000           6497.000000  6497.000000   \n",
280 |        "mean      0.056034            30.525319            115.744574     0.994697   \n",
281 |        "std       0.035034            17.749400             56.521855     0.002999   \n",
282 |        "min       0.009000             1.000000              6.000000     0.987110   \n",
283 |        "25%       0.038000            17.000000             77.000000     0.992340   \n",
284 |        "50%       0.047000            29.000000            118.000000     0.994890   \n",
285 |        "75%       0.065000            41.000000            156.000000     0.996990   \n",
286 |        "max       0.611000           289.000000            440.000000     1.038980   \n",
287 |        "\n",
288 |        "                pH    sulphates      alcohol      quality  \n",
289 |        "count  6497.000000  6497.000000  6497.000000  6497.000000  \n",
290 |        "mean      3.218501     0.531268    10.491801     5.818378  \n",
291 |        "std       0.160787     0.148806     1.192712     0.873255  \n",
292 |        "min       2.720000     0.220000     8.000000     3.000000  \n",
293 |        "25%       3.110000     0.430000     9.500000     5.000000  \n",
294 |        "50%       3.210000     0.510000    10.300000     6.000000  \n",
295 |        "75%       3.320000     0.600000    11.300000     6.000000  \n",
296 |        "max       4.010000     2.000000    14.900000     9.000000  "
297 |       ]
298 |      },
299 |      "execution_count": 7,
300 |      "metadata": {},
301 |      "output_type": "execute_result"
302 |     }
303 |    ],
304 |    "source": [
305 |     "# View the min, 25%, 50%, 75%, max pH values with Pandas describe\n",
306 |     "# High: Lowest 25% of pH values\n",
307 |     "# Moderately High: 25% - 50% of pH values\n",
308 |     "# Medium: 50% - 75% of pH values\n",
309 |     "# Low: 75% - max pH value\n",
310 |     "wine_df.describe()"
311 |    ]
312 |   },
313 |   {
314 |    "cell_type": "code",
315 |    "execution_count": 8,
316 |    "metadata": {
317 |     "collapsed": true
318 |    },
319 |    "outputs": [],
320 |    "source": [
321 |     "# Bin edges that will be used to \"cut\" the data into groups\n",
322 |     "bin_edges = [ 2.72, 3.11,3.21 , 3.32,4.01 ] # Fill in this list with five values you just found"
323 |    ]
324 |   },
325 |   {
326 |    "cell_type": "code",
327 |    "execution_count": 9,
328 |    "metadata": {
329 |     "collapsed": true
330 |    },
331 |    "outputs": [],
332 |    "source": [
333 |     "# Labels for the four acidity level groups\n",
334 |     "bin_names = [ 'High','Moderately High' ,'Meduim' ,'Low' ] # Name each acidity level category"
335 |    ]
336 |   },
337 |   {
338 |    "cell_type": "code",
339 |    "execution_count": 10,
340 |    "metadata": {},
341 |    "outputs": [
342 |     {
343 |      "data": {
344 |       "text/html": [
345 |        "<div>\n",
346 |        "<style>\n",
347 |        "    .dataframe thead tr:only-child th {\n",
348 |        "        text-align: right;\n",
349 |        "    }\n",
350 |        "\n",
351 |        "    .dataframe thead th {\n",
352 |        "        text-align: left;\n",
353 |        "    }\n",
354 |        "\n",
355 |        "    .dataframe tbody tr th {\n",
356 |        "        vertical-align: top;\n",
357 |        "    }\n",
358 |        "</style>\n",
359 |        "<table border=\"1\" class=\"dataframe\">\n",
360 |        "  <thead>\n",
361 |        "    <tr style=\"text-align: right;\">\n",
362 |        "      <th></th>\n",
363 |        "      <th>fixed_acidity</th>\n",
364 |        "      <th>volatile_acidity</th>\n",
365 |        "      <th>citric_acid</th>\n",
366 |        "      <th>residual_sugar</th>\n",
367 |        "      <th>chlorides</th>\n",
368 |        "      <th>free_sulfur_dioxide</th>\n",
369 |        "      <th>total_sulfur_dioxide</th>\n",
370 |        "      <th>density</th>\n",
371 |        "      <th>pH</th>\n",
372 |        "      <th>sulphates</th>\n",
373 |        "      <th>alcohol</th>\n",
374 |        "      <th>quality</th>\n",
375 |        "      <th>color</th>\n",
376 |        "      <th>acidity_levels</th>\n",
377 |        "    </tr>\n",
378 |        "  </thead>\n",
379 |        "  <tbody>\n",
380 |        "    <tr>\n",
381 |        "      <th>0</th>\n",
382 |        "      <td>7.4</td>\n",
383 |        "      <td>0.70</td>\n",
384 |        "      <td>0.00</td>\n",
385 |        "      <td>1.9</td>\n",
386 |        "      <td>0.076</td>\n",
387 |        "      <td>11.0</td>\n",
388 |        "      <td>34.0</td>\n",
389 |        "      <td>0.9978</td>\n",
390 |        "      <td>3.51</td>\n",
391 |        "      <td>0.56</td>\n",
392 |        "      <td>9.4</td>\n",
393 |        "      <td>5</td>\n",
394 |        "      <td>red</td>\n",
395 |        "      <td>Low</td>\n",
396 |        "    </tr>\n",
397 |        "    <tr>\n",
398 |        "      <th>1</th>\n",
399 |        "      <td>7.8</td>\n",
400 |        "      <td>0.88</td>\n",
401 |        "      <td>0.00</td>\n",
402 |        "      <td>2.6</td>\n",
403 |        "      <td>0.098</td>\n",
404 |        "      <td>25.0</td>\n",
405 |        "      <td>67.0</td>\n",
406 |        "      <td>0.9968</td>\n",
407 |        "      <td>3.20</td>\n",
408 |        "      <td>0.68</td>\n",
409 |        "      <td>9.8</td>\n",
410 |        "      <td>5</td>\n",
411 |        "      <td>red</td>\n",
412 |        "      <td>Moderately High</td>\n",
413 |        "    </tr>\n",
414 |        "    <tr>\n",
415 |        "      <th>2</th>\n",
416 |        "      <td>7.8</td>\n",
417 |        "      <td>0.76</td>\n",
418 |        "      <td>0.04</td>\n",
419 |        "      <td>2.3</td>\n",
420 |        "      <td>0.092</td>\n",
421 |        "      <td>15.0</td>\n",
422 |        "      <td>54.0</td>\n",
423 |        "      <td>0.9970</td>\n",
424 |        "      <td>3.26</td>\n",
425 |        "      <td>0.65</td>\n",
426 |        "      <td>9.8</td>\n",
427 |        "      <td>5</td>\n",
428 |        "      <td>red</td>\n",
429 |        "      <td>Meduim</td>\n",
430 |        "    </tr>\n",
431 |        "    <tr>\n",
432 |        "      <th>3</th>\n",
433 |        "      <td>11.2</td>\n",
434 |        "      <td>0.28</td>\n",
435 |        "      <td>0.56</td>\n",
436 |        "      <td>1.9</td>\n",
437 |        "      <td>0.075</td>\n",
438 |        "      <td>17.0</td>\n",
439 |        "      <td>60.0</td>\n",
440 |        "      <td>0.9980</td>\n",
441 |        "      <td>3.16</td>\n",
442 |        "      <td>0.58</td>\n",
443 |        "      <td>9.8</td>\n",
444 |        "      <td>6</td>\n",
445 |        "      <td>red</td>\n",
446 |        "      <td>Moderately High</td>\n",
447 |        "    </tr>\n",
448 |        "    <tr>\n",
449 |        "      <th>4</th>\n",
450 |        "      <td>7.4</td>\n",
451 |        "      <td>0.70</td>\n",
452 |        "      <td>0.00</td>\n",
453 |        "      <td>1.9</td>\n",
454 |        "      <td>0.076</td>\n",
455 |        "      <td>11.0</td>\n",
456 |        "      <td>34.0</td>\n",
457 |        "      <td>0.9978</td>\n",
458 |        "      <td>3.51</td>\n",
459 |        "      <td>0.56</td>\n",
460 |        "      <td>9.4</td>\n",
461 |        "      <td>5</td>\n",
462 |        "      <td>red</td>\n",
463 |        "      <td>Low</td>\n",
464 |        "    </tr>\n",
465 |        "  </tbody>\n",
466 |        "</table>\n",
467 |        "</div>"
468 |       ],
469 |       "text/plain": [
470 |        "   fixed_acidity  volatile_acidity  citric_acid  residual_sugar  chlorides  \\\n",
471 |        "0            7.4              0.70         0.00             1.9      0.076   \n",
472 |        "1            7.8              0.88         0.00             2.6      0.098   \n",
473 |        "2            7.8              0.76         0.04             2.3      0.092   \n",
474 |        "3           11.2              0.28         0.56             1.9      0.075   \n",
475 |        "4            7.4              0.70         0.00             1.9      0.076   \n",
476 |        "\n",
477 |        "   free_sulfur_dioxide  total_sulfur_dioxide  density    pH  sulphates  \\\n",
478 |        "0                 11.0                  34.0   0.9978  3.51       0.56   \n",
479 |        "1                 25.0                  67.0   0.9968  3.20       0.68   \n",
480 |        "2                 15.0                  54.0   0.9970  3.26       0.65   \n",
481 |        "3                 17.0                  60.0   0.9980  3.16       0.58   \n",
482 |        "4                 11.0                  34.0   0.9978  3.51       0.56   \n",
483 |        "\n",
484 |        "   alcohol  quality color   acidity_levels  \n",
485 |        "0      9.4        5   red              Low  \n",
486 |        "1      9.8        5   red  Moderately High  \n",
487 |        "2      9.8        5   red           Meduim  \n",
488 |        "3      9.8        6   red  Moderately High  \n",
489 |        "4      9.4        5   red              Low  "
490 |       ]
491 |      },
492 |      "execution_count": 10,
493 |      "metadata": {},
494 |      "output_type": "execute_result"
495 |     }
496 |    ],
497 |    "source": [
498 |     "# Creates acidity_levels column\n",
499 |     "wine_df['acidity_levels'] = pd.cut(wine_df['pH'], bin_edges, labels=bin_names)\n",
500 |     "\n",
501 |     "# Checks for successful creation of this column\n",
502 |     "wine_df.head()"
503 |    ]
504 |   },
505 |   {
506 |    "cell_type": "code",
507 |    "execution_count": 11,
508 |    "metadata": {},
509 |    "outputs": [
510 |     {
511 |      "data": {
512 |       "text/html": [
513 |        "<div>\n",
514 |        "<style>\n",
515 |        "    .dataframe thead tr:only-child th {\n",
516 |        "        text-align: right;\n",
517 |        "    }\n",
518 |        "\n",
519 |        "    .dataframe thead th {\n",
520 |        "        text-align: left;\n",
521 |        "    }\n",
522 |        "\n",
523 |        "    .dataframe tbody tr th {\n",
524 |        "        vertical-align: top;\n",
