├── README.md
├── LICENSE
├── Feature_Preprocessing_for_Categorical_and_Ordinal_Features_The_Most_Important_Step.ipynb
└── BreastTissue_Multiclass_Classification.ipynb


/README.md:
--------------------------------------------------------------------------------
1 | # blog-posts
2 | This repo contains code from the blog posts that I pubhish.
3 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
 1 | MIT License
 2 | 
 3 | Copyright (c) 2019 Sabina
 4 | 
 5 | Permission is hereby granted, free of charge, to any person obtaining a copy
 6 | of this software and associated documentation files (the "Software"), to deal
 7 | in the Software without restriction, including without limitation the rights
 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 | 
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 | 
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.
22 | 


--------------------------------------------------------------------------------
/Feature_Preprocessing_for_Categorical_and_Ordinal_Features_The_Most_Important_Step.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |   "nbformat": 4,
  3 |   "nbformat_minor": 0,
  4 |   "metadata": {
  5 |     "colab": {
  6 |       "name": "Feature Preprocessing for Categorical and Ordinal Features- The Most Important Step.ipynb",
  7 |       "provenance": [],
  8 |       "collapsed_sections": [],
  9 |       "include_colab_link": true
 10 |     },
 11 |     "kernelspec": {
 12 |       "name": "python3",
 13 |       "display_name": "Python 3"
 14 |     }
 15 |   },
 16 |   "cells": [
 17 |     {
 18 |       "cell_type": "markdown",
 19 |       "metadata": {
 20 |         "id": "view-in-github",
 21 |         "colab_type": "text"
 22 |       },
 23 |       "source": [
 24 |         "<a href=\"https://colab.research.google.com/github/sabiipoks/blog-posts/blob/master/Feature_Preprocessing_for_Categorical_and_Ordinal_Features_The_Most_Important_Step.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
 25 |       ]
 26 |     },
 27 |     {
 28 |       "cell_type": "markdown",
 29 |       "metadata": {
 30 |         "id": "qIrbn_FgFkbX",
 31 |         "colab_type": "text"
 32 |       },
 33 |       "source": [
 34 |         "# Feature Preprocessing for Categorical and Ordinal Features- The Most Important Step"
 35 |       ]
 36 |     },
 37 |     {
 38 |       "cell_type": "markdown",
 39 |       "metadata": {
 40 |         "id": "JPGkbECOFO2r",
 41 |         "colab_type": "text"
 42 |       },
 43 |       "source": [
 44 |         "\n",
 45 |         "\n",
 46 |         "Dataset from http://archive.ics.uci.edu/ml/datasets/Automobile obtained from UCI Machine Learning Repository.\n",
 47 |         "\n",
 48 |         "\n",
 49 |         "Dua, D. and Graff, C. (2019). UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science."
 50 |       ]
 51 |     },
 52 |     {
 53 |       "cell_type": "code",
 54 |       "metadata": {
 55 |         "id": "rBFE9nxxB2qz",
 56 |         "colab_type": "code",
 57 |         "colab": {}
 58 |       },
 59 |       "source": [
 60 |         "# import pandas\n",
 61 |         "import pandas as pd\n",
 62 |         "\n",
 63 |         "# define column names for the dataset as the dataset we will be importing does not have column names\n",
 64 |         "columns = ['symboling', 'normalized-losses', 'make', 'fuel-type', 'aspiration', 'num-of-doors', 'body-style', 'drive-wheels', 'engine-location', 'wheel-base', 'length', 'width', 'height',\n",
 65 |         "           'curb-weight', 'engine-type', 'num-of-cylinders', 'engine-size', 'fuel-system', 'bore', 'stroke', 'compression-ratio', 'horsepower', 'peak-rpm', 'city-mpg', 'highway-mpg', 'price']\n",
 66 |         "\n",
 67 |         "# read the dataset\n",
 68 |         "df = pd.read_csv('https://query.data.world/s/sdhzwzf6n2ivkvgabugicfo6oxiais', header=None, names=columns)"
 69 |       ],
 70 |       "execution_count": 0,
 71 |       "outputs": []
 72 |     },
 73 |     {
 74 |       "cell_type": "code",
 75 |       "metadata": {
 76 |         "id": "fDW15YqYB6KJ",
 77 |         "colab_type": "code",
 78 |         "colab": {
 79 |           "base_uri": "https://localhost:8080/",
 80 |           "height": 309
 81 |         },
 82 |         "outputId": "6e98ee8c-71b5-4daa-b544-05b7bcd3043d"
 83 |       },
 84 |       "source": [
 85 |         "df.head()"
 86 |       ],
 87 |       "execution_count": 128,
 88 |       "outputs": [
 89 |         {
 90 |           "output_type": "execute_result",
 91 |           "data": {
 92 |             "text/html": [
 93 |               "<div>\n",
 94 |               "<style scoped>\n",
 95 |               "    .dataframe tbody tr th:only-of-type {\n",
 96 |               "        vertical-align: middle;\n",
 97 |               "    }\n",
 98 |               "\n",
 99 |               "    .dataframe tbody tr th {\n",
100 |               "        vertical-align: top;\n",
101 |               "    }\n",
102 |               "\n",
103 |               "    .dataframe thead th {\n",
104 |               "        text-align: right;\n",
105 |               "    }\n",
106 |               "</style>\n",
107 |               "<table border=\"1\" class=\"dataframe\">\n",
108 |               "  <thead>\n",
109 |               "    <tr style=\"text-align: right;\">\n",
110 |               "      <th></th>\n",
111 |               "      <th>symboling</th>\n",
112 |               "      <th>normalized-losses</th>\n",
113 |               "      <th>make</th>\n",
114 |               "      <th>fuel-type</th>\n",
115 |               "      <th>aspiration</th>\n",
116 |               "      <th>num-of-doors</th>\n",
117 |               "      <th>body-style</th>\n",
118 |               "      <th>drive-wheels</th>\n",
119 |               "      <th>engine-location</th>\n",
120 |               "      <th>wheel-base</th>\n",
121 |               "      <th>length</th>\n",
122 |               "      <th>width</th>\n",
123 |               "      <th>height</th>\n",
124 |               "      <th>curb-weight</th>\n",
125 |               "      <th>engine-type</th>\n",
126 |               "      <th>num-of-cylinders</th>\n",
127 |               "      <th>engine-size</th>\n",
128 |               "      <th>fuel-system</th>\n",
129 |               "      <th>bore</th>\n",
130 |               "      <th>stroke</th>\n",
131 |               "      <th>compression-ratio</th>\n",
132 |               "      <th>horsepower</th>\n",
133 |               "      <th>peak-rpm</th>\n",
134 |               "      <th>city-mpg</th>\n",
135 |               "      <th>highway-mpg</th>\n",
136 |               "      <th>price</th>\n",
137 |               "    </tr>\n",
138 |               "  </thead>\n",
139 |               "  <tbody>\n",
140 |               "    <tr>\n",
141 |               "      <th>0</th>\n",
142 |               "      <td>3</td>\n",
143 |               "      <td>?</td>\n",
144 |               "      <td>alfa-romero</td>\n",
145 |               "      <td>gas</td>\n",
146 |               "      <td>std</td>\n",
147 |               "      <td>two</td>\n",
