├── .DS_Store
├── KNN
    ├── .ipynb_checkpoints
    │   └── TheorySample-checkpoint.ipynb
    ├── Excercises
    │   ├── .ipynb_checkpoints
    │   │   ├── KNExercise-checkpoint.ipynb
    │   │   └── dataset-checkpoint.csv
    │   ├── KNExercise.ipynb
    │   └── dataset.csv
    └── TheorySample.ipynb
├── LogisticRegression
    ├── .DS_Store
    ├── .ipynb_checkpoints
    │   ├── 7_logistic_regression-checkpoint.ipynb
    │   ├── Exercise-checkpoint.ipynb
    │   ├── LogisticeRegression-checkpoint.ipynb
    │   └── insurance_data-checkpoint.csv
    ├── Exercise.ipynb
    ├── Exercise
    │   ├── .ipynb_checkpoints
    │   │   ├── 7_logistic_regression_exercise-checkpoint.ipynb
    │   │   └── HR_comma_sep-checkpoint.csv
    │   ├── 7_logistic_regression_exercise.ipynb
    │   └── HR_comma_sep.csv
    ├── LogisticeRegression.ipynb
    └── insurance_data.csv
└── README.md


/.DS_Store:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/md-thayyib/DataScience-ML/174ef85031b5c97729404c86c6fdcf6d8f936b56/.DS_Store


--------------------------------------------------------------------------------
/KNN/.ipynb_checkpoints/TheorySample-checkpoint.ipynb:
--------------------------------------------------------------------------------
1 | {
2 |  "cells": [],
3 |  "metadata": {},
4 |  "nbformat": 4,
5 |  "nbformat_minor": 5
6 | }
7 | 


--------------------------------------------------------------------------------
/KNN/Excercises/.ipynb_checkpoints/KNExercise-checkpoint.ipynb:
--------------------------------------------------------------------------------
1 | {
2 |  "cells": [],
3 |  "metadata": {},
4 |  "nbformat": 4,
5 |  "nbformat_minor": 5
6 | }
7 | 


--------------------------------------------------------------------------------
/KNN/Excercises/.ipynb_checkpoints/dataset-checkpoint.csv:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/md-thayyib/DataScience-ML/174ef85031b5c97729404c86c6fdcf6d8f936b56/KNN/Excercises/.ipynb_checkpoints/dataset-checkpoint.csv


--------------------------------------------------------------------------------
/KNN/TheorySample.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "id": "1035894a-8de0-4ded-8565-f0b4520f0c27",
  6 |    "metadata": {},
  7 |    "source": [
  8 |     "# KNN\n",
  9 |     "\n",
 10 |     "KNN is one of the simplest alogorithm for both classification and regression. But it is mainly used for classification problem. The idea behing the KNN is to find the distance between the new data point and neighnour datas. We can set number of neigbour(k) and vote the nearest k neigbour in which the each data point belongs to class. The majority will win. So it is better to take k= odd number. There is no algo to choose the value of k. But choose k from 1 to n(say 40) and compare the errora and accuracy..\n",
 11 |     "\n",
 12 |     "There are 4 methods to calculate the distance\n",
 13 |     "1. Euclidian distance - Pythagorous distance - Like air distance\n",
 14 |     "2. Manhattan distance sum of absolute of distances (abs(x1-x2)+abs(y2-y1) \n",
 15 |     "The name Manhattan is an island in U.S. city distance. like car distance\n",
 16 |     "3. Minkowski - p=some values. If p=2 => Euclidian\n",
 17 |     "if p=1 => Manahatan, we can set another values\n",
 18 |     "4. Hamming distance - sum or avg of bit position at which the two code differs\n",
 19 |     "comes in one-hot encoding.  0 0 1 1\n",
 20 |     "                            1 0 0 1 distance equals 2/4 = .5\n",
 21 |     "                            \n",
 22 |     "\"K-Nearest Neighbors is the supervised machine learning algorithm used for classification and regression. It manipulates the training data and classifies the new test data based on distance metrics. It finds the k-nearest neighbors to the test data, and then classification is performed by the majority of class labels.\n",
 23 |     "\n",
 24 |     "Selecting the optimal K value to achieve the maximum accuracy of the model is always challenging for a data scientist.\"\n",
 25 |     "\n",
 26 |     "\n",
 27 |     "### This algo is a lazy because it trains each time when it sees a sample\n",
 28 |     "\n",
 29 |     "## Here I am using iris data set"
 30 |    ]
 31 |   },
 32 |   {
 33 |    "cell_type": "code",
 34 |    "execution_count": 28,
 35 |    "id": "afebc598-aea6-4238-93f6-57fc6305813b",
 36 |    "metadata": {},
 37 |    "outputs": [],
 38 |    "source": [
 39 |     "import pandas as pd\n",
 40 |     "import seaborn as sns\n",
 41 |     "import matplotlib.pyplot as plt\n",
 42 |     "from sklearn.datasets import load_iris"
 43 |    ]
 44 |   },
 45 |   {
 46 |    "cell_type": "code",
 47 |    "execution_count": 29,
 48 |    "id": "00d314e4-72a2-4381-bef5-499559d685c2",
 49 |    "metadata": {},
 50 |    "outputs": [
 51 |     {
 52 |      "data": {
 53 |       "text/plain": [
 54 |        "['sepal length (cm)',\n",
 55 |        " 'sepal width (cm)',\n",
 56 |        " 'petal length (cm)',\n",
 57 |        " 'petal width (cm)']"
 58 |       ]
 59 |      },
 60 |      "execution_count": 29,
 61 |      "metadata": {},
 62 |      "output_type": "execute_result"
 63 |     }
 64 |    ],
 65 |    "source": [
 66 |     "iris.feature_names"
 67 |    ]
 68 |   },
 69 |   {
 70 |    "cell_type": "code",
 71 |    "execution_count": 30,
 72 |    "id": "1791ce7e-768b-482e-b983-b88695d148f5",
 73 |    "metadata": {},
 74 |    "outputs": [
 75 |     {
 76 |      "data": {
 77 |       "text/plain": [
 78 |        "array(['setosa', 'versicolor', 'virginica'], dtype='<U10')"
 79 |       ]
 80 |      },
 81 |      "execution_count": 30,
 82 |      "metadata": {},
 83 |      "output_type": "execute_result"
 84 |     }
 85 |    ],
 86 |    "source": [
 87 |     "iris.target_names"
 88 |    ]
 89 |   },
 90 |   {
 91 |    "cell_type": "code",
 92 |    "execution_count": 31,
 93 |    "id": "ff3ddf9d-6e0e-45ec-ba52-fb05660f4779",
 94 |    "metadata": {},
 95 |    "outputs": [],
 96 |    "source": [
 97 |     "iris = load_iris()\n",
 98 |     "df = pd.DataFrame(iris.data,columns=iris.feature_names)"
 99 |    ]
100 |   },
101 |   {
102 |    "cell_type": "code",
103 |    "execution_count": 32,
104 |    "id": "6ad3de3e-0061-4e18-b462-6ab9c1c62021",
105 |    "metadata": {},
106 |    "outputs": [],
107 |    "source": [
108 |     "df['Species'] = iris.target"
109 |    ]
110 |   },
111 |   {
112 |    "cell_type": "code",
113 |    "execution_count": 33,
114 |    "id": "b2f289fd-7218-4f94-8dc9-a3d2eef0b0b9",
115 |    "metadata": {},
116 |    "outputs": [
117 |     {
118 |      "data": {
119 |       "text/html": [
120 |        "<div>\n",
121 |        "<style scoped>\n",
122 |        "    .dataframe tbody tr th:only-of-type {\n",
123 |        "        vertical-align: middle;\n",
124 |        "    }\n",
125 |        "\n",
126 |        "    .dataframe tbody tr th {\n",
127 |        "        vertical-align: top;\n",
128 |        "    }\n",
129 |        "\n",
130 |        "    .dataframe thead th {\n",
131 |        "        text-align: right;\n",
132 |        "    }\n",
133 |        "</style>\n",
134 |        "<table border=\"1\" class=\"dataframe\">\n",
135 |        "  <thead>\n",
136 |        "    <tr style=\"text-align: right;\">\n",
137 |        "      <th></th>\n",
138 |        "      <th>sepal length (cm)</th>\n",
139 |        "      <th>sepal width (cm)</th>\n",
140 |        "      <th>petal length (cm)</th>\n",
141 |        "      <th>petal width (cm)</th>\n",
142 |        "      <th>Species</th>\n",
143 |        "    </tr>\n",
144 |        "  </thead>\n",
145 |        "  <tbody>\n",
146 |        "    <tr>\n",
147 |        "      <th>0</th>\n",
148 |        "      <td>5.1</td>\n",
149 |        "      <td>3.5</td>\n",
150 |        "      <td>1.4</td>\n",
151 |        "      <td>0.2</td>\n",
152 |        "      <td>0</td>\n",
153 |        "    </tr>\n",
154 |        "    <tr>\n",
155 |        "      <th>1</th>\n",
156 |        "      <td>4.9</td>\n",
157 |        "      <td>3.0</td>\n",
158 |        "      <td>1.4</td>\n",
159 |        "      <td>0.2</td>\n",
160 |        "      <td>0</td>\n",
161 |        "    </tr>\n",
162 |        "    <tr>\n",
163 |        "      <th>2</th>\n",
164 |        "      <td>4.7</td>\n",
165 |        "      <td>3.2</td>\n",
166 |        "      <td>1.3</td>\n",
167 |        "      <td>0.2</td>\n",
168 |        "      <td>0</td>\n",
169 |        "    </tr>\n",
170 |        "    <tr>\n",
171 |        "      <th>3</th>\n",
172 |        "      <td>4.6</td>\n",
173 |        "      <td>3.1</td>\n",
174 |        "      <td>1.5</td>\n",
175 |        "      <td>0.2</td>\n",
176 |        "      <td>0</td>\n",
177 |        "    </tr>\n",
178 |        "    <tr>\n",
179 |        "      <th>4</th>\n",
180 |        "      <td>5.0</td>\n",
181 |        "      <td>3.6</td>\n",
182 |        "      <td>1.4</td>\n",
183 |        "      <td>0.2</td>\n",
184 |        "      <td>0</td>\n",
185 |        "    </tr>\n",
186 |        "  </tbody>\n",
187 |        "</table>\n",
188 |        "</div>"
189 |       ],
190 |       "text/plain": [
191 |        "   sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)  \\\n",
192 |        "0                5.1               3.5                1.4               0.2   \n",
193 |        "1                4.9               3.0                1.4               0.2   \n",
194 |        "2                4.7               3.2                1.3               0.2   \n",
195 |        "3                4.6               3.1                1.5               0.2   \n",
196 |        "4                5.0               3.6                1.4               0.2   \n",
197 |        "\n",
198 |        "   Species  \n",
199 |        "0        0  \n",
200 |        "1        0  \n",
201 |        "2        0  \n",
202 |        "3        0  \n",
203 |        "4        0  "
204 |       ]
205 |      },
206 |      "execution_count": 33,
207 |      "metadata": {},
208 |      "output_type": "execute_result"
209 |     }
210 |    ],
211 |    "source": [
212 |     "df.head()"
213 |    ]
214 |   },
215 |   {
216 |    "cell_type": "code",
217 |    "execution_count": 34,
218 |    "id": "d6d918fe-0a10-4434-975a-d90e2845641f",
219 |    "metadata": {},
220 |    "outputs": [
221 |     {
222 |      "data": {
223 |       "text/plain": [
224 |        "(150, 5)"
225 |       ]
226 |      },
227 |      "execution_count": 34,
228 |      "metadata": {},
229 |      "output_type": "execute_result"
230 |     }
231 |    ],
232 |    "source": [
233 |     "df.shape"
234 |    ]
235 |   },
236 |   {
237 |    "cell_type": "code",
238 |    "execution_count": 35,
239 |    "id": "70d0a5f7-7892-4e72-969b-9e0f959f49d2",
240 |    "metadata": {},
241 |    "outputs": [
242 |     {
243 |      "data": {
244 |       "text/plain": [
245 |        "<AxesSubplot:xlabel='petal length (cm)', ylabel='sepal length (cm)'>"
246 |       ]
247 |      },
248 |      "execution_count": 35,
249 |      "metadata": {},
250 |      "output_type": "execute_result"
251 |     },
252 |     {
253 |      "data": {
254 |       "image/png": "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\n",
255 |       "text/plain": [
256 |        "<Figure size 432x288 with 1 Axes>"
257 |       ]
258 |      },
259 |      "metadata": {
260 |       "needs_background": "light"
261 |      },
262 |      "output_type": "display_data"
263 |     }
264 |    ],
265 |    "source": [
266 |     "sns.stripplot(x = 'petal length (cm)',y = 'sepal length (cm)',data=df,hue='Species')"
267 |    ]
268 |   },
269 |   {
270 |    "cell_type": "markdown",
271 |    "id": "d2b4f452-92f1-4827-aec7-4a5917950739",
272 |    "metadata": {},
273 |    "source": [
274 |     "## Train test split"
275 |    ]
276 |   },
277 |   {
278 |    "cell_type": "code",
279 |    "execution_count": 36,
280 |    "id": "5dee6694-51e4-4e85-98f3-e76868b3ccc0",
281 |    "metadata": {},
282 |    "outputs": [],
283 |    "source": [
284 |     "X = df.drop('Species',axis=1)"
285 |    ]
286 |   },
287 |   {
288 |    "cell_type": "code",
289 |    "execution_count": 37,
290 |    "id": "f7c720f3-614b-4a15-9418-c88068ed9b60",
291 |    "metadata": {},
292 |    "outputs": [],
293 |    "source": [
294 |     "y = df.Species"
295 |    ]
296 |   },
297 |   {
298 |    "cell_type": "code",
299 |    "execution_count": 38,
300 |    "id": "46f601a4-38f2-4a6b-af0a-6441b8616c4c",
301 |    "metadata": {},
302 |    "outputs": [],
303 |    "source": [
304 |     "from sklearn.model_selection import train_test_split\n",
305 |     "X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=.3)"
306 |    ]
307 |   },
308 |   {
309 |    "cell_type": "markdown",
310 |    "id": "09792034-450d-405f-9c37-a6b6d62fe9b4",
311 |    "metadata": {},
312 |    "source": [
313 |     "## Create KNN model"
314 |    ]
315 |   },
316 |   {
317 |    "cell_type": "code",
318 |    "execution_count": 39,
319 |    "id": "a1ee0268-b025-4099-a4f7-e5dc3fbaa80b",
320 |    "metadata": {},
321 |    "outputs": [],
322 |    "source": [
323 |     "from sklearn.neighbors import KNeighborsClassifier"
324 |    ]
325 |   },
326 |   {
327 |    "cell_type": "code",
328 |    "execution_count": 64,
329 |    "id": "ea20c832-80ba-460e-8df4-1b39f3974a30",
330 |    "metadata": {},
331 |    "outputs": [],
332 |    "source": [
333 |     "model = KNeighborsClassifier(n_neighbors=5,metric='minkowski',p=2,)"
334 |    ]
335 |   },
336 |   {
337 |    "cell_type": "code",
338 |    "execution_count": 65,
339 |    "id": "46ba1653-536d-436c-be54-07c5c8363190",
340 |    "metadata": {},
341 |    "outputs": [
342 |     {
343 |      "data": {
344 |       "text/plain": [
345 |        "KNeighborsClassifier()"
346 |       ]
347 |      },
348 |      "execution_count": 65,
349 |      "metadata": {},
350 |      "output_type": "execute_result"
351 |     }
352 |    ],
353 |    "source": [
354 |     "model.fit(X_train,y_train)"
355 |    ]
356 |   },
357 |   {
358 |    "cell_type": "markdown",
359 |    "id": "93fc9293-30ed-4427-9900-671729820c8b",
360 |    "metadata": {},
361 |    "source": [
362 |     "### Score"
363 |    ]
364 |   },
365 |   {
366 |    "cell_type": "code",
367 |    "execution_count": 66,
368 |    "id": "3f91a26e-f4e0-4c6b-b136-dd7cbf7b74ff",
369 |    "metadata": {},
370 |    "outputs": [
371 |     {
372 |      "data": {
373 |       "text/plain": [
374 |        "0.9333333333333333"
375 |       ]
376 |      },
377 |      "execution_count": 66,
378 |      "metadata": {},
379 |      "output_type": "execute_result"
380 |     }
381 |    ],
382 |    "source": [
383 |     "model.score(X_test,y_test)"
384 |    ]
385 |   },
386 |   {
387 |    "cell_type": "code",
388 |    "execution_count": 80,
389 |    "id": "f7af8ca0-b959-4364-9ad9-52ee2891aec4",
390 |    "metadata": {},
391 |    "outputs": [
392 |     {
393 |      "data": {
394 |       "text/plain": [
395 |        "{'algorithm': 'auto',\n",
396 |        " 'leaf_size': 30,\n",
397 |        " 'metric': 'minkowski',\n",
398 |        " 'metric_params': None,\n",
399 |        " 'n_jobs': None,\n",
400 |        " 'n_neighbors': 5,\n",
401 |        " 'p': 2,\n",
402 |        " 'weights': 'uniform'}"
403 |       ]
404 |      },
405 |      "execution_count": 80,
406 |      "metadata": {},
407 |      "output_type": "execute_result"
408 |     }
409 |    ],
410 |    "source": [
411 |     "model.get_params()"
412 |    ]
413 |   },
414 |   {
415 |    "cell_type": "code",
416 |    "execution_count": null,
417 |    "id": "4c31a01e-8b97-4a63-9828-afa975401d88",
418 |    "metadata": {},
419 |    "outputs": [],
420 |    "source": []
421 |   },
422 |   {
423 |    "cell_type": "code",
424 |    "execution_count": null,
425 |    "id": "9c6cb8a3-5e57-4d7c-82a6-6256dadb58d3",
426 |    "metadata": {},
427 |    "outputs": [],
428 |    "source": []
429 |   }
430 |  ],
431 |  "metadata": {
432 |   "kernelspec": {
433 |    "display_name": "Python 3 (ipykernel)",
434 |    "language": "python",
435 |    "name": "python3"
436 |   },
437 |   "language_info": {
438 |    "codemirror_mode": {
439 |     "name": "ipython",
440 |     "version": 3
441 |    },
442 |    "file_extension": ".py",
443 |    "mimetype": "text/x-python",
444 |    "name": "python",
445 |    "nbconvert_exporter": "python",
446 |    "pygments_lexer": "ipython3",
447 |    "version": "3.9.12"
448 |   }
449 |  },
450 |  "nbformat": 4,
451 |  "nbformat_minor": 5
452 | }
453 | 


--------------------------------------------------------------------------------
/LogisticRegression/.DS_Store:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/md-thayyib/DataScience-ML/174ef85031b5c97729404c86c6fdcf6d8f936b56/LogisticRegression/.DS_Store


