├── AUTOML source code.ipynb
├── Anomaly Detection  .ipynb
├── Auto regressor Time series.ipynb
├── Blackadam.ipynb
├── Cricket score clustering(KMeans Clustering).ipynb
├── Decision_Tree.ipynb
├── Digit recognizer using KNN ( Kaggle comp ).ipynb
├── ETL scriptrfm.ipynb
├── Ensemble learning.ipynb
├── Hyper parameter tuning.ipynb
├── KNN algorithm.ipynb
├── LICENSE
├── LP1.py
├── Logistic regression.ipynb
├── MovieRecommedation.ipynb
├── Multivariate LR project.ipynb
├── Ridge regression - Jigsaw kaggle competition.ipynb
├── Salary prediction ( Linear Regression ).ipynb
├── Salary_Data.csv
├── Sample scores.csv
├── Time series analysis.ipynb
├── Untitled4.ipynb
├── Weather prediction (NaiveBayes algorithm ).ipynb
├── adboost algorithm.ipynb
├── airline-passenger-traffic(1).csv
├── amex-prediction.ipynb
├── brain-stroke-prediction-with-less-visualizations.ipynb
├── car data.csv
├── food-demand.ipynb
├── hm-recommender.ipynb
├── overfitting-vs-underfitting-simple-explanation.ipynb
├── price-elasticity.ipynb
└── walmart-sales-advanced-analysis-and-prediction.ipynb


/AUTOML source code.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": null,
  6 |    "id": "eight-refrigerator",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": []
 10 |   },
 11 |   {
 12 |    "cell_type": "code",
 13 |    "execution_count": 1,
 14 |    "id": "future-morrison",
 15 |    "metadata": {},
 16 |    "outputs": [
 17 |     {
 18 |      "data": {
 19 |       "application/vnd.jupyter.widget-view+json": {
 20 |        "model_id": "",
 21 |        "version_major": 2,
 22 |        "version_minor": 0
 23 |       },
 24 |       "text/plain": [
 25 |        "Optimization Progress:   0%|          | 0/300 [00:00<?, ?pipeline/s]"
 26 |       ]
 27 |      },
 28 |      "metadata": {},
 29 |      "output_type": "display_data"
 30 |     },
 31 |     {
 32 |      "name": "stdout",
 33 |      "output_type": "stream",
 34 |      "text": [
 35 |       "\n",
 36 |       "Generation 1 - Current best internal CV score: -12.183902491076243\n",
 37 |       "\n",
 38 |       "Generation 2 - Current best internal CV score: -12.183902491076243\n",
 39 |       "\n",
 40 |       "Generation 3 - Current best internal CV score: -12.064332520818585\n",
 41 |       "\n",
 42 |       "Generation 4 - Current best internal CV score: -12.064332520818585\n",
 43 |       "\n",
 44 |       "Generation 5 - Current best internal CV score: -12.064332520818585\n",
 45 |       "\n",
 46 |       "Best pipeline: XGBRegressor(RobustScaler(input_matrix), learning_rate=0.1, max_depth=9, min_child_weight=14, n_estimators=100, n_jobs=1, objective=reg:squarederror, subsample=0.7000000000000001, verbosity=0)\n",
 47 |       "-11.070680162041242\n"
 48 |      ]
 49 |     }
 50 |    ],
 51 |    "source": [
 52 |     "from tpot import TPOTRegressor\n",
 53 |     "from sklearn.datasets import load_boston\n",
 54 |     "from sklearn.model_selection import train_test_split\n",
 55 |     "\n",
 56 |     "housing = load_boston()\n",
 57 |     "X_train, X_test, y_train, y_test = train_test_split(housing.data, housing.target,\n",
 58 |     "                                                    train_size=0.75, test_size=0.25, random_state=42)\n",
 59 |     "\n",
 60 |     "tpot = TPOTRegressor(generations=5, population_size=50, verbosity=2,random_state=42)\n",
 61 |     "tpot.fit(X_train, y_train)\n",
 62 |     "print(tpot.score(X_test, y_test))\n",
 63 |     "tpot.export('tpot_boston_pipeline.py')"
 64 |    ]
 65 |   },
 66 |   {
 67 |    "cell_type": "code",
 68 |    "execution_count": null,
 69 |    "id": "alike-mambo",
 70 |    "metadata": {},
 71 |    "outputs": [],
 72 |    "source": []
 73 |   },
 74 |   {
 75 |    "cell_type": "code",
 76 |    "execution_count": 1,
 77 |    "id": "peaceful-satin",
 78 |    "metadata": {},
 79 |    "outputs": [
 80 |     {
 81 |      "data": {
 82 |       "application/vnd.jupyter.widget-view+json": {
 83 |        "model_id": "",
 84 |        "version_major": 2,
 85 |        "version_minor": 0
 86 |       },
 87 |       "text/plain": [
 88 |        "Optimization Progress:   0%|          | 0/300 [00:00<?, ?pipeline/s]"
 89 |       ]
 90 |      },
 91 |      "metadata": {},
 92 |      "output_type": "display_data"
 93 |     },
 94 |     {
 95 |      "name": "stdout",
 96 |      "output_type": "stream",
 97 |      "text": [
 98 |       "\n",
 99 |       "Generation 1 - Current best internal CV score: 0.9643728486851163\n",
100 |       "\n",
101 |       "Generation 2 - Current best internal CV score: 0.9725375189315709\n",
102 |       "\n",
103 |       "Generation 3 - Current best internal CV score: 0.9747597411537934\n",
104 |       "\n",