148 |               "      <td>convertible</td>\n",
149 |               "      <td>rwd</td>\n",
150 |               "      <td>front</td>\n",
151 |               "      <td>88.6</td>\n",
152 |               "      <td>168.8</td>\n",
153 |               "      <td>64.1</td>\n",
154 |               "      <td>48.8</td>\n",
155 |               "      <td>2548</td>\n",
156 |               "      <td>dohc</td>\n",
157 |               "      <td>four</td>\n",
158 |               "      <td>130</td>\n",
159 |               "      <td>mpfi</td>\n",
160 |               "      <td>3.47</td>\n",
161 |               "      <td>2.68</td>\n",
162 |               "      <td>9.0</td>\n",
163 |               "      <td>111</td>\n",
164 |               "      <td>5000</td>\n",
165 |               "      <td>21</td>\n",
166 |               "      <td>27</td>\n",
167 |               "      <td>13495</td>\n",
168 |               "    </tr>\n",
169 |               "    <tr>\n",
170 |               "      <th>1</th>\n",
171 |               "      <td>3</td>\n",
172 |               "      <td>?</td>\n",
173 |               "      <td>alfa-romero</td>\n",
174 |               "      <td>gas</td>\n",
175 |               "      <td>std</td>\n",
176 |               "      <td>two</td>\n",
177 |               "      <td>convertible</td>\n",
178 |               "      <td>rwd</td>\n",
179 |               "      <td>front</td>\n",
180 |               "      <td>88.6</td>\n",
181 |               "      <td>168.8</td>\n",
182 |               "      <td>64.1</td>\n",
183 |               "      <td>48.8</td>\n",
184 |               "      <td>2548</td>\n",
185 |               "      <td>dohc</td>\n",
186 |               "      <td>four</td>\n",
187 |               "      <td>130</td>\n",
188 |               "      <td>mpfi</td>\n",
189 |               "      <td>3.47</td>\n",
190 |               "      <td>2.68</td>\n",
191 |               "      <td>9.0</td>\n",
192 |               "      <td>111</td>\n",
193 |               "      <td>5000</td>\n",
194 |               "      <td>21</td>\n",
195 |               "      <td>27</td>\n",
196 |               "      <td>16500</td>\n",
197 |               "    </tr>\n",
198 |               "    <tr>\n",
199 |               "      <th>2</th>\n",
200 |               "      <td>1</td>\n",
201 |               "      <td>?</td>\n",
202 |               "      <td>alfa-romero</td>\n",
203 |               "      <td>gas</td>\n",
204 |               "      <td>std</td>\n",
205 |               "      <td>two</td>\n",
206 |               "      <td>hatchback</td>\n",
207 |               "      <td>rwd</td>\n",
208 |               "      <td>front</td>\n",
209 |               "      <td>94.5</td>\n",
210 |               "      <td>171.2</td>\n",
211 |               "      <td>65.5</td>\n",
212 |               "      <td>52.4</td>\n",
213 |               "      <td>2823</td>\n",
214 |               "      <td>ohcv</td>\n",
215 |               "      <td>six</td>\n",
216 |               "      <td>152</td>\n",
217 |               "      <td>mpfi</td>\n",
218 |               "      <td>2.68</td>\n",
219 |               "      <td>3.47</td>\n",
220 |               "      <td>9.0</td>\n",
221 |               "      <td>154</td>\n",
222 |               "      <td>5000</td>\n",
223 |               "      <td>19</td>\n",
224 |               "      <td>26</td>\n",
225 |               "      <td>16500</td>\n",
226 |               "    </tr>\n",
227 |               "    <tr>\n",
228 |               "      <th>3</th>\n",
229 |               "      <td>2</td>\n",
230 |               "      <td>164</td>\n",
231 |               "      <td>audi</td>\n",
232 |               "      <td>gas</td>\n",
233 |               "      <td>std</td>\n",
234 |               "      <td>four</td>\n",
235 |               "      <td>sedan</td>\n",
236 |               "      <td>fwd</td>\n",
237 |               "      <td>front</td>\n",
238 |               "      <td>99.8</td>\n",
239 |               "      <td>176.6</td>\n",
240 |               "      <td>66.2</td>\n",
241 |               "      <td>54.3</td>\n",
242 |               "      <td>2337</td>\n",
243 |               "      <td>ohc</td>\n",
244 |               "      <td>four</td>\n",
245 |               "      <td>109</td>\n",
246 |               "      <td>mpfi</td>\n",
247 |               "      <td>3.19</td>\n",
248 |               "      <td>3.40</td>\n",
249 |               "      <td>10.0</td>\n",
250 |               "      <td>102</td>\n",
251 |               "      <td>5500</td>\n",
252 |               "      <td>24</td>\n",
253 |               "      <td>30</td>\n",
254 |               "      <td>13950</td>\n",
255 |               "    </tr>\n",
256 |               "    <tr>\n",
257 |               "      <th>4</th>\n",
258 |               "      <td>2</td>\n",
259 |               "      <td>164</td>\n",
260 |               "      <td>audi</td>\n",
261 |               "      <td>gas</td>\n",
262 |               "      <td>std</td>\n",
263 |               "      <td>four</td>\n",
264 |               "      <td>sedan</td>\n",
265 |               "      <td>4wd</td>\n",
266 |               "      <td>front</td>\n",
267 |               "      <td>99.4</td>\n",
268 |               "      <td>176.6</td>\n",
269 |               "      <td>66.4</td>\n",
270 |               "      <td>54.3</td>\n",
271 |               "      <td>2824</td>\n",
272 |               "      <td>ohc</td>\n",
273 |               "      <td>five</td>\n",
274 |               "      <td>136</td>\n",
275 |               "      <td>mpfi</td>\n",
276 |               "      <td>3.19</td>\n",
277 |               "      <td>3.40</td>\n",
278 |               "      <td>8.0</td>\n",
279 |               "      <td>115</td>\n",
280 |               "      <td>5500</td>\n",
281 |               "      <td>18</td>\n",
282 |               "      <td>22</td>\n",
283 |               "      <td>17450</td>\n",
284 |               "    </tr>\n",
285 |               "  </tbody>\n",
286 |               "</table>\n",
287 |               "</div>"
288 |             ],
289 |             "text/plain": [
290 |               "   symboling normalized-losses         make  ... city-mpg highway-mpg  price\n",
291 |               "0          3                 ?  alfa-romero  ...       21          27  13495\n",
292 |               "1          3                 ?  alfa-romero  ...       21          27  16500\n",
293 |               "2          1                 ?  alfa-romero  ...       19          26  16500\n",
294 |               "3          2               164         audi  ...       24          30  13950\n",
295 |               "4          2               164         audi  ...       18          22  17450\n",
296 |               "\n",
297 |               "[5 rows x 26 columns]"
298 |             ]
299 |           },
300 |           "metadata": {
301 |             "tags": []
302 |           },
303 |           "execution_count": 128
304 |         }
305 |       ]
306 |     },
307 |     {
308 |       "cell_type": "code",