--------------------------------------------------------------------------------
/LogisticRegression/.ipynb_checkpoints/7_logistic_regression-checkpoint.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {},
  6 |    "source": [
  7 |     "<h2 style=\"color:green\" align=\"center\">Predicting if a person would buy life insurnace based on his age using logistic regression</h2>"
  8 |    ]
  9 |   },
 10 |   {
 11 |    "cell_type": "markdown",
 12 |    "metadata": {},
 13 |    "source": [
 14 |     "Above is a binary logistic regression problem as there are only two possible outcomes (i.e. if person buys insurance or he/she doesn't). "
 15 |    ]
 16 |   },
 17 |   {
 18 |    "cell_type": "code",
 19 |    "execution_count": 15,
 20 |    "metadata": {},
 21 |    "outputs": [],
 22 |    "source": [
 23 |     "import pandas as pd\n",
 24 |     "from matplotlib import pyplot as plt\n",
 25 |     "%matplotlib inline"
 26 |    ]
 27 |   },
 28 |   {
 29 |    "cell_type": "code",
 30 |    "execution_count": 16,
 31 |    "metadata": {},
 32 |    "outputs": [
 33 |     {
 34 |      "data": {
 35 |       "text/html": [
 36 |        "<div>\n",
 37 |        "<style scoped>\n",
 38 |        "    .dataframe tbody tr th:only-of-type {\n",
 39 |        "        vertical-align: middle;\n",
 40 |        "    }\n",
 41 |        "\n",
 42 |        "    .dataframe tbody tr th {\n",
 43 |        "        vertical-align: top;\n",
 44 |        "    }\n",
 45 |        "\n",
 46 |        "    .dataframe thead th {\n",
 47 |        "        text-align: right;\n",
 48 |        "    }\n",
 49 |        "</style>\n",
 50 |        "<table border=\"1\" class=\"dataframe\">\n",
 51 |        "  <thead>\n",
 52 |        "    <tr style=\"text-align: right;\">\n",
 53 |        "      <th></th>\n",
 54 |        "      <th>age</th>\n",
 55 |        "      <th>bought_insurance</th>\n",
 56 |        "    </tr>\n",
 57 |        "  </thead>\n",
 58 |        "  <tbody>\n",
 59 |        "    <tr>\n",
 60 |        "      <th>0</th>\n",
 61 |        "      <td>22</td>\n",
 62 |        "      <td>0</td>\n",
 63 |        "    </tr>\n",
 64 |        "    <tr>\n",
 65 |        "      <th>1</th>\n",
 66 |        "      <td>25</td>\n",
 67 |        "      <td>0</td>\n",
 68 |        "    </tr>\n",
 69 |        "    <tr>\n",
 70 |        "      <th>2</th>\n",
 71 |        "      <td>47</td>\n",
 72 |        "      <td>1</td>\n",
 73 |        "    </tr>\n",
 74 |        "    <tr>\n",
 75 |        "      <th>3</th>\n",
 76 |        "      <td>52</td>\n",
 77 |        "      <td>0</td>\n",
 78 |        "    </tr>\n",
 79 |        "    <tr>\n",
 80 |        "      <th>4</th>\n",
 81 |        "      <td>46</td>\n",
 82 |        "      <td>1</td>\n",
 83 |        "    </tr>\n",
 84 |        "  </tbody>\n",
 85 |        "</table>\n",
 86 |        "</div>"
 87 |       ],
 88 |       "text/plain": [
 89 |        "   age  bought_insurance\n",
 90 |        "0   22                 0\n",
 91 |        "1   25                 0\n",
 92 |        "2   47                 1\n",
 93 |        "3   52                 0\n",
 94 |        "4   46                 1"
 95 |       ]
 96 |      },
 97 |      "execution_count": 16,
 98 |      "metadata": {},
 99 |      "output_type": "execute_result"
100 |     }
101 |    ],
102 |    "source": [
103 |     "df = pd.read_csv(\"insurance_data.csv\")\n",
104 |     "df.head()"
105 |    ]
106 |   },
107 |   {
108 |    "cell_type": "code",
109 |    "execution_count": 17,
110 |    "metadata": {},
111 |    "outputs": [
112 |     {
113 |      "data": {
114 |       "text/plain": [
115 |        "<matplotlib.collections.PathCollection at 0x20a8cb15d30>"
116 |       ]
117 |      },
118 |      "execution_count": 17,
119 |      "metadata": {},
120 |      "output_type": "execute_result"
121 |     },
122 |     {
123 |      "data": {
124 |       "image/png": "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\n",
125 |       "text/plain": [
126 |        "<Figure size 432x288 with 1 Axes>"
127 |       ]
128 |      },
129 |      "metadata": {
130 |       "needs_background": "light"
131 |      },
132 |      "output_type": "display_data"
133 |     }
134 |    ],
135 |    "source": [
136 |     "plt.scatter(df.age,df.bought_insurance,marker='+',color='red')"
137 |    ]
138 |   },
139 |   {
140 |    "cell_type": "code",
141 |    "execution_count": 18,
142 |    "metadata": {},
143 |    "outputs": [],
144 |    "source": [
145 |     "from sklearn.model_selection import train_test_split"
146 |    ]
147 |   },
148 |   {
149 |    "cell_type": "code",
150 |    "execution_count": 29,
151 |    "metadata": {},
152 |    "outputs": [],
153 |    "source": [
154 |     "X_train, X_test, y_train, y_test = train_test_split(df[['age']],df.bought_insurance,train_size=0.8)"
155 |    ]
156 |   },
157 |   {
158 |    "cell_type": "code",
159 |    "execution_count": 30,
160 |    "metadata": {},
161 |    "outputs": [
162 |     {
163 |      "data": {
164 |       "text/html": [
165 |        "<div>\n",
166 |        "<style scoped>\n",
167 |        "    .dataframe tbody tr th:only-of-type {\n",
168 |        "        vertical-align: middle;\n",
169 |        "    }\n",
170 |        "\n",
171 |        "    .dataframe tbody tr th {\n",
172 |        "        vertical-align: top;\n",
173 |        "    }\n",
174 |        "\n",
175 |        "    .dataframe thead th {\n",
176 |        "        text-align: right;\n",
177 |        "    }\n",
178 |        "</style>\n",
179 |        "<table border=\"1\" class=\"dataframe\">\n",
180 |        "  <thead>\n",
181 |        "    <tr style=\"text-align: right;\">\n",
182 |        "      <th></th>\n",
183 |        "      <th>age</th>\n",
184 |        "    </tr>\n",
185 |        "  </thead>\n",
186 |        "  <tbody>\n",
187 |        "    <tr>\n",
188 |        "      <th>4</th>\n",
189 |        "      <td>46</td>\n",
190 |        "    </tr>\n",
191 |        "    <tr>\n",
192 |        "      <th>8</th>\n",
193 |        "      <td>62</td>\n",
194 |        "    </tr>\n",
195 |        "    <tr>\n",
196 |        "      <th>26</th>\n",
197 |        "      <td>23</td>\n",
198 |        "    </tr>\n",
199 |        "    <tr>\n",
200 |        "      <th>17</th>\n",
201 |        "      <td>58</td>\n",
202 |        "    </tr>\n",
203 |        "    <tr>\n",
204 |        "      <th>24</th>\n",
205 |        "      <td>50</td>\n",
206 |        "    </tr>\n",
207 |        "    <tr>\n",
208 |        "      <th>25</th>\n",
209 |        "      <td>54</td>\n",
210 |        "    </tr>\n",
211 |        "  </tbody>\n",
212 |        "</table>\n",
213 |        "</div>"
214 |       ],
215 |       "text/plain": [
216 |        "    age\n",
217 |        "4    46\n",
218 |        "8    62\n",
219 |        "26   23\n",
220 |        "17   58\n",
221 |        "24   50\n",
222 |        "25   54"
223 |       ]
224 |      },
225 |      "execution_count": 30,
226 |      "metadata": {},
227 |      "output_type": "execute_result"
228 |     }
229 |    ],
230 |    "source": [
231 |     "X_test"
232 |    ]
233 |   },
234 |   {
235 |    "cell_type": "code",
236 |    "execution_count": 31,
237 |    "metadata": {},
238 |    "outputs": [],
239 |    "source": [
240 |     "from sklearn.linear_model import LogisticRegression\n",
241 |     "model = LogisticRegression()"
242 |    ]
243 |   },
244 |   {
245 |    "cell_type": "code",
246 |    "execution_count": 66,
247 |    "metadata": {
248 |     "scrolled": true
249 |    },
250 |    "outputs": [
251 |     {
252 |      "name": "stderr",
253 |      "output_type": "stream",
254 |      "text": [
255 |       "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\logistic.py:433: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.\n",
256 |       "  FutureWarning)\n"
257 |      ]
258 |     },
259 |     {
260 |      "data": {
261 |       "text/plain": [
262 |        "LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
263 |        "          intercept_scaling=1, max_iter=100, multi_class='warn',\n",
264 |        "          n_jobs=None, penalty='l2', random_state=None, solver='warn',\n",
265 |        "          tol=0.0001, verbose=0, warm_start=False)"
266 |       ]
267 |      },
268 |      "execution_count": 66,
269 |      "metadata": {},
270 |      "output_type": "execute_result"
271 |     }
272 |    ],
273 |    "source": [
274 |     "model.fit(X_train, y_train)"
275 |    ]
276 |   },
277 |   {
278 |    "cell_type": "code",
279 |    "execution_count": 9,
280 |    "metadata": {},
281 |    "outputs": [
282 |     {
283 |      "data": {
284 |       "text/html": [
285 |        "<div>\n",
286 |        "<style scoped>\n",
287 |        "    .dataframe tbody tr th:only-of-type {\n",
288 |        "        vertical-align: middle;\n",
289 |        "    }\n",
290 |        "\n",
291 |        "    .dataframe tbody tr th {\n",
292 |        "        vertical-align: top;\n",
293 |        "    }\n",
294 |        "\n",
295 |        "    .dataframe thead th {\n",
296 |        "        text-align: right;\n",
297 |        "    }\n",
298 |        "</style>\n",
299 |        "<table border=\"1\" class=\"dataframe\">\n",
300 |        "  <thead>\n",
301 |        "    <tr style=\"text-align: right;\">\n",
302 |        "      <th></th>\n",
303 |        "      <th>age</th>\n",
304 |        "    </tr>\n",
305 |        "  </thead>\n",
306 |        "  <tbody>\n",
307 |        "    <tr>\n",
308 |        "      <th>16</th>\n",
309 |        "      <td>25</td>\n",
310 |        "    </tr>\n",
311 |        "    <tr>\n",
312 |        "      <th>21</th>\n",
313 |        "      <td>26</td>\n",
314 |        "    </tr>\n",
315 |        "    <tr>\n",
316 |        "      <th>2</th>\n",
317 |        "      <td>47</td>\n",
318 |        "    </tr>\n",
319 |        "  </tbody>\n",
320 |        "</table>\n",
321 |        "</div>"
322 |       ],
323 |       "text/plain": [
324 |        "    age\n",
325 |        "16   25\n",
326 |        "21   26\n",
327 |        "2    47"
328 |       ]
329 |      },
330 |      "execution_count": 9,
331 |      "metadata": {},
332 |      "output_type": "execute_result"
333 |     }
334 |    ],
335 |    "source": [
336 |     "X_test"
337 |    ]
338 |   },
339 |   {
340 |    "cell_type": "code",
341 |    "execution_count": 39,
342 |    "metadata": {},
343 |    "outputs": [],
344 |    "source": [
345 |     "y_predicted = model.predict(X_test)"
346 |    ]
347 |   },
348 |   {
349 |    "cell_type": "code",
350 |    "execution_count": 33,
351 |    "metadata": {},
352 |    "outputs": [
353 |     {
354 |      "data": {
355 |       "text/plain": [
356 |        "array([[0.40569485, 0.59430515],\n",
357 |        "       [0.26002994, 0.73997006],\n",
358 |        "       [0.63939494, 0.36060506],\n",
359 |        "       [0.29321765, 0.70678235],\n",
360 |        "       [0.36637568, 0.63362432],\n",
361 |        "       [0.32875922, 0.67124078]])"
362 |       ]
363 |      },
364 |      "execution_count": 33,
365 |      "metadata": {},
366 |      "output_type": "execute_result"
367 |     }
368 |    ],
369 |    "source": [
370 |     "model.predict_proba(X_test)"
371 |    ]
372 |   },
373 |   {
374 |    "cell_type": "code",
375 |    "execution_count": 34,
376 |    "metadata": {
377 |     "scrolled": true
378 |    },
379 |    "outputs": [
380 |     {
381 |      "data": {
382 |       "text/plain": [
383 |        "1.0"
384 |       ]
385 |      },
386 |      "execution_count": 34,
387 |      "metadata": {},
388 |      "output_type": "execute_result"
389 |     }
390 |    ],
391 |    "source": [
392 |     "model.score(X_test,y_test)"
393 |    ]
394 |   },
395 |   {
396 |    "cell_type": "code",
397 |    "execution_count": 40,
398 |    "metadata": {},
399 |    "outputs": [
400 |     {
401 |      "data": {
402 |       "text/plain": [
403 |        "array([1, 1, 0, 1, 1, 1], dtype=int64)"
404 |       ]
405 |      },
406 |      "execution_count": 40,
407 |      "metadata": {},
408 |      "output_type": "execute_result"
409 |     }
410 |    ],
411 |    "source": [
412 |     "y_predicted"
413 |    ]
414 |   },
415 |   {
416 |    "cell_type": "code",
417 |    "execution_count": 37,
418 |    "metadata": {
419 |     "scrolled": true
420 |    },
421 |    "outputs": [
422 |     {
423 |      "data": {
424 |       "text/html": [
425 |        "<div>\n",
426 |        "<style scoped>\n",
427 |        "    .dataframe tbody tr th:only-of-type {\n",
428 |        "        vertical-align: middle;\n",
429 |        "    }\n",
430 |        "\n",
431 |        "    .dataframe tbody tr th {\n",
432 |        "        vertical-align: top;\n",
433 |        "    }\n",
434 |        "\n",
435 |        "    .dataframe thead th {\n",
436 |        "        text-align: right;\n",
437 |        "    }\n",
438 |        "</style>\n",
439 |        "<table border=\"1\" class=\"dataframe\">\n",
440 |        "  <thead>\n",
441 |        "    <tr style=\"text-align: right;\">\n",
442 |        "      <th></th>\n",
443 |        "      <th>age</th>\n",
444 |        "    </tr>\n",
445 |        "  </thead>\n",
446 |        "  <tbody>\n",
447 |        "    <tr>\n",
448 |        "      <th>4</th>\n",
449 |        "      <td>46</td>\n",
450 |        "    </tr>\n",
451 |        "    <tr>\n",
452 |        "      <th>8</th>\n",
453 |        "      <td>62</td>\n",
454 |        "    </tr>\n",
455 |        "    <tr>\n",
456 |        "      <th>26</th>\n",
457 |        "      <td>23</td>\n",
458 |        "    </tr>\n",
459 |        "    <tr>\n",
460 |        "      <th>17</th>\n",
461 |        "      <td>58</td>\n",
462 |        "    </tr>\n",
463 |        "    <tr>\n",
464 |        "      <th>24</th>\n",
465 |        "      <td>50</td>\n",
466 |        "    </tr>\n",
467 |        "    <tr>\n",
468 |        "      <th>25</th>\n",
469 |        "      <td>54</td>\n",
470 |        "    </tr>\n",
471 |        "  </tbody>\n",
472 |        "</table>\n",
473 |        "</div>"
474 |       ],
475 |       "text/plain": [
476 |        "    age\n",
477 |        "4    46\n",
478 |        "8    62\n",
479 |        "26   23\n",
480 |        "17   58\n",
481 |        "24   50\n",
482 |        "25   54"
483 |       ]
484 |      },
485 |      "execution_count": 37,
486 |      "metadata": {},
487 |      "output_type": "execute_result"
488 |     }
489 |    ],
490 |    "source": [
491 |     "X_test"
492 |    ]
493 |   },
494 |   {
495 |    "cell_type": "markdown",
496 |    "metadata": {},
497 |    "source": [
498 |     "**model.coef_ indicates value of m in y=m*x + b equation**"
499 |    ]
500 |   },
501 |   {
502 |    "cell_type": "code",
503 |    "execution_count": 67,
504 |    "metadata": {
505 |     "scrolled": true
506 |    },
507 |    "outputs": [
508 |     {
509 |      "data": {
510 |       "text/plain": [
511 |        "array([[0.04150133]])"
512 |       ]
513 |      },
514 |      "execution_count": 67,
515 |      "metadata": {},
516 |      "output_type": "execute_result"
517 |     }
518 |    ],
519 |    "source": [
520 |     "model.coef_"
521 |    ]
522 |   },
523 |   {
524 |    "cell_type": "markdown",
525 |    "metadata": {},
526 |    "source": [
527 |     "**model.intercept_ indicates value of b in y=m*x + b equation**"
528 |    ]
529 |   },
530 |   {
531 |    "cell_type": "code",
532 |    "execution_count": 68,
533 |    "metadata": {
534 |     "scrolled": true
535 |    },
536 |    "outputs": [
537 |     {
538 |      "data": {
539 |       "text/plain": [
540 |        "array([-1.52726963])"
541 |       ]
542 |      },
543 |      "execution_count": 68,
544 |      "metadata": {},
545 |      "output_type": "execute_result"
546 |     }
547 |    ],
548 |    "source": [
549 |     "model.intercept_"
550 |    ]
551 |   },
552 |   {
553 |    "cell_type": "markdown",
554 |    "metadata": {},
555 |    "source": [
556 |     "**Lets defined sigmoid function now and do the math with hand**"
557 |    ]
558 |   },
559 |   {
560 |    "cell_type": "code",
561 |    "execution_count": 43,
562 |    "metadata": {},
563 |    "outputs": [],
564 |    "source": [
565 |     "import math\n",
566 |     "def sigmoid(x):\n",
567 |     "  return 1 / (1 + math.exp(-x))"
568 |    ]
569 |   },
570 |   {
571 |    "cell_type": "code",
572 |    "execution_count": 75,
573 |    "metadata": {},
574 |    "outputs": [],
575 |    "source": [
576 |     "def prediction_function(age):\n",
577 |     "    z = 0.042 * age - 1.53 # 0.04150133 ~ 0.042 and -1.52726963 ~ -1.53\n",
578 |     "    y = sigmoid(z)\n",
579 |     "    return y"
580 |    ]
581 |   },
582 |   {
583 |    "cell_type": "code",
584 |    "execution_count": 76,
585 |    "metadata": {},
586 |    "outputs": [
587 |     {
588 |      "data": {
589 |       "text/plain": [
590 |        "0.4850044983805899"
591 |       ]
592 |      },
593 |      "execution_count": 76,
594 |      "metadata": {},
595 |      "output_type": "execute_result"
596 |     }
597 |    ],
598 |    "source": [
599 |     "age = 35\n",
600 |     "prediction_function(age)"
601 |    ]
602 |   },
603 |   {
604 |    "cell_type": "markdown",
605 |    "metadata": {},
606 |    "source": [
607 |     "**0.485 is less than 0.5 which means person with 35 age will *not* buy insurance**"
608 |    ]
609 |   },
610 |   {
611 |    "cell_type": "code",
612 |    "execution_count": 77,
613 |    "metadata": {
614 |     "scrolled": true
615 |    },
616 |    "outputs": [
617 |     {
618 |      "data": {
619 |       "text/plain": [
620 |        "0.568565299077705"
621 |       ]
622 |      },
623 |      "execution_count": 77,
624 |      "metadata": {},
625 |      "output_type": "execute_result"
626 |     }
627 |    ],
628 |    "source": [
629 |     "age = 43\n",
630 |     "prediction_function(age)"
631 |    ]
632 |   },
633 |   {
634 |    "cell_type": "markdown",
635 |    "metadata": {},
636 |    "source": [
637 |     "**0.485 is more than 0.5 which means person with 43 will buy the insurance**"
638 |    ]
639 |   },
640 |   {
641 |    "cell_type": "markdown",
642 |    "metadata": {},
643 |    "source": [
644 |     "<h2 style=\"color:purple\">Exercise</h2>\n",
645 |     "\n",
646 |     "Download employee retention dataset from here: https://www.kaggle.com/giripujar/hr-analytics. \n",
647 |     "1. Now do some exploratory data analysis to figure out which variables have direct and clear impact on employee retention (i.e. whether they leave the company or continue to work)\n",
648 |     "2. Plot bar charts showing impact of employee salaries on retention\n",
649 |     "3. Plot bar charts showing corelation between department and employee retention\n",
650 |     "4. Now build logistic regression model using variables that were narrowed down in step 1\n",
651 |     "5. Measure the accuracy of the model"
652 |    ]
653 |   }
654 |  ],
655 |  "metadata": {
656 |   "kernelspec": {
657 |    "display_name": "Python 3",
658 |    "language": "python",
659 |    "name": "python3"
660 |   },
661 |   "language_info": {
662 |    "codemirror_mode": {
663 |     "name": "ipython",
664 |     "version": 3
665 |    },
666 |    "file_extension": ".py",
667 |    "mimetype": "text/x-python",
668 |    "name": "python",
669 |    "nbconvert_exporter": "python",
670 |    "pygments_lexer": "ipython3",
671 |    "version": "3.7.3"
672 |   }
673 |  },
674 |  "nbformat": 4,
675 |  "nbformat_minor": 2
676 | }
677 | 


--------------------------------------------------------------------------------
/LogisticRegression/.ipynb_checkpoints/Exercise-checkpoint.ipynb:
--------------------------------------------------------------------------------
1 | {
2 |  "cells": [],
3 |  "metadata": {},
4 |  "nbformat": 4,
5 |  "nbformat_minor": 5
6 | }
7 | 


--------------------------------------------------------------------------------
/LogisticRegression/.ipynb_checkpoints/LogisticeRegression-checkpoint.ipynb:
--------------------------------------------------------------------------------
1 | {
2 |  "cells": [],
3 |  "metadata": {},
4 |  "nbformat": 4,
5 |  "nbformat_minor": 5
6 | }
7 | 


--------------------------------------------------------------------------------
/LogisticRegression/.ipynb_checkpoints/insurance_data-checkpoint.csv:
--------------------------------------------------------------------------------
 1 | age,bought_insurance
 2 | 22,0
 3 | 25,0
 4 | 47,1
 5 | 52,0
 6 | 46,1
 7 | 56,1
 8 | 55,0
 9 | 60,1
10 | 62,1
11 | 61,1
12 | 18,0
13 | 28,0
14 | 27,0
15 | 29,0
16 | 49,1
17 | 55,1
18 | 25,1
19 | 58,1
20 | 19,0
21 | 18,0
22 | 21,0
23 | 26,0
24 | 40,1
25 | 45,1
26 | 50,1
27 | 54,1
28 | 23,0