105 |       "Generation 4 - Current best internal CV score: 0.9777199504337052\n",
106 |       "\n",
107 |       "Generation 5 - Current best internal CV score: 0.9777199504337052\n",
108 |       "\n",
109 |       "Best pipeline: DecisionTreeClassifier(LinearSVC(PolynomialFeatures(input_matrix, degree=2, include_bias=False, interaction_only=False), C=20.0, dual=True, loss=squared_hinge, penalty=l2, tol=1e-05), criterion=entropy, max_depth=6, min_samples_leaf=13, min_samples_split=5)\n",
110 |       "0.9888888888888889\n"
111 |      ]
112 |     }
113 |    ],
114 |    "source": [
115 |     "from tpot import TPOTClassifier\n",
116 |     "from sklearn.datasets import load_digits\n",
117 |     "from sklearn.model_selection import train_test_split\n",
118 |     "\n",
119 |     "digits = load_digits()\n",
120 |     "X_train, X_test, y_train, y_test = train_test_split(digits.data, digits.target,\n",
121 |     "                                                    train_size=0.75, test_size=0.25, random_state=42)\n",
122 |     "\n",
123 |     "tpot = TPOTClassifier(generations=5, population_size=50, verbosity=2)\n",
124 |     "tpot.fit(X_train, y_train)\n",
125 |     "print(tpot.score(X_test, y_test))\n",
126 |     "tpot.export('tpot_digits_pipeline.py')"
127 |    ]
128 |   },
129 |   {
130 |    "cell_type": "code",
131 |    "execution_count": null,
132 |    "id": "exceptional-moment",
133 |    "metadata": {},
134 |    "outputs": [],
135 |    "source": []
136 |   },
137 |   {
138 |    "cell_type": "code",
139 |    "execution_count": null,
140 |    "id": "floral-street",
141 |    "metadata": {},
142 |    "outputs": [],
143 |    "source": []
144 |   },
145 |   {
146 |    "cell_type": "code",
147 |    "execution_count": null,
148 |    "id": "intermediate-scratch",
149 |    "metadata": {},
150 |    "outputs": [],
151 |    "source": []
152 |   }
153 |  ],
154 |  "metadata": {
155 |   "kernelspec": {
156 |    "display_name": "Python 3",
157 |    "language": "python",
158 |    "name": "python3"
159 |   },
160 |   "language_info": {
161 |    "codemirror_mode": {
162 |     "name": "ipython",
163 |     "version": 3
164 |    },
165 |    "file_extension": ".py",
166 |    "mimetype": "text/x-python",
167 |    "name": "python",
168 |    "nbconvert_exporter": "python",
169 |    "pygments_lexer": "ipython3",
170 |    "version": "3.8.8"
171 |   }
172 |  },
173 |  "nbformat": 4,
174 |  "nbformat_minor": 5
175 | }
176 | 


--------------------------------------------------------------------------------
/Anomaly Detection  .ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 2,
  6 |    "id": "classical-banner",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import numpy as np\n",
 11 |     "import pandas as pd\n",
 12 |     "from sklearn.ensemble import IsolationForest"
 13 |    ]
 14 |   },
 15 |   {
 16 |    "cell_type": "code",
 17 |    "execution_count": 3,
 18 |    "id": "final-channels",
 19 |    "metadata": {},
 20 |    "outputs": [
 21 |     {
 22 |      "data": {
 23 |       "text/html": [
 24 |        "<div>\n",
 25 |        "<style scoped>\n",
 26 |        "    .dataframe tbody tr th:only-of-type {\n",
 27 |        "        vertical-align: middle;\n",
 28 |        "    }\n",
 29 |        "\n",
 30 |        "    .dataframe tbody tr th {\n",
 31 |        "        vertical-align: top;\n",
 32 |        "    }\n",
 33 |        "\n",
 34 |        "    .dataframe thead th {\n",
 35 |        "        text-align: right;\n",
 36 |        "    }\n",
 37 |        "</style>\n",
 38 |        "<table border=\"1\" class=\"dataframe\">\n",
 39 |        "  <thead>\n",
 40 |        "    <tr style=\"text-align: right;\">\n",
 41 |        "      <th></th>\n",
 42 |        "      <th>Overs</th>\n",
 43 |        "      <th>Scores</th>\n",
 44 |        "    </tr>\n",
 45 |        "  </thead>\n",
 46 |        "  <tbody>\n",
 47 |        "    <tr>\n",
 48 |        "      <th>0</th>\n",
 49 |        "      <td>1</td>\n",
 50 |        "      <td>15</td>\n",
 51 |        "    </tr>\n",
 52 |        "    <tr>\n",
 53 |        "      <th>1</th>\n",
 54 |        "      <td>2</td>\n",
 55 |        "      <td>10</td>\n",
 56 |        "    </tr>\n",
 57 |        "    <tr>\n",
 58 |        "      <th>2</th>\n",
 59 |        "      <td>3</td>\n",
 60 |        "      <td>17</td>\n",
 61 |        "    </tr>\n",
 62 |        "    <tr>\n",
 63 |        "      <th>3</th>\n",
 64 |        "      <td>4</td>\n",
 65 |        "      <td>10</td>\n",
 66 |        "    </tr>\n",
 67 |        "    <tr>\n",
 68 |        "      <th>4</th>\n",
 69 |        "      <td>5</td>\n",
 70 |        "      <td>12</td>\n",
 71 |        "    </tr>\n",
 72 |        "    <tr>\n",