309 |       "metadata": {
310 |         "id": "tmN3VGkPB8l_",
311 |         "colab_type": "code",
312 |         "colab": {
313 |           "base_uri": "https://localhost:8080/",
314 |           "height": 203
315 |         },
316 |         "outputId": "28c07121-59d3-492c-a0d3-a6d603bb30f0"
317 |       },
318 |       "source": [
319 |         "# As this dataset contains a lot of features, let us select a few categorical features for the purpose of demonstration.\n",
320 |         "select_columns = ['fuel-type','engine-location','num-of-cylinders']\n",
321 |         "\n",
322 |         "df = df[select_columns]\n",
323 |         "df.head()"
324 |       ],
325 |       "execution_count": 129,
326 |       "outputs": [
327 |         {
328 |           "output_type": "execute_result",
329 |           "data": {
330 |             "text/html": [
331 |               "<div>\n",
332 |               "<style scoped>\n",
333 |               "    .dataframe tbody tr th:only-of-type {\n",
334 |               "        vertical-align: middle;\n",
335 |               "    }\n",
336 |               "\n",
337 |               "    .dataframe tbody tr th {\n",
338 |               "        vertical-align: top;\n",
339 |               "    }\n",
340 |               "\n",
341 |               "    .dataframe thead th {\n",
342 |               "        text-align: right;\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>fuel-type</th>\n",
350 |               "      <th>engine-location</th>\n",
351 |               "      <th>num-of-cylinders</th>\n",
352 |               "    </tr>\n",
353 |               "  </thead>\n",
354 |               "  <tbody>\n",
355 |               "    <tr>\n",
356 |               "      <th>0</th>\n",
357 |               "      <td>gas</td>\n",
358 |               "      <td>front</td>\n",
359 |               "      <td>four</td>\n",
360 |               "    </tr>\n",
361 |               "    <tr>\n",
362 |               "      <th>1</th>\n",
363 |               "      <td>gas</td>\n",
364 |               "      <td>front</td>\n",
365 |               "      <td>four</td>\n",
366 |               "    </tr>\n",
367 |               "    <tr>\n",
368 |               "      <th>2</th>\n",
369 |               "      <td>gas</td>\n",
370 |               "      <td>front</td>\n",
371 |               "      <td>six</td>\n",
372 |               "    </tr>\n",
373 |               "    <tr>\n",
374 |               "      <th>3</th>\n",
375 |               "      <td>gas</td>\n",
376 |               "      <td>front</td>\n",
377 |               "      <td>four</td>\n",
378 |               "    </tr>\n",
379 |               "    <tr>\n",
380 |               "      <th>4</th>\n",
381 |               "      <td>gas</td>\n",
382 |               "      <td>front</td>\n",
383 |               "      <td>five</td>\n",
384 |               "    </tr>\n",
385 |               "  </tbody>\n",
386 |               "</table>\n",
387 |               "</div>"
388 |             ],
389 |             "text/plain": [
390 |               "  fuel-type engine-location num-of-cylinders\n",
391 |               "0       gas           front             four\n",
392 |               "1       gas           front             four\n",
393 |               "2       gas           front              six\n",
394 |               "3       gas           front             four\n",
395 |               "4       gas           front             five"
396 |             ]
397 |           },
398 |           "metadata": {
399 |             "tags": []
400 |           },
401 |           "execution_count": 129
402 |         }
403 |       ]
404 |     },
405 |     {
406 |       "cell_type": "code",
407 |       "metadata": {
408 |         "id": "QxFIqfzvF1LR",
409 |         "colab_type": "code",
410 |         "colab": {
411 |           "base_uri": "https://localhost:8080/",
412 |           "height": 71
413 |         },
414 |         "outputId": "42c57254-7936-48b0-d13e-6555834833eb"
415 |       },
416 |       "source": [
417 |         "# find unique values for feature fuel-type\n",
418 |         "print(df['fuel-type'].unique())\n",
419 |         "\n",
420 |         "# find unique values for feature engine-location\n",
421 |         "print(df['engine-location'].unique())\n",
422 |         "\n",
423 |         "# find unique values for feature num-of-cylinders\n",
424 |         "print(df['num-of-cylinders'].unique())"
425 |       ],
426 |       "execution_count": 130,
427 |       "outputs": [
428 |         {
429 |           "output_type": "stream",
430 |           "text": [
431 |             "['gas' 'diesel']\n",
432 |             "['front' 'rear']\n",
433 |             "['four' 'six' 'five' 'three' 'twelve' 'two' 'eight']\n"
434 |           ],
435 |           "name": "stdout"
436 |         }
437 |       ]
438 |     },
439 |     {
440 |       "cell_type": "code",
441 |       "metadata": {
442 |         "id": "peck2hzVF-hK",
443 |         "colab_type": "code",
444 |         "colab": {
445 |           "base_uri": "https://localhost:8080/",
446 |           "height": 203
447 |         },
448 |         "outputId": "ff55a7cc-91bd-49ca-fe8e-f346463b6bba"
449 |       },
450 |       "source": [
451 |         "# import Label encoder\n",
452 |         "from sklearn.preprocessing import LabelEncoder\n",
453 |         "\n",
454 |         "# create laber encoder\n",
455 |         "label_encoder = LabelEncoder()\n",
456 |         "\n",
457 |         "# create a copy of dataset\n",
458 |         "df_le = df.copy()\n",
459 |         "\n",
460 |         "# fit the label encoder and transform the labels in the dataset to create new label encoded features\n",
461 |         "df_le['enc-fuel-type'] = label_encoder.fit_transform(df_le['fuel-type'])\n",
462 |         "df_le['enc-engine-location'] = label_encoder.fit_transform(df_le['engine-location'])\n",
463 |         "df_le['enc-num-of-cylinders'] = label_encoder.fit_transform(df_le['num-of-cylinders'])\n",
464 |         "\n",
465 |         "# drop original categorical features\n",
466 |         "columns_to_drop = ['fuel-type','engine-location','num-of-cylinders']\n",
467 |         "df_le = df_le.drop(columns=columns_to_drop)\n",
468 |         "\n",
469 |         "df_le.head()"
470 |       ],
471 |       "execution_count": 131,
472 |       "outputs": [
473 |         {
474 |           "output_type": "execute_result",
475 |           "data": {
476 |             "text/html": [
477 |               "<div>\n",
478 |               "<style scoped>\n",
479 |               "    .dataframe tbody tr th:only-of-type {\n",
480 |               "        vertical-align: middle;\n",
481 |               "    }\n",
482 |               "\n",
483 |               "    .dataframe tbody tr th {\n",
484 |               "        vertical-align: top;\n",
485 |               "    }\n",
486 |               "\n",
487 |               "    .dataframe thead th {\n",
488 |               "        text-align: right;\n",
489 |               "    }\n",
490 |               "</style>\n",
491 |               "<table border=\"1\" class=\"dataframe\">\n",
492 |               "  <thead>\n",