--------------------------------------------------------------------------------
/LogisticRegression/Exercise/.ipynb_checkpoints/7_logistic_regression_exercise-checkpoint.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "markdown",
   5 |    "metadata": {},
   6 |    "source": [
   7 |     "Dataset is downloaded from Kaggle. Link: https://www.kaggle.com/giripujar/hr-analytics"
   8 |    ]
   9 |   },
  10 |   {
  11 |    "cell_type": "code",
  12 |    "execution_count": 13,
  13 |    "metadata": {
  14 |     "collapsed": true
  15 |    },
  16 |    "outputs": [],
  17 |    "source": [
  18 |     "import pandas as pd\n",
  19 |     "from matplotlib import pyplot as plt\n",
  20 |     "%matplotlib inline"
  21 |    ]
  22 |   },
  23 |   {
  24 |    "cell_type": "code",
  25 |    "execution_count": 3,
  26 |    "metadata": {},
  27 |    "outputs": [
  28 |     {
  29 |      "data": {
  30 |       "text/html": [
  31 |        "<div>\n",
  32 |        "<style scoped>\n",
  33 |        "    .dataframe tbody tr th:only-of-type {\n",
  34 |        "        vertical-align: middle;\n",
  35 |        "    }\n",
  36 |        "\n",
  37 |        "    .dataframe tbody tr th {\n",
  38 |        "        vertical-align: top;\n",
  39 |        "    }\n",
  40 |        "\n",
  41 |        "    .dataframe thead th {\n",
  42 |        "        text-align: right;\n",
  43 |        "    }\n",
  44 |        "</style>\n",
  45 |        "<table border=\"1\" class=\"dataframe\">\n",
  46 |        "  <thead>\n",
  47 |        "    <tr style=\"text-align: right;\">\n",
  48 |        "      <th></th>\n",
  49 |        "      <th>satisfaction_level</th>\n",
  50 |        "      <th>last_evaluation</th>\n",
  51 |        "      <th>number_project</th>\n",
  52 |        "      <th>average_montly_hours</th>\n",
  53 |        "      <th>time_spend_company</th>\n",
  54 |        "      <th>Work_accident</th>\n",
  55 |        "      <th>left</th>\n",
  56 |        "      <th>promotion_last_5years</th>\n",
  57 |        "      <th>Department</th>\n",
  58 |        "      <th>salary</th>\n",
  59 |        "    </tr>\n",
  60 |        "  </thead>\n",
  61 |        "  <tbody>\n",
  62 |        "    <tr>\n",
  63 |        "      <th>0</th>\n",
  64 |        "      <td>0.38</td>\n",
  65 |        "      <td>0.53</td>\n",
  66 |        "      <td>2</td>\n",
  67 |        "      <td>157</td>\n",
  68 |        "      <td>3</td>\n",
  69 |        "      <td>0</td>\n",
  70 |        "      <td>1</td>\n",
  71 |        "      <td>0</td>\n",
  72 |        "      <td>sales</td>\n",
  73 |        "      <td>low</td>\n",
  74 |        "    </tr>\n",
  75 |        "    <tr>\n",
  76 |        "      <th>1</th>\n",
  77 |        "      <td>0.80</td>\n",
  78 |        "      <td>0.86</td>\n",
  79 |        "      <td>5</td>\n",
  80 |        "      <td>262</td>\n",
  81 |        "      <td>6</td>\n",
  82 |        "      <td>0</td>\n",
  83 |        "      <td>1</td>\n",
  84 |        "      <td>0</td>\n",
  85 |        "      <td>sales</td>\n",
  86 |        "      <td>medium</td>\n",
  87 |        "    </tr>\n",
  88 |        "    <tr>\n",
  89 |        "      <th>2</th>\n",
  90 |        "      <td>0.11</td>\n",
  91 |        "      <td>0.88</td>\n",
  92 |        "      <td>7</td>\n",
  93 |        "      <td>272</td>\n",
  94 |        "      <td>4</td>\n",
  95 |        "      <td>0</td>\n",
  96 |        "      <td>1</td>\n",
  97 |        "      <td>0</td>\n",
  98 |        "      <td>sales</td>\n",
  99 |        "      <td>medium</td>\n",
 100 |        "    </tr>\n",
 101 |        "    <tr>\n",
 102 |        "      <th>3</th>\n",
 103 |        "      <td>0.72</td>\n",
 104 |        "      <td>0.87</td>\n",
 105 |        "      <td>5</td>\n",
 106 |        "      <td>223</td>\n",
 107 |        "      <td>5</td>\n",
 108 |        "      <td>0</td>\n",
 109 |        "      <td>1</td>\n",
 110 |        "      <td>0</td>\n",
 111 |        "      <td>sales</td>\n",
 112 |        "      <td>low</td>\n",
 113 |        "    </tr>\n",
 114 |        "    <tr>\n",
 115 |        "      <th>4</th>\n",
 116 |        "      <td>0.37</td>\n",
 117 |        "      <td>0.52</td>\n",
 118 |        "      <td>2</td>\n",
 119 |        "      <td>159</td>\n",
 120 |        "      <td>3</td>\n",
 121 |        "      <td>0</td>\n",
 122 |        "      <td>1</td>\n",
 123 |        "      <td>0</td>\n",
 124 |        "      <td>sales</td>\n",
 125 |        "      <td>low</td>\n",
 126 |        "    </tr>\n",
 127 |        "  </tbody>\n",
 128 |        "</table>\n",
 129 |        "</div>"
 130 |       ],
 131 |       "text/plain": [
 132 |        "   satisfaction_level  last_evaluation  number_project  average_montly_hours  \\\n",
 133 |        "0                0.38             0.53               2                   157   \n",
 134 |        "1                0.80             0.86               5                   262   \n",
 135 |        "2                0.11             0.88               7                   272   \n",
 136 |        "3                0.72             0.87               5                   223   \n",
 137 |        "4                0.37             0.52               2                   159   \n",
 138 |        "\n",
 139 |        "   time_spend_company  Work_accident  left  promotion_last_5years Department  \\\n",
 140 |        "0                   3              0     1                      0      sales   \n",
 141 |        "1                   6              0     1                      0      sales   \n",
 142 |        "2                   4              0     1                      0      sales   \n",
 143 |        "3                   5              0     1                      0      sales   \n",
 144 |        "4                   3              0     1                      0      sales   \n",
 145 |        "\n",
 146 |        "   salary  \n",
 147 |        "0     low  \n",
 148 |        "1  medium  \n",
 149 |        "2  medium  \n",
 150 |        "3     low  \n",
 151 |        "4     low  "
 152 |       ]
 153 |      },
 154 |      "execution_count": 3,
 155 |      "metadata": {},
 156 |      "output_type": "execute_result"
 157 |     }
 158 |    ],
 159 |    "source": [
 160 |     "df = pd.read_csv(\"HR_comma_sep.csv\")\n",
 161 |     "df.head()"
 162 |    ]
 163 |   },
 164 |   {
 165 |    "cell_type": "markdown",
 166 |    "metadata": {},
 167 |    "source": [
 168 |     "<h2 style=\"color:purple\">Data exploration and visualization</h2>"
 169 |    ]
 170 |   },
 171 |   {
 172 |    "cell_type": "code",
 173 |    "execution_count": 73,
 174 |    "metadata": {},
 175 |    "outputs": [
 176 |     {
 177 |      "data": {
 178 |       "text/plain": [
 179 |        "(3571, 10)"
 180 |       ]
 181 |      },
 182 |      "execution_count": 73,
 183 |      "metadata": {},
 184 |      "output_type": "execute_result"
 185 |     }
 186 |    ],
 187 |    "source": [
 188 |     "left = df[df.left==1]\n",
 189 |     "left.shape"
 190 |    ]
 191 |   },
 192 |   {
 193 |    "cell_type": "code",
 194 |    "execution_count": 74,
 195 |    "metadata": {},
 196 |    "outputs": [
 197 |     {
 198 |      "data": {
 199 |       "text/plain": [
 200 |        "(11428, 10)"
 201 |       ]
 202 |      },
 203 |      "execution_count": 74,
 204 |      "metadata": {},
 205 |      "output_type": "execute_result"
 206 |     }
 207 |    ],
 208 |    "source": [
 209 |     "retained = df[df.left==0]\n",
 210 |     "retained.shape"
 211 |    ]
 212 |   },
 213 |   {
 214 |    "cell_type": "markdown",
 215 |    "metadata": {},
 216 |    "source": [
 217 |     "**Average numbers for all columns** "
 218 |    ]
 219 |   },
 220 |   {
 221 |    "cell_type": "code",
 222 |    "execution_count": 31,
 223 |    "metadata": {
 224 |     "scrolled": false
 225 |    },
 226 |    "outputs": [
 227 |     {
 228 |      "data": {
 229 |       "text/html": [
 230 |        "<div>\n",
 231 |        "<style scoped>\n",
 232 |        "    .dataframe tbody tr th:only-of-type {\n",
 233 |        "        vertical-align: middle;\n",
 234 |        "    }\n",
 235 |        "\n",
 236 |        "    .dataframe tbody tr th {\n",
 237 |        "        vertical-align: top;\n",
 238 |        "    }\n",
 239 |        "\n",
 240 |        "    .dataframe thead th {\n",
 241 |        "        text-align: right;\n",
 242 |        "    }\n",
 243 |        "</style>\n",
 244 |        "<table border=\"1\" class=\"dataframe\">\n",
 245 |        "  <thead>\n",
 246 |        "    <tr style=\"text-align: right;\">\n",
 247 |        "      <th></th>\n",
 248 |        "      <th>satisfaction_level</th>\n",
 249 |        "      <th>last_evaluation</th>\n",
 250 |        "      <th>number_project</th>\n",
 251 |        "      <th>average_montly_hours</th>\n",
 252 |        "      <th>time_spend_company</th>\n",
 253 |        "      <th>Work_accident</th>\n",
 254 |        "      <th>promotion_last_5years</th>\n",
 255 |        "    </tr>\n",
 256 |        "    <tr>\n",
 257 |        "      <th>left</th>\n",
 258 |        "      <th></th>\n",
 259 |        "      <th></th>\n",
 260 |        "      <th></th>\n",
 261 |        "      <th></th>\n",
 262 |        "      <th></th>\n",
 263 |        "      <th></th>\n",
 264 |        "      <th></th>\n",
 265 |        "    </tr>\n",
 266 |        "  </thead>\n",
 267 |        "  <tbody>\n",
 268 |        "    <tr>\n",
 269 |        "      <th>0</th>\n",
 270 |        "      <td>0.666810</td>\n",
 271 |        "      <td>0.715473</td>\n",
 272 |        "      <td>3.786664</td>\n",
 273 |        "      <td>199.060203</td>\n",
 274 |        "      <td>3.380032</td>\n",
 275 |        "      <td>0.175009</td>\n",
 276 |        "      <td>0.026251</td>\n",
 277 |        "    </tr>\n",
 278 |        "    <tr>\n",
 279 |        "      <th>1</th>\n",
 280 |        "      <td>0.440098</td>\n",
 281 |        "      <td>0.718113</td>\n",
 282 |        "      <td>3.855503</td>\n",
 283 |        "      <td>207.419210</td>\n",
 284 |        "      <td>3.876505</td>\n",
 285 |        "      <td>0.047326</td>\n",
 286 |        "      <td>0.005321</td>\n",
 287 |        "    </tr>\n",
 288 |        "  </tbody>\n",
 289 |        "</table>\n",
 290 |        "</div>"
 291 |       ],
 292 |       "text/plain": [
 293 |        "      satisfaction_level  last_evaluation  number_project  \\\n",
 294 |        "left                                                        \n",
 295 |        "0               0.666810         0.715473        3.786664   \n",
 296 |        "1               0.440098         0.718113        3.855503   \n",
 297 |        "\n",
 298 |        "      average_montly_hours  time_spend_company  Work_accident  \\\n",
 299 |        "left                                                            \n",
 300 |        "0               199.060203            3.380032       0.175009   \n",
 301 |        "1               207.419210            3.876505       0.047326   \n",
 302 |        "\n",
 303 |        "      promotion_last_5years  \n",
 304 |        "left                         \n",
 305 |        "0                  0.026251  \n",
 306 |        "1                  0.005321  "
 307 |       ]
 308 |      },
 309 |      "execution_count": 31,
 310 |      "metadata": {},
 311 |      "output_type": "execute_result"
 312 |     }
 313 |    ],
 314 |    "source": [
 315 |     "df.groupby('left').mean()"
 316 |    ]
 317 |   },
 318 |   {
 319 |    "cell_type": "markdown",
 320 |    "metadata": {},
 321 |    "source": [
 322 |     "From above table we can draw following conclusions,\n",
 323 |     "<ol>\n",
 324 |     "    <li>**Satisfaction Level**: Satisfaction level seems to be relatively low (0.44) in employees leaving the firm vs the retained ones (0.66)</li>\n",
 325 |     "    <li>**Average Monthly Hours**: Average monthly hours are higher in employees leaving the firm (199 vs 207)</li>\n",
 326 |     "    <li>**Promotion Last 5 Years**: Employees who are given promotion are likely to be retained at firm </li>\n",
 327 |     "</ol>"
 328 |    ]
 329 |   },
 330 |   {
 331 |    "cell_type": "markdown",
 332 |    "metadata": {},
 333 |    "source": [
 334 |     "**Impact of salary on employee retention**"
 335 |    ]
 336 |   },
 337 |   {
 338 |    "cell_type": "code",
 339 |    "execution_count": 37,
 340 |    "metadata": {
 341 |     "scrolled": true
 342 |    },
 343 |    "outputs": [
 344 |     {
 345 |      "data": {
 346 |       "text/plain": [
 347 |        "<matplotlib.axes._subplots.AxesSubplot at 0x1442bf3eda0>"
 348 |       ]
 349 |      },
 350 |      "execution_count": 37,
 351 |      "metadata": {},
 352 |      "output_type": "execute_result"
 353 |     },
 354 |     {
 355 |      "data": {
 356 |       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYEAAAEpCAYAAAB1Fp6nAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nSUVORK5CYII=\n",
 357 |       "text/plain": [
 358 |        "<matplotlib.figure.Figure at 0x14429998240>"
 359 |       ]
 360 |      },
 361 |      "metadata": {},
 362 |      "output_type": "display_data"
 363 |     }
 364 |    ],
 365 |    "source": [
 366 |     "pd.crosstab(df.salary,df.left).plot(kind='bar')"
 367 |    ]
 368 |   },
 369 |   {
 370 |    "cell_type": "markdown",
 371 |    "metadata": {},
 372 |    "source": [
 373 |     "Above bar chart shows employees with high salaries are likely to not leave the company"
 374 |    ]
 375 |   },
 376 |   {
 377 |    "cell_type": "markdown",
 378 |    "metadata": {},
 379 |    "source": [
 380 |     "**Department wise employee retention rate**"
 381 |    ]
 382 |   },
 383 |   {
 384 |    "cell_type": "code",
 385 |    "execution_count": 38,
 386 |    "metadata": {
 387 |     "scrolled": true
 388 |    },
 389 |    "outputs": [
 390 |     {
 391 |      "data": {
 392 |       "text/plain": [
 393 |        "<matplotlib.axes._subplots.AxesSubplot at 0x1442bf75128>"
 394 |       ]
 395 |      },
 396 |      "execution_count": 38,
 397 |      "metadata": {},
 398 |      "output_type": "execute_result"
 399 |     },
 400 |     {
 401 |      "data": {
 402 |       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYEAAAFDCAYAAADcebKbAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ngg==\n",
 403 |       "text/plain": [
 404 |        "<matplotlib.figure.Figure at 0x1442bf7cba8>"
 405 |       ]
 406 |      },
 407 |      "metadata": {},
 408 |      "output_type": "display_data"
 409 |     }
 410 |    ],
 411 |    "source": [
 412 |     "pd.crosstab(df.Department,df.left).plot(kind='bar')"
 413 |    ]
 414 |   },
 415 |   {
 416 |    "cell_type": "markdown",
 417 |    "metadata": {},
 418 |    "source": [
 419 |     "From above chart there seem to be some impact of department on employee retention but it is not major hence we will ignore department in our analysis"
 420 |    ]
 421 |   },
 422 |   {
 423 |    "cell_type": "markdown",
 424 |    "metadata": {},
 425 |    "source": [
 426 |     "<h3 style=\"color:purple\">From the data analysis so far we can conclude that we will use following variables as independant variables in our model</h3>\n",
 427 |     "<ol>\n",
 428 |     "    <li>**Satisfaction Level**</li>\n",
 429 |     "    <li>**Average Monthly Hours**</li>\n",
 430 |     "    <li>**Promotion Last 5 Years**</li>\n",
 431 |     "    <li>**Salary**</li>\n",
 432 |     "</ol>"
 433 |    ]
 434 |   },
 435 |   {
 436 |    "cell_type": "code",
 437 |    "execution_count": 76,
 438 |    "metadata": {},
 439 |    "outputs": [
 440 |     {
 441 |      "data": {
 442 |       "text/html": [
 443 |        "<div>\n",
 444 |        "<style scoped>\n",
 445 |        "    .dataframe tbody tr th:only-of-type {\n",
 446 |        "        vertical-align: middle;\n",
 447 |        "    }\n",
 448 |        "\n",
 449 |        "    .dataframe tbody tr th {\n",
 450 |        "        vertical-align: top;\n",
 451 |        "    }\n",
 452 |        "\n",
 453 |        "    .dataframe thead th {\n",
 454 |        "        text-align: right;\n",
 455 |        "    }\n",
 456 |        "</style>\n",
 457 |        "<table border=\"1\" class=\"dataframe\">\n",
 458 |        "  <thead>\n",
 459 |        "    <tr style=\"text-align: right;\">\n",
 460 |        "      <th></th>\n",
 461 |        "      <th>satisfaction_level</th>\n",
 462 |        "      <th>average_montly_hours</th>\n",
 463 |        "      <th>promotion_last_5years</th>\n",
 464 |        "      <th>salary</th>\n",
 465 |        "    </tr>\n",
 466 |        "  </thead>\n",
 467 |        "  <tbody>\n",
 468 |        "    <tr>\n",
 469 |        "      <th>0</th>\n",
 470 |        "      <td>0.38</td>\n",
 471 |        "      <td>157</td>\n",
 472 |        "      <td>0</td>\n",
 473 |        "      <td>low</td>\n",
 474 |        "    </tr>\n",
 475 |        "    <tr>\n",
 476 |        "      <th>1</th>\n",
 477 |        "      <td>0.80</td>\n",
 478 |        "      <td>262</td>\n",
 479 |        "      <td>0</td>\n",
 480 |        "      <td>medium</td>\n",
 481 |        "    </tr>\n",
 482 |        "    <tr>\n",
 483 |        "      <th>2</th>\n",
 484 |        "      <td>0.11</td>\n",
 485 |        "      <td>272</td>\n",
 486 |        "      <td>0</td>\n",
 487 |        "      <td>medium</td>\n",
 488 |        "    </tr>\n",
 489 |        "    <tr>\n",
 490 |        "      <th>3</th>\n",
 491 |        "      <td>0.72</td>\n",
 492 |        "      <td>223</td>\n",
 493 |        "      <td>0</td>\n",
 494 |        "      <td>low</td>\n",
 495 |        "    </tr>\n",
 496 |        "    <tr>\n",
 497 |        "      <th>4</th>\n",
 498 |        "      <td>0.37</td>\n",
 499 |        "      <td>159</td>\n",
 500 |        "      <td>0</td>\n",
 501 |        "      <td>low</td>\n",
 502 |        "    </tr>\n",
 503 |        "  </tbody>\n",
 504 |        "</table>\n",
 505 |        "</div>"
 506 |       ],
 507 |       "text/plain": [
 508 |        "   satisfaction_level  average_montly_hours  promotion_last_5years  salary\n",