 73 |        "      <th>5</th>\n",
 74 |        "      <td>6</td>\n",
 75 |        "      <td>20</td>\n",
 76 |        "    </tr>\n",
 77 |        "    <tr>\n",
 78 |        "      <th>6</th>\n",
 79 |        "      <td>7</td>\n",
 80 |        "      <td>100</td>\n",
 81 |        "    </tr>\n",
 82 |        "    <tr>\n",
 83 |        "      <th>7</th>\n",
 84 |        "      <td>8</td>\n",
 85 |        "      <td>7</td>\n",
 86 |        "    </tr>\n",
 87 |        "    <tr>\n",
 88 |        "      <th>8</th>\n",
 89 |        "      <td>9</td>\n",
 90 |        "      <td>8</td>\n",
 91 |        "    </tr>\n",
 92 |        "    <tr>\n",
 93 |        "      <th>9</th>\n",
 94 |        "      <td>10</td>\n",
 95 |        "      <td>11</td>\n",
 96 |        "    </tr>\n",
 97 |        "    <tr>\n",
 98 |        "      <th>10</th>\n",
 99 |        "      <td>11</td>\n",
100 |        "      <td>100</td>\n",
101 |        "    </tr>\n",
102 |        "    <tr>\n",
103 |        "      <th>11</th>\n",
104 |        "      <td>12</td>\n",
105 |        "      <td>14</td>\n",
106 |        "    </tr>\n",
107 |        "    <tr>\n",
108 |        "      <th>12</th>\n",
109 |        "      <td>13</td>\n",
110 |        "      <td>3</td>\n",
111 |        "    </tr>\n",
112 |        "    <tr>\n",
113 |        "      <th>13</th>\n",
114 |        "      <td>14</td>\n",
115 |        "      <td>100</td>\n",
116 |        "    </tr>\n",
117 |        "    <tr>\n",
118 |        "      <th>14</th>\n",
119 |        "      <td>15</td>\n",
120 |        "      <td>11</td>\n",
121 |        "    </tr>\n",
122 |        "    <tr>\n",
123 |        "      <th>15</th>\n",
124 |        "      <td>16</td>\n",
125 |        "      <td>13</td>\n",
126 |        "    </tr>\n",
127 |        "    <tr>\n",
128 |        "      <th>16</th>\n",
129 |        "      <td>17</td>\n",
130 |        "      <td>100</td>\n",
131 |        "    </tr>\n",
132 |        "    <tr>\n",
133 |        "      <th>17</th>\n",
134 |        "      <td>18</td>\n",
135 |        "      <td>16</td>\n",
136 |        "    </tr>\n",
137 |        "    <tr>\n",
138 |        "      <th>18</th>\n",
139 |        "      <td>19</td>\n",
140 |        "      <td>26</td>\n",
141 |        "    </tr>\n",
142 |        "    <tr>\n",
143 |        "      <th>19</th>\n",
144 |        "      <td>20</td>\n",
145 |        "      <td>30</td>\n",
146 |        "    </tr>\n",
147 |        "  </tbody>\n",
148 |        "</table>\n",
149 |        "</div>"
150 |       ],
151 |       "text/plain": [
152 |        "    Overs  Scores\n",
153 |        "0       1      15\n",
154 |        "1       2      10\n",
155 |        "2       3      17\n",
156 |        "3       4      10\n",
157 |        "4       5      12\n",
158 |        "5       6      20\n",
159 |        "6       7     100\n",
160 |        "7       8       7\n",
161 |        "8       9       8\n",
162 |        "9      10      11\n",
163 |        "10     11     100\n",
164 |        "11     12      14\n",
165 |        "12     13       3\n",
166 |        "13     14     100\n",
167 |        "14     15      11\n",
168 |        "15     16      13\n",
169 |        "16     17     100\n",
170 |        "17     18      16\n",
171 |        "18     19      26\n",
172 |        "19     20      30"
173 |       ]
174 |      },
175 |      "execution_count": 3,
176 |      "metadata": {},
177 |      "output_type": "execute_result"
178 |     }
179 |    ],
180 |    "source": [
181 |     "df = pd.read_csv('Sample scores.csv')\n",
182 |     "df"
183 |    ]
184 |   },
185 |   {
186 |    "cell_type": "code",
187 |    "execution_count": 4,
188 |    "id": "prerequisite-invasion",
189 |    "metadata": {},
190 |    "outputs": [
191 |     {
192 |      "data": {
193 |       "text/plain": [
194 |        "IsolationForest(contamination=0.2, n_estimators=1000)"
195 |       ]
196 |      },
197 |      "execution_count": 4,
198 |      "metadata": {},
199 |      "output_type": "execute_result"
200 |     }
201 |    ],
202 |    "source": [
203 |     "model=IsolationForest(n_estimators=1000,max_samples='auto',contamination=float(0.2),max_features=1.0)\n",
204 |     "model.fit(df[['Scores']])"
205 |    ]
206 |   },
207 |   {
208 |    "cell_type": "code",
209 |    "execution_count": 5,
210 |    "id": "planned-wilson",
211 |    "metadata": {},
212 |    "outputs": [
213 |     {
214 |      "data": {
215 |       "text/html": [
216 |        "<div>\n",
217 |        "<style scoped>\n",
218 |        "    .dataframe tbody tr th:only-of-type {\n",
219 |        "        vertical-align: middle;\n",
220 |        "    }\n",
221 |        "\n",
222 |        "    .dataframe tbody tr th {\n",
223 |        "        vertical-align: top;\n",