493 |               "    <tr style=\"text-align: right;\">\n",
494 |               "      <th></th>\n",
495 |               "      <th>enc-fuel-type</th>\n",
496 |               "      <th>enc-engine-location</th>\n",
497 |               "      <th>enc-num-of-cylinders</th>\n",
498 |               "    </tr>\n",
499 |               "  </thead>\n",
500 |               "  <tbody>\n",
501 |               "    <tr>\n",
502 |               "      <th>0</th>\n",
503 |               "      <td>1</td>\n",
504 |               "      <td>0</td>\n",
505 |               "      <td>2</td>\n",
506 |               "    </tr>\n",
507 |               "    <tr>\n",
508 |               "      <th>1</th>\n",
509 |               "      <td>1</td>\n",
510 |               "      <td>0</td>\n",
511 |               "      <td>2</td>\n",
512 |               "    </tr>\n",
513 |               "    <tr>\n",
514 |               "      <th>2</th>\n",
515 |               "      <td>1</td>\n",
516 |               "      <td>0</td>\n",
517 |               "      <td>3</td>\n",
518 |               "    </tr>\n",
519 |               "    <tr>\n",
520 |               "      <th>3</th>\n",
521 |               "      <td>1</td>\n",
522 |               "      <td>0</td>\n",
523 |               "      <td>2</td>\n",
524 |               "    </tr>\n",
525 |               "    <tr>\n",
526 |               "      <th>4</th>\n",
527 |               "      <td>1</td>\n",
528 |               "      <td>0</td>\n",
529 |               "      <td>1</td>\n",
530 |               "    </tr>\n",
531 |               "  </tbody>\n",
532 |               "</table>\n",
533 |               "</div>"
534 |             ],
535 |             "text/plain": [
536 |               "   enc-fuel-type  enc-engine-location  enc-num-of-cylinders\n",
537 |               "0              1                    0                     2\n",
538 |               "1              1                    0                     2\n",
539 |               "2              1                    0                     3\n",
540 |               "3              1                    0                     2\n",
541 |               "4              1                    0                     1"
542 |             ]
543 |           },
544 |           "metadata": {
545 |             "tags": []
546 |           },
547 |           "execution_count": 131
548 |         }
549 |       ]
550 |     },
551 |     {
552 |       "cell_type": "code",
553 |       "metadata": {
554 |         "id": "yeUMeFhqKugN",
555 |         "colab_type": "code",
556 |         "colab": {
557 |           "base_uri": "https://localhost:8080/",
558 |           "height": 203
559 |         },
560 |         "outputId": "435e70c7-6fd2-44c8-d3c9-7ac02f1e3d5d"
561 |       },
562 |       "source": [
563 |         "# import OneHotEncoder\n",
564 |         "from sklearn.preprocessing import OneHotEncoder\n",
565 |         "\n",
566 |         "# create one hot encoder\n",
567 |         "one_hot_encoder = OneHotEncoder()\n",
568 |         "\n",
569 |         "# create a copy of the dataset\n",
570 |         "df_ohe = df.copy()\n",
571 |         "\n",
572 |         "# fit one hot encoder\n",
573 |         "one_hot_encoder = one_hot_encoder.fit(df_ohe)\n",
574 |         "\n",
575 |         "# transform dataset \n",
576 |         "ohelabels = one_hot_encoder.transform(df_ohe).toarray()\n",
577 |         "df_ohe = pd.DataFrame(ohelabels, columns=one_hot_encoder.get_feature_names())\n",
578 |         "\n",
579 |         "df_ohe.head()\n"
580 |       ],
581 |       "execution_count": 132,
582 |       "outputs": [
583 |         {
584 |           "output_type": "execute_result",
585 |           "data": {
586 |             "text/html": [
587 |               "<div>\n",
588 |               "<style scoped>\n",
589 |               "    .dataframe tbody tr th:only-of-type {\n",
590 |               "        vertical-align: middle;\n",
591 |               "    }\n",
592 |               "\n",
593 |               "    .dataframe tbody tr th {\n",
594 |               "        vertical-align: top;\n",
595 |               "    }\n",
596 |               "\n",
597 |               "    .dataframe thead th {\n",
598 |               "        text-align: right;\n",
599 |               "    }\n",
600 |               "</style>\n",
601 |               "<table border=\"1\" class=\"dataframe\">\n",
602 |               "  <thead>\n",
603 |               "    <tr style=\"text-align: right;\">\n",
604 |               "      <th></th>\n",
605 |               "      <th>x0_diesel</th>\n",
606 |               "      <th>x0_gas</th>\n",
607 |               "      <th>x1_front</th>\n",
608 |               "      <th>x1_rear</th>\n",
609 |               "      <th>x2_eight</th>\n",
610 |               "      <th>x2_five</th>\n",
611 |               "      <th>x2_four</th>\n",
612 |               "      <th>x2_six</th>\n",
613 |               "      <th>x2_three</th>\n",
614 |               "      <th>x2_twelve</th>\n",
615 |               "      <th>x2_two</th>\n",
616 |               "    </tr>\n",
617 |               "  </thead>\n",
618 |               "  <tbody>\n",
619 |               "    <tr>\n",
620 |               "      <th>0</th>\n",
621 |               "      <td>0.0</td>\n",
622 |               "      <td>1.0</td>\n",
623 |               "      <td>1.0</td>\n",
624 |               "      <td>0.0</td>\n",
625 |               "      <td>0.0</td>\n",
626 |               "      <td>0.0</td>\n",
627 |               "      <td>1.0</td>\n",
628 |               "      <td>0.0</td>\n",
629 |               "      <td>0.0</td>\n",
630 |               "      <td>0.0</td>\n",
631 |               "      <td>0.0</td>\n",
632 |               "    </tr>\n",
633 |               "    <tr>\n",
634 |               "      <th>1</th>\n",
635 |               "      <td>0.0</td>\n",
636 |               "      <td>1.0</td>\n",
637 |               "      <td>1.0</td>\n",
638 |               "      <td>0.0</td>\n",
639 |               "      <td>0.0</td>\n",
640 |               "      <td>0.0</td>\n",
641 |               "      <td>1.0</td>\n",
642 |               "      <td>0.0</td>\n",
643 |               "      <td>0.0</td>\n",
644 |               "      <td>0.0</td>\n",
645 |               "      <td>0.0</td>\n",
646 |               "    </tr>\n",
647 |               "    <tr>\n",
648 |               "      <th>2</th>\n",
649 |               "      <td>0.0</td>\n",
650 |               "      <td>1.0</td>\n",
651 |               "      <td>1.0</td>\n",
652 |               "      <td>0.0</td>\n",
653 |               "      <td>0.0</td>\n",
654 |               "      <td>0.0</td>\n",
655 |               "      <td>0.0</td>\n",
656 |               "      <td>1.0</td>\n",
657 |               "      <td>0.0</td>\n",
658 |               "      <td>0.0</td>\n",
659 |               "      <td>0.0</td>\n",
660 |               "    </tr>\n",
661 |               "    <tr>\n",
662 |               "      <th>3</th>\n",
663 |               "      <td>0.0</td>\n",
664 |               "      <td>1.0</td>\n",