 509 |        "0                0.38                   157                      0     low\n",
 510 |        "1                0.80                   262                      0  medium\n",
 511 |        "2                0.11                   272                      0  medium\n",
 512 |        "3                0.72                   223                      0     low\n",
 513 |        "4                0.37                   159                      0     low"
 514 |       ]
 515 |      },
 516 |      "execution_count": 76,
 517 |      "metadata": {},
 518 |      "output_type": "execute_result"
 519 |     }
 520 |    ],
 521 |    "source": [
 522 |     "subdf = df[['satisfaction_level','average_montly_hours','promotion_last_5years','salary']]\n",
 523 |     "subdf.head()"
 524 |    ]
 525 |   },
 526 |   {
 527 |    "cell_type": "markdown",
 528 |    "metadata": {},
 529 |    "source": [
 530 |     "**Tackle salary dummy variable**"
 531 |    ]
 532 |   },
 533 |   {
 534 |    "cell_type": "markdown",
 535 |    "metadata": {},
 536 |    "source": [
 537 |     "Salary has all text data. It needs to be converted to numbers and we will use dummy variable for that. Check my one hot encoding tutorial to understand purpose behind dummy variables."
 538 |    ]
 539 |   },
 540 |   {
 541 |    "cell_type": "code",
 542 |    "execution_count": 78,
 543 |    "metadata": {},
 544 |    "outputs": [],
 545 |    "source": [
 546 |     "salary_dummies = pd.get_dummies(subdf.salary, prefix=\"salary\")"
 547 |    ]
 548 |   },
 549 |   {
 550 |    "cell_type": "code",
 551 |    "execution_count": 79,
 552 |    "metadata": {},
 553 |    "outputs": [],
 554 |    "source": [
 555 |     "df_with_dummies = pd.concat([subdf,salary_dummies],axis='columns')"
 556 |    ]
 557 |   },
 558 |   {
 559 |    "cell_type": "code",
 560 |    "execution_count": 80,
 561 |    "metadata": {},
 562 |    "outputs": [
 563 |     {
 564 |      "data": {
 565 |       "text/html": [
 566 |        "<div>\n",
 567 |        "<style scoped>\n",
 568 |        "    .dataframe tbody tr th:only-of-type {\n",
 569 |        "        vertical-align: middle;\n",
 570 |        "    }\n",
 571 |        "\n",
 572 |        "    .dataframe tbody tr th {\n",
 573 |        "        vertical-align: top;\n",
 574 |        "    }\n",
 575 |        "\n",
 576 |        "    .dataframe thead th {\n",
 577 |        "        text-align: right;\n",
 578 |        "    }\n",
 579 |        "</style>\n",
 580 |        "<table border=\"1\" class=\"dataframe\">\n",
 581 |        "  <thead>\n",
 582 |        "    <tr style=\"text-align: right;\">\n",
 583 |        "      <th></th>\n",
 584 |        "      <th>satisfaction_level</th>\n",
 585 |        "      <th>average_montly_hours</th>\n",
 586 |        "      <th>promotion_last_5years</th>\n",
 587 |        "      <th>salary</th>\n",
 588 |        "      <th>salary_high</th>\n",
 589 |        "      <th>salary_low</th>\n",
 590 |        "      <th>salary_medium</th>\n",
 591 |        "    </tr>\n",
 592 |        "  </thead>\n",
 593 |        "  <tbody>\n",
 594 |        "    <tr>\n",
 595 |        "      <th>0</th>\n",
 596 |        "      <td>0.38</td>\n",
 597 |        "      <td>157</td>\n",
 598 |        "      <td>0</td>\n",
 599 |        "      <td>low</td>\n",
 600 |        "      <td>0</td>\n",
 601 |        "      <td>1</td>\n",
 602 |        "      <td>0</td>\n",
 603 |        "    </tr>\n",
 604 |        "    <tr>\n",
 605 |        "      <th>1</th>\n",
 606 |        "      <td>0.80</td>\n",
 607 |        "      <td>262</td>\n",
 608 |        "      <td>0</td>\n",
 609 |        "      <td>medium</td>\n",
 610 |        "      <td>0</td>\n",
 611 |        "      <td>0</td>\n",
 612 |        "      <td>1</td>\n",
 613 |        "    </tr>\n",
 614 |        "    <tr>\n",
 615 |        "      <th>2</th>\n",
 616 |        "      <td>0.11</td>\n",
 617 |        "      <td>272</td>\n",
 618 |        "      <td>0</td>\n",
 619 |        "      <td>medium</td>\n",
 620 |        "      <td>0</td>\n",
 621 |        "      <td>0</td>\n",
 622 |        "      <td>1</td>\n",
 623 |        "    </tr>\n",
 624 |        "    <tr>\n",
 625 |        "      <th>3</th>\n",
 626 |        "      <td>0.72</td>\n",
 627 |        "      <td>223</td>\n",
 628 |        "      <td>0</td>\n",
 629 |        "      <td>low</td>\n",
 630 |        "      <td>0</td>\n",
 631 |        "      <td>1</td>\n",
 632 |        "      <td>0</td>\n",
 633 |        "    </tr>\n",
 634 |        "    <tr>\n",
 635 |        "      <th>4</th>\n",
 636 |        "      <td>0.37</td>\n",
 637 |        "      <td>159</td>\n",
 638 |        "      <td>0</td>\n",
 639 |        "      <td>low</td>\n",
 640 |        "      <td>0</td>\n",
 641 |        "      <td>1</td>\n",
 642 |        "      <td>0</td>\n",
 643 |        "    </tr>\n",
 644 |        "  </tbody>\n",
 645 |        "</table>\n",
 646 |        "</div>"
 647 |       ],
 648 |       "text/plain": [
 649 |        "   satisfaction_level  average_montly_hours  promotion_last_5years  salary  \\\n",
 650 |        "0                0.38                   157                      0     low   \n",
 651 |        "1                0.80                   262                      0  medium   \n",
 652 |        "2                0.11                   272                      0  medium   \n",
 653 |        "3                0.72                   223                      0     low   \n",
 654 |        "4                0.37                   159                      0     low   \n",
 655 |        "\n",
 656 |        "   salary_high  salary_low  salary_medium  \n",
 657 |        "0            0           1              0  \n",
 658 |        "1            0           0              1  \n",
 659 |        "2            0           0              1  \n",
 660 |        "3            0           1              0  \n",
 661 |        "4            0           1              0  "
 662 |       ]
 663 |      },
 664 |      "execution_count": 80,
 665 |      "metadata": {},
 666 |      "output_type": "execute_result"
 667 |     }
 668 |    ],
 669 |    "source": [
 670 |     "df_with_dummies.head()"
 671 |    ]
 672 |   },
 673 |   {
 674 |    "cell_type": "markdown",
 675 |    "metadata": {},
 676 |    "source": [
 677 |     "Now we need to remove salary column which is text data. It is already replaced by dummy variables so we can safely remove it"
 678 |    ]
 679 |   },
 680 |   {
 681 |    "cell_type": "code",
 682 |    "execution_count": 81,
 683 |    "metadata": {},
 684 |    "outputs": [
 685 |     {
 686 |      "data": {
 687 |       "text/html": [
 688 |        "<div>\n",
 689 |        "<style scoped>\n",
 690 |        "    .dataframe tbody tr th:only-of-type {\n",
 691 |        "        vertical-align: middle;\n",
 692 |        "    }\n",
 693 |        "\n",
 694 |        "    .dataframe tbody tr th {\n",
 695 |        "        vertical-align: top;\n",
 696 |        "    }\n",
 697 |        "\n",
 698 |        "    .dataframe thead th {\n",
 699 |        "        text-align: right;\n",
 700 |        "    }\n",
 701 |        "</style>\n",
 702 |        "<table border=\"1\" class=\"dataframe\">\n",
 703 |        "  <thead>\n",
 704 |        "    <tr style=\"text-align: right;\">\n",
 705 |        "      <th></th>\n",
 706 |        "      <th>satisfaction_level</th>\n",
 707 |        "      <th>average_montly_hours</th>\n",
 708 |        "      <th>promotion_last_5years</th>\n",
 709 |        "      <th>salary_high</th>\n",
 710 |        "      <th>salary_low</th>\n",
 711 |        "      <th>salary_medium</th>\n",
 712 |        "    </tr>\n",
 713 |        "  </thead>\n",
 714 |        "  <tbody>\n",
 715 |        "    <tr>\n",
 716 |        "      <th>0</th>\n",
 717 |        "      <td>0.38</td>\n",
 718 |        "      <td>157</td>\n",
 719 |        "      <td>0</td>\n",
 720 |        "      <td>0</td>\n",
 721 |        "      <td>1</td>\n",
 722 |        "      <td>0</td>\n",
 723 |        "    </tr>\n",
 724 |        "    <tr>\n",
 725 |        "      <th>1</th>\n",
 726 |        "      <td>0.80</td>\n",
 727 |        "      <td>262</td>\n",
 728 |        "      <td>0</td>\n",
 729 |        "      <td>0</td>\n",
 730 |        "      <td>0</td>\n",
 731 |        "      <td>1</td>\n",
 732 |        "    </tr>\n",
 733 |        "    <tr>\n",
 734 |        "      <th>2</th>\n",
 735 |        "      <td>0.11</td>\n",
 736 |        "      <td>272</td>\n",
 737 |        "      <td>0</td>\n",
 738 |        "      <td>0</td>\n",
 739 |        "      <td>0</td>\n",
 740 |        "      <td>1</td>\n",
 741 |        "    </tr>\n",
 742 |        "    <tr>\n",
 743 |        "      <th>3</th>\n",
 744 |        "      <td>0.72</td>\n",
 745 |        "      <td>223</td>\n",
 746 |        "      <td>0</td>\n",
 747 |        "      <td>0</td>\n",
 748 |        "      <td>1</td>\n",
 749 |        "      <td>0</td>\n",
 750 |        "    </tr>\n",
 751 |        "    <tr>\n",
 752 |        "      <th>4</th>\n",
 753 |        "      <td>0.37</td>\n",
 754 |        "      <td>159</td>\n",
 755 |        "      <td>0</td>\n",
 756 |        "      <td>0</td>\n",
 757 |        "      <td>1</td>\n",
 758 |        "      <td>0</td>\n",
 759 |        "    </tr>\n",
 760 |        "  </tbody>\n",
 761 |        "</table>\n",
 762 |        "</div>"
 763 |       ],
 764 |       "text/plain": [
 765 |        "   satisfaction_level  average_montly_hours  promotion_last_5years  \\\n",
 766 |        "0                0.38                   157                      0   \n",
 767 |        "1                0.80                   262                      0   \n",
 768 |        "2                0.11                   272                      0   \n",
 769 |        "3                0.72                   223                      0   \n",
 770 |        "4                0.37                   159                      0   \n",
 771 |        "\n",
 772 |        "   salary_high  salary_low  salary_medium  \n",
 773 |        "0            0           1              0  \n",
 774 |        "1            0           0              1  \n",
 775 |        "2            0           0              1  \n",
 776 |        "3            0           1              0  \n",
 777 |        "4            0           1              0  "
 778 |       ]
 779 |      },
 780 |      "execution_count": 81,
 781 |      "metadata": {},
 782 |      "output_type": "execute_result"
 783 |     }
 784 |    ],
 785 |    "source": [
 786 |     "df_with_dummies.drop('salary',axis='columns',inplace=True)\n",
 787 |     "df_with_dummies.head()"
 788 |    ]
 789 |   },
 790 |   {
 791 |    "cell_type": "code",
 792 |    "execution_count": 82,
 793 |    "metadata": {},
 794 |    "outputs": [
 795 |     {
 796 |      "data": {
 797 |       "text/html": [
 798 |        "<div>\n",
 799 |        "<style scoped>\n",
 800 |        "    .dataframe tbody tr th:only-of-type {\n",
 801 |        "        vertical-align: middle;\n",
 802 |        "    }\n",
 803 |        "\n",
 804 |        "    .dataframe tbody tr th {\n",
 805 |        "        vertical-align: top;\n",
 806 |        "    }\n",
 807 |        "\n",
 808 |        "    .dataframe thead th {\n",
 809 |        "        text-align: right;\n",
 810 |        "    }\n",
 811 |        "</style>\n",
 812 |        "<table border=\"1\" class=\"dataframe\">\n",
 813 |        "  <thead>\n",
 814 |        "    <tr style=\"text-align: right;\">\n",
 815 |        "      <th></th>\n",
 816 |        "      <th>satisfaction_level</th>\n",
 817 |        "      <th>average_montly_hours</th>\n",
 818 |        "      <th>promotion_last_5years</th>\n",
 819 |        "      <th>salary_high</th>\n",
 820 |        "      <th>salary_low</th>\n",
 821 |        "      <th>salary_medium</th>\n",
 822 |        "    </tr>\n",
 823 |        "  </thead>\n",
 824 |        "  <tbody>\n",
 825 |        "    <tr>\n",
 826 |        "      <th>0</th>\n",
 827 |        "      <td>0.38</td>\n",
 828 |        "      <td>157</td>\n",
 829 |        "      <td>0</td>\n",
 830 |        "      <td>0</td>\n",
 831 |        "      <td>1</td>\n",
 832 |        "      <td>0</td>\n",
 833 |        "    </tr>\n",
 834 |        "    <tr>\n",
 835 |        "      <th>1</th>\n",
 836 |        "      <td>0.80</td>\n",
 837 |        "      <td>262</td>\n",
 838 |        "      <td>0</td>\n",
 839 |        "      <td>0</td>\n",
 840 |        "      <td>0</td>\n",
 841 |        "      <td>1</td>\n",
 842 |        "    </tr>\n",
 843 |        "    <tr>\n",
 844 |        "      <th>2</th>\n",
 845 |        "      <td>0.11</td>\n",
 846 |        "      <td>272</td>\n",
 847 |        "      <td>0</td>\n",
 848 |        "      <td>0</td>\n",
 849 |        "      <td>0</td>\n",
 850 |        "      <td>1</td>\n",
 851 |        "    </tr>\n",
 852 |        "    <tr>\n",
 853 |        "      <th>3</th>\n",
 854 |        "      <td>0.72</td>\n",
 855 |        "      <td>223</td>\n",
 856 |        "      <td>0</td>\n",
 857 |        "      <td>0</td>\n",
 858 |        "      <td>1</td>\n",
 859 |        "      <td>0</td>\n",
 860 |        "    </tr>\n",
 861 |        "    <tr>\n",
 862 |        "      <th>4</th>\n",
 863 |        "      <td>0.37</td>\n",
 864 |        "      <td>159</td>\n",
 865 |        "      <td>0</td>\n",
 866 |        "      <td>0</td>\n",
 867 |        "      <td>1</td>\n",
 868 |        "      <td>0</td>\n",
 869 |        "    </tr>\n",
 870 |        "  </tbody>\n",
 871 |        "</table>\n",
 872 |        "</div>"
 873 |       ],
 874 |       "text/plain": [
 875 |        "   satisfaction_level  average_montly_hours  promotion_last_5years  \\\n",
 876 |        "0                0.38                   157                      0   \n",
 877 |        "1                0.80                   262                      0   \n",
 878 |        "2                0.11                   272                      0   \n",
 879 |        "3                0.72                   223                      0   \n",
 880 |        "4                0.37                   159                      0   \n",
 881 |        "\n",
 882 |        "   salary_high  salary_low  salary_medium  \n",
 883 |        "0            0           1              0  \n",
 884 |        "1            0           0              1  \n",
 885 |        "2            0           0              1  \n",
 886 |        "3            0           1              0  \n",
 887 |        "4            0           1              0  "
 888 |       ]
 889 |      },
 890 |      "execution_count": 82,
 891 |      "metadata": {},
 892 |      "output_type": "execute_result"
 893 |     }
 894 |    ],
 895 |    "source": [
 896 |     "X = df_with_dummies\n",
 897 |     "X.head()"
 898 |    ]
 899 |   },
 900 |   {
 901 |    "cell_type": "code",
 902 |    "execution_count": 83,
 903 |    "metadata": {},
 904 |    "outputs": [],
 905 |    "source": [
 906 |     "y = df.left"
 907 |    ]
 908 |   },
 909 |   {
 910 |    "cell_type": "code",
 911 |    "execution_count": 91,
 912 |    "metadata": {},
 913 |    "outputs": [],
 914 |    "source": [
 915 |     "from sklearn.model_selection import train_test_split\n",
 916 |     "X_train, X_test, y_train, y_test = train_test_split(X,y,train_size=0.3)"
 917 |    ]
 918 |   },
 919 |   {
 920 |    "cell_type": "code",
 921 |    "execution_count": 87,
 922 |    "metadata": {},
 923 |    "outputs": [],
 924 |    "source": [
 925 |     "from sklearn.linear_model import LogisticRegression\n",
 926 |     "model = LogisticRegression()"
 927 |    ]
 928 |   },
 929 |   {
 930 |    "cell_type": "code",
 931 |    "execution_count": 88,
 932 |    "metadata": {},
 933 |    "outputs": [
 934 |     {
 935 |      "data": {
 936 |       "text/plain": [
 937 |        "LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
 938 |        "          intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,\n",
 939 |        "          penalty='l2', random_state=None, solver='liblinear', tol=0.0001,\n",
 940 |        "          verbose=0, warm_start=False)"
 941 |       ]
 942 |      },
 943 |      "execution_count": 88,
 944 |      "metadata": {},
 945 |      "output_type": "execute_result"
 946 |     }
 947 |    ],
 948 |    "source": [
 949 |     "model.fit(X_train, y_train)"
 950 |    ]
 951 |   },
 952 |   {
 953 |    "cell_type": "code",
 954 |    "execution_count": 89,
 955 |    "metadata": {},
 956 |    "outputs": [
 957 |     {
 958 |      "data": {
 959 |       "text/plain": [
 960 |        "array([0, 0, 0, ..., 0, 0, 1], dtype=int64)"
 961 |       ]
 962 |      },
 963 |      "execution_count": 89,
 964 |      "metadata": {},
 965 |      "output_type": "execute_result"
 966 |     }
 967 |    ],
 968 |    "source": [
 969 |     "model.predict(X_test)"
 970 |    ]
 971 |   },
 972 |   {
 973 |    "cell_type": "markdown",
 974 |    "metadata": {},
 975 |    "source": [
 976 |     "**Accuracy of the model**"
 977 |    ]
 978 |   },
 979 |   {
 980 |    "cell_type": "code",
 981 |    "execution_count": 90,
 982 |    "metadata": {},
 983 |    "outputs": [
 984 |     {
 985 |      "data": {
 986 |       "text/plain": [
 987 |        "0.78428571428571425"
 988 |       ]
 989 |      },
 990 |      "execution_count": 90,
 991 |      "metadata": {},
 992 |      "output_type": "execute_result"
 993 |     }
 994 |    ],
 995 |    "source": [
 996 |     "model.score(X_test,y_test)"
 997 |    ]
 998 |   }
 999 |  ],
1000 |  "metadata": {
1001 |   "kernelspec": {
1002 |    "display_name": "Python 3",
1003 |    "language": "python",
1004 |    "name": "python3"
1005 |   },
1006 |   "language_info": {
1007 |    "codemirror_mode": {
1008 |     "name": "ipython",
1009 |     "version": 3
1010 |    },
1011 |    "file_extension": ".py",
1012 |    "mimetype": "text/x-python",
1013 |    "name": "python",
1014 |    "nbconvert_exporter": "python",
1015 |    "pygments_lexer": "ipython3",
1016 |    "version": "3.7.3"
1017 |   }
1018 |  },
1019 |  "nbformat": 4,
1020 |  "nbformat_minor": 2
1021 | }
1022 | 