224 |        "    }\n",
225 |        "\n",
226 |        "    .dataframe thead th {\n",
227 |        "        text-align: right;\n",
228 |        "    }\n",
229 |        "</style>\n",
230 |        "<table border=\"1\" class=\"dataframe\">\n",
231 |        "  <thead>\n",
232 |        "    <tr style=\"text-align: right;\">\n",
233 |        "      <th></th>\n",
234 |        "      <th>Overs</th>\n",
235 |        "      <th>Scores</th>\n",
236 |        "      <th>scores</th>\n",
237 |        "      <th>anomaly</th>\n",
238 |        "    </tr>\n",
239 |        "  </thead>\n",
240 |        "  <tbody>\n",
241 |        "    <tr>\n",
242 |        "      <th>0</th>\n",
243 |        "      <td>1</td>\n",
244 |        "      <td>15</td>\n",
245 |        "      <td>0.217062</td>\n",
246 |        "      <td>1</td>\n",
247 |        "    </tr>\n",
248 |        "    <tr>\n",
249 |        "      <th>1</th>\n",
250 |        "      <td>2</td>\n",
251 |        "      <td>10</td>\n",
252 |        "      <td>0.238335</td>\n",
253 |        "      <td>1</td>\n",
254 |        "    </tr>\n",
255 |        "    <tr>\n",
256 |        "      <th>2</th>\n",
257 |        "      <td>3</td>\n",
258 |        "      <td>17</td>\n",
259 |        "      <td>0.182980</td>\n",
260 |        "      <td>1</td>\n",
261 |        "    </tr>\n",
262 |        "    <tr>\n",
263 |        "      <th>3</th>\n",
264 |        "      <td>4</td>\n",
265 |        "      <td>10</td>\n",
266 |        "      <td>0.238335</td>\n",
267 |        "      <td>1</td>\n",
268 |        "    </tr>\n",
269 |        "    <tr>\n",
270 |        "      <th>4</th>\n",
271 |        "      <td>5</td>\n",
272 |        "      <td>12</td>\n",
273 |        "      <td>0.234626</td>\n",
274 |        "      <td>1</td>\n",
275 |        "    </tr>\n",
276 |        "    <tr>\n",
277 |        "      <th>5</th>\n",
278 |        "      <td>6</td>\n",
279 |        "      <td>20</td>\n",
280 |        "      <td>0.109175</td>\n",
281 |        "      <td>1</td>\n",
282 |        "    </tr>\n",
283 |        "    <tr>\n",
284 |        "      <th>6</th>\n",
285 |        "      <td>7</td>\n",
286 |        "      <td>100</td>\n",
287 |        "      <td>-0.021292</td>\n",
288 |        "      <td>-1</td>\n",
289 |        "    </tr>\n",
290 |        "    <tr>\n",
291 |        "      <th>7</th>\n",
292 |        "      <td>8</td>\n",
293 |        "      <td>7</td>\n",
294 |        "      <td>0.144497</td>\n",
295 |        "      <td>1</td>\n",
296 |        "    </tr>\n",
297 |        "    <tr>\n",
298 |        "      <th>8</th>\n",
299 |        "      <td>9</td>\n",
300 |        "      <td>8</td>\n",
301 |        "      <td>0.177666</td>\n",
302 |        "      <td>1</td>\n",
303 |        "    </tr>\n",
304 |        "    <tr>\n",
305 |        "      <th>9</th>\n",
306 |        "      <td>10</td>\n",
307 |        "      <td>11</td>\n",
308 |        "      <td>0.248936</td>\n",
309 |        "      <td>1</td>\n",
310 |        "    </tr>\n",
311 |        "    <tr>\n",
312 |        "      <th>10</th>\n",
313 |        "      <td>11</td>\n",
314 |        "      <td>100</td>\n",
315 |        "      <td>-0.021292</td>\n",
316 |        "      <td>-1</td>\n",
317 |        "    </tr>\n",
318 |        "    <tr>\n",
319 |        "      <th>11</th>\n",
320 |        "      <td>12</td>\n",
321 |        "      <td>14</td>\n",
322 |        "      <td>0.223662</td>\n",
323 |        "      <td>1</td>\n",
324 |        "    </tr>\n",
325 |        "    <tr>\n",
326 |        "      <th>12</th>\n",
327 |        "      <td>13</td>\n",
328 |        "      <td>3</td>\n",
329 |        "      <td>0.005323</td>\n",
330 |        "      <td>1</td>\n",
331 |        "    </tr>\n",
332 |        "    <tr>\n",
333 |        "      <th>13</th>\n",
334 |        "      <td>14</td>\n",
335 |        "      <td>100</td>\n",
336 |        "      <td>-0.021292</td>\n",
337 |        "      <td>-1</td>\n",
338 |        "    </tr>\n",
339 |        "    <tr>\n",
340 |        "      <th>14</th>\n",
341 |        "      <td>15</td>\n",
342 |        "      <td>11</td>\n",
343 |        "      <td>0.248936</td>\n",
344 |        "      <td>1</td>\n",
345 |        "    </tr>\n",
346 |        "    <tr>\n",
347 |        "      <th>15</th>\n",
348 |        "      <td>16</td>\n",
349 |        "      <td>13</td>\n",
350 |        "      <td>0.229416</td>\n",
351 |        "      <td>1</td>\n",
352 |        "    </tr>\n",
353 |        "    <tr>\n",
354 |        "      <th>16</th>\n",
355 |        "      <td>17</td>\n",
356 |        "      <td>100</td>\n",
357 |        "      <td>-0.021292</td>\n",
358 |        "      <td>-1</td>\n",
359 |        "    </tr>\n",