665 |               "      <td>1.0</td>\n",
666 |               "      <td>0.0</td>\n",
667 |               "      <td>0.0</td>\n",
668 |               "      <td>0.0</td>\n",
669 |               "      <td>1.0</td>\n",
670 |               "      <td>0.0</td>\n",
671 |               "      <td>0.0</td>\n",
672 |               "      <td>0.0</td>\n",
673 |               "      <td>0.0</td>\n",
674 |               "    </tr>\n",
675 |               "    <tr>\n",
676 |               "      <th>4</th>\n",
677 |               "      <td>0.0</td>\n",
678 |               "      <td>1.0</td>\n",
679 |               "      <td>1.0</td>\n",
680 |               "      <td>0.0</td>\n",
681 |               "      <td>0.0</td>\n",
682 |               "      <td>1.0</td>\n",
683 |               "      <td>0.0</td>\n",
684 |               "      <td>0.0</td>\n",
685 |               "      <td>0.0</td>\n",
686 |               "      <td>0.0</td>\n",
687 |               "      <td>0.0</td>\n",
688 |               "    </tr>\n",
689 |               "  </tbody>\n",
690 |               "</table>\n",
691 |               "</div>"
692 |             ],
693 |             "text/plain": [
694 |               "   x0_diesel  x0_gas  x1_front  x1_rear  ...  x2_six  x2_three  x2_twelve  x2_two\n",
695 |               "0        0.0     1.0       1.0      0.0  ...     0.0       0.0        0.0     0.0\n",
696 |               "1        0.0     1.0       1.0      0.0  ...     0.0       0.0        0.0     0.0\n",
697 |               "2        0.0     1.0       1.0      0.0  ...     1.0       0.0        0.0     0.0\n",
698 |               "3        0.0     1.0       1.0      0.0  ...     0.0       0.0        0.0     0.0\n",
699 |               "4        0.0     1.0       1.0      0.0  ...     0.0       0.0        0.0     0.0\n",
700 |               "\n",
701 |               "[5 rows x 11 columns]"
702 |             ]
703 |           },
704 |           "metadata": {
705 |             "tags": []
706 |           },
707 |           "execution_count": 132
708 |         }
709 |       ]
710 |     },
711 |     {
712 |       "cell_type": "code",
713 |       "metadata": {
714 |         "id": "uCV-EhaBqTxO",
715 |         "colab_type": "code",
716 |         "colab": {}
717 |       },
718 |       "source": [
719 |         ""
720 |       ],
721 |       "execution_count": 0,
722 |       "outputs": []
723 |     }
724 |   ]
725 | }


--------------------------------------------------------------------------------
/BreastTissue_Multiclass_Classification.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |   "nbformat": 4,
  3 |   "nbformat_minor": 0,
  4 |   "metadata": {
  5 |     "colab": {
  6 |       "name": "BreastTissue - Multiclass Classification.ipynb",
  7 |       "provenance": [],
  8 |       "collapsed_sections": [],
  9 |       "include_colab_link": true
 10 |     },
 11 |     "kernelspec": {
 12 |       "name": "python3",
 13 |       "display_name": "Python 3"
 14 |     }
 15 |   },
 16 |   "cells": [
 17 |     {
 18 |       "cell_type": "markdown",
 19 |       "metadata": {
 20 |         "id": "view-in-github",
 21 |         "colab_type": "text"
 22 |       },
 23 |       "source": [
 24 |         "<a href=\"https://colab.research.google.com/github/sabiipoks/blog-posts/blob/master/BreastTissue_Multiclass_Classification.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
 25 |       ]
 26 |     },
 27 |     {
 28 |       "cell_type": "markdown",
 29 |       "metadata": {
 30 |         "id": "GCe-2DR1O39Z",
 31 |         "colab_type": "text"
 32 |       },
 33 |       "source": [
 34 |         "# Multiclass Classification Model for Breast Tissue"
 35 |       ]
 36 |     },
 37 |     {
 38 |       "cell_type": "markdown",
 39 |       "metadata": {
 40 |         "id": "nyjq0183Dltz",
 41 |         "colab_type": "text"
 42 |       },
 43 |       "source": [
 44 |         "Data Source: https://archive.ics.uci.edu/ml/datasets/Breast+Tissue\n",
 45 |         "\n",
 46 |         "Dua, D. and Graff, C. (2019). UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science."
 47 |       ]
 48 |     },
 49 |     {
 50 |       "cell_type": "code",
 51 |       "metadata": {
 52 |         "id": "y3WuFJBmC8bU",
 53 |         "colab_type": "code",
 54 |         "outputId": "05f61a62-898c-4d6c-b3d1-bbc730a4e7b2",
 55 |         "colab": {
 56 |           "resources": {
 57 |             "http://localhost:8080/nbextensions/google.colab/files.js": {
 58 |               "data": "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",
 59 |               "ok": true,
 60 |               "headers": [
 61 |                 [
 62 |                   "content-type",
 63 |                   "application/javascript"
 64 |                 ]
 65 |               ],
 66 |               "status": 200,
 67 |               "status_text": ""
 68 |             }
 69 |           },
 70 |           "base_uri": "https://localhost:8080/",
 71 |           "height": 75
 72 |         }
 73 |       },
 74 |       "source": [
 75 |         "from google.colab import files\n",
 76 |         "uploaded = files.upload()"
 77 |       ],
 78 |       "execution_count": 1,
 79 |       "outputs": [
 80 |         {
 81 |           "output_type": "display_data",
 82 |           "data": {
 83 |             "text/html": [
 84 |               "\n",
 85 |               "     <input type=\"file\" id=\"files-f53805b9-3a09-48f3-b49f-d5d23d0e2bf9\" name=\"files[]\" multiple disabled />\n",
 86 |               "     <output id=\"result-f53805b9-3a09-48f3-b49f-d5d23d0e2bf9\">\n",
 87 |               "      Upload widget is only available when the cell has been executed in the\n",
 88 |               "      current browser session. Please rerun this cell to enable.\n",
 89 |               "      </output>\n",
 90 |               "      <script src=\"/nbextensions/google.colab/files.js\"></script> "
 91 |             ],
 92 |             "text/plain": [
 93 |               "<IPython.core.display.HTML object>"
 94 |             ]
 95 |           },
 96 |           "metadata": {
 97 |             "tags": []
 98 |           }
 99 |         },
100 |         {
101 |           "output_type": "stream",
102 |           "text": [
103 |             "Saving BreastTissue.csv to BreastTissue.csv\n"
104 |           ],
105 |           "name": "stdout"
106 |         }
107 |       ]
108 |     },
109 |     {
110 |       "cell_type": "code",
111 |       "metadata": {
112 |         "id": "ktwxF3kc9haU",
113 |         "colab_type": "code",
114 |         "colab": {
115 |           "base_uri": "https://localhost:8080/",
116 |           "height": 203
117 |         },
118 |         "outputId": "a91382eb-d766-4088-9296-7d8cab7fe6ac"
119 |       },
120 |       "source": [
121 |         "# import pandas\n",
122 |         "import pandas as pd\n",
123 |         "\n",
124 |         "# read the dataset\n",
125 |         "df = pd.read_csv('BreastTissue.csv')\n",
126 |         "\n",
127 |         "df.head()"
128 |       ],
129 |       "execution_count": 2,
130 |       "outputs": [
131 |         {
132 |           "output_type": "execute_result",