--------------------------------------------------------------------------------
/LogisticRegression/Exercise/7_logistic_regression_exercise.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "markdown",
   5 |    "metadata": {},
   6 |    "source": [
   7 |     "Dataset is downloaded from Kaggle. Link: https://www.kaggle.com/giripujar/hr-analytics"
   8 |    ]
   9 |   },
  10 |   {
  11 |    "cell_type": "code",
  12 |    "execution_count": 13,
  13 |    "metadata": {
  14 |     "collapsed": true,
  15 |     "jupyter": {
  16 |      "outputs_hidden": true
  17 |     }
  18 |    },
  19 |    "outputs": [],
  20 |    "source": [
  21 |     "import pandas as pd\n",
  22 |     "from matplotlib import pyplot as plt\n",
  23 |     "%matplotlib inline"
  24 |    ]
  25 |   },
  26 |   {
  27 |    "cell_type": "code",
  28 |    "execution_count": 3,
  29 |    "metadata": {},
  30 |    "outputs": [
  31 |     {
  32 |      "data": {
  33 |       "text/html": [
  34 |        "<div>\n",
  35 |        "<style scoped>\n",
  36 |        "    .dataframe tbody tr th:only-of-type {\n",
  37 |        "        vertical-align: middle;\n",
  38 |        "    }\n",
  39 |        "\n",
  40 |        "    .dataframe tbody tr th {\n",
  41 |        "        vertical-align: top;\n",
  42 |        "    }\n",
  43 |        "\n",
  44 |        "    .dataframe thead th {\n",
  45 |        "        text-align: right;\n",
  46 |        "    }\n",
  47 |        "</style>\n",
  48 |        "<table border=\"1\" class=\"dataframe\">\n",
  49 |        "  <thead>\n",
  50 |        "    <tr style=\"text-align: right;\">\n",
  51 |        "      <th></th>\n",
  52 |        "      <th>satisfaction_level</th>\n",
  53 |        "      <th>last_evaluation</th>\n",
  54 |        "      <th>number_project</th>\n",
  55 |        "      <th>average_montly_hours</th>\n",
  56 |        "      <th>time_spend_company</th>\n",
  57 |        "      <th>Work_accident</th>\n",
  58 |        "      <th>left</th>\n",
  59 |        "      <th>promotion_last_5years</th>\n",
  60 |        "      <th>Department</th>\n",
  61 |        "      <th>salary</th>\n",
  62 |        "    </tr>\n",
  63 |        "  </thead>\n",
  64 |        "  <tbody>\n",
  65 |        "    <tr>\n",
  66 |        "      <th>0</th>\n",
  67 |        "      <td>0.38</td>\n",
  68 |        "      <td>0.53</td>\n",
  69 |        "      <td>2</td>\n",
  70 |        "      <td>157</td>\n",
  71 |        "      <td>3</td>\n",
  72 |        "      <td>0</td>\n",
  73 |        "      <td>1</td>\n",
  74 |        "      <td>0</td>\n",
  75 |        "      <td>sales</td>\n",
  76 |        "      <td>low</td>\n",
  77 |        "    </tr>\n",
  78 |        "    <tr>\n",
  79 |        "      <th>1</th>\n",
  80 |        "      <td>0.80</td>\n",
  81 |        "      <td>0.86</td>\n",
  82 |        "      <td>5</td>\n",
  83 |        "      <td>262</td>\n",
  84 |        "      <td>6</td>\n",
  85 |        "      <td>0</td>\n",
  86 |        "      <td>1</td>\n",
  87 |        "      <td>0</td>\n",
  88 |        "      <td>sales</td>\n",
  89 |        "      <td>medium</td>\n",
  90 |        "    </tr>\n",
  91 |        "    <tr>\n",
  92 |        "      <th>2</th>\n",
  93 |        "      <td>0.11</td>\n",
  94 |        "      <td>0.88</td>\n",
  95 |        "      <td>7</td>\n",
  96 |        "      <td>272</td>\n",
  97 |        "      <td>4</td>\n",
  98 |        "      <td>0</td>\n",
  99 |        "      <td>1</td>\n",
 100 |        "      <td>0</td>\n",
 101 |        "      <td>sales</td>\n",
 102 |        "      <td>medium</td>\n",
 103 |        "    </tr>\n",
 104 |        "    <tr>\n",
 105 |        "      <th>3</th>\n",
 106 |        "      <td>0.72</td>\n",
 107 |        "      <td>0.87</td>\n",
 108 |        "      <td>5</td>\n",
 109 |        "      <td>223</td>\n",
 110 |        "      <td>5</td>\n",
 111 |        "      <td>0</td>\n",
 112 |        "      <td>1</td>\n",
 113 |        "      <td>0</td>\n",
 114 |        "      <td>sales</td>\n",
 115 |        "      <td>low</td>\n",
 116 |        "    </tr>\n",
 117 |        "    <tr>\n",
 118 |        "      <th>4</th>\n",
 119 |        "      <td>0.37</td>\n",
 120 |        "      <td>0.52</td>\n",
 121 |        "      <td>2</td>\n",
 122 |        "      <td>159</td>\n",
 123 |        "      <td>3</td>\n",
 124 |        "      <td>0</td>\n",
 125 |        "      <td>1</td>\n",
 126 |        "      <td>0</td>\n",
 127 |        "      <td>sales</td>\n",
 128 |        "      <td>low</td>\n",
 129 |        "    </tr>\n",
 130 |        "  </tbody>\n",
 131 |        "</table>\n",
 132 |        "</div>"
 133 |       ],
 134 |       "text/plain": [
 135 |        "   satisfaction_level  last_evaluation  number_project  average_montly_hours  \\\n",
 136 |        "0                0.38             0.53               2                   157   \n",
 137 |        "1                0.80             0.86               5                   262   \n",
 138 |        "2                0.11             0.88               7                   272   \n",
 139 |        "3                0.72             0.87               5                   223   \n",
 140 |        "4                0.37             0.52               2                   159   \n",
 141 |        "\n",
 142 |        "   time_spend_company  Work_accident  left  promotion_last_5years Department  \\\n",
 143 |        "0                   3              0     1                      0      sales   \n",
 144 |        "1                   6              0     1                      0      sales   \n",
 145 |        "2                   4              0     1                      0      sales   \n",
 146 |        "3                   5              0     1                      0      sales   \n",
 147 |        "4                   3              0     1                      0      sales   \n",
 148 |        "\n",
 149 |        "   salary  \n",
 150 |        "0     low  \n",
 151 |        "1  medium  \n",
 152 |        "2  medium  \n",
 153 |        "3     low  \n",
 154 |        "4     low  "
 155 |       ]
 156 |      },
 157 |      "execution_count": 3,
 158 |      "metadata": {},
 159 |      "output_type": "execute_result"
 160 |     }
 161 |    ],
 162 |    "source": [
 163 |     "df = pd.read_csv(\"HR_comma_sep.csv\")\n",
 164 |     "df.head()"
 165 |    ]
 166 |   },
 167 |   {
 168 |    "cell_type": "markdown",
 169 |    "metadata": {},
 170 |    "source": [
 171 |     "<h2 style=\"color:purple\">Data exploration and visualization</h2>"
 172 |    ]
 173 |   },
 174 |   {
 175 |    "cell_type": "code",
 176 |    "execution_count": 73,
 177 |    "metadata": {},
 178 |    "outputs": [
 179 |     {
 180 |      "data": {
 181 |       "text/plain": [
 182 |        "(3571, 10)"
 183 |       ]
 184 |      },
 185 |      "execution_count": 73,
 186 |      "metadata": {},
 187 |      "output_type": "execute_result"
 188 |     }
 189 |    ],
 190 |    "source": [
 191 |     "left = df[df.left==1]\n",
 192 |     "left.shape"
 193 |    ]
 194 |   },
 195 |   {
 196 |    "cell_type": "code",
 197 |    "execution_count": 74,
 198 |    "metadata": {},
 199 |    "outputs": [
 200 |     {
 201 |      "data": {
 202 |       "text/plain": [
 203 |        "(11428, 10)"
 204 |       ]
 205 |      },
 206 |      "execution_count": 74,
 207 |      "metadata": {},
 208 |      "output_type": "execute_result"
 209 |     }
 210 |    ],
 211 |    "source": [
 212 |     "retained = df[df.left==0]\n",
 213 |     "retained.shape"
 214 |    ]
 215 |   },
 216 |   {
 217 |    "cell_type": "markdown",
 218 |    "metadata": {},
 219 |    "source": [
 220 |     "**Average numbers for all columns** "
 221 |    ]
 222 |   },
 223 |   {
 224 |    "cell_type": "code",
 225 |    "execution_count": 31,
 226 |    "metadata": {},
 227 |    "outputs": [
 228 |     {
 229 |      "data": {
 230 |       "text/html": [
 231 |        "<div>\n",
 232 |        "<style scoped>\n",
 233 |        "    .dataframe tbody tr th:only-of-type {\n",
 234 |        "        vertical-align: middle;\n",
 235 |        "    }\n",
 236 |        "\n",
 237 |        "    .dataframe tbody tr th {\n",
 238 |        "        vertical-align: top;\n",
 239 |        "    }\n",
 240 |        "\n",
 241 |        "    .dataframe thead th {\n",
 242 |        "        text-align: right;\n",
 243 |        "    }\n",
 244 |        "</style>\n",
 245 |        "<table border=\"1\" class=\"dataframe\">\n",
 246 |        "  <thead>\n",
 247 |        "    <tr style=\"text-align: right;\">\n",
 248 |        "      <th></th>\n",
 249 |        "      <th>satisfaction_level</th>\n",
 250 |        "      <th>last_evaluation</th>\n",
 251 |        "      <th>number_project</th>\n",
 252 |        "      <th>average_montly_hours</th>\n",
 253 |        "      <th>time_spend_company</th>\n",
 254 |        "      <th>Work_accident</th>\n",
 255 |        "      <th>promotion_last_5years</th>\n",
 256 |        "    </tr>\n",
 257 |        "    <tr>\n",
 258 |        "      <th>left</th>\n",
 259 |        "      <th></th>\n",
 260 |        "      <th></th>\n",
 261 |        "      <th></th>\n",
 262 |        "      <th></th>\n",
 263 |        "      <th></th>\n",
 264 |        "      <th></th>\n",
 265 |        "      <th></th>\n",
 266 |        "    </tr>\n",
 267 |        "  </thead>\n",
 268 |        "  <tbody>\n",
 269 |        "    <tr>\n",
 270 |        "      <th>0</th>\n",
 271 |        "      <td>0.666810</td>\n",
 272 |        "      <td>0.715473</td>\n",
 273 |        "      <td>3.786664</td>\n",
 274 |        "      <td>199.060203</td>\n",
 275 |        "      <td>3.380032</td>\n",
 276 |        "      <td>0.175009</td>\n",
 277 |        "      <td>0.026251</td>\n",
 278 |        "    </tr>\n",
 279 |        "    <tr>\n",
 280 |        "      <th>1</th>\n",
 281 |        "      <td>0.440098</td>\n",
 282 |        "      <td>0.718113</td>\n",
 283 |        "      <td>3.855503</td>\n",
 284 |        "      <td>207.419210</td>\n",
 285 |        "      <td>3.876505</td>\n",
 286 |        "      <td>0.047326</td>\n",
 287 |        "      <td>0.005321</td>\n",
 288 |        "    </tr>\n",
 289 |        "  </tbody>\n",
 290 |        "</table>\n",
 291 |        "</div>"
 292 |       ],
 293 |       "text/plain": [
 294 |        "      satisfaction_level  last_evaluation  number_project  \\\n",
 295 |        "left                                                        \n",
 296 |        "0               0.666810         0.715473        3.786664   \n",
 297 |        "1               0.440098         0.718113        3.855503   \n",
 298 |        "\n",
 299 |        "      average_montly_hours  time_spend_company  Work_accident  \\\n",
 300 |        "left                                                            \n",
 301 |        "0               199.060203            3.380032       0.175009   \n",
 302 |        "1               207.419210            3.876505       0.047326   \n",
 303 |        "\n",
 304 |        "      promotion_last_5years  \n",
 305 |        "left                         \n",
 306 |        "0                  0.026251  \n",
 307 |        "1                  0.005321  "
 308 |       ]
 309 |      },
 310 |      "execution_count": 31,
 311 |      "metadata": {},
 312 |      "output_type": "execute_result"
 313 |     }
 314 |    ],
 315 |    "source": [
 316 |     "df.groupby('left').mean()"
 317 |    ]
 318 |   },
 319 |   {
 320 |    "cell_type": "markdown",
 321 |    "metadata": {},
 322 |    "source": [
 323 |     "From above table we can draw following conclusions,\n",
 324 |     "<ol>\n",
 325 |     "    <li>**Satisfaction Level**: Satisfaction level seems to be relatively low (0.44) in employees leaving the firm vs the retained ones (0.66)</li>\n",
 326 |     "    <li>**Average Monthly Hours**: Average monthly hours are higher in employees leaving the firm (199 vs 207)</li>\n",
 327 |     "    <li>**Promotion Last 5 Years**: Employees who are given promotion are likely to be retained at firm </li>\n",
 328 |     "</ol>"
 329 |    ]
 330 |   },
 331 |   {
 332 |    "cell_type": "markdown",
 333 |    "metadata": {},
 334 |    "source": [
 335 |     "**Impact of salary on employee retention**"
 336 |    ]
 337 |   },
 338 |   {
 339 |    "cell_type": "code",
 340 |    "execution_count": 37,
 341 |    "metadata": {
 342 |     "scrolled": true
 343 |    },
 344 |    "outputs": [
 345 |     {
 346 |      "data": {
 347 |       "text/plain": [
 348 |        "<matplotlib.axes._subplots.AxesSubplot at 0x1442bf3eda0>"
 349 |       ]
 350 |      },
 351 |      "execution_count": 37,
 352 |      "metadata": {},
 353 |      "output_type": "execute_result"
 354 |     },
 355 |     {
 356 |      "data": {
 357 |       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYEAAAEpCAYAAAB1Fp6nAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nSUVORK5CYII=\n",
 358 |       "text/plain": [
 359 |        "<matplotlib.figure.Figure at 0x14429998240>"
 360 |       ]
 361 |      },
 362 |      "metadata": {},
 363 |      "output_type": "display_data"
 364 |     }
 365 |    ],
 366 |    "source": [
 367 |     "pd.crosstab(df.salary,df.left).plot(kind='bar')"
 368 |    ]
 369 |   },
 370 |   {
 371 |    "cell_type": "markdown",
 372 |    "metadata": {},
 373 |    "source": [
 374 |     "Above bar chart shows employees with high salaries are likely to not leave the company"
 375 |    ]
 376 |   },
 377 |   {
 378 |    "cell_type": "markdown",
 379 |    "metadata": {},
 380 |    "source": [
 381 |     "**Department wise employee retention rate**"
 382 |    ]
 383 |   },
 384 |   {
 385 |    "cell_type": "code",
 386 |    "execution_count": 38,
 387 |    "metadata": {
 388 |     "scrolled": true
 389 |    },
 390 |    "outputs": [
 391 |     {
 392 |      "data": {
 393 |       "text/plain": [
 394 |        "<matplotlib.axes._subplots.AxesSubplot at 0x1442bf75128>"
 395 |       ]
 396 |      },
 397 |      "execution_count": 38,
 398 |      "metadata": {},
 399 |      "output_type": "execute_result"
 400 |     },
 401 |     {
 402 |      "data": {
 403 |       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYEAAAFDCAYAAADcebKbAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ngg==\n",
 404 |       "text/plain": [
 405 |        "<matplotlib.figure.Figure at 0x1442bf7cba8>"
 406 |       ]
 407 |      },
 408 |      "metadata": {},
 409 |      "output_type": "display_data"
 410 |     }
 411 |    ],
 412 |    "source": [
 413 |     "pd.crosstab(df.Department,df.left).plot(kind='bar')"
 414 |    ]
 415 |   },
 416 |   {
 417 |    "cell_type": "markdown",
 418 |    "metadata": {},
 419 |    "source": [
 420 |     "From above chart there seem to be some impact of department on employee retention but it is not major hence we will ignore department in our analysis"
 421 |    ]
 422 |   },
 423 |   {
 424 |    "cell_type": "markdown",
 425 |    "metadata": {},
 426 |    "source": [
 427 |     "<h3 style=\"color:purple\">From the data analysis so far we can conclude that we will use following variables as independant variables in our model</h3>\n",
 428 |     "<ol>\n",
 429 |     "    <li>**Satisfaction Level**</li>\n",
 430 |     "    <li>**Average Monthly Hours**</li>\n",
 431 |     "    <li>**Promotion Last 5 Years**</li>\n",
 432 |     "    <li>**Salary**</li>\n",
 433 |     "</ol>"
 434 |    ]
 435 |   },
 436 |   {
 437 |    "cell_type": "code",
 438 |    "execution_count": 76,
 439 |    "metadata": {},
 440 |    "outputs": [
 441 |     {
 442 |      "data": {
 443 |       "text/html": [
 444 |        "<div>\n",
 445 |        "<style scoped>\n",
 446 |        "    .dataframe tbody tr th:only-of-type {\n",
 447 |        "        vertical-align: middle;\n",
 448 |        "    }\n",
 449 |        "\n",
 450 |        "    .dataframe tbody tr th {\n",
 451 |        "        vertical-align: top;\n",
 452 |        "    }\n",
 453 |        "\n",
 454 |        "    .dataframe thead th {\n",
 455 |        "        text-align: right;\n",
 456 |        "    }\n",
 457 |        "</style>\n",
 458 |        "<table border=\"1\" class=\"dataframe\">\n",
 459 |        "  <thead>\n",
 460 |        "    <tr style=\"text-align: right;\">\n",
 461 |        "      <th></th>\n",
 462 |        "      <th>satisfaction_level</th>\n",
 463 |        "      <th>average_montly_hours</th>\n",
 464 |        "      <th>promotion_last_5years</th>\n",
 465 |        "      <th>salary</th>\n",
 466 |        "    </tr>\n",
 467 |        "  </thead>\n",
 468 |        "  <tbody>\n",
 469 |        "    <tr>\n",
 470 |        "      <th>0</th>\n",
 471 |        "      <td>0.38</td>\n",
 472 |        "      <td>157</td>\n",
 473 |        "      <td>0</td>\n",
 474 |        "      <td>low</td>\n",
 475 |        "    </tr>\n",
 476 |        "    <tr>\n",
 477 |        "      <th>1</th>\n",
 478 |        "      <td>0.80</td>\n",
 479 |        "      <td>262</td>\n",
 480 |        "      <td>0</td>\n",
 481 |        "      <td>medium</td>\n",
 482 |        "    </tr>\n",
 483 |        "    <tr>\n",
 484 |        "      <th>2</th>\n",
 485 |        "      <td>0.11</td>\n",
 486 |        "      <td>272</td>\n",
 487 |        "      <td>0</td>\n",
 488 |        "      <td>medium</td>\n",
 489 |        "    </tr>\n",
 490 |        "    <tr>\n",
 491 |        "      <th>3</th>\n",
 492 |        "      <td>0.72</td>\n",
 493 |        "      <td>223</td>\n",
 494 |        "      <td>0</td>\n",
 495 |        "      <td>low</td>\n",
 496 |        "    </tr>\n",
 497 |        "    <tr>\n",
 498 |        "      <th>4</th>\n",
 499 |        "      <td>0.37</td>\n",
 500 |        "      <td>159</td>\n",
 501 |        "      <td>0</td>\n",
 502 |        "      <td>low</td>\n",
 503 |        "    </tr>\n",
 504 |        "  </tbody>\n",
 505 |        "</table>\n",
 506 |        "</div>"
 507 |       ],
 508 |       "text/plain": [
 509 |        "   satisfaction_level  average_montly_hours  promotion_last_5years  salary\n",