360 |        "    <tr>\n",
361 |        "      <th>17</th>\n",
362 |        "      <td>18</td>\n",
363 |        "      <td>16</td>\n",
364 |        "      <td>0.206693</td>\n",
365 |        "      <td>1</td>\n",
366 |        "    </tr>\n",
367 |        "    <tr>\n",
368 |        "      <th>18</th>\n",
369 |        "      <td>19</td>\n",
370 |        "      <td>26</td>\n",
371 |        "      <td>0.058269</td>\n",
372 |        "      <td>1</td>\n",
373 |        "    </tr>\n",
374 |        "    <tr>\n",
375 |        "      <th>19</th>\n",
376 |        "      <td>20</td>\n",
377 |        "      <td>30</td>\n",
378 |        "      <td>0.008441</td>\n",
379 |        "      <td>1</td>\n",
380 |        "    </tr>\n",
381 |        "  </tbody>\n",
382 |        "</table>\n",
383 |        "</div>"
384 |       ],
385 |       "text/plain": [
386 |        "    Overs  Scores    scores  anomaly\n",
387 |        "0       1      15  0.217062        1\n",
388 |        "1       2      10  0.238335        1\n",
389 |        "2       3      17  0.182980        1\n",
390 |        "3       4      10  0.238335        1\n",
391 |        "4       5      12  0.234626        1\n",
392 |        "5       6      20  0.109175        1\n",
393 |        "6       7     100 -0.021292       -1\n",
394 |        "7       8       7  0.144497        1\n",
395 |        "8       9       8  0.177666        1\n",
396 |        "9      10      11  0.248936        1\n",
397 |        "10     11     100 -0.021292       -1\n",
398 |        "11     12      14  0.223662        1\n",
399 |        "12     13       3  0.005323        1\n",
400 |        "13     14     100 -0.021292       -1\n",
401 |        "14     15      11  0.248936        1\n",
402 |        "15     16      13  0.229416        1\n",
403 |        "16     17     100 -0.021292       -1\n",
404 |        "17     18      16  0.206693        1\n",
405 |        "18     19      26  0.058269        1\n",
406 |        "19     20      30  0.008441        1"
407 |       ]
408 |      },
409 |      "execution_count": 5,
410 |      "metadata": {},
411 |      "output_type": "execute_result"
412 |     }
413 |    ],
414 |    "source": [
415 |     "df['scores']=model.decision_function(df[['Scores']])\n",
416 |     "df['anomaly']=model.predict(df[['Scores']])\n",
417 |     "df.head(20)"
418 |    ]
419 |   },
420 |   {
421 |    "cell_type": "code",
422 |    "execution_count": 6,
423 |    "id": "posted-pencil",
424 |    "metadata": {},
425 |    "outputs": [
426 |     {
427 |      "data": {
428 |       "text/plain": [
429 |        "4"
430 |       ]
431 |      },
432 |      "execution_count": 6,
433 |      "metadata": {},
434 |      "output_type": "execute_result"
435 |     }
436 |    ],
437 |    "source": [
438 |     "outliers_counter = len(df[df['Scores'] > 36])\n",
439 |     "outliers_counter"
440 |    ]
441 |   },
442 |   {
443 |    "cell_type": "code",
444 |    "execution_count": null,
445 |    "id": "developed-potato",
446 |    "metadata": {},
447 |    "outputs": [],
448 |    "source": []
449 |   }
450 |  ],
451 |  "metadata": {
452 |   "kernelspec": {
453 |    "display_name": "Python 3",
454 |    "language": "python",
455 |    "name": "python3"
456 |   },
457 |   "language_info": {
458 |    "codemirror_mode": {
459 |     "name": "ipython",
460 |     "version": 3
461 |    },
462 |    "file_extension": ".py",
463 |    "mimetype": "text/x-python",
464 |    "name": "python",
465 |    "nbconvert_exporter": "python",
466 |    "pygments_lexer": "ipython3",
467 |    "version": "3.8.8"
468 |   }
469 |  },
470 |  "nbformat": 4,
471 |  "nbformat_minor": 5
472 | }
473 | 


--------------------------------------------------------------------------------
/Cricket score clustering(KMeans Clustering).ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "sixth-membership",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "from pandas import pandas as pd\n",
 11 |     "from pandas import DataFrame\n",
 12 |     "import matplotlib.pyplot as plt\n",
 13 |     "from sklearn.cluster import KMeans"
 14 |    ]
 15 |   },
 16 |   {
 17 |    "cell_type": "code",
 18 |    "execution_count": 2,
 19 |    "id": "color-shower",
 20 |    "metadata": {},
 21 |    "outputs": [
 22 |     {
 23 |      "data": {
 24 |       "text/html": [
 25 |        "<div>\n",
 26 |        "<style scoped>\n",
 27 |        "    .dataframe tbody tr th:only-of-type {\n",
 28 |        "        vertical-align: middle;\n",
 29 |        "    }\n",
 30 |        "\n",
 31 |        "    .dataframe tbody tr th {\n",
 32 |        "        vertical-align: top;\n",
 33 |        "    }\n",
 34 |        "\n",
 35 |        "    .dataframe thead th {\n",