133 |           "data": {
134 |             "text/html": [
135 |               "<div>\n",
136 |               "<style scoped>\n",
137 |               "    .dataframe tbody tr th:only-of-type {\n",
138 |               "        vertical-align: middle;\n",
139 |               "    }\n",
140 |               "\n",
141 |               "    .dataframe tbody tr th {\n",
142 |               "        vertical-align: top;\n",
143 |               "    }\n",
144 |               "\n",
145 |               "    .dataframe thead th {\n",
146 |               "        text-align: right;\n",
147 |               "    }\n",
148 |               "</style>\n",
149 |               "<table border=\"1\" class=\"dataframe\">\n",
150 |               "  <thead>\n",
151 |               "    <tr style=\"text-align: right;\">\n",
152 |               "      <th></th>\n",
153 |               "      <th>Case #</th>\n",
154 |               "      <th>Class</th>\n",
155 |               "      <th>I0</th>\n",
156 |               "      <th>PA500</th>\n",
157 |               "      <th>HFS</th>\n",
158 |               "      <th>DA</th>\n",
159 |               "      <th>Area</th>\n",
160 |               "      <th>A/DA</th>\n",
161 |               "      <th>Max IP</th>\n",
162 |               "      <th>DR</th>\n",
163 |               "      <th>P</th>\n",
164 |               "    </tr>\n",
165 |               "  </thead>\n",
166 |               "  <tbody>\n",
167 |               "    <tr>\n",
168 |               "      <th>0</th>\n",
169 |               "      <td>1</td>\n",
170 |               "      <td>car</td>\n",
171 |               "      <td>524.794072</td>\n",
172 |               "      <td>0.187448</td>\n",
173 |               "      <td>0.032114</td>\n",
174 |               "      <td>228.800228</td>\n",
175 |               "      <td>6843.598481</td>\n",
176 |               "      <td>29.910803</td>\n",
177 |               "      <td>60.204880</td>\n",
178 |               "      <td>220.737212</td>\n",
179 |               "      <td>556.828334</td>\n",
180 |               "    </tr>\n",
181 |               "    <tr>\n",
182 |               "      <th>1</th>\n",
183 |               "      <td>2</td>\n",
184 |               "      <td>car</td>\n",
185 |               "      <td>330.000000</td>\n",
186 |               "      <td>0.226893</td>\n",
187 |               "      <td>0.265290</td>\n",
188 |               "      <td>121.154201</td>\n",
189 |               "      <td>3163.239472</td>\n",
190 |               "      <td>26.109202</td>\n",
191 |               "      <td>69.717361</td>\n",
192 |               "      <td>99.084964</td>\n",
193 |               "      <td>400.225776</td>\n",
194 |               "    </tr>\n",
195 |               "    <tr>\n",
196 |               "      <th>2</th>\n",
197 |               "      <td>3</td>\n",
198 |               "      <td>car</td>\n",
199 |               "      <td>551.879287</td>\n",
200 |               "      <td>0.232478</td>\n",
201 |               "      <td>0.063530</td>\n",
202 |               "      <td>264.804935</td>\n",
203 |               "      <td>11888.391830</td>\n",
204 |               "      <td>44.894903</td>\n",
205 |               "      <td>77.793297</td>\n",
206 |               "      <td>253.785300</td>\n",
207 |               "      <td>656.769449</td>\n",
208 |               "    </tr>\n",
209 |               "    <tr>\n",
210 |               "      <th>3</th>\n",
211 |               "      <td>4</td>\n",
212 |               "      <td>car</td>\n",
213 |               "      <td>380.000000</td>\n",
214 |               "      <td>0.240855</td>\n",
215 |               "      <td>0.286234</td>\n",
216 |               "      <td>137.640111</td>\n",
217 |               "      <td>5402.171180</td>\n",
218 |               "      <td>39.248524</td>\n",
219 |               "      <td>88.758446</td>\n",
220 |               "      <td>105.198568</td>\n",
221 |               "      <td>493.701813</td>\n",
222 |               "    </tr>\n",
223 |               "    <tr>\n",
224 |               "      <th>4</th>\n",
225 |               "      <td>5</td>\n",
226 |               "      <td>car</td>\n",
227 |               "      <td>362.831266</td>\n",
228 |               "      <td>0.200713</td>\n",
229 |               "      <td>0.244346</td>\n",
230 |               "      <td>124.912559</td>\n",
231 |               "      <td>3290.462446</td>\n",
232 |               "      <td>26.342127</td>\n",
233 |               "      <td>69.389389</td>\n",
234 |               "      <td>103.866552</td>\n",
235 |               "      <td>424.796503</td>\n",
236 |               "    </tr>\n",
237 |               "  </tbody>\n",
238 |               "</table>\n",
239 |               "</div>"
240 |             ],
241 |             "text/plain": [
242 |               "   Case # Class          I0  ...     Max IP          DR           P\n",
243 |               "0       1   car  524.794072  ...  60.204880  220.737212  556.828334\n",
244 |               "1       2   car  330.000000  ...  69.717361   99.084964  400.225776\n",
245 |               "2       3   car  551.879287  ...  77.793297  253.785300  656.769449\n",
246 |               "3       4   car  380.000000  ...  88.758446  105.198568  493.701813\n",
247 |               "4       5   car  362.831266  ...  69.389389  103.866552  424.796503\n",
248 |               "\n",
249 |               "[5 rows x 11 columns]"
250 |             ]
251 |           },
252 |           "metadata": {
253 |             "tags": []
254 |           },
255 |           "execution_count": 2
256 |         }
257 |       ]
258 |     },
259 |     {
260 |       "cell_type": "code",
261 |       "metadata": {
262 |         "id": "F4I9l_YmEdrn",
263 |         "colab_type": "code",
264 |         "outputId": "0367968e-2fa1-48a6-f7bc-870f25e12f77",
265 |         "colab": {
266 |           "base_uri": "https://localhost:8080/",
267 |           "height": 331
268 |         }
269 |       },
270 |       "source": [
271 |         "print(df.shape)\n",
272 |         "\n",
273 |         "num_of_classes = len(df.Class.unique())\n",
274 |         "print(num_of_classes)\n",
275 |         "\n",
276 |         "df.describe()"
277 |       ],
278 |       "execution_count": 3,
279 |       "outputs": [
280 |         {
281 |           "output_type": "stream",
282 |           "text": [
283 |             "(106, 11)\n",
284 |             "6\n"
285 |           ],
286 |           "name": "stdout"
287 |         },
288 |         {
289 |           "output_type": "execute_result",
290 |           "data": {
291 |             "text/html": [
292 |               "<div>\n",
293 |               "<style scoped>\n",
294 |               "    .dataframe tbody tr th:only-of-type {\n",
295 |               "        vertical-align: middle;\n",
296 |               "    }\n",
297 |               "\n",
298 |               "    .dataframe tbody tr th {\n",
299 |               "        vertical-align: top;\n",
300 |               "    }\n",
301 |               "\n",
302 |               "    .dataframe thead th {\n",