525 |        "    }\n",
526 |        "</style>\n",
527 |        "<table border=\"1\" class=\"dataframe\">\n",
528 |        "  <thead>\n",
529 |        "    <tr style=\"text-align: right;\">\n",
530 |        "      <th></th>\n",
531 |        "      <th>fixed_acidity</th>\n",
532 |        "      <th>volatile_acidity</th>\n",
533 |        "      <th>citric_acid</th>\n",
534 |        "      <th>residual_sugar</th>\n",
535 |        "      <th>chlorides</th>\n",
536 |        "      <th>free_sulfur_dioxide</th>\n",
537 |        "      <th>total_sulfur_dioxide</th>\n",
538 |        "      <th>density</th>\n",
539 |        "      <th>pH</th>\n",
540 |        "      <th>sulphates</th>\n",
541 |        "      <th>alcohol</th>\n",
542 |        "      <th>quality</th>\n",
543 |        "    </tr>\n",
544 |        "    <tr>\n",
545 |        "      <th>acidity_levels</th>\n",
546 |        "      <th></th>\n",
547 |        "      <th></th>\n",
548 |        "      <th></th>\n",
549 |        "      <th></th>\n",
550 |        "      <th></th>\n",
551 |        "      <th></th>\n",
552 |        "      <th></th>\n",
553 |        "      <th></th>\n",
554 |        "      <th></th>\n",
555 |        "      <th></th>\n",
556 |        "      <th></th>\n",
557 |        "      <th></th>\n",
558 |        "    </tr>\n",
559 |        "  </thead>\n",
560 |        "  <tbody>\n",
561 |        "    <tr>\n",
562 |        "      <th>High</th>\n",
563 |        "      <td>7.543914</td>\n",
564 |        "      <td>0.294683</td>\n",
565 |        "      <td>0.370792</td>\n",
566 |        "      <td>7.088876</td>\n",
567 |        "      <td>0.055131</td>\n",
568 |        "      <td>33.179965</td>\n",
569 |        "      <td>129.897496</td>\n",
570 |        "      <td>0.994708</td>\n",
571 |        "      <td>3.029062</td>\n",
572 |        "      <td>0.503937</td>\n",
573 |        "      <td>10.330208</td>\n",
574 |        "      <td>5.783343</td>\n",
575 |        "    </tr>\n",
576 |        "    <tr>\n",
577 |        "      <th>Moderately High</th>\n",
578 |        "      <td>7.365064</td>\n",
579 |        "      <td>0.318551</td>\n",
580 |        "      <td>0.340548</td>\n",
581 |        "      <td>5.931984</td>\n",
582 |        "      <td>0.054666</td>\n",
583 |        "      <td>33.229154</td>\n",
584 |        "      <td>126.815886</td>\n",
585 |        "      <td>0.994697</td>\n",
586 |        "      <td>3.164833</td>\n",
587 |        "      <td>0.509300</td>\n",
588 |        "      <td>10.391073</td>\n",
589 |        "      <td>5.784540</td>\n",
590 |        "    </tr>\n",
591 |        "    <tr>\n",
592 |        "      <th>Meduim</th>\n",
593 |        "      <td>7.143566</td>\n",
594 |        "      <td>0.346751</td>\n",
595 |        "      <td>0.313585</td>\n",
596 |        "      <td>4.721159</td>\n",
597 |        "      <td>0.055715</td>\n",
598 |        "      <td>28.983995</td>\n",
599 |        "      <td>111.182138</td>\n",
600 |        "      <td>0.994476</td>\n",
601 |        "      <td>3.267010</td>\n",
602 |        "      <td>0.541287</td>\n",
603 |        "      <td>10.610369</td>\n",
604 |        "      <td>5.850832</td>\n",
605 |        "    </tr>\n",
606 |        "    <tr>\n",
607 |        "      <th>Low</th>\n",
608 |        "      <td>6.769949</td>\n",
609 |        "      <td>0.403815</td>\n",
610 |        "      <td>0.243901</td>\n",
611 |        "      <td>3.848983</td>\n",
612 |        "      <td>0.058777</td>\n",
613 |        "      <td>26.327510</td>\n",
614 |        "      <td>93.244917</td>\n",
615 |        "      <td>0.994899</td>\n",
616 |        "      <td>3.433348</td>\n",
617 |        "      <td>0.574136</td>\n",
618 |        "      <td>10.656057</td>\n",
619 |        "      <td>5.859593</td>\n",
620 |        "    </tr>\n",
621 |        "  </tbody>\n",
622 |        "</table>\n",
623 |        "</div>"
624 |       ],
625 |       "text/plain": [
626 |        "                 fixed_acidity  volatile_acidity  citric_acid  residual_sugar  \\\n",
627 |        "acidity_levels                                                                  \n",
628 |        "High                  7.543914          0.294683     0.370792        7.088876   \n",
629 |        "Moderately High       7.365064          0.318551     0.340548        5.931984   \n",
630 |        "Meduim                7.143566          0.346751     0.313585        4.721159   \n",
631 |        "Low                   6.769949          0.403815     0.243901        3.848983   \n",
632 |        "\n",
633 |        "                 chlorides  free_sulfur_dioxide  total_sulfur_dioxide  \\\n",
634 |        "acidity_levels                                                          \n",
635 |        "High              0.055131            33.179965            129.897496   \n",
636 |        "Moderately High   0.054666            33.229154            126.815886   \n",
637 |        "Meduim            0.055715            28.983995            111.182138   \n",
638 |        "Low               0.058777            26.327510             93.244917   \n",
639 |        "\n",
640 |        "                  density        pH  sulphates    alcohol   quality  \n",
641 |        "acidity_levels                                                       \n",
642 |        "High             0.994708  3.029062   0.503937  10.330208  5.783343  \n",
643 |        "Moderately High  0.994697  3.164833   0.509300  10.391073  5.784540  \n",
644 |        "Meduim           0.994476  3.267010   0.541287  10.610369  5.850832  \n",
645 |        "Low              0.994899  3.433348   0.574136  10.656057  5.859593  "
646 |       ]
647 |      },
648 |      "execution_count": 11,
649 |      "metadata": {},
650 |      "output_type": "execute_result"
651 |     }
652 |    ],
653 |    "source": [
654 |     "# Find the mean quality of each acidity level with groupby\n",
655 |     "wine_df.groupby('acidity_levels').mean()"
656 |    ]
657 |   },
658 |   {
659 |    "cell_type": "code",
660 |    "execution_count": 13,
661 |    "metadata": {},
662 |    "outputs": [],
663 |    "source": [
664 |     "# Save changes for the next section\n",
665 |     "wine_df.to_csv('winequality_edited.csv', index=False)"
666 |    ]
667 |   },
668 |   {
669 |    "cell_type": "markdown",
670 |    "metadata": {},
671 |    "source": [
672 |     "## QUIZ Q&A"
673 |    ]
674 |   },
675 |   {
676 |    "cell_type": "markdown",
677 |    "metadata": {},
678 |    "source": [
679 |     "### Is the mean quality of red wine greater than, less than, or equal to that of white wine?\n",
680 |     "Less"
681 |    ]
682 |   },
683 |   {
684 |    "cell_type": "markdown",
685 |    "metadata": {},
686 |    "source": [
687 |     "### What level of acidity receives the highest average rating?\n",
688 |     "Low acidity "
689 |    ]
690 |   },
691 |   {
692 |    "cell_type": "code",
693 |    "execution_count": null,
694 |    "metadata": {
695 |     "collapsed": true
696 |    },
697 |    "outputs": [],
698 |    "source": []
699 |   }
700 |  ],
701 |  "metadata": {
702 |   "kernelspec": {
703 |    "display_name": "Python 3",
704 |    "language": "python",
705 |    "name": "python3"
706 |   },
707 |   "language_info": {
708 |    "codemirror_mode": {
709 |     "name": "ipython",
710 |     "version": 3
711 |    },
712 |    "file_extension": ".py",
713 |    "mimetype": "text/x-python",
714 |    "name": "python",
715 |    "nbconvert_exporter": "python",
716 |    "pygments_lexer": "ipython3",
717 |    "version": "3.6.1"
718 |   }
719 |  },
720 |  "nbformat": 4,
721 |  "nbformat_minor": 2
722 | }
723 | 


--------------------------------------------------------------------------------
/conclusions_query.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {},
  6 |    "source": [
  7 |     "# Drawing Conclusions Using Query"
  8 |    ]
  9 |   },
 10 |   {
 11 |    "cell_type": "code",
 12 |    "execution_count": 1,
 13 |    "metadata": {
 14 |     "collapsed": true
 15 |    },
 16 |    "outputs": [],
 17 |    "source": [
 18 |     "import pandas as pd"
 19 |    ]
 20 |   },
 21 |   {
 22 |    "cell_type": "code",
 23 |    "execution_count": 2,
 24 |    "metadata": {
 25 |     "collapsed": true
 26 |    },
 27 |    "outputs": [],
 28 |    "source": [
 29 |     "# Load `winequality_edited.csv`\n",
 30 |     "\n",
 31 |     "df = pd.read_csv('winequality_edited.csv')"
 32 |    ]
 33 |   },
 34 |   {
 35 |    "cell_type": "code",
 36 |    "execution_count": 11,
 37 |    "metadata": {},
 38 |    "outputs": [
 39 |     {
 40 |      "name": "stdout",
 41 |      "output_type": "stream",
 42 |      "text": [
 43 |       "<class 'pandas.core.frame.DataFrame'>\n",
 44 |       "RangeIndex: 6497 entries, 0 to 6496\n",
 45 |       "Data columns (total 14 columns):\n",
 46 |       "fixed_acidity           6497 non-null float64\n",
 47 |       "volatile_acidity        6497 non-null float64\n",
 48 |       "citric_acid             6497 non-null float64\n",
 49 |       "residual_sugar          6497 non-null float64\n",
 50 |       "chlorides               6497 non-null float64\n",
 51 |       "free_sulfur_dioxide     6497 non-null float64\n",
 52 |       "total_sulfur_dioxide    6497 non-null float64\n",
 53 |       "density                 6497 non-null float64\n",
 54 |       "pH                      6497 non-null float64\n",
 55 |       "sulphates               6497 non-null float64\n",
 56 |       "alcohol                 6497 non-null float64\n",
 57 |       "quality                 6497 non-null int64\n",
 58 |       "color                   6497 non-null object\n",
 59 |       "acidity_levels          6496 non-null object\n",
 60 |       "dtypes: float64(11), int64(1), object(2)\n",
 61 |       "memory usage: 710.7+ KB\n"
 62 |      ]
 63 |     }
 64 |    ],
 65 |    "source": [
 66 |     "df.info()"
 67 |    ]
 68 |   },
 69 |   {
 70 |    "cell_type": "markdown",
 71 |    "metadata": {
 72 |     "collapsed": true
 73 |    },
 74 |    "source": [
 75 |     "### Do wines with higher alcoholic content receive better ratings?"