 36 |        "        text-align: right;\n",
 37 |        "    }\n",
 38 |        "</style>\n",
 39 |        "<table border=\"1\" class=\"dataframe\">\n",
 40 |        "  <thead>\n",
 41 |        "    <tr style=\"text-align: right;\">\n",
 42 |        "      <th></th>\n",
 43 |        "      <th>Overs</th>\n",
 44 |        "      <th>Scores</th>\n",
 45 |        "    </tr>\n",
 46 |        "  </thead>\n",
 47 |        "  <tbody>\n",
 48 |        "    <tr>\n",
 49 |        "      <th>0</th>\n",
 50 |        "      <td>1</td>\n",
 51 |        "      <td>15</td>\n",
 52 |        "    </tr>\n",
 53 |        "    <tr>\n",
 54 |        "      <th>1</th>\n",
 55 |        "      <td>2</td>\n",
 56 |        "      <td>10</td>\n",
 57 |        "    </tr>\n",
 58 |        "    <tr>\n",
 59 |        "      <th>2</th>\n",
 60 |        "      <td>3</td>\n",
 61 |        "      <td>17</td>\n",
 62 |        "    </tr>\n",
 63 |        "    <tr>\n",
 64 |        "      <th>3</th>\n",
 65 |        "      <td>4</td>\n",
 66 |        "      <td>10</td>\n",
 67 |        "    </tr>\n",
 68 |        "    <tr>\n",
 69 |        "      <th>4</th>\n",
 70 |        "      <td>5</td>\n",
 71 |        "      <td>12</td>\n",
 72 |        "    </tr>\n",
 73 |        "    <tr>\n",
 74 |        "      <th>5</th>\n",
 75 |        "      <td>6</td>\n",
 76 |        "      <td>20</td>\n",
 77 |        "    </tr>\n",
 78 |        "    <tr>\n",
 79 |        "      <th>6</th>\n",
 80 |        "      <td>7</td>\n",
 81 |        "      <td>10</td>\n",
 82 |        "    </tr>\n",
 83 |        "    <tr>\n",
 84 |        "      <th>7</th>\n",
 85 |        "      <td>8</td>\n",
 86 |        "      <td>7</td>\n",
 87 |        "    </tr>\n",
 88 |        "    <tr>\n",
 89 |        "      <th>8</th>\n",
 90 |        "      <td>9</td>\n",
 91 |        "      <td>8</td>\n",
 92 |        "    </tr>\n",
 93 |        "    <tr>\n",
 94 |        "      <th>9</th>\n",
 95 |        "      <td>10</td>\n",
 96 |        "      <td>11</td>\n",
 97 |        "    </tr>\n",
 98 |        "    <tr>\n",
 99 |        "      <th>10</th>\n",
100 |        "      <td>11</td>\n",
101 |        "      <td>4</td>\n",
102 |        "    </tr>\n",
103 |        "    <tr>\n",
104 |        "      <th>11</th>\n",
105 |        "      <td>12</td>\n",
106 |        "      <td>14</td>\n",
107 |        "    </tr>\n",
108 |        "    <tr>\n",
109 |        "      <th>12</th>\n",
110 |        "      <td>13</td>\n",
111 |        "      <td>3</td>\n",
112 |        "    </tr>\n",
113 |        "    <tr>\n",
114 |        "      <th>13</th>\n",
115 |        "      <td>14</td>\n",
116 |        "      <td>6</td>\n",
117 |        "    </tr>\n",
118 |        "    <tr>\n",
119 |        "      <th>14</th>\n",
120 |        "      <td>15</td>\n",
121 |        "      <td>11</td>\n",
122 |        "    </tr>\n",
123 |        "    <tr>\n",
124 |        "      <th>15</th>\n",
125 |        "      <td>16</td>\n",
126 |        "      <td>13</td>\n",
127 |        "    </tr>\n",
128 |        "    <tr>\n",
129 |        "      <th>16</th>\n",
130 |        "      <td>17</td>\n",
131 |        "      <td>20</td>\n",
132 |        "    </tr>\n",
133 |        "    <tr>\n",
134 |        "      <th>17</th>\n",
135 |        "      <td>18</td>\n",
136 |        "      <td>16</td>\n",
137 |        "    </tr>\n",
138 |        "    <tr>\n",
139 |        "      <th>18</th>\n",
140 |        "      <td>19</td>\n",
141 |        "      <td>26</td>\n",
142 |        "    </tr>\n",
143 |        "    <tr>\n",
144 |        "      <th>19</th>\n",
145 |        "      <td>20</td>\n",
146 |        "      <td>30</td>\n",
147 |        "    </tr>\n",
148 |        "  </tbody>\n",
149 |        "</table>\n",
150 |        "</div>"
151 |       ],
152 |       "text/plain": [
153 |        "    Overs  Scores\n",
154 |        "0       1      15\n",
155 |        "1       2      10\n",
156 |        "2       3      17\n",
157 |        "3       4      10\n",
158 |        "4       5      12\n",
159 |        "5       6      20\n",
160 |        "6       7      10\n",
161 |        "7       8       7\n",
162 |        "8       9       8\n",
163 |        "9      10      11\n",
164 |        "10     11       4\n",
165 |        "11     12      14\n",
166 |        "12     13       3\n",
167 |        "13     14       6\n",
168 |        "14     15      11\n",
169 |        "15     16      13\n",
170 |        "16     17      20\n",
171 |        "17     18      16\n",
172 |        "18     19      26\n",
173 |        "19     20      30"
174 |       ]
175 |      },
176 |      "execution_count": 2,
177 |      "metadata": {},
178 |      "output_type": "execute_result"
179 |     }