303 |               "        text-align: right;\n",
304 |               "    }\n",
305 |               "</style>\n",
306 |               "<table border=\"1\" class=\"dataframe\">\n",
307 |               "  <thead>\n",
308 |               "    <tr style=\"text-align: right;\">\n",
309 |               "      <th></th>\n",
310 |               "      <th>Case #</th>\n",
311 |               "      <th>I0</th>\n",
312 |               "      <th>PA500</th>\n",
313 |               "      <th>HFS</th>\n",
314 |               "      <th>DA</th>\n",
315 |               "      <th>Area</th>\n",
316 |               "      <th>A/DA</th>\n",
317 |               "      <th>Max IP</th>\n",
318 |               "      <th>DR</th>\n",
319 |               "      <th>P</th>\n",
320 |               "    </tr>\n",
321 |               "  </thead>\n",
322 |               "  <tbody>\n",
323 |               "    <tr>\n",
324 |               "      <th>count</th>\n",
325 |               "      <td>106.000000</td>\n",
326 |               "      <td>106.000000</td>\n",
327 |               "      <td>106.000000</td>\n",
328 |               "      <td>106.000000</td>\n",
329 |               "      <td>106.000000</td>\n",
330 |               "      <td>106.000000</td>\n",
331 |               "      <td>106.000000</td>\n",
332 |               "      <td>106.000000</td>\n",
333 |               "      <td>106.000000</td>\n",
334 |               "      <td>106.000000</td>\n",
335 |               "    </tr>\n",
336 |               "    <tr>\n",
337 |               "      <th>mean</th>\n",
338 |               "      <td>53.500000</td>\n",
339 |               "      <td>784.251618</td>\n",
340 |               "      <td>0.120133</td>\n",
341 |               "      <td>0.114691</td>\n",
342 |               "      <td>190.568642</td>\n",
343 |               "      <td>7335.155161</td>\n",
344 |               "      <td>23.473784</td>\n",
345 |               "      <td>75.381258</td>\n",
346 |               "      <td>166.710575</td>\n",
347 |               "      <td>810.638127</td>\n",
348 |               "    </tr>\n",
349 |               "    <tr>\n",
350 |               "      <th>std</th>\n",
351 |               "      <td>30.743563</td>\n",
352 |               "      <td>753.950075</td>\n",
353 |               "      <td>0.068596</td>\n",
354 |               "      <td>0.101347</td>\n",
355 |               "      <td>190.801448</td>\n",
356 |               "      <td>18580.314212</td>\n",
357 |               "      <td>23.354672</td>\n",
358 |               "      <td>81.345838</td>\n",
359 |               "      <td>181.309580</td>\n",
360 |               "      <td>763.019135</td>\n",
361 |               "    </tr>\n",
362 |               "    <tr>\n",
363 |               "      <th>min</th>\n",
364 |               "      <td>1.000000</td>\n",
365 |               "      <td>103.000000</td>\n",
366 |               "      <td>0.012392</td>\n",
367 |               "      <td>-0.066323</td>\n",
368 |               "      <td>19.647670</td>\n",
369 |               "      <td>70.426239</td>\n",
370 |               "      <td>1.595742</td>\n",
371 |               "      <td>7.968783</td>\n",
372 |               "      <td>-9.257696</td>\n",
373 |               "      <td>124.978561</td>\n",
374 |               "    </tr>\n",
375 |               "    <tr>\n",
376 |               "      <th>25%</th>\n",
377 |               "      <td>27.250000</td>\n",
378 |               "      <td>250.000000</td>\n",
379 |               "      <td>0.067413</td>\n",
380 |               "      <td>0.043982</td>\n",
381 |               "      <td>53.845470</td>\n",
382 |               "      <td>409.647141</td>\n",
383 |               "      <td>8.180321</td>\n",
384 |               "      <td>26.893773</td>\n",
385 |               "      <td>41.781258</td>\n",
386 |               "      <td>270.215238</td>\n",
387 |               "    </tr>\n",
388 |               "    <tr>\n",
389 |               "      <th>50%</th>\n",
390 |               "      <td>53.500000</td>\n",
391 |               "      <td>384.936489</td>\n",
392 |               "      <td>0.105418</td>\n",
393 |               "      <td>0.086568</td>\n",
394 |               "      <td>120.777303</td>\n",
395 |               "      <td>2219.581163</td>\n",
396 |               "      <td>16.133657</td>\n",
397 |               "      <td>44.216040</td>\n",
398 |               "      <td>97.832557</td>\n",
399 |               "      <td>454.108153</td>\n",
400 |               "    </tr>\n",
401 |               "    <tr>\n",
402 |               "      <th>75%</th>\n",
403 |               "      <td>79.750000</td>\n",
404 |               "      <td>1487.989626</td>\n",
405 |               "      <td>0.169602</td>\n",
406 |               "      <td>0.166504</td>\n",
407 |               "      <td>255.334809</td>\n",
408 |               "      <td>7615.204968</td>\n",
409 |               "      <td>30.953294</td>\n",
410 |               "      <td>83.671755</td>\n",
411 |               "      <td>232.990070</td>\n",
412 |               "      <td>1301.559438</td>\n",
413 |               "    </tr>\n",
414 |               "    <tr>\n",
415 |               "      <th>max</th>\n",
416 |               "      <td>106.000000</td>\n",
417 |               "      <td>2800.000000</td>\n",
418 |               "      <td>0.358316</td>\n",
419 |               "      <td>0.467748</td>\n",
420 |               "      <td>1063.441427</td>\n",
421 |               "      <td>174480.476200</td>\n",
422 |               "      <td>164.071543</td>\n",
423 |               "      <td>436.099640</td>\n",
424 |               "      <td>977.552367</td>\n",
425 |               "      <td>2896.582483</td>\n",
426 |               "    </tr>\n",
427 |               "  </tbody>\n",
428 |               "</table>\n",
429 |               "</div>"
430 |             ],
431 |             "text/plain": [
432 |               "           Case #           I0       PA500  ...      Max IP          DR            P\n",
433 |               "count  106.000000   106.000000  106.000000  ...  106.000000  106.000000   106.000000\n",
434 |               "mean    53.500000   784.251618    0.120133  ...   75.381258  166.710575   810.638127\n",
435 |               "std     30.743563   753.950075    0.068596  ...   81.345838  181.309580   763.019135\n",
436 |               "min      1.000000   103.000000    0.012392  ...    7.968783   -9.257696   124.978561\n",
437 |               "25%     27.250000   250.000000    0.067413  ...   26.893773   41.781258   270.215238\n",
438 |               "50%     53.500000   384.936489    0.105418  ...   44.216040   97.832557   454.108153\n",
439 |               "75%     79.750000  1487.989626    0.169602  ...   83.671755  232.990070  1301.559438\n",
440 |               "max    106.000000  2800.000000    0.358316  ...  436.099640  977.552367  2896.582483\n",
441 |               "\n",
442 |               "[8 rows x 10 columns]"
443 |             ]
444 |           },
445 |           "metadata": {