 76 |    ]
 77 |   },
 78 |   {
 79 |    "cell_type": "code",
 80 |    "execution_count": 3,
 81 |    "metadata": {},
 82 |    "outputs": [
 83 |     {
 84 |      "data": {
 85 |       "text/plain": [
 86 |        "10.3"
 87 |       ]
 88 |      },
 89 |      "execution_count": 3,
 90 |      "metadata": {},
 91 |      "output_type": "execute_result"
 92 |     }
 93 |    ],
 94 |    "source": [
 95 |     "# get the median amount of alcohol content\n",
 96 |     "df['alcohol'].median()"
 97 |    ]
 98 |   },
 99 |   {
100 |    "cell_type": "code",
101 |    "execution_count": 5,
102 |    "metadata": {},
103 |    "outputs": [
104 |     {
105 |      "data": {
106 |       "text/plain": [
107 |        "True"
108 |       ]
109 |      },
110 |      "execution_count": 5,
111 |      "metadata": {},
112 |      "output_type": "execute_result"
113 |     }
114 |    ],
115 |    "source": [
116 |     "# select samples with alcohol content less than the median\n",
117 |     "low_alcohol = df.query('alcohol < 10.3')\n",
118 |     "\n",
119 |     "# select samples with alcohol content greater than or equal to the median\n",
120 |     "high_alcohol = df.query('alcohol >= 10.3')\n",
121 |     "\n",
122 |     "# ensure these queries included each sample exactly once\n",
123 |     "num_samples = df.shape[0]\n",
124 |     "num_samples == low_alcohol['quality'].count() + high_alcohol['quality'].count() # should be True"
125 |    ]
126 |   },
127 |   {
128 |    "cell_type": "code",
129 |    "execution_count": 9,
130 |    "metadata": {},
131 |    "outputs": [
132 |     {
133 |      "data": {
134 |       "text/plain": [
135 |        "5.475920679886686"
136 |       ]
137 |      },
138 |      "execution_count": 9,
139 |      "metadata": {},
140 |      "output_type": "execute_result"
141 |     }
142 |    ],
143 |    "source": [
144 |     "# get mean quality rating for the low alcohol and high alcohol groups\n",
145 |     "low_alcohol['quality'].mean()\n"
146 |    ]
147 |   },
148 |   {
149 |    "cell_type": "code",
150 |    "execution_count": 10,
151 |    "metadata": {},
152 |    "outputs": [
153 |     {
154 |      "data": {
155 |       "text/plain": [
156 |        "6.1460843373493974"
157 |       ]
158 |      },
159 |      "execution_count": 10,
160 |      "metadata": {},
161 |      "output_type": "execute_result"
162 |     }
163 |    ],
164 |    "source": [
165 |     "high_alcohol['quality'].mean()"
166 |    ]
167 |   },
168 |   {
169 |    "cell_type": "markdown",
170 |    "metadata": {},
171 |    "source": [
172 |     "#### QUESTION 1 OF 2\n",
173 |     "\n",
174 |     "*Do wines with higher alcoholic content generally receive better ratings?*\n",
175 |     "Yes"
176 |    ]
177 |   },
178 |   {
179 |    "cell_type": "markdown",
180 |    "metadata": {},
181 |    "source": [
182 |     "### Do sweeter wines receive better ratings?"
183 |    ]
184 |   },
185 |   {
186 |    "cell_type": "code",
187 |    "execution_count": 13,
188 |    "metadata": {},
189 |    "outputs": [
190 |     {
191 |      "data": {
192 |       "text/plain": [
193 |        "3.0"
194 |       ]
195 |      },
196 |      "execution_count": 13,
197 |      "metadata": {},
198 |      "output_type": "execute_result"
199 |     }
200 |    ],
201 |    "source": [
202 |     "# get the median amount of residual sugar\n",
203 |     "df['residual_sugar'].median()"
204 |    ]
205 |   },
206 |   {
207 |    "cell_type": "code",
208 |    "execution_count": 14,
209 |    "metadata": {},
210 |    "outputs": [
211 |     {
212 |      "data": {
213 |       "text/plain": [
214 |        "True"
215 |       ]
216 |      },
217 |      "execution_count": 14,
218 |      "metadata": {},
219 |      "output_type": "execute_result"
220 |     }
221 |    ],
222 |    "source": [
223 |     "# select samples with residual sugar less than the median\n",
224 |     "low_sugar = df.query('residual_sugar < 3.0')\n",
225 |     "\n",
226 |     "# select samples with residual sugar greater than or equal to the median\n",
227 |     "high_sugar = df.query('residual_sugar >= 3.0')\n",
228 |     "\n",
229 |     "# ensure these queries included each sample exactly once\n",
230 |     "num_samples == low_sugar['quality'].count() + high_sugar['quality'].count() # should be True"
231 |    ]
232 |   },
233 |   {
234 |    "cell_type": "code",
235 |    "execution_count": 15,
236 |    "metadata": {},
237 |    "outputs": [
238 |     {
239 |      "data": {
240 |       "text/plain": [
241 |        "5.8088007437248219"
242 |       ]
243 |      },
244 |      "execution_count": 15,
245 |      "metadata": {},
246 |      "output_type": "execute_result"
247 |     }
248 |    ],
249 |    "source": [
250 |     "# get mean quality rating for the low sugar groups\n",
251 |     "low_sugar['quality'].mean()"
252 |    ]
253 |   },
254 |   {
255 |    "cell_type": "code",
256 |    "execution_count": 16,
257 |    "metadata": {},
258 |    "outputs": [
259 |     {
260 |      "data": {
261 |       "text/plain": [
262 |        "5.8278287461773699"
263 |       ]
264 |      },
265 |      "execution_count": 16,
266 |      "metadata": {},
267 |      "output_type": "execute_result"
268 |     }
269 |    ],
270 |    "source": [
271 |     "# get mean quality rating for the high sugar groups\n",
272 |     "high_sugar['quality'].mean()"
273 |    ]
274 |   },
275 |   {
276 |    "cell_type": "markdown",
277 |    "metadata": {},
278 |    "source": [
279 |     "#### QUESTION 2 OF 2\n",
280 |     "\n",
281 |     "*Do sweeter wines generally receive higher ratings?*\n",
282 |     "Yes"
283 |    ]
284 |   },
285 |   {
286 |    "cell_type": "code",
287 |    "execution_count": null,
288 |    "metadata": {
289 |     "collapsed": true
290 |    },
291 |    "outputs": [],
292 |    "source": []
293 |   }
294 |  ],
295 |  "metadata": {
296 |   "kernelspec": {
297 |    "display_name": "Python 3",
298 |    "language": "python",
299 |    "name": "python3"
300 |   },
301 |   "language_info": {
302 |    "codemirror_mode": {
303 |     "name": "ipython",
304 |     "version": 3
305 |    },
306 |    "file_extension": ".py",
307 |    "mimetype": "text/x-python",
308 |    "name": "python",
309 |    "nbconvert_exporter": "python",
310 |    "pygments_lexer": "ipython3",
311 |    "version": "3.6.1"
312 |   }
313 |  },
314 |  "nbformat": 4,
315 |  "nbformat_minor": 2
316 | }
317 | 


--------------------------------------------------------------------------------
/conclusions_quiz.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {},
  6 |    "source": [
  7 |     "# Drawing Conclusions Quiz\n",
  8 |     "Use the space below to explore `store_data.csv` to answer the quiz questions below."
  9 |    ]
 10 |   },
 11 |   {
 12 |    "cell_type": "code",
 13 |    "execution_count": 8,
 14 |    "metadata": {
 15 |     "collapsed": true
 16 |    },
 17 |    "outputs": [],
 18 |    "source": [
 19 |     "# imports and load data\n",
 20 |     "import pandas as pd\n",
 21 |     "import numpy as np\n",
 22 |     "from datetime import datetime\n",
 23 |     "% matplotlib inline\n",
 24 |     "\n",
 25 |     "df_store = pd.read_csv('store_data.csv')\n"
 26 |    ]
 27 |   },
 28 |   {
 29 |    "cell_type": "code",
 30 |    "execution_count": 2,
 31 |    "metadata": {},
 32 |    "outputs": [
 33 |     {
 34 |      "name": "stdout",
 35 |      "output_type": "stream",
 36 |      "text": [
 37 |       "<class 'pandas.core.frame.DataFrame'>\n",
 38 |       "RangeIndex: 200 entries, 0 to 199\n",
 39 |       "Data columns (total 6 columns):\n",
 40 |       "week      200 non-null object\n",
 41 |       "storeA    200 non-null int64\n",
 42 |       "storeB    200 non-null int64\n",
 43 |       "storeC    200 non-null int64\n",
 44 |       "storeD    200 non-null int64\n",
 45 |       "storeE    200 non-null int64\n",
 46 |       "dtypes: int64(5), object(1)\n",
 47 |       "memory usage: 9.5+ KB\n"
 48 |      ]
 49 |     },
 50 |     {
 51 |      "data": {
 52 |       "text/html": [
 53 |        "<div>\n",
 54 |        "<style>\n",
 55 |        "    .dataframe thead tr:only-child th {\n",
 56 |        "        text-align: right;\n",
 57 |        "    }\n",
 58 |        "\n",
 59 |        "    .dataframe thead th {\n",
 60 |        "        text-align: left;\n",
 61 |        "    }\n",
 62 |        "\n",
 63 |        "    .dataframe tbody tr th {\n",
 64 |        "        vertical-align: top;\n",
 65 |        "    }\n",
 66 |        "</style>\n",
 67 |        "<table border=\"1\" class=\"dataframe\">\n",
 68 |        "  <thead>\n",
 69 |        "    <tr style=\"text-align: right;\">\n",
 70 |        "      <th></th>\n",
 71 |        "      <th>week</th>\n",
 72 |        "      <th>storeA</th>\n",
 73 |        "      <th>storeB</th>\n",
 74 |        "      <th>storeC</th>\n",
 75 |        "      <th>storeD</th>\n",
 76 |        "      <th>storeE</th>\n",
 77 |        "    </tr>\n",
 78 |        "  </thead>\n",
 79 |        "  <tbody>\n",
 80 |        "    <tr>\n",
 81 |        "      <th>0</th>\n",
 82 |        "      <td>2014-05-04</td>\n",
 83 |        "      <td>2643</td>\n",
 84 |        "      <td>8257</td>\n",
 85 |        "      <td>3893</td>\n",
 86 |        "      <td>6231</td>\n",
 87 |        "      <td>1294</td>\n",
 88 |        "    </tr>\n",
 89 |        "    <tr>\n",
 90 |        "      <th>1</th>\n",
 91 |        "      <td>2014-05-11</td>\n",
 92 |        "      <td>6444</td>\n",
 93 |        "      <td>5736</td>\n",
 94 |        "      <td>5634</td>\n",
 95 |        "      <td>7092</td>\n",
 96 |        "      <td>2907</td>\n",
 97 |        "    </tr>\n",
 98 |        "    <tr>\n",
 99 |        "      <th>2</th>\n",
100 |        "      <td>2014-05-18</td>\n",
101 |        "      <td>9646</td>\n",
102 |        "      <td>2552</td>\n",
103 |        "      <td>4253</td>\n",
104 |        "      <td>5447</td>\n",
105 |        "      <td>4736</td>\n",
106 |        "    </tr>\n",
107 |        "    <tr>\n",
108 |        "      <th>3</th>\n",
109 |        "      <td>2014-05-25</td>\n",
110 |        "      <td>5960</td>\n",
111 |        "      <td>10740</td>\n",
112 |        "      <td>8264</td>\n",
113 |        "      <td>6063</td>\n",
114 |        "      <td>949</td>\n",
115 |        "    </tr>\n",
116 |        "    <tr>\n",
117 |        "      <th>4</th>\n",