180 |    ],
181 |    "source": [
182 |     "data = pd.read_csv('Sample scores.csv')\n",
183 |     "data"
184 |    ]
185 |   },
186 |   {
187 |    "cell_type": "code",
188 |    "execution_count": 3,
189 |    "id": "seeing-collaboration",
190 |    "metadata": {},
191 |    "outputs": [
192 |     {
193 |      "data": {
194 |       "image/png": "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\n",
195 |       "text/plain": [
196 |        "<Figure size 432x288 with 1 Axes>"
197 |       ]
198 |      },
199 |      "metadata": {
200 |       "needs_background": "light"
201 |      },
202 |      "output_type": "display_data"
203 |     }
204 |    ],
205 |    "source": [
206 |     "plt.scatter(data['Overs'],data['Scores'])\n",
207 |     "plt.xlabel('x')\n",
208 |     "plt.ylabel('y')\n",
209 |     "plt.show()"
210 |    ]
211 |   },
212 |   {
213 |    "cell_type": "code",
214 |    "execution_count": 4,
215 |    "id": "confused-stuff",
216 |    "metadata": {},
217 |    "outputs": [
218 |     {
219 |      "data": {
220 |       "text/html": [
221 |        "<div>\n",
222 |        "<style scoped>\n",
223 |        "    .dataframe tbody tr th:only-of-type {\n",
224 |        "        vertical-align: middle;\n",
225 |        "    }\n",
226 |        "\n",
227 |        "    .dataframe tbody tr th {\n",
228 |        "        vertical-align: top;\n",
229 |        "    }\n",
230 |        "\n",
231 |        "    .dataframe thead th {\n",
232 |        "        text-align: right;\n",
233 |        "    }\n",
234 |        "</style>\n",
235 |        "<table border=\"1\" class=\"dataframe\">\n",
236 |        "  <thead>\n",
237 |        "    <tr style=\"text-align: right;\">\n",
238 |        "      <th></th>\n",
239 |        "      <th>Scores</th>\n",
240 |        "      <th>Overs</th>\n",
241 |        "    </tr>\n",
242 |        "  </thead>\n",
243 |        "  <tbody>\n",
244 |        "    <tr>\n",
245 |        "      <th>0</th>\n",
246 |        "      <td>15</td>\n",
247 |        "      <td>1</td>\n",
248 |        "    </tr>\n",
249 |        "    <tr>\n",
250 |        "      <th>1</th>\n",
251 |        "      <td>10</td>\n",
252 |        "      <td>2</td>\n",
253 |        "    </tr>\n",
254 |        "    <tr>\n",
255 |        "      <th>2</th>\n",
256 |        "      <td>17</td>\n",
257 |        "      <td>3</td>\n",
258 |        "    </tr>\n",
259 |        "    <tr>\n",
260 |        "      <th>3</th>\n",
261 |        "      <td>10</td>\n",
262 |        "      <td>4</td>\n",
263 |        "    </tr>\n",
264 |        "    <tr>\n",
265 |        "      <th>4</th>\n",
266 |        "      <td>12</td>\n",
267 |        "      <td>5</td>\n",
268 |        "    </tr>\n",
269 |        "    <tr>\n",
270 |        "      <th>5</th>\n",
271 |        "      <td>20</td>\n",
272 |        "      <td>6</td>\n",
273 |        "    </tr>\n",
274 |        "    <tr>\n",
275 |        "      <th>6</th>\n",
276 |        "      <td>10</td>\n",
277 |        "      <td>7</td>\n",
278 |        "    </tr>\n",
279 |        "    <tr>\n",
280 |        "      <th>7</th>\n",
281 |        "      <td>7</td>\n",
282 |        "      <td>8</td>\n",
283 |        "    </tr>\n",
284 |        "    <tr>\n",
285 |        "      <th>8</th>\n",
286 |        "      <td>8</td>\n",
287 |        "      <td>9</td>\n",
288 |        "    </tr>\n",
289 |        "    <tr>\n",
290 |        "      <th>9</th>\n",
291 |        "      <td>11</td>\n",
292 |        "      <td>10</td>\n",
293 |        "    </tr>\n",
294 |        "    <tr>\n",
295 |        "      <th>10</th>\n",
296 |        "      <td>4</td>\n",
297 |        "      <td>11</td>\n",
298 |        "    </tr>\n",
299 |        "    <tr>\n",
300 |        "      <th>11</th>\n",
301 |        "      <td>14</td>\n",
302 |        "      <td>12</td>\n",
303 |        "    </tr>\n",
304 |        "    <tr>\n",
305 |        "      <th>12</th>\n",
306 |        "      <td>3</td>\n",
307 |        "      <td>13</td>\n",
308 |        "    </tr>\n",
309 |        "    <tr>\n",
310 |        "      <th>13</th>\n",
311 |        "      <td>6</td>\n",
312 |        "      <td>14</td>\n",
313 |        "    </tr>\n",
314 |        "    <tr>\n",
315 |        "      <th>14</th>\n",
316 |        "      <td>11</td>\n",
317 |        "      <td>15</td>\n",
318 |        "    </tr>\n",
319 |        "    <tr>\n",
320 |        "      <th>15</th>\n",
321 |        "      <td>13</td>\n",
322 |        "      <td>16</td>\n",
323 |        "    </tr>\n",
324 |        "    <tr>\n",
325 |        "      <th>16</th>\n",
326 |        "      <td>20</td>\n",
327 |        "      <td>17</td>\n",
328 |        "    </tr>\n",
329 |        "    <tr>\n",
330 |        "      <th>17</th>\n",