446 |             "tags": []
447 |           },
448 |           "execution_count": 3
449 |         }
450 |       ]
451 |     },
452 |     {
453 |       "cell_type": "code",
454 |       "metadata": {
455 |         "id": "iBr_P8exEFLa",
456 |         "colab_type": "code",
457 |         "outputId": "b326530e-aa71-4caa-81c0-af98a1931c8f",
458 |         "colab": {
459 |           "base_uri": "https://localhost:8080/",
460 |           "height": 53
461 |         }
462 |       },
463 |       "source": [
464 |         "# split train input and output data\n",
465 |         "X = df.drop(axis=0, columns=['Class', 'Case #'])\n",
466 |         "Y = df.Class\n",
467 |         "\n",
468 |         "#Print the shape of X and Y\n",
469 |         "print(X.shape)\n",
470 |         "print(Y.shape)"
471 |       ],
472 |       "execution_count": 4,
473 |       "outputs": [
474 |         {
475 |           "output_type": "stream",
476 |           "text": [
477 |             "(106, 9)\n",
478 |             "(106,)\n"
479 |           ],
480 |           "name": "stdout"
481 |         }
482 |       ]
483 |     },
484 |     {
485 |       "cell_type": "code",
486 |       "metadata": {
487 |         "id": "QCV1u4tqFIqm",
488 |         "colab_type": "code",
489 |         "colab": {}
490 |       },
491 |       "source": [
492 |         "from sklearn.model_selection import train_test_split\n",
493 |         "\n",
494 |         "# Split into training and test sets\n",
495 |         "X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.33, random_state=42)"
496 |       ],
497 |       "execution_count": 0,
498 |       "outputs": []
499 |     },
500 |     {
501 |       "cell_type": "code",
502 |       "metadata": {
503 |         "id": "3oMEHRVgF640",
504 |         "colab_type": "code",
505 |         "outputId": "9136f352-5b1d-40f4-9ba1-26c066f21f55",
506 |         "colab": {
507 |           "base_uri": "https://localhost:8080/",
508 |           "height": 35
509 |         }
510 |       },
511 |       "source": [
512 |         "from xgboost import XGBClassifier\n",
513 |         "from sklearn.metrics import roc_auc_score\n",
514 |         "from sklearn import preprocessing\n",
515 |         "\n",
516 |         "xgb = XGBClassifier(booster='gbtree', objective='multi:softprob', random_state=42, eval_metric=\"auc\", num_class=num_of_classes)\n",
517 |         "\n",
518 |         "xgb.fit(X_train,y_train)\n",
519 |         "\n",
520 |         "pred = xgb.predict(X_test)\n",
521 |         "val = xgb.predict(X_test)\n",
522 |         "\n",
523 |         "lb = preprocessing.LabelBinarizer()\n",
524 |         "lb.fit(y_test)\n",
525 |         "\n",
526 |         "y_test_lb = lb.transform(y_test)\n",
527 |         "val_lb = lb.transform(val)\n",
528 |         "\n",
529 |         "roc_auc_score(y_test_lb, val_lb, average='macro')"
530 |       ],
531 |       "execution_count": 9,
532 |       "outputs": [
533 |         {
534 |           "output_type": "execute_result",
535 |           "data": {
536 |             "text/plain": [
537 |               "0.835727969348659"
538 |             ]
539 |           },
540 |           "metadata": {
541 |             "tags": []
542 |           },
543 |           "execution_count": 9
544 |         }
545 |       ]
546 |     },
547 |     {
548 |       "cell_type": "code",
549 |       "metadata": {
550 |         "id": "81Qqa0BzrEvL",
551 |         "colab_type": "code",
552 |         "colab": {
553 |           "base_uri": "https://localhost:8080/",
554 |           "height": 203
555 |         },
556 |         "outputId": "8dde22fc-0597-480e-d5d0-92a2559bda4c"
557 |       },
558 |       "source": [
559 |         "output = pd.DataFrame()\n",
560 |         "output['Expected Output'] = y_test\n",
561 |         "output['Predicted Output'] = val\n",
562 |         "output.tail()"
563 |       ],
564 |       "execution_count": 10,
565 |       "outputs": [
566 |         {
567 |           "output_type": "execute_result",
568 |           "data": {
569 |             "text/html": [
570 |               "<div>\n",
571 |               "<style scoped>\n",
572 |               "    .dataframe tbody tr th:only-of-type {\n",
573 |               "        vertical-align: middle;\n",
574 |               "    }\n",
575 |               "\n",
576 |               "    .dataframe tbody tr th {\n",
577 |               "        vertical-align: top;\n",
578 |               "    }\n",
579 |               "\n",
580 |               "    .dataframe thead th {\n",
581 |               "        text-align: right;\n",
582 |               "    }\n",
583 |               "</style>\n",
584 |               "<table border=\"1\" class=\"dataframe\">\n",
585 |               "  <thead>\n",
586 |               "    <tr style=\"text-align: right;\">\n",
587 |               "      <th></th>\n",
588 |               "      <th>Expected Output</th>\n",
589 |               "      <th>Predicted Output</th>\n",
590 |               "    </tr>\n",
591 |               "  </thead>\n",
592 |               "  <tbody>\n",
593 |               "    <tr>\n",
594 |               "      <th>36</th>\n",
595 |               "      <td>mas</td>\n",
596 |               "      <td>fad</td>\n",
597 |               "    </tr>\n",
598 |               "    <tr>\n",
599 |               "      <th>88</th>\n",
600 |               "      <td>adi</td>\n",
601 |               "      <td>adi</td>\n",
602 |               "    </tr>\n",
603 |               "    <tr>\n",
604 |               "      <th>9</th>\n",
605 |               "      <td>car</td>\n",
606 |               "      <td>car</td>\n",
607 |               "    </tr>\n",
608 |               "    <tr>\n",
609 |               "      <th>53</th>\n",
610 |               "      <td>mas</td>\n",
611 |               "      <td>fad</td>\n",
612 |               "    </tr>\n",
613 |               "    <tr>\n",
614 |               "      <th>95</th>\n",
615 |               "      <td>adi</td>\n",
616 |               "      <td>adi</td>\n",
617 |               "    </tr>\n",
618 |               "  </tbody>\n",
619 |               "</table>\n",
620 |               "</div>"
621 |             ],
622 |             "text/plain": [
623 |               "   Expected Output Predicted Output\n",
624 |               "36             mas              fad\n",
625 |               "88             adi              adi\n",
626 |               "9              car              car\n",
627 |               "53             mas              fad\n",
628 |               "95             adi              adi"
629 |             ]
630 |           },
631 |           "metadata": {
632 |             "tags": []
633 |           },
634 |           "execution_count": 10
635 |         }
636 |       ]
637 |     },
638 |     {
639 |       "cell_type": "code",
640 |       "metadata": {
641 |         "id": "euLoXe4LrnnQ",
642 |         "colab_type": "code",
643 |         "colab": {}
644 |       },
645 |       "source": [
646 |         ""
647 |       ],
648 |       "execution_count": 0,
649 |       "outputs": []
650 |     }
651 |   ]
652 | }


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