118 |        "      <td>2014-06-01</td>\n",
119 |        "      <td>7412</td>\n",
120 |        "      <td>7374</td>\n",
121 |        "      <td>3208</td>\n",
122 |        "      <td>3985</td>\n",
123 |        "      <td>3023</td>\n",
124 |        "    </tr>\n",
125 |        "  </tbody>\n",
126 |        "</table>\n",
127 |        "</div>"
128 |       ],
129 |       "text/plain": [
130 |        "         week  storeA  storeB  storeC  storeD  storeE\n",
131 |        "0  2014-05-04    2643    8257    3893    6231    1294\n",
132 |        "1  2014-05-11    6444    5736    5634    7092    2907\n",
133 |        "2  2014-05-18    9646    2552    4253    5447    4736\n",
134 |        "3  2014-05-25    5960   10740    8264    6063     949\n",
135 |        "4  2014-06-01    7412    7374    3208    3985    3023"
136 |       ]
137 |      },
138 |      "execution_count": 2,
139 |      "metadata": {},
140 |      "output_type": "execute_result"
141 |     }
142 |    ],
143 |    "source": [
144 |     "# explore data\n",
145 |     "df_store.info()\n",
146 |     "\n",
147 |     "df_store.head()"
148 |    ]
149 |   },
150 |   {
151 |    "cell_type": "code",
152 |    "execution_count": 3,
153 |    "metadata": {},
154 |    "outputs": [
155 |     {
156 |      "name": "stdout",
157 |      "output_type": "stream",
158 |      "text": [
159 |       "Total sales is 5115145\n",
160 |       "Max total sales is 1351342\n",
161 |       "store with max total sales is storeB\n"
162 |      ]
163 |     }
164 |    ],
165 |    "source": [
166 |     "# total sales for the last month\n",
167 |     "#first make new column with total values for all stores on that date\n",
168 |     "df_store['total'] = df_store['storeA'] + df_store['storeB'] + df_store['storeC'] + df_store['storeD'] +df_store['storeE'] \n",
169 |     "#get total sales\n",
170 |     "total_sales = sum(df_store['total'])\n",
171 |     "print('Total sales is {}'.format(total_sales))\n",
172 |     "list_store_names = ['storeA', 'storeB', 'storeC', 'storeD', 'storeE']\n",
173 |     "\n",
174 |     "list_total = []\n",
175 |     "sum_A = sum(df_store['storeA'])\n",
176 |     "sum_B = sum(df_store['storeB'])\n",
177 |     "sum_C = sum(df_store['storeC'])\n",
178 |     "sum_D = sum(df_store['storeD'])\n",
179 |     "sum_E = sum(df_store['storeE'])\n",
180 |     "list_total = [sum_A, sum_B, sum_C, sum_D, sum_E]\n",
181 |     "max_tot = max(list_total)\n",
182 |     "#compute max value and return position\n",
183 |     "pos = list_total.index(max_tot)\n",
184 |     "print(\"Max total sales is {}\".format(max_tot))\n",
185 |     "print(\"store with max total sales is {}\".format(list_store_names[pos]))\n"
186 |    ]
187 |   },
188 |   {
189 |    "cell_type": "code",
190 |    "execution_count": 44,
191 |    "metadata": {},
192 |    "outputs": [
193 |     {
194 |      "name": "stdout",
195 |      "output_type": "stream",
196 |      "text": [
197 |       "Store with max sales in last month is storeA\n"
198 |      ]
199 |     }
200 |    ],
201 |    "source": [
202 |     "#calculate sales for final month\n",
203 |     "\n",
204 |     "#find time range\n",
205 |     "#df_store[180:]   #inspect last months to determine span\n",
206 |     "\n",
207 |     "df_span_last = df_store[(df_store['week'] > '2018-02-04') & (df_store['week'] < '2018-02-25')]\n",
208 |     "#print(df_span_last) #checkpoint\n",
209 |     "a3 = sum(df_span_last['storeA'])\n",
210 |     "b3 = sum(df_span_last['storeB'])\n",
211 |     "c3 = sum(df_span_last['storeC'])\n",
212 |     "d3 = sum(df_span_last['storeD'])\n",
213 |     "e3 = sum(df_span_last['storeE'])\n",
214 |     "last = [a3,b3,c3,d3,e3]\n",
215 |     "max_last = max(last)\n",
216 |     "#print(last, max_last) #checkpoint\n",
217 |     "store_max_last = list_store_names[last.index(max_last)]\n",
218 |     "print('Store with max sales in last month is {}'.format(store_max_last))\n",
219 |     "\n",
220 |     "\n"
221 |    ]
222 |   },
223 |   {
224 |    "cell_type": "code",
225 |    "execution_count": 4,
226 |    "metadata": {},
227 |    "outputs": [
228 |     {
229 |      "name": "stdout",
230 |      "output_type": "stream",
231 |      "text": [
232 |       "store with highest average sales [using lists] is storeB\n",
233 |       "store with highest average sales [using dicts] is storeB\n"
234 |      ]
235 |     }
236 |    ],
237 |    "source": [
238 |     "# average sales\n",
239 |     "avg_A = df_store['storeA'].mean()\n",
240 |     "avg_B = df_store['storeB'].mean()\n",
241 |     "avg_C = df_store['storeC'].mean()\n",
242 |     "avg_D = df_store['storeD'].mean()\n",
243 |     "avg_E = df_store['storeE'].mean()\n",
244 |     "\n",
245 |     "#compute store with highest average sales using lists\n",
246 |     "list_avg = [avg_A, avg_B, avg_C, avg_D, avg_E]\n",
247 |     "list_store_names = ['storeA', 'storeB', 'storeC', 'storeD', 'storeE']\n",
248 |     "#print(list_avg) #check-point to verify contents as five averages\n",
249 |     "\n",
250 |     "max_avg = max(list_avg)\n",
251 |     "#compute max value and return position\n",
252 |     "pos = list_avg.index(max_avg)\n",
253 |     "#use the position value to select store\n",
254 |     "print(\"store with highest average sales [using lists] is {}\".format(list_store_names[pos]))\n",
255 |     "\n",
256 |     "#compute store with highest average sales using dicts\n",
257 |     "dict_avg = {'storeA' : avg_A, 'storeB' : avg_B, 'storeC' : avg_C, \n",
258 |     "            'storeD' : avg_D, 'storeE' : avg_E}\n",
259 |     "dict_max = max(dict_avg, key=dict_avg.get)\n",
260 |     "print(\"store with highest average sales [using dicts] is {}\".format(dict_max))\n"
261 |    ]
262 |   },
263 |   {
264 |    "cell_type": "code",
265 |    "execution_count": 5,
266 |    "metadata": {},
267 |    "outputs": [
268 |     {
269 |      "name": "stdout",
270 |      "output_type": "stream",
271 |      "text": [
272 |       "          week  storeA  storeB  storeC  storeD  storeE  total\n",
273 |       "97  2016-03-13    2054    1390    5112    5513    2536  16605\n",
274 |       "    storeA  storeB  storeC  storeD  storeE\n",
275 |       "97    2054    1390    5112    5513    2536\n"
276 |      ]
277 |     }
278 |    ],
279 |    "source": [
280 |     "# sales on march 13, 2016\n",
281 |     "\n",
282 |     "# calculate sales on week of March 13th, 2016\n",
283 |     "sale = df_store.loc[df_store['week'] == '2016-03-13']\n",
284 |     "print(sale)   #checkpoint to verify record returned\n",
285 |     "\n",
286 |     "del sale['week']\n",
287 |     "del sale['total']\n",
288 |     "print(sale)\n"
289 |    ]
290 |   },
291 |   {
292 |    "cell_type": "code",
293 |    "execution_count": 6,
294 |    "metadata": {},
295 |    "outputs": [
296 |     {
297 |      "name": "stdout",
298 |      "output_type": "stream",
299 |      "text": [
300 |       "         week  storeA  storeB  storeC  storeD  storeE  total\n",
301 |       "9  2014-07-06    8567    3228     927    3277     168  16167\n"
302 |      ]
303 |     }
304 |    ],
305 |    "source": [
306 |     "# worst week for store C\n",
307 |     "sale_storeC = []\n",
308 |     "sale_storeC = df_store['storeC']\n",
309 |     "date_storeC = df_store['week']\n",
310 |     "\n",
311 |     "minC = min(sale_storeC)\n",
312 |     "\n",
313 |     "\n",
314 |     "print(df_store.loc[df_store['storeC'] == minC])"
315 |    ]
316 |   },
317 |   {
318 |    "cell_type": "code",
319 |    "execution_count": 39,
320 |    "metadata": {},
321 |    "outputs": [
322 |     {
323 |      "name": "stdout",
324 |      "output_type": "stream",
325 |      "text": [
326 |       "2014-05-04\n",
327 |       "2018-02-25\n",
328 |       "[74852, 68640, 56848, 63367, 24636] 74852\n",
329 |       "Store with max sales in last 3 month period is storeA\n"
330 |      ]
331 |     }
332 |    ],
333 |    "source": [
334 |     "# total sales during most recent 3 month period\n",
335 |     "\n",
336 |     "#find time range\n",
337 |     "dates_ranges = df_store['week']\n",
338 |     "print(min(dates_ranges))\n",
339 |     "print(max(dates_ranges))\n",
340 |     "#df_store[180:]   #inspect last months to determine span\n",
341 |     "\n",
342 |     "#df_span = df_store[(df_store['week'] > '2017-09-03') & (df_store['week'] < '2017-12-17')]\n",
343 |     "#print(df_span)\n",
344 |     "\n",
345 |     "\n",
346 |     "df_span_last3 = df_store[(df_store['week'] > '2017-12-03') & (df_store['week'] < '2018-02-25')]\n",
347 |     "#print(df_span_last3) #checkpoint\n",
348 |     "a3 = sum(df_span_last3['storeA'])\n",
349 |     "b3 = sum(df_span_last3['storeB'])\n",
350 |     "c3 = sum(df_span_last3['storeC'])\n",
351 |     "d3 = sum(df_span_last3['storeD'])\n",
352 |     "e3 = sum(df_span_last3['storeE'])\n",
353 |     "last3 = [a3,b3,c3,d3,e3]\n",
354 |     "max_last3 = max(last3)\n",
355 |     "#print(last3, max_last3) #checkpoint\n",
356 |     "store_max_last3 = list_store_names[last3.index(max_last3)]\n",
357 |     "print('Store with max sales in last 3 month period is {}'.format(store_max_last3))\n",
358 |     "\n",
359 |     "\n",
360 |     "#df_new=df_store[df_store['week'] == '2018-02-25']\n",
361 |     "#print(df_new)\n"
362 |    ]
363 |   },
364 |   {
365 |    "cell_type": "code",
366 |    "execution_count": null,
367 |    "metadata": {
368 |     "collapsed": true
369 |    },
370 |    "outputs": [],
371 |    "source": []
372 |   }
373 |  ],
374 |  "metadata": {
375 |   "kernelspec": {
376 |    "display_name": "Python 3",
377 |    "language": "python",
378 |    "name": "python3"
379 |   },
380 |   "language_info": {
381 |    "codemirror_mode": {
382 |     "name": "ipython",
383 |     "version": 3
384 |    },
385 |    "file_extension": ".py",
386 |    "mimetype": "text/x-python",
387 |    "name": "python",
388 |    "nbconvert_exporter": "python",
389 |    "pygments_lexer": "ipython3",
390 |    "version": "3.6.1"
391 |   }
392 |  },
393 |  "nbformat": 4,
394 |  "nbformat_minor": 2
395 | }
396 | 


--------------------------------------------------------------------------------
/fix_datatypes_cyl.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {},
  6 |    "source": [
  7 |     "# Fixing `cyl` Data Type\n",
  8 |     "- 2008: extract int from string\n",
  9 |     "- 2018: convert float to int"
 10 |    ]