 510 |        "0                0.38                   157                      0     low\n",
 511 |        "1                0.80                   262                      0  medium\n",
 512 |        "2                0.11                   272                      0  medium\n",
 513 |        "3                0.72                   223                      0     low\n",
 514 |        "4                0.37                   159                      0     low"
 515 |       ]
 516 |      },
 517 |      "execution_count": 76,
 518 |      "metadata": {},
 519 |      "output_type": "execute_result"
 520 |     }
 521 |    ],
 522 |    "source": [
 523 |     "subdf = df[['satisfaction_level','average_montly_hours','promotion_last_5years','salary']]\n",
 524 |     "subdf.head()"
 525 |    ]
 526 |   },
 527 |   {
 528 |    "cell_type": "markdown",
 529 |    "metadata": {},
 530 |    "source": [
 531 |     "**Tackle salary dummy variable**"
 532 |    ]
 533 |   },
 534 |   {
 535 |    "cell_type": "markdown",
 536 |    "metadata": {},
 537 |    "source": [
 538 |     "Salary has all text data. It needs to be converted to numbers and we will use dummy variable for that. Check my one hot encoding tutorial to understand purpose behind dummy variables."
 539 |    ]
 540 |   },
 541 |   {
 542 |    "cell_type": "code",
 543 |    "execution_count": 78,
 544 |    "metadata": {},
 545 |    "outputs": [],
 546 |    "source": [
 547 |     "salary_dummies = pd.get_dummies(subdf.salary, prefix=\"salary\")"
 548 |    ]
 549 |   },
 550 |   {
 551 |    "cell_type": "code",
 552 |    "execution_count": 79,
 553 |    "metadata": {},
 554 |    "outputs": [],
 555 |    "source": [
 556 |     "df_with_dummies = pd.concat([subdf,salary_dummies],axis='columns')"
 557 |    ]
 558 |   },
 559 |   {
 560 |    "cell_type": "code",
 561 |    "execution_count": 80,
 562 |    "metadata": {},
 563 |    "outputs": [
 564 |     {
 565 |      "data": {
 566 |       "text/html": [
 567 |        "<div>\n",
 568 |        "<style scoped>\n",
 569 |        "    .dataframe tbody tr th:only-of-type {\n",
 570 |        "        vertical-align: middle;\n",
 571 |        "    }\n",
 572 |        "\n",
 573 |        "    .dataframe tbody tr th {\n",
 574 |        "        vertical-align: top;\n",
 575 |        "    }\n",
 576 |        "\n",
 577 |        "    .dataframe thead th {\n",
 578 |        "        text-align: right;\n",
 579 |        "    }\n",
 580 |        "</style>\n",
 581 |        "<table border=\"1\" class=\"dataframe\">\n",
 582 |        "  <thead>\n",
 583 |        "    <tr style=\"text-align: right;\">\n",
 584 |        "      <th></th>\n",
 585 |        "      <th>satisfaction_level</th>\n",
 586 |        "      <th>average_montly_hours</th>\n",
 587 |        "      <th>promotion_last_5years</th>\n",
 588 |        "      <th>salary</th>\n",
 589 |        "      <th>salary_high</th>\n",
 590 |        "      <th>salary_low</th>\n",
 591 |        "      <th>salary_medium</th>\n",
 592 |        "    </tr>\n",
 593 |        "  </thead>\n",
 594 |        "  <tbody>\n",
 595 |        "    <tr>\n",
 596 |        "      <th>0</th>\n",
 597 |        "      <td>0.38</td>\n",
 598 |        "      <td>157</td>\n",
 599 |        "      <td>0</td>\n",
 600 |        "      <td>low</td>\n",
 601 |        "      <td>0</td>\n",
 602 |        "      <td>1</td>\n",
 603 |        "      <td>0</td>\n",
 604 |        "    </tr>\n",
 605 |        "    <tr>\n",
 606 |        "      <th>1</th>\n",
 607 |        "      <td>0.80</td>\n",
 608 |        "      <td>262</td>\n",
 609 |        "      <td>0</td>\n",
 610 |        "      <td>medium</td>\n",
 611 |        "      <td>0</td>\n",
 612 |        "      <td>0</td>\n",
 613 |        "      <td>1</td>\n",
 614 |        "    </tr>\n",
 615 |        "    <tr>\n",
 616 |        "      <th>2</th>\n",
 617 |        "      <td>0.11</td>\n",
 618 |        "      <td>272</td>\n",
 619 |        "      <td>0</td>\n",
 620 |        "      <td>medium</td>\n",
 621 |        "      <td>0</td>\n",
 622 |        "      <td>0</td>\n",
 623 |        "      <td>1</td>\n",
 624 |        "    </tr>\n",
 625 |        "    <tr>\n",
 626 |        "      <th>3</th>\n",
 627 |        "      <td>0.72</td>\n",
 628 |        "      <td>223</td>\n",
 629 |        "      <td>0</td>\n",
 630 |        "      <td>low</td>\n",
 631 |        "      <td>0</td>\n",
 632 |        "      <td>1</td>\n",
 633 |        "      <td>0</td>\n",
 634 |        "    </tr>\n",
 635 |        "    <tr>\n",
 636 |        "      <th>4</th>\n",
 637 |        "      <td>0.37</td>\n",
 638 |        "      <td>159</td>\n",
 639 |        "      <td>0</td>\n",
 640 |        "      <td>low</td>\n",
 641 |        "      <td>0</td>\n",
 642 |        "      <td>1</td>\n",
 643 |        "      <td>0</td>\n",
 644 |        "    </tr>\n",
 645 |        "  </tbody>\n",
 646 |        "</table>\n",
 647 |        "</div>"
 648 |       ],
 649 |       "text/plain": [
 650 |        "   satisfaction_level  average_montly_hours  promotion_last_5years  salary  \\\n",
 651 |        "0                0.38                   157                      0     low   \n",
 652 |        "1                0.80                   262                      0  medium   \n",
 653 |        "2                0.11                   272                      0  medium   \n",
 654 |        "3                0.72                   223                      0     low   \n",
 655 |        "4                0.37                   159                      0     low   \n",
 656 |        "\n",
 657 |        "   salary_high  salary_low  salary_medium  \n",
 658 |        "0            0           1              0  \n",
 659 |        "1            0           0              1  \n",
 660 |        "2            0           0              1  \n",
 661 |        "3            0           1              0  \n",
 662 |        "4            0           1              0  "
 663 |       ]
 664 |      },
 665 |      "execution_count": 80,
 666 |      "metadata": {},
 667 |      "output_type": "execute_result"
 668 |     }
 669 |    ],
 670 |    "source": [
 671 |     "df_with_dummies.head()"
 672 |    ]
 673 |   },
 674 |   {
 675 |    "cell_type": "markdown",
 676 |    "metadata": {},
 677 |    "source": [
 678 |     "Now we need to remove salary column which is text data. It is already replaced by dummy variables so we can safely remove it"
 679 |    ]
 680 |   },
 681 |   {
 682 |    "cell_type": "code",
 683 |    "execution_count": 81,
 684 |    "metadata": {},
 685 |    "outputs": [
 686 |     {
 687 |      "data": {
 688 |       "text/html": [
 689 |        "<div>\n",
 690 |        "<style scoped>\n",
 691 |        "    .dataframe tbody tr th:only-of-type {\n",
 692 |        "        vertical-align: middle;\n",
 693 |        "    }\n",
 694 |        "\n",
 695 |        "    .dataframe tbody tr th {\n",
 696 |        "        vertical-align: top;\n",
 697 |        "    }\n",
 698 |        "\n",
 699 |        "    .dataframe thead th {\n",
 700 |        "        text-align: right;\n",
 701 |        "    }\n",
 702 |        "</style>\n",
 703 |        "<table border=\"1\" class=\"dataframe\">\n",
 704 |        "  <thead>\n",
 705 |        "    <tr style=\"text-align: right;\">\n",
 706 |        "      <th></th>\n",
 707 |        "      <th>satisfaction_level</th>\n",
 708 |        "      <th>average_montly_hours</th>\n",
 709 |        "      <th>promotion_last_5years</th>\n",
 710 |        "      <th>salary_high</th>\n",
 711 |        "      <th>salary_low</th>\n",
 712 |        "      <th>salary_medium</th>\n",
 713 |        "    </tr>\n",
 714 |        "  </thead>\n",
 715 |        "  <tbody>\n",
 716 |        "    <tr>\n",
 717 |        "      <th>0</th>\n",
 718 |        "      <td>0.38</td>\n",
 719 |        "      <td>157</td>\n",
 720 |        "      <td>0</td>\n",
 721 |        "      <td>0</td>\n",
 722 |        "      <td>1</td>\n",
 723 |        "      <td>0</td>\n",
 724 |        "    </tr>\n",
 725 |        "    <tr>\n",
 726 |        "      <th>1</th>\n",
 727 |        "      <td>0.80</td>\n",
 728 |        "      <td>262</td>\n",
 729 |        "      <td>0</td>\n",
 730 |        "      <td>0</td>\n",
 731 |        "      <td>0</td>\n",
 732 |        "      <td>1</td>\n",
 733 |        "    </tr>\n",
 734 |        "    <tr>\n",
 735 |        "      <th>2</th>\n",
 736 |        "      <td>0.11</td>\n",
 737 |        "      <td>272</td>\n",
 738 |        "      <td>0</td>\n",
 739 |        "      <td>0</td>\n",
 740 |        "      <td>0</td>\n",
 741 |        "      <td>1</td>\n",
 742 |        "    </tr>\n",
 743 |        "    <tr>\n",
 744 |        "      <th>3</th>\n",
 745 |        "      <td>0.72</td>\n",
 746 |        "      <td>223</td>\n",
 747 |        "      <td>0</td>\n",
 748 |        "      <td>0</td>\n",
 749 |        "      <td>1</td>\n",
 750 |        "      <td>0</td>\n",
 751 |        "    </tr>\n",
 752 |        "    <tr>\n",
 753 |        "      <th>4</th>\n",
 754 |        "      <td>0.37</td>\n",
 755 |        "      <td>159</td>\n",
 756 |        "      <td>0</td>\n",
 757 |        "      <td>0</td>\n",
 758 |        "      <td>1</td>\n",
 759 |        "      <td>0</td>\n",
 760 |        "    </tr>\n",
 761 |        "  </tbody>\n",
 762 |        "</table>\n",
 763 |        "</div>"
 764 |       ],
 765 |       "text/plain": [
 766 |        "   satisfaction_level  average_montly_hours  promotion_last_5years  \\\n",
 767 |        "0                0.38                   157                      0   \n",
 768 |        "1                0.80                   262                      0   \n",
 769 |        "2                0.11                   272                      0   \n",
 770 |        "3                0.72                   223                      0   \n",
 771 |        "4                0.37                   159                      0   \n",
 772 |        "\n",
 773 |        "   salary_high  salary_low  salary_medium  \n",
 774 |        "0            0           1              0  \n",
 775 |        "1            0           0              1  \n",
 776 |        "2            0           0              1  \n",
 777 |        "3            0           1              0  \n",
 778 |        "4            0           1              0  "
 779 |       ]
 780 |      },
 781 |      "execution_count": 81,
 782 |      "metadata": {},
 783 |      "output_type": "execute_result"
 784 |     }
 785 |    ],
 786 |    "source": [
 787 |     "df_with_dummies.drop('salary',axis='columns',inplace=True)\n",
 788 |     "df_with_dummies.head()"
 789 |    ]
 790 |   },
 791 |   {
 792 |    "cell_type": "code",
 793 |    "execution_count": 82,
 794 |    "metadata": {},
 795 |    "outputs": [
 796 |     {
 797 |      "data": {
 798 |       "text/html": [
 799 |        "<div>\n",
 800 |        "<style scoped>\n",
 801 |        "    .dataframe tbody tr th:only-of-type {\n",
 802 |        "        vertical-align: middle;\n",
 803 |        "    }\n",
 804 |        "\n",
 805 |        "    .dataframe tbody tr th {\n",
 806 |        "        vertical-align: top;\n",
 807 |        "    }\n",
 808 |        "\n",
 809 |        "    .dataframe thead th {\n",
 810 |        "        text-align: right;\n",
 811 |        "    }\n",
 812 |        "</style>\n",
 813 |        "<table border=\"1\" class=\"dataframe\">\n",
 814 |        "  <thead>\n",
 815 |        "    <tr style=\"text-align: right;\">\n",
 816 |        "      <th></th>\n",
 817 |        "      <th>satisfaction_level</th>\n",
 818 |        "      <th>average_montly_hours</th>\n",
 819 |        "      <th>promotion_last_5years</th>\n",
 820 |        "      <th>salary_high</th>\n",
 821 |        "      <th>salary_low</th>\n",
 822 |        "      <th>salary_medium</th>\n",
 823 |        "    </tr>\n",
 824 |        "  </thead>\n",
 825 |        "  <tbody>\n",
 826 |        "    <tr>\n",
 827 |        "      <th>0</th>\n",
 828 |        "      <td>0.38</td>\n",
 829 |        "      <td>157</td>\n",
 830 |        "      <td>0</td>\n",
 831 |        "      <td>0</td>\n",
 832 |        "      <td>1</td>\n",
 833 |        "      <td>0</td>\n",
 834 |        "    </tr>\n",
 835 |        "    <tr>\n",
 836 |        "      <th>1</th>\n",
 837 |        "      <td>0.80</td>\n",
 838 |        "      <td>262</td>\n",
 839 |        "      <td>0</td>\n",
 840 |        "      <td>0</td>\n",
 841 |        "      <td>0</td>\n",
 842 |        "      <td>1</td>\n",
 843 |        "    </tr>\n",
 844 |        "    <tr>\n",
 845 |        "      <th>2</th>\n",
 846 |        "      <td>0.11</td>\n",
 847 |        "      <td>272</td>\n",
 848 |        "      <td>0</td>\n",
 849 |        "      <td>0</td>\n",
 850 |        "      <td>0</td>\n",
 851 |        "      <td>1</td>\n",
 852 |        "    </tr>\n",
 853 |        "    <tr>\n",
 854 |        "      <th>3</th>\n",
 855 |        "      <td>0.72</td>\n",
 856 |        "      <td>223</td>\n",
 857 |        "      <td>0</td>\n",
 858 |        "      <td>0</td>\n",
 859 |        "      <td>1</td>\n",
 860 |        "      <td>0</td>\n",
 861 |        "    </tr>\n",
 862 |        "    <tr>\n",
 863 |        "      <th>4</th>\n",
 864 |        "      <td>0.37</td>\n",
 865 |        "      <td>159</td>\n",
 866 |        "      <td>0</td>\n",
 867 |        "      <td>0</td>\n",
 868 |        "      <td>1</td>\n",
 869 |        "      <td>0</td>\n",
 870 |        "    </tr>\n",
 871 |        "  </tbody>\n",
 872 |        "</table>\n",
 873 |        "</div>"
 874 |       ],
 875 |       "text/plain": [
 876 |        "   satisfaction_level  average_montly_hours  promotion_last_5years  \\\n",
 877 |        "0                0.38                   157                      0   \n",
 878 |        "1                0.80                   262                      0   \n",
 879 |        "2                0.11                   272                      0   \n",
 880 |        "3                0.72                   223                      0   \n",
 881 |        "4                0.37                   159                      0   \n",
 882 |        "\n",
 883 |        "   salary_high  salary_low  salary_medium  \n",
 884 |        "0            0           1              0  \n",
 885 |        "1            0           0              1  \n",
 886 |        "2            0           0              1  \n",
 887 |        "3            0           1              0  \n",
 888 |        "4            0           1              0  "
 889 |       ]
 890 |      },
 891 |      "execution_count": 82,
 892 |      "metadata": {},
 893 |      "output_type": "execute_result"
 894 |     }
 895 |    ],
 896 |    "source": [
 897 |     "X = df_with_dummies\n",
 898 |     "X.head()"
 899 |    ]
 900 |   },
 901 |   {
 902 |    "cell_type": "code",
 903 |    "execution_count": 83,
 904 |    "metadata": {},
 905 |    "outputs": [],
 906 |    "source": [
 907 |     "y = df.left"
 908 |    ]
 909 |   },
 910 |   {
 911 |    "cell_type": "code",
 912 |    "execution_count": 91,
 913 |    "metadata": {},
 914 |    "outputs": [],
 915 |    "source": [
 916 |     "from sklearn.model_selection import train_test_split\n",
 917 |     "X_train, X_test, y_train, y_test = train_test_split(X,y,train_size=0.3)"
 918 |    ]
 919 |   },
 920 |   {
 921 |    "cell_type": "code",
 922 |    "execution_count": 87,
 923 |    "metadata": {},
 924 |    "outputs": [],
 925 |    "source": [
 926 |     "from sklearn.linear_model import LogisticRegression\n",
 927 |     "model = LogisticRegression()"
 928 |    ]
 929 |   },
 930 |   {
 931 |    "cell_type": "code",
 932 |    "execution_count": 88,
 933 |    "metadata": {},
 934 |    "outputs": [
 935 |     {
 936 |      "data": {
 937 |       "text/plain": [
 938 |        "LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
 939 |        "          intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,\n",
 940 |        "          penalty='l2', random_state=None, solver='liblinear', tol=0.0001,\n",
 941 |        "          verbose=0, warm_start=False)"
 942 |       ]
 943 |      },
 944 |      "execution_count": 88,
 945 |      "metadata": {},
 946 |      "output_type": "execute_result"
 947 |     }
 948 |    ],
 949 |    "source": [
 950 |     "model.fit(X_train, y_train)"
 951 |    ]
 952 |   },
 953 |   {
 954 |    "cell_type": "code",
 955 |    "execution_count": 89,
 956 |    "metadata": {},
 957 |    "outputs": [
 958 |     {
 959 |      "data": {
 960 |       "text/plain": [
 961 |        "array([0, 0, 0, ..., 0, 0, 1], dtype=int64)"
 962 |       ]
 963 |      },
 964 |      "execution_count": 89,
 965 |      "metadata": {},
 966 |      "output_type": "execute_result"
 967 |     }
 968 |    ],
 969 |    "source": [
 970 |     "model.predict(X_test)"
 971 |    ]
 972 |   },
 973 |   {
 974 |    "cell_type": "markdown",
 975 |    "metadata": {},
 976 |    "source": [
 977 |     "**Accuracy of the model**"
 978 |    ]
 979 |   },
 980 |   {
 981 |    "cell_type": "code",
 982 |    "execution_count": 90,
 983 |    "metadata": {},
 984 |    "outputs": [
 985 |     {
 986 |      "data": {
 987 |       "text/plain": [
 988 |        "0.78428571428571425"
 989 |       ]
 990 |      },
 991 |      "execution_count": 90,
 992 |      "metadata": {},
 993 |      "output_type": "execute_result"
 994 |     }
 995 |    ],
 996 |    "source": [
 997 |     "model.score(X_test,y_test)"
 998 |    ]
 999 |   }
1000 |  ],
1001 |  "metadata": {
1002 |   "kernelspec": {
1003 |    "display_name": "Python 3 (ipykernel)",
1004 |    "language": "python",
1005 |    "name": "python3"
1006 |   },
1007 |   "language_info": {
1008 |    "codemirror_mode": {
1009 |     "name": "ipython",
1010 |     "version": 3
1011 |    },
1012 |    "file_extension": ".py",
1013 |    "mimetype": "text/x-python",
1014 |    "name": "python",
1015 |    "nbconvert_exporter": "python",
1016 |    "pygments_lexer": "ipython3",
1017 |    "version": "3.9.12"
1018 |   }
1019 |  },
1020 |  "nbformat": 4,
1021 |  "nbformat_minor": 4
1022 | }
1023 | 