 11 |   },
 12 |   {
 13 |    "cell_type": "code",
 14 |    "execution_count": 21,
 15 |    "metadata": {
 16 |     "collapsed": true
 17 |    },
 18 |    "outputs": [],
 19 |    "source": [
 20 |     "import pandas as pd"
 21 |    ]
 22 |   },
 23 |   {
 24 |    "cell_type": "code",
 25 |    "execution_count": 22,
 26 |    "metadata": {
 27 |     "collapsed": true
 28 |    },
 29 |    "outputs": [],
 30 |    "source": [
 31 |     "# load datasets\n",
 32 |     "\n",
 33 |     "df_08 = pd.read_csv('data_08.csv')\n",
 34 |     "df_18 = pd.read_csv('data_18.csv')"
 35 |    ]
 36 |   },
 37 |   {
 38 |    "cell_type": "code",
 39 |    "execution_count": 23,
 40 |    "metadata": {},
 41 |    "outputs": [
 42 |     {
 43 |      "data": {
 44 |       "text/plain": [
 45 |        "6     409\n",
 46 |        "4     283\n",
 47 |        "8     199\n",
 48 |        "5      48\n",
 49 |        "12     30\n",
 50 |        "10     14\n",
 51 |        "2       2\n",
 52 |        "16      1\n",
 53 |        "Name: cyl, dtype: int64"
 54 |       ]
 55 |      },
 56 |      "execution_count": 23,
 57 |      "metadata": {},
 58 |      "output_type": "execute_result"
 59 |     }
 60 |    ],
 61 |    "source": [
 62 |     "# check value counts for the 2008 cyl column\n",
 63 |     "df_08['cyl'].value_counts()"
 64 |    ]
 65 |   },
 66 |   {
 67 |    "cell_type": "markdown",
 68 |    "metadata": {},
 69 |    "source": [
 70 |     "Read [this](https://stackoverflow.com/questions/35376387/extract-int-from-string-in-pandas) to help you extract ints from strings in Pandas for the next step."
 71 |    ]
 72 |   },
 73 |   {
 74 |    "cell_type": "code",
 75 |    "execution_count": 24,
 76 |    "metadata": {},
 77 |    "outputs": [
 78 |     {
 79 |      "ename": "AttributeError",
 80 |      "evalue": "Can only use .str accessor with string values, which use np.object_ dtype in pandas",
 81 |      "output_type": "error",
 82 |      "traceback": [
 83 |       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
 84 |       "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
 85 |       "\u001b[0;32m<ipython-input-24-9b7bf11a5afd>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;31m# Extract int from strings in the 2008 cyl column\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mdf_08\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'cyl'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf_08\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'cyl'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mextract\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'(\\d+)'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mastype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mint\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
 86 |       "\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/generic.py\u001b[0m in \u001b[0;36m__getattr__\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m   3075\u001b[0m         if (name in self._internal_names_set or name in self._metadata or\n\u001b[1;32m   3076\u001b[0m                 name in self._accessors):\n\u001b[0;32m-> 3077\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mobject\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__getattribute__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   3078\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3079\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mname\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_info_axis\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
 87 |       "\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/base.py\u001b[0m in \u001b[0;36m__get__\u001b[0;34m(self, instance, owner)\u001b[0m\n\u001b[1;32m    241\u001b[0m             \u001b[0;31m# this ensures that Series.str.<method> is well defined\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    242\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0maccessor_cls\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 243\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconstruct_accessor\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minstance\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    244\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    245\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m__set__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minstance\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
 88 |       "\u001b[0;32m/opt/conda/lib/python3.6/site-packages/pandas/core/strings.py\u001b[0m in \u001b[0;36m_make_str_accessor\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   1907\u001b[0m             \u001b[0;31m# (instead of test for object dtype), but that isn't practical for\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1908\u001b[0m             \u001b[0;31m# performance reasons until we have a str dtype (GH 9343)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1909\u001b[0;31m             raise AttributeError(\"Can only use .str accessor with string \"\n\u001b[0m\u001b[1;32m   1910\u001b[0m                                  \u001b[0;34m\"values, which use np.object_ dtype in \"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1911\u001b[0m                                  \"pandas\")\n",
 89 |       "\u001b[0;31mAttributeError\u001b[0m: Can only use .str accessor with string values, which use np.object_ dtype in pandas"
 90 |      ]
 91 |     }
 92 |    ],
 93 |    "source": [
 94 |     "# Extract int from strings in the 2008 cyl column\n",
 95 |     "df_08['cyl'] = df_08['cyl'].str.extract('(\\d+)').astype(int)"
 96 |    ]
 97 |   },
 98 |   {
 99 |    "cell_type": "code",
100 |    "execution_count": 25,
101 |    "metadata": {},
102 |    "outputs": [
103 |     {
104 |      "data": {
105 |       "text/plain": [
106 |        "6     409\n",
107 |        "4     283\n",
108 |        "8     199\n",
109 |        "5      48\n",
110 |        "12     30\n",
111 |        "10     14\n",
112 |        "2       2\n",
113 |        "16      1\n",
114 |        "Name: cyl, dtype: int64"
115 |       ]
116 |      },
117 |      "execution_count": 25,
118 |      "metadata": {},
119 |      "output_type": "execute_result"
120 |     }
121 |    ],
122 |    "source": [
123 |     "# Check value counts for 2008 cyl column again to confirm the change\n",
124 |     "df_08['cyl'].value_counts()"
125 |    ]
126 |   },
127 |   {
128 |    "cell_type": "code",
129 |    "execution_count": 26,
130 |    "metadata": {
131 |     "collapsed": true
132 |    },
133 |    "outputs": [],
134 |    "source": [
135 |     "# convert 2018 cyl column to int\n",
136 |     "#df_18['cyl'] = int(df_18['cyl'])\n",
137 |     "df_18.cyl = df_18.cyl.astype(int)"
138 |    ]
139 |   },
140 |   {
141 |    "cell_type": "code",
142 |    "execution_count": 27,
143 |    "metadata": {},
144 |    "outputs": [
145 |     {
146 |      "data": {
147 |       "text/plain": [
148 |        "4     365\n",
149 |        "6     246\n",
150 |        "8     153\n",
151 |        "3      18\n",
152 |        "12      9\n",
153 |        "5       2\n",
154 |        "16      1\n",
155 |        "Name: cyl, dtype: int64"
156 |       ]
157 |      },
158 |      "execution_count": 27,
159 |      "metadata": {},
160 |      "output_type": "execute_result"
161 |     }
162 |    ],
163 |    "source": [
164 |     "# Check value counts for 2018 cyl column again to confirm the change\n",
165 |     "df_18['cyl'].value_counts()"
166 |    ]
167 |   },
168 |   {
169 |    "cell_type": "code",
170 |    "execution_count": 28,
171 |    "metadata": {
172 |     "collapsed": true
173 |    },
174 |    "outputs": [],
175 |    "source": [
176 |     "df_08.to_csv('data_08.csv', index=False)\n",
177 |     "df_18.to_csv('data_18.csv', index=False)"
178 |    ]
179 |   },
180 |   {
181 |    "cell_type": "code",
182 |    "execution_count": null,
183 |    "metadata": {
184 |     "collapsed": true
185 |    },
186 |    "outputs": [],
187 |    "source": []
188 |   }
189 |  ],
190 |  "metadata": {
191 |   "kernelspec": {
192 |    "display_name": "Python 3",
193 |    "language": "python",
194 |    "name": "python3"
195 |   },
196 |   "language_info": {
197 |    "codemirror_mode": {
198 |     "name": "ipython",
199 |     "version": 3
200 |    },
201 |    "file_extension": ".py",
202 |    "mimetype": "text/x-python",
203 |    "name": "python",
204 |    "nbconvert_exporter": "python",
205 |    "pygments_lexer": "ipython3",
206 |    "version": "3.6.1"
207 |   }
208 |  },
209 |  "nbformat": 4,
210 |  "nbformat_minor": 2
211 | }
212 | 


--------------------------------------------------------------------------------
/matplotlib_example.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {
  6 |     "collapsed": true
  7 |    },
  8 |    "source": [
  9 |     "# Creating a Bar Chart Using Matplotlib"
 10 |    ]
 11 |   },
 12 |   {
 13 |    "cell_type": "code",
 14 |    "execution_count": 2,
 15 |    "metadata": {
 16 |     "collapsed": true
 17 |    },
 18 |    "outputs": [],
 19 |    "source": [
 20 |     "import matplotlib.pyplot as plt\n",
 21 |     "% matplotlib inline"
 22 |    ]
 23 |   },
 24 |   {
 25 |    "cell_type": "markdown",
 26 |    "metadata": {},
 27 |    "source": [
 28 |     "There are two required arguments in pyplot's `bar` function: the x-coordinates of the bars, and the heights of the bars."
 29 |    ]
 30 |   },
 31 |   {
 32 |    "cell_type": "code",
 33 |    "execution_count": 3,
 34 |    "metadata": {},
 35 |    "outputs": [
 36 |     {
 37 |      "data": {
 38 |       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAD8CAYAAAB5Pm/hAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nZ8Vx7M5o+qYAAAAASUVORK5CYII=\n",
 39 |       "text/plain": [
 40 |        "<matplotlib.figure.Figure at 0x7f86c4629898>"
 41 |       ]
 42 |      },
 43 |      "metadata": {},
 44 |      "output_type": "display_data"
 45 |     }
 46 |    ],
 47 |    "source": [
 48 |     "plt.bar([1, 2, 3], [224, 620, 425]);"
 49 |    ]
 50 |   },
 51 |   {
 52 |    "cell_type": "markdown",
 53 |    "metadata": {},
 54 |    "source": [
 55 |     "You can specify the x tick labels using pyplot's `xticks` function, or by specifying another parameter in the `bar` function. The two cells below accomplish the same thing."