--------------------------------------------------------------------------------
/LogisticRegression/LogisticeRegression.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "id": "4198d27c-1b64-41a0-a45f-46349884e9fa",
  6 |    "metadata": {},
  7 |    "source": [
  8 |     "<h2 style=\"color:Tomato;\"> Predicting if a person buy insurance or not</h2>"
  9 |    ]
 10 |   },
 11 |   {
 12 |    "cell_type": "code",
 13 |    "execution_count": 23,
 14 |    "id": "991790ec-201a-4ac6-811e-e03d6b1563d2",
 15 |    "metadata": {},
 16 |    "outputs": [],
 17 |    "source": [
 18 |     "# import all the libs\n",
 19 |     "import pandas as pd\n",
 20 |     "import numpy as np\n",
 21 |     "import seaborn as sns\n",
 22 |     "import matplotlib.pyplot as plt"
 23 |    ]
 24 |   },
 25 |   {
 26 |    "cell_type": "code",
 27 |    "execution_count": 24,
 28 |    "id": "efe9539f-e255-454c-9b64-bc8cc604512f",
 29 |    "metadata": {},
 30 |    "outputs": [],
 31 |    "source": [
 32 |     "insurance = pd.read_csv('insurance_data.csv')"
 33 |    ]
 34 |   },
 35 |   {
 36 |    "cell_type": "code",
 37 |    "execution_count": 25,
 38 |    "id": "55856df2-f456-423a-bc94-046aecfa63ce",
 39 |    "metadata": {},
 40 |    "outputs": [],
 41 |    "source": [
 42 |     "df = pd.DataFrame(insurance)"
 43 |    ]
 44 |   },
 45 |   {
 46 |    "cell_type": "code",
 47 |    "execution_count": 26,
 48 |    "id": "b87436f2-4891-45d2-920b-08905c4a157f",
 49 |    "metadata": {},
 50 |    "outputs": [
 51 |     {
 52 |      "data": {
 53 |       "text/html": [
 54 |        "<div>\n",
 55 |        "<style scoped>\n",
 56 |        "    .dataframe tbody tr th:only-of-type {\n",
 57 |        "        vertical-align: middle;\n",
 58 |        "    }\n",
 59 |        "\n",
 60 |        "    .dataframe tbody tr th {\n",
 61 |        "        vertical-align: top;\n",
 62 |        "    }\n",
 63 |        "\n",
 64 |        "    .dataframe thead th {\n",
 65 |        "        text-align: right;\n",
 66 |        "    }\n",
 67 |        "</style>\n",
 68 |        "<table border=\"1\" class=\"dataframe\">\n",
 69 |        "  <thead>\n",
 70 |        "    <tr style=\"text-align: right;\">\n",
 71 |        "      <th></th>\n",
 72 |        "      <th>age</th>\n",
 73 |        "      <th>bought_insurance</th>\n",
 74 |        "    </tr>\n",
 75 |        "  </thead>\n",
 76 |        "  <tbody>\n",
 77 |        "    <tr>\n",
 78 |        "      <th>0</th>\n",
 79 |        "      <td>22</td>\n",
 80 |        "      <td>0</td>\n",
 81 |        "    </tr>\n",
 82 |        "    <tr>\n",
 83 |        "      <th>1</th>\n",
 84 |        "      <td>25</td>\n",
 85 |        "      <td>0</td>\n",
 86 |        "    </tr>\n",
 87 |        "    <tr>\n",
 88 |        "      <th>2</th>\n",
 89 |        "      <td>47</td>\n",
 90 |        "      <td>1</td>\n",
 91 |        "    </tr>\n",
 92 |        "    <tr>\n",
 93 |        "      <th>3</th>\n",
 94 |        "      <td>52</td>\n",
 95 |        "      <td>0</td>\n",
 96 |        "    </tr>\n",
 97 |        "    <tr>\n",
 98 |        "      <th>4</th>\n",
 99 |        "      <td>46</td>\n",
100 |        "      <td>1</td>\n",
101 |        "    </tr>\n",
102 |        "  </tbody>\n",
103 |        "</table>\n",
104 |        "</div>"
105 |       ],
106 |       "text/plain": [
107 |        "   age  bought_insurance\n",
108 |        "0   22                 0\n",
109 |        "1   25                 0\n",
110 |        "2   47                 1\n",
111 |        "3   52                 0\n",
112 |        "4   46                 1"
113 |       ]
114 |      },
115 |      "execution_count": 26,
116 |      "metadata": {},
117 |      "output_type": "execute_result"
118 |     }
119 |    ],
120 |    "source": [
121 |     "df.shape\n",
122 |     "df.head()"
123 |    ]
124 |   },
125 |   {
126 |    "cell_type": "code",
127 |    "execution_count": 36,
128 |    "id": "a9f48eeb-e85c-4471-9962-a63170cb7e3e",
129 |    "metadata": {},
130 |    "outputs": [
131 |     {
132 |      "data": {
133 |       "text/plain": [
134 |        "[<matplotlib.lines.Line2D at 0x7fdda80ad2e0>]"
135 |       ]
136 |      },
137 |      "execution_count": 36,
138 |      "metadata": {},
139 |      "output_type": "execute_result"
140 |     },
141 |     {
142 |      "data": {
143 |       "image/png": "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\n",
144 |       "text/plain": [
145 |        "<Figure size 432x288 with 1 Axes>"
146 |       ]
147 |      },
148 |      "metadata": {
149 |       "needs_background": "light"
150 |      },
151 |      "output_type": "display_data"
152 |     }
153 |    ],
154 |    "source": [
155 |     "plt.scatter(df.age,df.bought_insurance,marker=\"+\",color='red')\n",
156 |     "from sklearn.linear_model import LinearRegression\n",
157 |     "\n",
158 |     "lreg=LinearRegression().fit(df[['age']],df.bought_insurance)\n",
159 |     "y_pred = lreg.predict(df[['age']])\n",
160 |     "plt.plot(df.age,y_pred)\n",
161 |     "\n",
162 |     "# The line show the linear regression \n",
163 |     "# if an outlier is there this will make problem"
164 |    ]
165 |   },
166 |   {
167 |    "cell_type": "code",
168 |    "execution_count": 37,
169 |    "id": "02f54e10-f091-4be3-bc09-6e94df563249",
170 |    "metadata": {},
171 |    "outputs": [
172 |     {
173 |      "data": {
174 |       "text/plain": [
175 |        "0.5364021643885126"
176 |       ]
177 |      },
178 |      "execution_count": 37,
179 |      "metadata": {},
180 |      "output_type": "execute_result"
181 |     }
182 |    ],
183 |    "source": [
184 |     "# score\n",
185 |     "lreg.score(df[['age']],df.bought_insurance)"
186 |    ]
187 |   },
188 |   {
189 |    "cell_type": "markdown",
190 |    "id": "12633885-e051-4c9f-9cfd-fe853732b6f3",
191 |    "metadata": {},
192 |    "source": [
193 |     "##  sklearn  logistice regression\n",
194 |     "\n",
195 |     "### Step 1: Split the dataset into train and test"
196 |    ]
197 |   },
198 |   {
199 |    "cell_type": "code",
200 |    "execution_count": 59,
201 |    "id": "d867c81d-c0f1-44fc-bf5d-41498613af89",
202 |    "metadata": {},
203 |    "outputs": [],
204 |    "source": [
205 |     "from sklearn.model_selection import train_test_split\n",
206 |     "X_train,X_test,y_train,y_test = train_test_split(df[['age']],df.bought_insurance,test_size=.2)"
207 |    ]
208 |   },
209 |   {
210 |    "cell_type": "markdown",
211 |    "id": "7f587acf-56eb-4e3e-8776-bfec932d98e1",
212 |    "metadata": {},
213 |    "source": [
214 |     "### Step 2: Model creation"
215 |    ]
216 |   },
217 |   {
218 |    "cell_type": "code",
219 |    "execution_count": 60,
220 |    "id": "8f282469-ebd1-47c2-add8-c5528a296cfb",
221 |    "metadata": {},
222 |    "outputs": [],
223 |    "source": [
224 |     "from sklearn.linear_model import LogisticRegression\n",
225 |     "model = LogisticRegression()"
226 |    ]
227 |   },
228 |   {
229 |    "cell_type": "code",
230 |    "execution_count": 61,
231 |    "id": "79c48062-710b-45c6-b298-95929cb5b5a6",
232 |    "metadata": {},
233 |    "outputs": [
234 |     {
235 |      "data": {
236 |       "text/plain": [
237 |        "LogisticRegression()"
238 |       ]
239 |      },
240 |      "execution_count": 61,
241 |      "metadata": {},
242 |      "output_type": "execute_result"
243 |     }
244 |    ],
245 |    "source": [
246 |     "# fit the model\n",
247 |     "model.fit(X_train,y_train)"
248 |    ]
249 |   },
250 |   {
251 |    "cell_type": "code",
252 |    "execution_count": 62,
253 |    "id": "ce799e97-6d9c-4343-bd28-61ee2672c101",
254 |    "metadata": {},
255 |    "outputs": [],
256 |    "source": [
257 |     "y_pred = model.predict(X_test)"
258 |    ]
259 |   },
260 |   {
261 |    "cell_type": "code",
262 |    "execution_count": 63,
263 |    "id": "2599d297-9383-4994-8118-9e7b253d3dcc",
264 |    "metadata": {},
265 |    "outputs": [
266 |     {
267 |      "data": {
268 |       "text/plain": [
269 |        "array([0, 1, 1, 1, 1, 1])"
270 |       ]
271 |      },
272 |      "execution_count": 63,
273 |      "metadata": {},
274 |      "output_type": "execute_result"
275 |     }
276 |    ],
277 |    "source": [
278 |     "y_pred"
279 |    ]
280 |   },
281 |   {
282 |    "cell_type": "code",
283 |    "execution_count": 90,
284 |    "id": "8dd3aa2b-459b-430a-9c62-0a55bf343993",
285 |    "metadata": {},
286 |    "outputs": [
287 |     {
288 |      "name": "stdout",
289 |      "output_type": "stream",
290 |      "text": [
291 |       "[[0.8925775  0.1074225 ]\n",
292 |       " [0.10266326 0.89733674]\n",
293 |       " [0.04501951 0.95498049]\n",
294 |       " [0.02937193 0.97062807]\n",
295 |       " [0.217319   0.782681  ]\n",
296 |       " [0.0684156  0.9315844 ]]\n"
297 |      ]
298 |     }
299 |    ],
300 |    "source": [
301 |     "pd.options.display.float_format = '{:.2f}'.format \n",
302 |     "np.set_printoptions(suppress=True)\n",
303 |     "print(model.predict_proba(X_test))\n",
304 |     "# the below shows the probability of 0 and then 1\n",
305 |     "\n"
306 |    ]
307 |   },
308 |   {
309 |    "cell_type": "code",
310 |    "execution_count": 78,
311 |    "id": "779bc740-e0f5-4768-b137-027c85fd9c60",
312 |    "metadata": {},
313 |    "outputs": [
314 |     {
315 |      "data": {
316 |       "text/plain": [
317 |        "array([0.8925775 , 0.10266326, 0.04501951, 0.02937193, 0.217319  ,\n",
318 |        "       0.0684156 ])"
319 |       ]
320 |      },
321 |      "execution_count": 78,
322 |      "metadata": {},
323 |      "output_type": "execute_result"
324 |     }
325 |    ],
326 |    "source": []
327 |   },
328 |   {
329 |    "cell_type": "markdown",
330 |    "id": "92bf3c64-795f-48a0-8269-68644690ad55",
331 |    "metadata": {},
332 |    "source": [
333 |     "#### coefficiten (m)"
334 |    ]
335 |   },
336 |   {
337 |    "cell_type": "code",
338 |    "execution_count": 65,
339 |    "id": "85aa88e3-54a1-40ec-8586-346ada059764",
340 |    "metadata": {},
341 |    "outputs": [
342 |     {
343 |      "data": {
344 |       "text/plain": [
345 |        "array([[0.14776968]])"
346 |       ]
347 |      },
348 |      "execution_count": 65,
349 |      "metadata": {},
350 |      "output_type": "execute_result"
351 |     }
352 |    ],
353 |    "source": [
354 |     "model.coef_"
355 |    ]
356 |   },
357 |   {
358 |    "cell_type": "markdown",
359 |    "id": "1d7284e5-f019-4179-bee0-92a8c4e5e800",
360 |    "metadata": {},
361 |    "source": [
362 |     "#### Intercept (b)"
363 |    ]
364 |   },
365 |   {
366 |    "cell_type": "code",
367 |    "execution_count": 66,
368 |    "id": "a94df50a-878a-4827-9416-25c64bd3231c",
369 |    "metadata": {},
370 |    "outputs": [
371 |     {
372 |      "data": {
373 |       "text/plain": [
374 |        "array([-5.51604619])"
375 |       ]
376 |      },
377 |      "execution_count": 66,
378 |      "metadata": {},
379 |      "output_type": "execute_result"
380 |     }
381 |    ],
382 |    "source": [
383 |     "model.intercept_"
384 |    ]
385 |   },
386 |   {
387 |    "cell_type": "markdown",
388 |    "id": "fc41e137-0011-4c86-b465-2c0a2cc92642",
389 |    "metadata": {},
390 |    "source": [
391 |     "#### Score"
392 |    ]
393 |   },
394 |   {
395 |    "cell_type": "code",
396 |    "execution_count": 67,
397 |    "id": "a0784512-112f-489c-bf49-a4bf8712345d",
398 |    "metadata": {},
399 |    "outputs": [
400 |     {
401 |      "data": {
402 |       "text/plain": [
403 |        "0.8333333333333334"
404 |       ]
405 |      },
406 |      "execution_count": 67,
407 |      "metadata": {},
408 |      "output_type": "execute_result"
409 |     }
410 |    ],
411 |    "source": [
412 |     "model.score(X_test,y_test)"
413 |    ]
414 |   },
415 |   {
416 |    "cell_type": "code",
417 |    "execution_count": 68,
418 |    "id": "a83f5ebc-6a85-4c29-81bb-042a4d2c7186",
419 |    "metadata": {},
420 |    "outputs": [
421 |     {
422 |      "data": {
423 |       "text/plain": [
424 |        "0.9047619047619048"
425 |       ]
426 |      },
427 |      "execution_count": 68,
428 |      "metadata": {},
429 |      "output_type": "execute_result"
430 |     }
431 |    ],
432 |    "source": [
433 |     "model.score(X_train,y_train)"
434 |    ]
435 |   },
436 |   {
437 |    "cell_type": "markdown",
438 |    "id": "b1d88203-cfc5-4276-afc6-2d21717dac71",
439 |    "metadata": {},
440 |    "source": [
441 |     "#### Logistice regression plot"
442 |    ]
443 |   },
444 |   {
445 |    "cell_type": "code",
446 |    "execution_count": 75,
447 |    "id": "6418ed1c-ceb8-4124-bd0b-ba18bd7aa69e",
448 |    "metadata": {},
449 |    "outputs": [
450 |     {
451 |      "name": "stderr",
452 |      "output_type": "stream",
453 |      "text": [
454 |       "/opt/anaconda3/envs/jenv/lib/python3.9/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
455 |       "  warnings.warn(\n"
456 |      ]
457 |     },
458 |     {
459 |      "data": {
460 |       "text/plain": [
461 |        "<AxesSubplot:xlabel='age'>"
462 |       ]
463 |      },
464 |      "execution_count": 75,
465 |      "metadata": {},
466 |      "output_type": "execute_result"
467 |     },
468 |     {
469 |      "data": {
470 |       "image/png": "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\n",
471 |       "text/plain": [
472 |        "<Figure size 432x288 with 1 Axes>"
473 |       ]
474 |      },
475 |      "metadata": {
476 |       "needs_background": "light"
477 |      },
478 |      "output_type": "display_data"
479 |     }
480 |    ],
481 |    "source": [
482 |     "\n",
483 |     "plt.scatter(df.age,df.bought_insurance)\n",
484 |     "sns.lineplot(df.age,model.predict(df[['age']]))"
485 |    ]
486 |   },
487 |   {
488 |    "cell_type": "markdown",
489 |    "id": "4e8c78be-b39a-4a40-8186-c92ebe5b596e",
490 |    "metadata": {},
491 |    "source": [
492 |     "####  Probability curve"
493 |    ]
494 |   },
495 |   {
496 |    "cell_type": "code",
497 |    "execution_count": 88,
498 |    "id": "6e1fc4ed-2dcf-4a56-8c7b-6219990b8d44",
499 |    "metadata": {},
500 |    "outputs": [
501 |     {
502 |      "name": "stderr",
503 |      "output_type": "stream",
504 |      "text": [
505 |       "/opt/anaconda3/envs/jenv/lib/python3.9/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
506 |       "  warnings.warn(\n"
507 |      ]
508 |     },
509 |     {
510 |      "data": {
511 |       "text/plain": [
512 |        "<AxesSubplot:xlabel='age'>"
513 |       ]
514 |      },
515 |      "execution_count": 88,
516 |      "metadata": {},
517 |      "output_type": "execute_result"
518 |     },
519 |     {
520 |      "data": {