 56 |    ]
 57 |   },
 58 |   {
 59 |    "cell_type": "code",
 60 |    "execution_count": 4,
 61 |    "metadata": {},
 62 |    "outputs": [
 63 |     {
 64 |      "data": {
 65 |       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAD8CAYAAAB5Pm/hAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
 66 |       "text/plain": [
 67 |        "<matplotlib.figure.Figure at 0x7f86c43255c0>"
 68 |       ]
 69 |      },
 70 |      "metadata": {},
 71 |      "output_type": "display_data"
 72 |     }
 73 |    ],
 74 |    "source": [
 75 |     "# plot bars\n",
 76 |     "plt.bar([1, 2, 3], [224, 620, 425])\n",
 77 |     "\n",
 78 |     "# specify x coordinates of tick labels and their labels\n",
 79 |     "plt.xticks([1, 2, 3], ['a', 'b', 'c']);"
 80 |    ]
 81 |   },
 82 |   {
 83 |    "cell_type": "code",
 84 |    "execution_count": 5,
 85 |    "metadata": {},
 86 |    "outputs": [
 87 |     {
 88 |      "data": {
 89 |       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAD8CAYAAAB5Pm/hAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
 90 |       "text/plain": [
 91 |        "<matplotlib.figure.Figure at 0x7f86c423c8d0>"
 92 |       ]
 93 |      },
 94 |      "metadata": {},
 95 |      "output_type": "display_data"
 96 |     }
 97 |    ],
 98 |    "source": [
 99 |     "# plot bars with x tick labels\n",
100 |     "plt.bar([1, 2, 3], [224, 620, 425], tick_label=['a', 'b', 'c']);"
101 |    ]
102 |   },
103 |   {
104 |    "cell_type": "markdown",
105 |    "metadata": {},
106 |    "source": [
107 |     "Set the title and label axes like this."
108 |    ]
109 |   },
110 |   {
111 |    "cell_type": "code",
112 |    "execution_count": null,
113 |    "metadata": {
114 |     "collapsed": true
115 |    },
116 |    "outputs": [],
117 |    "source": [
118 |     "plt.bar([1, 2, 3], [224, 620, 425], tick_label=['a', 'b', 'c'])\n",
119 |     "plt.title('Some Title')\n",
120 |     "plt.xlabel('Some X Label')\n",
121 |     "plt.ylabel('Some Y Label');"
122 |    ]
123 |   }
124 |  ],
125 |  "metadata": {
126 |   "kernelspec": {
127 |    "display_name": "Python 3",
128 |    "language": "python",
129 |    "name": "python3"
130 |   },
131 |   "language_info": {
132 |    "codemirror_mode": {
133 |     "name": "ipython",
134 |     "version": 3
135 |    },
136 |    "file_extension": ".py",
137 |    "mimetype": "text/x-python",
138 |    "name": "python",
139 |    "nbconvert_exporter": "python",
140 |    "pygments_lexer": "ipython3",
141 |    "version": "3.6.1"
142 |   }
143 |  },
144 |  "nbformat": 4,
145 |  "nbformat_minor": 2
146 | }
147 | 


--------------------------------------------------------------------------------
/plots-pandas.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "metadata": {
  7 |     "collapsed": true
  8 |    },
  9 |    "outputs": [],
 10 |    "source": [
 11 |     "import pandas as pd\n",
 12 |     "% matplotlib inline"
 13 |    ]
 14 |   },
 15 |   {
 16 |    "cell_type": "code",
 17 |    "execution_count": 2,
 18 |    "metadata": {},
 19 |    "outputs": [
 20 |     {
 21 |      "data": {
 22 |       "text/html": [
 23 |        "<div>\n",
 24 |        "<style>\n",
 25 |        "    .dataframe thead tr:only-child th {\n",
 26 |        "        text-align: right;\n",
 27 |        "    }\n",
 28 |        "\n",
 29 |        "    .dataframe thead th {\n",
 30 |        "        text-align: left;\n",
 31 |        "    }\n",
 32 |        "\n",
 33 |        "    .dataframe tbody tr th {\n",
 34 |        "        vertical-align: top;\n",
 35 |        "    }\n",
 36 |        "</style>\n",
 37 |        "<table border=\"1\" class=\"dataframe\">\n",
 38 |        "  <thead>\n",
 39 |        "    <tr style=\"text-align: right;\">\n",
 40 |        "      <th></th>\n",
 41 |        "      <th>year</th>\n",
 42 |        "      <th>city</th>\n",
 43 |        "      <th>country</th>\n",
 44 |        "      <th>avg_temp</th>\n",
 45 |        "      <th>sevenDayMA</th>\n",
 46 |        "      <th>FiveYearMA</th>\n",
 47 |        "      <th>TenYearMA</th>\n",
 48 |        "    </tr>\n",
 49 |        "  </thead>\n",
 50 |        "  <tbody>\n",
 51 |        "    <tr>\n",
 52 |        "      <th>0</th>\n",
 53 |        "      <td>1743</td>\n",
 54 |        "      <td>Chicago</td>\n",
 55 |        "      <td>United States</td>\n",
 56 |        "      <td>5.44</td>\n",
 57 |        "      <td>NaN</td>\n",
 58 |        "      <td>NaN</td>\n",
 59 |        "      <td>NaN</td>\n",
 60 |        "    </tr>\n",
 61 |        "    <tr>\n",
 62 |        "      <th>1</th>\n",
 63 |        "      <td>1744</td>\n",
 64 |        "      <td>Chicago</td>\n",
 65 |        "      <td>United States</td>\n",
 66 |        "      <td>11.73</td>\n",
 67 |        "      <td>NaN</td>\n",
 68 |        "      <td>NaN</td>\n",
 69 |        "      <td>NaN</td>\n",
 70 |        "    </tr>\n",
 71 |        "    <tr>\n",
 72 |        "      <th>2</th>\n",
 73 |        "      <td>1745</td>\n",
 74 |        "      <td>Chicago</td>\n",
 75 |        "      <td>United States</td>\n",
 76 |        "      <td>1.80</td>\n",
 77 |        "      <td>NaN</td>\n",
 78 |        "      <td>NaN</td>\n",
 79 |        "      <td>NaN</td>\n",
 80 |        "    </tr>\n",
 81 |        "    <tr>\n",
 82 |        "      <th>3</th>\n",
 83 |        "      <td>1746</td>\n",
 84 |        "      <td>Chicago</td>\n",
 85 |        "      <td>United States</td>\n",
 86 |        "      <td>0.00</td>\n",
 87 |        "      <td>NaN</td>\n",
 88 |        "      <td>NaN</td>\n",
 89 |        "      <td>NaN</td>\n",
 90 |        "    </tr>\n",
 91 |        "    <tr>\n",
 92 |        "      <th>4</th>\n",
 93 |        "      <td>1747</td>\n",
 94 |        "      <td>Chicago</td>\n",
 95 |        "      <td>United States</td>\n",
 96 |        "      <td>0.00</td>\n",
 97 |        "      <td>NaN</td>\n",
 98 |        "      <td>3.794</td>\n",
 99 |        "      <td>NaN</td>\n",
100 |        "    </tr>\n",
101 |        "  </tbody>\n",
102 |        "</table>\n",
103 |        "</div>"
104 |       ],
105 |       "text/plain": [
106 |        "   year     city        country  avg_temp  sevenDayMA  FiveYearMA  TenYearMA\n",
107 |        "0  1743  Chicago  United States      5.44         NaN         NaN        NaN\n",
108 |        "1  1744  Chicago  United States     11.73         NaN         NaN        NaN\n",
109 |        "2  1745  Chicago  United States      1.80         NaN         NaN        NaN\n",
110 |        "3  1746  Chicago  United States      0.00         NaN         NaN        NaN\n",
111 |        "4  1747  Chicago  United States      0.00         NaN       3.794        NaN"
112 |       ]
113 |      },
114 |      "execution_count": 2,
115 |      "metadata": {},
116 |      "output_type": "execute_result"
117 |     }
118 |    ],
119 |    "source": [
120 |     "df_temp = pd.read_csv('ChicagoResults.csv')\n",
121 |     "df_temp.head()"
122 |    ]
123 |   },
124 |   {
125 |    "cell_type": "code",
126 |    "execution_count": 7,
127 |    "metadata": {},
128 |    "outputs": [],
129 |    "source": [
130 |     "df_19 = df_temp[df_temp['year'] > 1800]"
131 |    ]
132 |   },
133 |   {
134 |    "cell_type": "code",
135 |    "execution_count": 8,
136 |    "metadata": {},
137 |    "outputs": [
138 |     {
139 |      "data": {
140 |       "text/html": [
141 |        "<div>\n",
142 |        "<style>\n",
143 |        "    .dataframe thead tr:only-child th {\n",
144 |        "        text-align: right;\n",
145 |        "    }\n",
146 |        "\n",
147 |        "    .dataframe thead th {\n",
148 |        "        text-align: left;\n",
149 |        "    }\n",
150 |        "\n",
151 |        "    .dataframe tbody tr th {\n",
152 |        "        vertical-align: top;\n",
153 |        "    }\n",
154 |        "</style>\n",
155 |        "<table border=\"1\" class=\"dataframe\">\n",
156 |        "  <thead>\n",
157 |        "    <tr style=\"text-align: right;\">\n",
158 |        "      <th></th>\n",
159 |        "      <th>year</th>\n",
160 |        "      <th>city</th>\n",
161 |        "      <th>country</th>\n",
162 |        "      <th>avg_temp</th>\n",
163 |        "      <th>sevenDayMA</th>\n",
164 |        "      <th>FiveYearMA</th>\n",
165 |        "      <th>TenYearMA</th>\n",
166 |        "    </tr>\n",
167 |        "  </thead>\n",
168 |        "  <tbody>\n",
169 |        "    <tr>\n",
170 |        "      <th>58</th>\n",
171 |        "      <td>1801</td>\n",
172 |        "      <td>Chicago</td>\n",
173 |        "      <td>United States</td>\n",
174 |        "      <td>10.47</td>\n",
175 |        "      <td>10.101429</td>\n",
176 |        "      <td>10.156</td>\n",
177 |        "      <td>10.083</td>\n",
178 |        "    </tr>\n",
179 |        "    <tr>\n",
180 |        "      <th>59</th>\n",
181 |        "      <td>1802</td>\n",
182 |        "      <td>Chicago</td>\n",
183 |        "      <td>United States</td>\n",
184 |        "      <td>10.66</td>\n",
185 |        "      <td>10.194286</td>\n",
186 |        "      <td>10.356</td>\n",
187 |        "      <td>10.187</td>\n",
188 |        "    </tr>\n",
189 |        "    <tr>\n",
190 |        "      <th>60</th>\n",
191 |        "      <td>1803</td>\n",
192 |        "      <td>Chicago</td>\n",
193 |        "      <td>United States</td>\n",
194 |        "      <td>10.48</td>\n",
195 |        "      <td>10.274286</td>\n",
196 |        "      <td>10.366</td>\n",
197 |        "      <td>10.215</td>\n",
198 |        "    </tr>\n",
199 |        "    <tr>\n",
200 |        "      <th>61</th>\n",
201 |        "      <td>1804</td>\n",
202 |        "      <td>Chicago</td>\n",
203 |        "      <td>United States</td>\n",
204 |        "      <td>10.41</td>\n",
205 |        "      <td>10.381429</td>\n",
206 |        "      <td>10.426</td>\n",
207 |        "      <td>10.226</td>\n",
208 |        "    </tr>\n",
209 |        "    <tr>\n",
210 |        "      <th>62</th>\n",
211 |        "      <td>1805</td>\n",
212 |        "      <td>Chicago</td>\n",
213 |        "      <td>United States</td>\n",
214 |        "      <td>10.63</td>\n",
215 |        "      <td>10.410000</td>\n",
216 |        "      <td>10.530</td>\n",
217 |        "      <td>10.288</td>\n",
218 |        "    </tr>\n",
219 |        "  </tbody>\n",
220 |        "</table>\n",
221 |        "</div>"
222 |       ],
223 |       "text/plain": [
224 |        "    year     city        country  avg_temp  sevenDayMA  FiveYearMA  TenYearMA\n",
225 |        "58  1801  Chicago  United States     10.47   10.101429      10.156     10.083\n",
226 |        "59  1802  Chicago  United States     10.66   10.194286      10.356     10.187\n",
227 |        "60  1803  Chicago  United States     10.48   10.274286      10.366     10.215\n",
228 |        "61  1804  Chicago  United States     10.41   10.381429      10.426     10.226\n",
229 |        "62  1805  Chicago  United States     10.63   10.410000      10.530     10.288"
230 |       ]
231 |      },
232 |      "execution_count": 8,
233 |      "metadata": {},
234 |      "output_type": "execute_result"
235 |     }
236 |    ],
237 |    "source": [
238 |     "df_19.head()"
239 |    ]
240 |   },
241 |   {
242 |    "cell_type": "code",
243 |    "execution_count": 10,
244 |    "metadata": {},
245 |    "outputs": [
246 |     {
247 |      "data": {
248 |       "text/html": [
249 |        "<div>\n",
250 |        "<style>\n",
251 |        "    .dataframe thead tr:only-child th {\n",
252 |        "        text-align: right;\n",
253 |        "    }\n",
254 |        "\n",
255 |        "    .dataframe thead th {\n",
256 |        "        text-align: left;\n",
257 |        "    }\n",
258 |        "\n",
259 |        "    .dataframe tbody tr th {\n",
260 |        "        vertical-align: top;\n",
261 |        "    }\n",
262 |        "</style>\n",
263 |        "<table border=\"1\" class=\"dataframe\">\n",
264 |        "  <thead>\n",
265 |        "    <tr style=\"text-align: right;\">\n",
266 |        "      <th></th>\n",
267 |        "      <th>year</th>\n",
268 |        "      <th>city</th>\n",
269 |        "      <th>country</th>\n",
270 |        "      <th>avg_temp</th>\n",
271 |        "      <th>sevenDayMA</th>\n",
272 |        "      <th>FiveYearMA</th>\n",
273 |        "      <th>TenYearMA</th>\n",
274 |        "    </tr>\n",
275 |        "  </thead>\n",
276 |        "  <tbody>\n",
277 |        "    <tr>\n",
278 |        "      <th>158</th>\n",
279 |        "      <td>1901</td>\n",
280 |        "      <td>Chicago</td>\n",
281 |        "      <td>United States</td>\n",
282 |        "      <td>9.87</td>\n",
283 |        "      <td>10.088571</td>\n",
284 |        "      <td>10.182</td>\n",
285 |        "      <td>9.953</td>\n",
286 |        "    </tr>\n",
287 |        "    <tr>\n",
288 |        "      <th>159</th>\n",
289 |        "      <td>1902</td>\n",
290 |        "      <td>Chicago</td>\n",
291 |        "      <td>United States</td>\n",
292 |        "      <td>10.04</td>\n",
293 |        "      <td>10.191429</td>\n",
294 |        "      <td>10.180</td>\n",
295 |        "      <td>10.036</td>\n",
296 |        "    </tr>\n",
297 |        "    <tr>\n",
298 |        "      <th>160</th>\n",
299 |        "      <td>1903</td>\n",
300 |        "      <td>Chicago</td>\n",
301 |        "      <td>United States</td>\n",
302 |        "      <td>9.57</td>\n",
303 |        "      <td>10.074286</td>\n",
304 |        "      <td>10.046</td>\n",
305 |        "      <td>10.102</td>\n",
306 |        "    </tr>\n",
307 |        "    <tr>\n",
308 |        "      <th>161</th>\n",
309 |        "      <td>1904</td>\n",
310 |        "      <td>Chicago</td>\n",
311 |        "      <td>United States</td>\n",
312 |        "      <td>8.56</td>\n",
313 |        "      <td>9.861429</td>\n",
314 |        "      <td>9.734</td>\n",
315 |        "      <td>9.879</td>\n",
316 |        "    </tr>\n",
317 |        "    <tr>\n",
318 |        "      <th>162</th>\n",
319 |        "      <td>1905</td>\n",
320 |        "      <td>Chicago</td>\n",
321 |        "      <td>United States</td>\n",
322 |        "      <td>9.42</td>\n",
323 |        "      <td>9.744286</td>\n",
324 |        "      <td>9.492</td>\n",
325 |        "      <td>9.889</td>\n",
326 |        "    </tr>\n",
327 |        "  </tbody>\n",
328 |        "</table>\n",
329 |        "</div>"
330 |       ],
331 |       "text/plain": [
332 |        "     year     city        country  avg_temp  sevenDayMA  FiveYearMA  TenYearMA\n",
333 |        "158  1901  Chicago  United States      9.87   10.088571      10.182      9.953\n",
334 |        "159  1902  Chicago  United States     10.04   10.191429      10.180     10.036\n",
335 |        "160  1903  Chicago  United States      9.57   10.074286      10.046     10.102\n",
336 |        "161  1904  Chicago  United States      8.56    9.861429       9.734      9.879\n",
337 |        "162  1905  Chicago  United States      9.42    9.744286       9.492      9.889"
338 |       ]
339 |      },
340 |      "execution_count": 10,
341 |      "metadata": {},
342 |      "output_type": "execute_result"
343 |     }
344 |    ],
345 |    "source": [
346 |     "mask = df_temp['year'] > 1900\n",
347 |     "df_20 = df_temp[mask]\n",
348 |     "df_20.head()"
349 |    ]
350 |   },
351 |   {
352 |    "cell_type": "code",
353 |    "execution_count": 11,
354 |    "metadata": {},
355 |    "outputs": [
356 |     {
357 |      "data": {
358 |       "text/plain": [
359 |        "count    213.000000\n",
360 |        "mean      10.140751\n",
361 |        "std        0.892496\n",
362 |        "min        7.800000\n",
363 |        "25%        9.560000\n",
364 |        "50%       10.140000\n",
365 |        "75%       10.660000\n",
366 |        "max       12.820000\n",
367 |        "Name: avg_temp, dtype: float64"
368 |       ]
369 |      },
370 |      "execution_count": 11,
371 |      "metadata": {},
372 |      "output_type": "execute_result"
373 |     }
374 |    ],
375 |    "source": [
376 |     "df_19['avg_temp'].describe()"
377 |    ]
378 |   },
379 |   {
380 |    "cell_type": "code",
381 |    "execution_count": null,
382 |    "metadata": {
383 |     "collapsed": true
384 |    },
385 |    "outputs": [],
386 |    "source": []
387 |   }
388 |  ],
389 |  "metadata": {
390 |   "kernelspec": {
391 |    "display_name": "Python 3",
392 |    "language": "python",
393 |    "name": "python3"
394 |   },
395 |   "language_info": {
396 |    "codemirror_mode": {
397 |     "name": "ipython",
398 |     "version": 3
399 |    },
400 |    "file_extension": ".py",
401 |    "mimetype": "text/x-python",
402 |    "name": "python",
403 |    "nbconvert_exporter": "python",
404 |    "pygments_lexer": "ipython3",
405 |    "version": "3.6.2"
406 |   }
407 |  },
408 |  "nbformat": 4,
409 |  "nbformat_minor": 2
410 | }
411 | 


--------------------------------------------------------------------------------
/plotting_type_quality.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {
  6 |     "collapsed": true
  7 |    },
  8 |    "source": [
  9 |     "# Plotting Wine Type and Quality with Matplotlib"
 10 |    ]
 11 |   },
 12 |   {
 13 |    "cell_type": "code",
 14 |    "execution_count": 14,
 15 |    "metadata": {
 16 |     "collapsed": true
 17 |    },
 18 |    "outputs": [],
 19 |    "source": [
 20 |     "import numpy as np\n",
 21 |     "import pandas as pd\n",
 22 |     "import matplotlib.pyplot as plt\n",
 23 |     "% matplotlib inline\n",
 24 |     "import seaborn as sns\n",
 25 |     "sns.set_style('darkgrid')\n",
 26 |     "\n",
 27 |     "wine_df = pd.read_csv('winequality_edited.csv')"
 28 |    ]
 29 |   },
 30 |   {
 31 |    "cell_type": "markdown",
 32 |    "metadata": {},
 33 |    "source": [
 34 |     "### Create arrays for red bar heights white bar heights\n",
 35 |     "Remember, there's a bar for each combination of color and quality rating. Each bar's height is based on the proportion of samples of that color with that quality rating.\n",
 36 |     "1. Red bar proportions = counts for each quality rating / total # of red samples\n",
 37 |     "2. White bar proportions = counts for each quality rating / total # of white samples"
 38 |    ]
 39 |   },
 40 |   {
 41 |    "cell_type": "code",
 42 |    "execution_count": 15,
 43 |    "metadata": {},
 44 |    "outputs": [
 45 |     {
 46 |      "data": {
 47 |       "text/plain": [
 48 |        "color  quality\n",
 49 |        "red    3            10\n",
 50 |        "       4            53\n",
 51 |        "       5           681\n",
 52 |        "       6           638\n",
 53 |        "       7           199\n",
 54 |        "       8            18\n",
 55 |        "white  3            20\n",
 56 |        "       4           163\n",
 57 |        "       5          1457\n",
 58 |        "       6          2198\n",
 59 |        "       7           880\n",
 60 |        "       8           175\n",
 61 |        "       9             5\n",
 62 |        "Name: pH, dtype: int64"
 63 |       ]
 64 |      },
 65 |      "execution_count": 15,
 66 |      "metadata": {},
 67 |      "output_type": "execute_result"
 68 |     }
 69 |    ],
 70 |    "source": [
 71 |     "# get counts for each rating and color\n",
 72 |     "color_counts = wine_df.groupby(['color', 'quality']).count()['pH']\n",
 73 |     "color_counts"
 74 |    ]
 75 |   },
 76 |   {
 77 |    "cell_type": "code",
 78 |    "execution_count": 16,
 79 |    "metadata": {},
 80 |    "outputs": [
 81 |     {
 82 |      "data": {
 83 |       "text/plain": [
 84 |        "color\n",
 85 |        "red      1599\n",
 86 |        "white    4898\n",
 87 |        "Name: pH, dtype: int64"
 88 |       ]
 89 |      },
 90 |      "execution_count": 16,
 91 |      "metadata": {},
 92 |      "output_type": "execute_result"
 93 |     }
 94 |    ],
 95 |    "source": [
 96 |     "# get total counts for each color\n",
 97 |     "color_totals = wine_df.groupby('color').count()['pH']\n",
 98 |     "color_totals"
 99 |    ]
100 |   },
101 |   {
102 |    "cell_type": "code",
103 |    "execution_count": 17,
104 |    "metadata": {},
105 |    "outputs": [
106 |     {
107 |      "data": {
108 |       "text/plain": [
109 |        "quality\n",
110 |        "3    0.006254\n",
111 |        "4    0.033146\n",
112 |        "5    0.425891\n",
113 |        "6    0.398999\n",
114 |        "7    0.124453\n",
115 |        "8    0.011257\n",
116 |        "Name: pH, dtype: float64"
117 |       ]
118 |      },
119 |      "execution_count": 17,
120 |      "metadata": {},
121 |      "output_type": "execute_result"
122 |     }
123 |    ],
124 |    "source": [
125 |     "# get proportions by dividing red rating counts by total # of red samples\n",
126 |     "red_proportions = color_counts['red'] / color_totals['red']\n",
127 |     "red_proportions"
128 |    ]
129 |   },
130 |   {
131 |    "cell_type": "code",
132 |    "execution_count": 18,
133 |    "metadata": {},
134 |    "outputs": [
135 |     {
136 |      "data": {
137 |       "text/plain": [
138 |        "quality\n",
139 |        "3    0.004083\n",
140 |        "4    0.033279\n",
141 |        "5    0.297468\n",
142 |        "6    0.448755\n",
143 |        "7    0.179665\n",
144 |        "8    0.035729\n",
145 |        "9    0.001021\n",
146 |        "Name: pH, dtype: float64"
147 |       ]
148 |      },
149 |      "execution_count": 18,
150 |      "metadata": {},
151 |      "output_type": "execute_result"
152 |     }
153 |    ],
154 |    "source": [
155 |     "# get proportions by dividing white rating counts by total # of white samples\n",
156 |     "white_proportions = color_counts['white'] / color_totals['white']\n",
157 |     "white_proportions"
158 |    ]
159 |   },
160 |   {
161 |    "cell_type": "markdown",
162 |    "metadata": {},
163 |    "source": [
164 |     "### Plot proportions on a bar chart\n",
165 |     "Set the x coordinate location for each rating group and and width of each bar."