521 |       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXQAAAEGCAYAAAB1iW6ZAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/YYfK9AAAACXBIWXMAAAsTAAALEwEAmpwYAAAjDklEQVR4nO3deXhV5bn+8e9DEkiYEoaEISSCzMhsIDgrasFZa7WKWkEUbasdfq0Wz+mxPbXnaNUO9qh1QHCWOotWpVZFEQUTkBkCyJSBIQwJQ0Km/f7+yIbGEJJNspO1h/tzXbnIGvZaT9699+3yXetdy5xziIhI+GvldQEiIhIcCnQRkQihQBcRiRAKdBGRCKFAFxGJELFe7bhr166ud+/eXu1eRCQsLV68eJdzLrmuZZ4Feu/evcnOzvZq9yIiYcnMthxrmbpcREQihAJdRCRCKNBFRCKEAl1EJEIo0EVEIkSDV7mY2UzgYmCnc25oHcsNeBi4ECgBJjvnlgS70Ejx1tf5PDg3h4KiUnomJXDnhIFcPirV67LEL1Ten/rqaOyy5thfJP/doVRnoKyhuy2a2ZnAAeC5YwT6hcAdVAd6JvCwcy6zoR1nZGS4aLts8a2v87n7jRWUVlQdmZcQF8N93x2mUA8BofL+1FcH0Khl9dXf2P0Fu01C6e9ujvZqbJ21mdli51xGncsCuX2umfUG3j1GoD8BzHPOveyfzgHOds5tq2+b0Rjop93/MflFpUfNT01KYMH08R5UJDWFyvtTXx1Ao5bVV39j9xfsNgmlv7s52quxddZWX6AHY2BRKpBbYzrPP++oQDezacA0gPT09CDsOrwU1PFm1jdfWlaovD+NqaOxy5pjf40VDn93Y1/XUm0ZjJOiVse8Og/7nXNPOucynHMZycl1jlyNaD39/5UOdL60rFB5f+qro7HLmmN/wRZKf3djX+d1WwYj0POAtBrTvYCCIGw34tw5YSAJcTHfmpcQF8OdEwZ6VJHUFCrvT311NHZZc+wv2ELp7w6lOo9HMLpc5gC3m9lsqk+KFjfUfx6tDp/4CIWrKORoofL+BFJHY5c1x/6CJRT/7lCo83gEcpXLy8DZQFdgB/AbIA7AOfe4/7LFR4CJVF+2OMU51+DZzmg8KSoi0aeyyseO/WVsKyqloPgQ24pKGZaayKn9ujZqe006Keqcu7aB5Q74caMqExEJc2WVVeTvLSV3bym5e0rI3VtC3p5S8otK2VZcSuH+Mny1jpunnXliowO9Pp7dPldEJFw459hWfIgNOw+wYecBvims/nfL7hJ27D9EzY6O1jGtSO2UQGpSAmf2T6ZHYjw9khLokRhPz6QEuifG0zE+rlnqVKCLiPhVVPnYsvsgG3YePBLahwO8pPzfA4ISE+Lol9Ke0/p1Ja1zAmmd2pLWuS1pnRPo1iGeVq3quviv+SnQRSQq7T5QxvK8YpbmFrF2+74jR9yVNfpHeibG0zelPVdnpNEvpT39UtrTN7k9Xdu3pvr0YWhRoItIxDtQVsmKvGKW5RWxPK+IZbnFR0ZttjLo07Ud/VLaM3Fo9yOh3Te5Pe3ahFdEhle1IiINKKusYs22/SzPK2JpbhHL84r5pvDAkX7utM4JjEpPYvKpvRneK5GhqYlhF9zHEhl/hYhEreKSChZt2s3CjXvI3rKHNdv2UVFVnd5d27dhRK9ELh3Rk+G9EhneK4nO7Vp7XHHzUaCLSFjZd6iCrE17+PKb3Xy5cTert+3DOWgT24rR6Z2YevqJjEyrDu8eifEh2dfdXBToIhLSfD7H6m37+GTtTuatK+TrrXvxOWgd24rR6Un87NwBjDuxMyPTk2gTG9PwBiOYAl1EQk5xSQXzNxQyL6f6Z9eBMgCG90rkx+f045S+XRid3on4uOgO8NoU6CISEvYdqmDuyu28s3wbCzbsosrnSEyI44z+XTlnYApnDkgmuUMbr8sMaQp0EfFMaXkVH63dwTvLCvgkp5DySh+9OiVwyxknct7gFEamJREbo0cfB0qBLiItqrzSx/z1hcxZVsCHq3dQUl5Fcoc2XJeZziUjejIqLSmqTmQGkwJdRJpdlc+xaONu5iwr4P2V2ykurSAxIY7LRvbkkuE9yTyxCzEeDZePJAp0EWkWzjmW5hbx9tIC/rFiG4X7y2jbOobvDOnGpSN7cnq/ZFrHqjslmBToIhJU5ZU+/rGigJmfb2ZFfjGtY1sxfmAKl4zoyfhBKSS01pUpzUWBLiJBsetAGS8t2srzC7dQuL+Mvsnt+P3lQ7l0ZM9mu12sfJsCXUSaZM22fcxasIm3lhZQXunjrAHJ3HRVH87o19Wz28hGKwW6iBw3n8/x8dqdzFywiS++2U1CXAxXZ/Ri8ql96JfS3uvyopYCXUQCdqCsklezc3nmi81s2V1Cj8R4pl8wiGvGpJHUNnJvehUuFOgi0qDcPSU888VmXsnKZX9ZJSef0Ik7JwxkwkndidPAn5ChQBeRY8rbW8IjH2/g1cV5GHDR8B5MOa0PI9OSvC5N6qBAF5Gj7Nh3iEc/2cDLX23FMG4YdwK3ndWX7onxXpcm9VCgi8gRuw6U8fi8b3h+4RaqfI6rMtK4Y3w/eiYleF2aBECBLiKUlFfy+LxvmPH5Jg5VVHHFqF789Nz+pHdp63VpchwU6CJRzDnH3FXb+d07qykoPsRFw3vw8/MG6NLDMKVAF4lSGwsP8Js5q5i/fheDunfgL9eMYmyfzl6XJU2gQBeJMiXllTzy8Qaemr+R+NgYfnPJEG4Yd4LuOx4BFOgiUcI5xwcrt3Pvu9XdK98dncr0CwaR0kFXrkQKBbpIFKjdvfLwtaMY01vdK5FGgS4SwWp3r/z2kiFcr+6ViKVAF4lAtbtXrhzdi+kXDNJDliNcQIFuZhOBh4EYYIZz7v5ayxOBF4B0/zYfcs7NCnKtIhKATbsOcs/bK5m/fheDe3Tkr9eOIkPdK1GhwUA3sxjgUeB8IA/IMrM5zrnVNVb7MbDaOXeJmSUDOWb2onOuvFmqFpGj+HyO577czH3vr6V1bCt1r0ShQI7QxwIbnHMbAcxsNnAZUDPQHdDBqh/V3R7YA1QGuVYROYaColLuem05n2/YxTkDk/nDlcNJ6airV6JNIIGeCuTWmM4DMmut8wgwBygAOgDfd875am/IzKYB0wDS09MbU6+I1OCc462l+dzz9iqqfI77vjuMa8akUX1sJdEmkECv65Phak1PAJYC44G+wIdmNt85t+9bL3LuSeBJgIyMjNrbEJHjsOdgOf/55greX7mdjBM68cerR3BCl3ZelyUeCiTQ84C0GtO9qD4Sr2kKcL9zzgEbzGwTMAj4KihVisi3fJKzkztfXc6+0gqmXzCIW844kRg9vzPqBRLoWUB/M+sD5APXAJNqrbMVOBeYb2bdgIHAxmAWKiJQUeXjobk5PPHZRgZ178DzU8cyuEdHr8uSENFgoDvnKs3sdmAu1ZctznTOrTKz2/zLHwfuBZ4xsxVUd9H8yjm3qxnrFok6+UWl3PHSEpZsLeK6zHT+6+IhxMfFeF2WhJCArkN3zr0HvFdr3uM1fi8AvhPc0kTksI/W7OAXry6jssrxf9eO4pIRPb0uSUKQRoqKhLCKKh8Pzs3hyc82clLPjjwyaTR9uurEp9RNgS4SogqKSvnxS0v4emsRN4w7gf+8aLC6WKReCnSRELR2+z5unPkVB8uqeHTSaC4a3sPrkiQMKNBFQkzW5j1MfSaLhNYxvP7DUxnYvYPXJUmYUKCLhJAPV+/g9peWkNopgeduGkuvTnpIswROgS4SIl7JymX6G8sZlprIrClj6dyutdclSZhRoIt4zDnHY/O+4cG5OZzRvyuPX38y7droqynHT58aEQ/5fI57/7GaWQs2c+mInjx01Qhax+p2t9I4CnQRj5RX+vjlq8uYs6yAKaf15r8uGkIr3Y9FmkCBLuKBg2WV3PbCYuav38VdEwfyw7P66pa30mQKdJEWtvtAGTc9k8WK/GIeuHI4V49Ja/hFIgFQoIu0oLy9Jfzg6a/ILyrliRsyOH9IN69LkgiiQBdpIYdHf5aWV/HCzZmM0YObJcgU6CItoOboz1duO4VB3XUPcwk+BbpIMzsy+jMpgeemavSnNB8Fukgzqjn6c+bkMXRp38brkiSCKdBFmoFGf4oX9AkTCTKN/hSvKNBFgkijP8VLCnSRINHoT/GaAl0kCDT6U0KBAl2kiTT6U0KFAl2kCWqO/nx+aiZj+2j0p3hHgS7SSBr9KaFGgS7SCDVHfz5701jSOmv0p3hPgS5ynDT6U0KVAl0kQBr9KaFOn0aRAGj0p4QDBbpIAzT6U8KFAl2kHhr9KeEkoP9nNLOJZpZjZhvMbPox1jnbzJaa2Soz+zS4ZYq0vN0Hypj01EIWbNjFH64cxo/O7qcwl5DW4BG6mcUAjwLnA3lAlpnNcc6trrFOEvAYMNE5t9XMUpqpXpEWodGfEo4C6XIZC2xwzm0EMLPZwGXA6hrrTALecM5tBXDO7Qx2oSIt5fDozxKN/pQwE0iXSyqQW2M6zz+vpgFAJzObZ2aLzewHdW3IzKaZWbaZZRcWFjauYpFmtGTrXq5+/Eucg1dvO0VhLmElkCP0ujoNXR3bORk4F0gAvjSzhc65dd96kXNPAk8CZGRk1N6GiKcWbdzNTc9k0bVDG16YmqnRnxJ2Agn0PKDmvUB7AQV1rLPLOXcQOGhmnwEjgHWIhIH56wu55blsUpMSePHmcXRPjPe6JJHjFkiXSxbQ38z6mFlr4BpgTq113gbOMLNYM2sLZAJrgluqSPP4aM0Opj6bTe8u7fj7racozCVsNXiE7pyrNLPbgblADDDTObfKzG7zL3/cObfGzD4AlgM+YIZzbmVzFi4SDO+v2MZPZn/NoO4dee6msXRq19rrkkQazZzzpis7IyPDZWdne7JvEYC3l+bz/15ZxoheicyaMpbEhDivSxJpkJktds5l1LVMI0UlKr2Slcuv3ljO2N6deXryGNrrJlsSAfQplqjz3JebueftVZzRvytP3pBBQusYr0sSCQoFukSVpz7byP+8t4bzBqfw6HWjaROrMJfIoUCXqPF/H63njx+u48Jh3fnL90fp9rcScRToEvGcczz0zxwe/eQbrhiVyoPfG05sjMJcIo8CXSKac47f/2MNT3++iWvGpPG/VwzTvcwlYinQJWL5fI575qzkhYVbufGUE/jNJScpzCWiKdAlIlX5HNNfX86ri/O49cwTmX7BIN3LXCKeAl0iTkWVj1+8Uv3IuJ+e25+fnddfYS5RQYEuEaW80scdLy9h7qod3DVxID86u5/XJYm0GAW6RIxDFVX88IXFfJJTyD0XD+Gm0/t4XZJIi1KgS0QoKa/klueyWbBhN/9zxVCuyzzB65JEWpwCXcLe/kMVTH0mm+wte3joqhF87+ReXpck4gkFuoS14pIKfjDrK1bmF/PwNaO4ZERPr0sS8YwCXcLWnoPlXD9jEet37uex60Yz4aTuXpck4ikFuoSlnfsPcf2MRWzZXcJTP8jg7IEpXpck4jkFuoSdbcWlXPfUIrYVH2LW5DGc2q+r1yWJhAQFuoSV3D0lTJqxkL0HK3h+6lgyenf2uiSRkKFAl7CxaddBJj21kJLyKl68OZMRaUlelyQSUhToEhbW79jPpBmLqPI5Xr5lHEN6dvS6JJGQo0CXkLeqoJgbnv6KmFbG36eNo3+3Dl6XJBKSdJd/CWlLc4u49smFxMe24pVbT1GYi9RDR+gSsrI272HKrCw6tYvjpZvHkda5rdcliYQ0BbqEpC827GLqs9n0SIznxVsy6ZGY4HVJIiFPXS4Scj7J2cmUZ7JI65zA7FvHKcxFAqQjdAkpc1dt5/aXljCgWween5pJ53atvS5JJGwo0CVkvLOsgJ/9fSnDUhN5dspYEtvGeV2SSFhRoEtIeG1xHne9toyMEzozc8oY2rfRR1PkeKkPXTz34qIt/PLVZZzatyvP3KQwF2ksfXPEUzM/38Tv3l3N+EEpPHbdaOLjYrwuSSRsKdDFM4/N28ADH+Qw8aTu/PXaUbSO1f8wijRFQN8gM5toZjlmtsHMptez3hgzqzKz7wWvRIk0zjn+9OE6Hvggh0tH9OSRSQpzkWBo8FtkZjHAo8AFwBDgWjMbcoz1/gDMDXaREjmcc9z//lr++tF6rjq5F3/+/khiYxTmIsEQyDdpLLDBObfROVcOzAYuq2O9O4DXgZ1BrE8iiM/n+O2cVTzx2UauH5fOH64cTkwr87oskYgRSKCnArk1pvP8844ws1TgCuDx+jZkZtPMLNvMsgsLC4+3VgljVT7Hf7y5gme/3MLNp/fh3suG0kphLhJUgQR6Xd86V2v6L8CvnHNV9W3IOfekcy7DOZeRnJwcYIkS7iqrfPzy1WXMzsrl9nP68Z8XDcZMYS4SbIFc5ZIHpNWY7gUU1FonA5jt/5J2BS40s0rn3FvBKFLCV3mlj5/9/WveW7GdX35nALeP7+91SSIRK5BAzwL6m1kfIB+4BphUcwXnXJ/Dv5vZM8C7CnM5VFHF7S8t4V9rdvLriwZz8xknel2SSERrMNCdc5VmdjvVV6/EADOdc6vM7Db/8nr7zSU6lZZXMe35bOav38W9lw/lhnEneF2SSMQLaGCRc+494L1a8+oMcufc5KaXJeHsQFklU5/J4qvNe3jgyuFcPSat4ReJSJNppKgE1b5DFUye+RXL8or5y/dHctnI1IZfJCJBoUCXoNl7sJwfzPyKtdv38eikUUwc2sPrkkSiigJdgqJwfxk3PL2IjbsO8sQNJzN+UDevSxKJOgp0abLtxYe4bsZC8otKmXnjGE7v39XrkkSikgJdmiRvbwnXzVjErv1lPHdTJmP7dPa6JJGopUCXRtu86yDXzVjEvkMVPH9zJqPTO3ldkkhUU6BLo2zYeYBJTy2kosrHy7eMY2hqotcliUQ9BboctzXb9nH9jEWYGbOnncLA7h28LklEUKDLcVqRV8wNMxcRHxvDi7dk0je5vdcliYifAl0CtnjLXibP/IrEtnG8dPM40ru09bokEalBgS4B+fKb3Ux9NouUDm146ZZx9ExK8LokEalFgS4N+mxdIbc8l01657a8eHMmKR3jvS5JROqgQJd6/Wv1Dn704hL6prTnhalj6dK+jdclicgx6Om8ckz/WL6N215YzOAeHXj5lkyFuUiI0xG61OnNr/P4xSvLGJ3eiZlTxtAxPs7rkkSkAQp0Ocrsr7Zy95srGNenCzNuzKBdG31MRMKBvqnyLc9+sZnfzFnFWQOSeeKGk4mPi/G6JBEJkAJdjnji02+47/21nD+kG49MGkWbWIW5SDhRoAvOOf760Qb+/K91XDy8B3/+/kjiYnS+XCTcKNCjnHOOB+bm8Ld53/Dd0ak8+L0RxLQyr8sSkUZQoEcx5xy/e3c1sxZsZlJmOr+/bCitFOYiYUuBHqV8Psev317JS4u2MuW03txz8RDMFOYi4UyBHoWqfI67XlvO60vy+OHZfblrwkCFuUgEUKBHmYoqHz//+1LeXb6Nn583gJ+c209hLhIhFOhRpKyyijte+pp/rt7B3RcM4taz+npdkogEkQI9ShyqqOLW5xfz6bpC/vvSk7jx1N5elyQiQaZAjwIl5ZXc/Gw2X27czf3fHcY1Y9O9LklEmoECPcLtOVjOrc9ns3jLXv509QiuGNXL65JEpJko0CPYZ+sK+cWryyguqeD/rh3NRcN7eF2SiDQjBXoEOlRRxQMf5DBzwSb6p7Tn2SljGdKzo9dliUgzC+iGHWY20cxyzGyDmU2vY/l1Zrbc//OFmY0IfqkSiLXb93H5owuYuWATk0/tzTt3nK4wF4kSDR6hm1kM8ChwPpAHZJnZHOfc6hqrbQLOcs7tNbMLgCeBzOYoWOrmnOOZLzZz3/tr6Rgfx6wpYzhnYIrXZYlICwqky2UssME5txHAzGYDlwFHAt0590WN9RcCOvPWgrYVlzL99RV8uq6Q8wancP+Vw+mqx8WJRJ1AAj0VyK0xnUf9R99TgffrWmBm04BpAOnpunSuqXw+x8tZW7nvvbVU+Rz3Xj6U6zPTNfJTJEoFEuh1pYOrc0Wzc6gO9NPrWu6ce5Lq7hgyMjLq3IYEZtOug0x/fTmLNu3h9H5due+7w0jr3NbrskTEQ4EEeh6QVmO6F1BQeyUzGw7MAC5wzu0OTnlSW2WVj6c/38SfPlxH69hWPHDlcK7K6KWjchEJKNCzgP5m1gfIB64BJtVcwczSgTeAG5xz64JepQCwumAfv3p9OSvyi/nOkG7ce/lQunWM97osEQkRDQa6c67SzG4H5gIxwEzn3Cozu82//HHgHqAL8Jj/SLHSOZfRfGVHl32HKvjLh+t59svNdGobx6OTRnPhsO46KheRbzHnvOnKzsjIcNnZ2Z7sO1z4fI7XluTxwAdr2X2wnGvGpHPXhIF0atfa69JExCNmtvhYB8waKRqiluUW8Zs5q1iaW8To9CRmTR7LsF6JXpclIiFMgR5idh8o44EPcnhlcS5d2rXhj1eN4IpRqXrWp4g0SIEeIkrKK5m1YDOPz/uG0ooqbj69Dz85tz8d4uO8Lk1EwoQC3WMVVT5mZ+Xy14/WU7i/jPMGd2P6BQPpl9LB69JEJMwo0D3i8zneXbGNP/4zhy27SxjTuxN/u240Gb07e12aiIQpBXoLc84xL6eQh/6Zw6qCfQzq3oGZkzM4Z2CKLkMUkSZRoLeQ8kof7ywr4Kn5G1m7fT+9OiXw5++P4NIRqcTohKeIBIECvZkVl1bw8ldbmbVgEzv2lTGgW3se/N5wLhuZSuvYgG5HLyISEAV6M8kvKmXW55uYnZXLgbJKTuvXhT9cOZyzBiSra0VEmoUCPchW5hczY/5G3lm+DYCLh/fgljNOZGiqBgWJSPNSoAeBc45P1xXy1PyNLNiwm3atY5h8am9uOr0PqUkJXpcnIlFCgd4E5ZU+5iwr4KnPNpKzYz/dOrZh+gWDuHZsOokJGhAkIi1Lgd4IOdv382p2Lm9+nc/ug+UM7NaBh64awaUjeupEp4h4RoEeoOLSCt5ZVsCr2bksyysmtpVx3uBuXJuZzpn9u+pEp4h4ToFej8oqH198s5s3luTx/srtlFX6GNitA7++aDBXjEqlix7ELCIhRIFeS5XPsWjjbt5dsY0PVm5nz8FyOsTHclVGL67OSGNYaqKOxkUkJCnQqb6vSvaWvby7vID3Vmxn14EyEuJiOHdwChcP78nZA5OJj4vxukwRkXpFbaDvOlDG/PWFfJpTyGfrd7HnYDltYlsxflB1iI8flEJCa4W4iISPqAn0yiofX+cW8WlOIZ+uK2RFfjEAXdq15qwByZw9MJlzB3ejfZuoaRIRiTARnV7bikv5bF11gM9fv4v9hyqJaWWMTk/il98ZwFkDUjipZ0c9DUhEIkJEBfqhiioWb9nLp+uqu1JyduwHoHvHeC4c2oOzByZzar+uGvQjIhEprAN914EysjfvJXvzHrK37GVVQTEVVY7WMa0Y06cTV548iLMGpDCgW3tdmSIiES/sAn1FXjHPfrmZxVv2smnXQQBax7ZiRK9Epp5+ImP7dCKzTxfaqS9cRKJM2KXe7oNlfLx2Jyef0IlrxqSR0bsTQ1MTaROrK1JEJLqFXaCf0T+Zxb8+T10oIiK1hF2g63FtIiJ1060BRUQihAJdRCRCKNBFRCKEAl1EJEIo0EVEIkRAV7mY2UTgYSAGmOGcu7/WcvMvvxAoASY755YEuVZ+/dYKXl6US5VzxJhxbWYav798GABvfZ3Pg3NzKCgqpWdSAndOGMjlo1Ib3GZ9r2vsspbeX3PUKdJUwf7s6bPcsAYD3cxigEeB84E8IMvM5jjnVtdY7QKgv/8nE/ib/9+g+fVbK3hh4dYj01XOHZnOOKEzd7+xgtKKKgDyi0q5+40VAPW+4W99nX/M1wGNWtbS+2uOOkWaqr7PemM+e8HeXqQy51z9K5idAvzWOTfBP303gHPuvhrrPAHMc8697J/OAc52zm071nYzMjJcdnZ2wIX2vfs9quqoNcaM7onx5BeVHrUsNSmBBdPHH3Obp93/8TFfBzRqWUvvrznqFGmq+j7rjfnsBXt74czMFjvnMupaFkiXSyqQW2M6j6OPvutaJxX4VqCb2TRgGkB6enoAu/63usL88PyCOt5o4JjzG1pe3+sau6yl99eUOkWaqrHfyZbaXqQK5KRoXUMza6drIOvgnHvSOZfhnMtITk4OpL4jYo4x1D/GjJ7+o9HajjW/oeU9kxIavayl99ccdYo0VbA/e/osByaQQM8D0mpM9wIKGrFOk1ybmXbM+XdOGEhCrWd+JsTFcOeEgfVus77XNXZZS++vOeoUaapgf/b0WQ5MIF0uWUB/M+sD5APXAJNqrTMHuN3MZlPdHVNcX/95Yxy+muVYV7kAx30G/PDy+l7X2GUtvb9g1inSVIF81r3cXqRq8KQogJldCPyF6ssWZzrn/sfMbgNwzj3uv2zxEWAi1ZctTnHO1XvG83hPioqISNNPiuKcew94r9a8x2v87oAfN6VIERFpGo0UFRGJEAp0EZEIoUAXEYkQCnQRkQgR0FUuzbJjs0JgSwvvtiuwq4X3GerUJnVTuxxNbXI0L9rkBOdcnSMzPQt0L5hZ9rEu94lWapO6qV2OpjY5Wqi1ibpcREQihAJdRCRCRFugP+l1ASFIbVI3tcvR1CZHC6k2iao+dBGRSBZtR+giIhFLgS4iEiEiNtDNLM3MPjGzNWa2ysx+6p/f2cw+NLP1/n87eV1rSzGzeDP7ysyW+dvkv/3zo7ZNDjOzGDP72sze9U9HdZuY2WYzW2FmS80s2z8v2tskycxeM7O1/lw5JdTaJGIDHagEfuGcGwyMA35sZkOA6cBHzrn+wEf+6WhRBox3zo0ARgITzWwc0d0mh/0UWFNjWm0C5zjnRta4zjra2+Rh4APn3CBgBNWfl9BqE+dcVPwAbwPnAzlAD/+8HkCO17V51B5tgSVUP5AkqtuE6idsfQSMB971z4v2NtkMdK01L2rbBOgIbMJ/IUmotkkkH6EfYWa9gVHAIqCb8z9Nyf9vioeltTh/18JSYCfwoXMu6tuE6oe33AX4asyL9jZxwD/NbLH/4e4Q3W1yIlAIzPJ3zc0ws3aEWJtEfKCbWXvgdeBnzrl9XtfjNedclXNuJNVHpWPNbKjHJXnKzC4GdjrnFntdS4g5zTk3GriA6u7KM70uyGOxwGjgb865UcBBvO5eqUNEB7qZxVEd5i86597wz95hZj38y3tQfaQadZxzRcA8qh8bGM1tchpwqZltBmYD483sBaK7TXDOFfj/3Qm8CYwlutskD8jz/x8twGtUB3xItUnEBrr/OadPA2ucc3+qsWgOcKP/9xup7luPCmaWbGZJ/t8TgPOAtURxmzjn7nbO9XLO9ab6AegfO+euJ4rbxMzamVmHw78D3wFWEsVt4pzbDuSa2UD/rHOB1YRYm0TsSFEzOx2YD6zg332j/0F1P/orQDqwFbjKObfHkyJbmJkNB56l+mHfrYBXnHO/M7MuRGmb1GRmZwO/dM5dHM1tYmYnUn1UDtVdDS+56gfDR22bAJjZSGAG0BrYCEzB/z0iRNokYgNdRCTaRGyXi4hItFGgi4hECAW6iEiEUKCLiEQIBbqISIRQoIuIRAgFuohIhFCgS1Qys7f8N55adfjmU2Y21czWmdk8M3vKzB7xz082s9fNLMv/c5q31YvUTQOLJCqZWWfn3B7/LRCygAnAAqrvz7Ef+BhY5py73cxeAh5zzn1uZunAXFd9n32RkBLrdQEiHvmJmV3h/z0NuAH49PCwbTN7FRjgX34eMKT69kAAdDSzDs65/S1ZsEhDFOgSdfz3bDkPOMU5V2Jm86h+UMGxjrpb+dctbZECRRpJfegSjRKBvf4wH0T1IwrbAmeZWScziwWurLH+P4HbD0/4b9IkEnIU6BKNPgBizWw5cC+wEMgH/pfqu3H+i+pboxb71/8JkGFmy81sNXBby5cs0jCdFBXxM7P2zrkD/iP0N4GZzrk3G3qdSKjQEbrIv/3W/7zVlVQ/EPgtT6sROU46QhcRiRA6QhcRiRAKdBGRCKFAFxGJEAp0EZEIoUAXEYkQ/x8+HOpmJNX5IwAAAABJRU5ErkJggg==\n",
522 |       "text/plain": [
523 |        "<Figure size 432x288 with 1 Axes>"
524 |       ]
525 |      },
526 |      "metadata": {
527 |       "needs_background": "light"
528 |      },
529 |      "output_type": "display_data"
530 |     }
531 |    ],
532 |    "source": [
533 |     "plt.scatter(df.age,df.bought_insurance)\n",
534 |     "# line plot will plot the line in ascending order of the points\n",
535 |     "# lineplot age vs probability of 1\n",
536 |     "sns.lineplot(df.age,model.predict_proba(df[['age']])[:,1])"
537 |    ]
538 |   },
539 |   {
540 |    "cell_type": "markdown",
541 |    "id": "4e968b38-792a-4037-80a2-f4c8223aa092",
542 |    "metadata": {},
543 |    "source": [
544 |     "#### Define the fuction manually"
545 |    ]
546 |   },
547 |   {
548 |    "cell_type": "code",
549 |    "execution_count": 98,
550 |    "id": "ec2b055a-4140-4a4d-bd03-b961466ee5b9",
551 |    "metadata": {},
552 |    "outputs": [],
553 |    "source": [
554 |     "import math\n",
555 |     "def sigmoid(z):\n",
556 |     "    return (1/(1+math.exp(-z)))"
557 |    ]
558 |   },
559 |   {
560 |    "cell_type": "code",
561 |    "execution_count": 112,
562 |    "id": "b9ad4eeb-82aa-4a86-9c0b-6d33f6ddcad0",
563 |    "metadata": {},
564 |    "outputs": [],
565 |    "source": [
566 |     "def predicts(age):\n",
567 |     "    z = age*0.14776968-5.51604619\n",
568 |     "    y =sigmoid(z)\n",
569 |     "    if y<=.5: return 0 \n",
570 |     "    else: return 1"
571 |    ]
572 |   },
573 |   {
574 |    "cell_type": "code",
575 |    "execution_count": 127,
576 |    "id": "1d56fce8-9439-4f45-a31b-f630774d411e",
577 |    "metadata": {},
578 |    "outputs": [
579 |     {
580 |      "data": {
581 |       "text/plain": [
582 |        "1"
583 |       ]
584 |      },
585 |      "execution_count": 127,
586 |      "metadata": {},
587 |      "output_type": "execute_result"
588 |     }
589 |    ],
590 |    "source": [
591 |     "\n",
592 |     "predicts(37.5)"
593 |    ]
594 |   },
595 |   {
596 |    "cell_type": "code",
597 |    "execution_count": 126,
598 |    "id": "00ce06ab-bdd5-4aae-b7d2-76c843d426c4",
599 |    "metadata": {},
600 |    "outputs": [
601 |     {
602 |      "name": "stderr",
603 |      "output_type": "stream",
604 |      "text": [
605 |       "/opt/anaconda3/envs/jenv/lib/python3.9/site-packages/sklearn/base.py:450: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names\n",
606 |       "  warnings.warn(\n"
607 |      ]
608 |     },
609 |     {
610 |      "data": {
611 |       "text/plain": [
612 |        "array([1])"
613 |       ]
614 |      },
615 |      "execution_count": 126,
616 |      "metadata": {},
617 |      "output_type": "execute_result"
618 |     }
619 |    ],
620 |    "source": [
621 |     "model.predict([[37.5]])"
622 |    ]
623 |   },
624 |   {
625 |    "cell_type": "code",
626 |    "execution_count": null,
627 |    "id": "dc6f3bb2-eafb-49c9-b8c5-191f1e56413c",
628 |    "metadata": {},
629 |    "outputs": [],
630 |    "source": []
631 |   },
632 |   {
633 |    "cell_type": "code",
634 |    "execution_count": null,
635 |    "id": "0a23e2a7-8c34-4f7a-8072-9d318a482ea7",
636 |    "metadata": {},
637 |    "outputs": [],
638 |    "source": []
639 |   }
640 |  ],
641 |  "metadata": {
642 |   "kernelspec": {
643 |    "display_name": "Python 3 (ipykernel)",
644 |    "language": "python",
645 |    "name": "python3"
646 |   },
647 |   "language_info": {
648 |    "codemirror_mode": {
649 |     "name": "ipython",
650 |     "version": 3
651 |    },
652 |    "file_extension": ".py",
653 |    "mimetype": "text/x-python",
654 |    "name": "python",
655 |    "nbconvert_exporter": "python",
656 |    "pygments_lexer": "ipython3",
657 |    "version": "3.9.12"
658 |   }
659 |  },
660 |  "nbformat": 4,
661 |  "nbformat_minor": 5
662 | }
663 | 


--------------------------------------------------------------------------------
/LogisticRegression/insurance_data.csv:
--------------------------------------------------------------------------------
 1 | age,bought_insurance
 2 | 22,0
 3 | 25,0
 4 | 47,1
 5 | 52,0
 6 | 46,1
 7 | 56,1
 8 | 55,0
 9 | 60,1
10 | 62,1
11 | 61,1
12 | 18,0
13 | 28,0
14 | 27,0
15 | 29,0
16 | 49,1
17 | 55,1
18 | 25,1
19 | 58,1
20 | 19,0
21 | 18,0
22 | 21,0
23 | 26,0
24 | 40,1
25 | 45,1
26 | 50,1
27 | 54,1
28 | 23,0


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # DataScience-ML
2 | 
3 | *Here I will upload my data science and machine learning journey*
4 | 
5 | U can find the algoritms and some exercise on the respective folders
6 | 


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