166 |    ]
167 |   },
168 |   {
169 |    "cell_type": "code",
170 |    "execution_count": 19,
171 |    "metadata": {
172 |     "collapsed": true
173 |    },
174 |    "outputs": [],
175 |    "source": [
176 |     "ind = np.arange(len(red_proportions))  # the x locations for the groups\n",
177 |     "width = 0.35       # the width of the bars"
178 |    ]
179 |   },
180 |   {
181 |    "cell_type": "markdown",
182 |    "metadata": {},
183 |    "source": [
184 |     "Now let’s create the plot."
185 |    ]
186 |   },
187 |   {
188 |    "cell_type": "code",
189 |    "execution_count": 21,
190 |    "metadata": {},
191 |    "outputs": [
192 |     {
193 |      "ename": "ValueError",
194 |      "evalue": "shape mismatch: objects cannot be broadcast to a single shape",
195 |      "output_type": "error",
196 |      "traceback": [
197 |       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
198 |       "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
199 |       "\u001b[0;32m<ipython-input-21-8e175eda6196>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;31m# plot bars\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0mred_bars\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbar\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mind\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mred_proportions\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwidth\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcolor\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'r'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0malpha\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m.7\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlabel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'Red Wine'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0mwhite_bars\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbar\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mind\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mwidth\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwhite_proportions\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwidth\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcolor\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'w'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0malpha\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m.7\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlabel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'White Wine'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      4\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0;31m# title and labels\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
200 |       "\u001b[0;32m/opt/conda/lib/python3.6/site-packages/matplotlib/pyplot.py\u001b[0m in \u001b[0;36mbar\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m   2625\u001b[0m                       mplDeprecation)\n\u001b[1;32m   2626\u001b[0m     \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2627\u001b[0;31m         \u001b[0mret\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0max\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbar\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2628\u001b[0m     \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2629\u001b[0m         \u001b[0max\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_hold\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mwashold\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
201 |       "\u001b[0;32m/opt/conda/lib/python3.6/site-packages/matplotlib/__init__.py\u001b[0m in \u001b[0;36minner\u001b[0;34m(ax, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1708\u001b[0m                     warnings.warn(msg % (label_namer, func.__name__),\n\u001b[1;32m   1709\u001b[0m                                   RuntimeWarning, stacklevel=2)\n\u001b[0;32m-> 1710\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0max\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1711\u001b[0m         \u001b[0mpre_doc\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0minner\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__doc__\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1712\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mpre_doc\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
202 |       "\u001b[0;32m/opt/conda/lib/python3.6/site-packages/matplotlib/axes/_axes.py\u001b[0m in \u001b[0;36mbar\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   2079\u001b[0m         x, height, width, y, linewidth = np.broadcast_arrays(\n\u001b[1;32m   2080\u001b[0m             \u001b[0;31m# Make args iterable too.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2081\u001b[0;31m             np.atleast_1d(x), height, width, y, linewidth)\n\u001b[0m\u001b[1;32m   2082\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2083\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0morientation\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m'vertical'\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
203 |       "\u001b[0;32m/opt/conda/lib/python3.6/site-packages/numpy/lib/stride_tricks.py\u001b[0m in \u001b[0;36mbroadcast_arrays\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    247\u001b[0m     \u001b[0margs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0marray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0m_m\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcopy\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msubok\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msubok\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0m_m\u001b[0m \u001b[0;32min\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    248\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 249\u001b[0;31m     \u001b[0mshape\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_broadcast_shape\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    250\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    251\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mall\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0marray\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0mshape\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0marray\u001b[0m \u001b[0;32min\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
204 |       "\u001b[0;32m/opt/conda/lib/python3.6/site-packages/numpy/lib/stride_tricks.py\u001b[0m in \u001b[0;36m_broadcast_shape\u001b[0;34m(*args)\u001b[0m\n\u001b[1;32m    182\u001b[0m     \u001b[0;31m# use the old-iterator because np.nditer does not handle size 0 arrays\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    183\u001b[0m     \u001b[0;31m# consistently\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 184\u001b[0;31m     \u001b[0mb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbroadcast\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;36m32\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    185\u001b[0m     \u001b[0;31m# unfortunately, it cannot handle 32 or more arguments directly\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    186\u001b[0m     \u001b[0;32mfor\u001b[0m \u001b[0mpos\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m32\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m31\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
205 |       "\u001b[0;31mValueError\u001b[0m: shape mismatch: objects cannot be broadcast to a single shape"
206 |      ]
207 |     },
208 |     {
209 |      "data": {
210 |       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXYAAAD1CAYAAABEDd6nAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nMP8HDmMzSpqwHYkAAAAASUVORK5CYII=\n",
211 |       "text/plain": [
212 |        "<matplotlib.figure.Figure at 0x7f704d32aeb8>"
213 |       ]
214 |      },
215 |      "metadata": {},
216 |      "output_type": "display_data"
217 |     }
218 |    ],
219 |    "source": [
220 |     "# plot bars\n",
221 |     "red_bars = plt.bar(ind, red_proportions, width, color='r', alpha=.7, label='Red Wine')\n",
222 |     "white_bars = plt.bar(ind + width, white_proportions, width, color='w', alpha=.7, label='White Wine')\n",
223 |     "\n",
224 |     "# title and labels\n",
225 |     "plt.ylabel('Proportion')\n",
226 |     "plt.xlabel('Quality')\n",
227 |     "plt.title('Proportion by Wine Color and Quality')\n",
228 |     "locations = ind + width / 2  # xtick locations\n",
229 |     "labels = ['3', '4', '5', '6', '7', '8', '9']  # xtick labels\n",
230 |     "plt.xticks(locations, labels)\n",
231 |     "\n",
232 |     "# legend\n",
233 |     "plt.legend()"
234 |    ]
235 |   },
236 |   {
237 |    "cell_type": "markdown",
238 |    "metadata": {},
239 |    "source": [
240 |     "Oh, that didn't work because we're missing a red wine value for a the 9 rating. Even though this number is a 0, we need it for our plot. Run the last two cells after running the cell below."
241 |    ]
242 |   },
243 |   {
244 |    "cell_type": "code",
245 |    "execution_count": 22,
246 |    "metadata": {},
247 |    "outputs": [
248 |     {
249 |      "data": {
250 |       "text/plain": [
251 |        "quality\n",
252 |        "3    0.006254\n",
253 |        "4    0.033146\n",
254 |        "5    0.425891\n",
255 |        "6    0.398999\n",
256 |        "7    0.124453\n",
257 |        "8    0.011257\n",
258 |        "9    0.000000\n",
259 |        "Name: pH, dtype: float64"
260 |       ]
261 |      },
262 |      "execution_count": 22,
263 |      "metadata": {},
264 |      "output_type": "execute_result"
265 |     }
266 |    ],
267 |    "source": [
268 |     "red_proportions['9'] = 0\n",
269 |     "red_proportions"
270 |    ]
271 |   },
272 |   {
273 |    "cell_type": "code",
274 |    "execution_count": null,
275 |    "metadata": {
276 |     "collapsed": true
277 |    },
278 |    "outputs": [],
279 |    "source": []
280 |   }
281 |  ],
282 |  "metadata": {
283 |   "kernelspec": {
284 |    "display_name": "Python 3",
285 |    "language": "python",
286 |    "name": "python3"
287 |   },
288 |   "language_info": {
289 |    "codemirror_mode": {
290 |     "name": "ipython",
291 |     "version": 3
292 |    },
293 |    "file_extension": ".py",
294 |    "mimetype": "text/x-python",
295 |    "name": "python",
296 |    "nbconvert_exporter": "python",
297 |    "pygments_lexer": "ipython3",
298 |    "version": "3.6.1"
299 |   }
300 |  },
301 |  "nbformat": 4,
302 |  "nbformat_minor": 2
303 | }
304 | 


--------------------------------------------------------------------------------