331 |        "      <td>16</td>\n",
332 |        "      <td>18</td>\n",
333 |        "    </tr>\n",
334 |        "    <tr>\n",
335 |        "      <th>18</th>\n",
336 |        "      <td>26</td>\n",
337 |        "      <td>19</td>\n",
338 |        "    </tr>\n",
339 |        "    <tr>\n",
340 |        "      <th>19</th>\n",
341 |        "      <td>30</td>\n",
342 |        "      <td>20</td>\n",
343 |        "    </tr>\n",
344 |        "  </tbody>\n",
345 |        "</table>\n",
346 |        "</div>"
347 |       ],
348 |       "text/plain": [
349 |        "    Scores  Overs\n",
350 |        "0       15      1\n",
351 |        "1       10      2\n",
352 |        "2       17      3\n",
353 |        "3       10      4\n",
354 |        "4       12      5\n",
355 |        "5       20      6\n",
356 |        "6       10      7\n",
357 |        "7        7      8\n",
358 |        "8        8      9\n",
359 |        "9       11     10\n",
360 |        "10       4     11\n",
361 |        "11      14     12\n",
362 |        "12       3     13\n",
363 |        "13       6     14\n",
364 |        "14      11     15\n",
365 |        "15      13     16\n",
366 |        "16      20     17\n",
367 |        "17      16     18\n",
368 |        "18      26     19\n",
369 |        "19      30     20"
370 |       ]
371 |      },
372 |      "execution_count": 4,
373 |      "metadata": {},
374 |      "output_type": "execute_result"
375 |     }
376 |    ],
377 |    "source": [
378 |     "df = DataFrame(data,columns=['Scores','Overs'])\n",
379 |     "df"
380 |    ]
381 |   },
382 |   {
383 |    "cell_type": "code",
384 |    "execution_count": 5,
385 |    "id": "dependent-gibson",
386 |    "metadata": {},
387 |    "outputs": [],
388 |    "source": [
389 |     "kmeans = KMeans(n_clusters=3).fit(df)"
390 |    ]
391 |   },
392 |   {
393 |    "cell_type": "code",
394 |    "execution_count": 6,
395 |    "id": "closing-jacksonville",
396 |    "metadata": {},
397 |    "outputs": [
398 |     {
399 |      "name": "stdout",
400 |      "output_type": "stream",
401 |      "text": [
402 |       "[[13.42857143  4.        ]\n",
403 |       " [23.         18.5       ]\n",
404 |       " [ 8.55555556 12.        ]]\n"
405 |      ]
406 |     }
407 |    ],
408 |    "source": [
409 |     "centroids = kmeans.cluster_centers_\n",
410 |     "print(centroids)"
411 |    ]
412 |   },
413 |   {
414 |    "cell_type": "code",
415 |    "execution_count": 7,
416 |    "id": "handy-proportion",
417 |    "metadata": {},
418 |    "outputs": [
419 |     {
420 |      "data": {
421 |       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAEGCAYAAABiq/5QAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8+yak3AAAACXBIWXMAAAsTAAALEwEAmpwYAAAhoUlEQVR4nO3deZhcZZn38e9dW+9Ntg6EEAiQYIQoARtkiRJQAUEFHEkAF3QY4ygjMiLCoO/AMA7zzjCAvi5oGJCgAkFAQSYqDMsAKpqORJZkQoIEWULS2Xtfqu73j1OddNJVne6kq05Vn9/nuvrq6uepqnPnUPz69HOe8xxzd0REJDpiYRcgIiLFpeAXEYkYBb+ISMQo+EVEIkbBLyISMYmwCxiKCRMm+NSpU8MuQ0SkrCxdunSDuzfs2l4WwT916lSamprCLkNEpKyY2au52jXUIyISMQp+EZGIUfCLiESMgl9EJGLK4uSuiMhIaOnq4u4XnuPnK1fg7pw5/W18/J1HMqayKuzSiqpgwW9mlcCTQEV2O/e6+9VmdjBwNzAeWAp80t27C1WHiAjA5o4OPnL3j9nY0U5nby8Ar2zZzI+eW8YD532CfWtrQ66weAo51NMFnOLuRwKzgNPN7Djg34Cb3H0asBm4qIA1iIgAcP1vn2J9W+v20AfoSqfZ2NHOPz/5eIiVFV/Bgt8Drdkfk9kvB04B7s22LwTOLlQNIiJ9Hli5gp5MZkB72p1H/ryannQ6hKrCUdCTu2YWN7NlwHrgEeBlYIu79/3KfR2YnOe1882sycyampubC1mmiIxy7r7Tkf6uMu50K/hHhrun3X0WcABwLDBjGK9d4O6N7t7Y0DDgimMRkSEzM6aPG5+3f7/aOqqTySJWFK6iTOd09y3A48DxwBgz6zupfADwRjFqEJFou/yE91CZGDifpSqR4CvHn4iZhVBVOAoW/GbWYGZjso+rgA8AKwh+AXws+7QLgQcKVYOISJ/3HXIo15x0CrWp1Pav6mSSy094D2fNODzs8oqqkPP4JwELzSxO8AvmHnd/yMyWA3eb2TeAZ4FbC1iDiMh2c494B2fPOJxlb63F3Zm13yQqcvwVMNoV7F/s7s8BR+Vo/zPBeL+ISNGl4nGOnXxA2GWESks2iIhEjIJfRCRiFPwiIhGj4BcRiRgFv4hIxCj4RUQiRsEvIhIxCn4RkYhR8IuIRIyCX0QkYhT8IiIRo+AXEYkYBb+ISMQo+EVEIkbBLyISMQp+EZGIUfCLiESMgl9EJGIU/CIiERO9uwyLyKiwtqWFX65+ibaebo7Z/wDePfkAzCzsssqCgl9Eys7NS37P//vD7wDoTqepSiY5eMxYfnzOuexTWRlydaVPQz0iUlae+ssavrPkGbrSabrSaRxo7+nhpY0buOzhX4ZdXllQ8ItIWflB0x/o6O0d0N6TyfD0a6/S3N4WQlXlRcEvImXllS1b8vZVxOO8sW1b8YopUwp+ESkrB9TX5+3rTqeZVFtXxGrKk4JfRMrK/KOPoSqRHNCeiMVo3H8y+9bWhlBVeVHwi0hZed8hh/LJd86iMpEgEQsirCaZ5ID6em467cyQqysPms4pImXnytnvZe4RM3lw5f/S0t3FcZOncPLBh2z/RSCDK1jwm9kU4A5gX8CBBe7+LTO7Bvgs0Jx96lXuvrhQdYjI6HTI2HFcetwJYZdRlgp5xN8LXObufzSzOmCpmT2S7bvJ3f+jgNsWEZE8Chb87r4WWJt93GJmK4DJhdqeiIgMTVEGxMxsKnAU8Pts09+Z2XNmdpuZjc3zmvlm1mRmTc3NzbmeIiIie6DgwW9mtcB9wKXuvg24GTgUmEXwF8ENuV7n7gvcvdHdGxsaGgpdpohIZBQ0+M0sSRD6P3H3+wHcfZ27p909A9wCHFvIGkREZGcFC34L1ke9FVjh7jf2a5/U72nnAC8UqgYRERmokLN6TgQ+CTxvZsuybVcB55vZLIIpnmuAzxWwBhER2UUhZ/U8DeS6K4Lm7IuIhEiXuYmIRIyCX0QkYhT8IiIRo+AXEYkYBb+ISMQo+EVEIkbBLyISMQp+EZGIUfCLiESMgl9EJGIU/CIiEaPgFxGJGAW/iEjEKPhFRCJGwS8iEjEKfhGRiFHwi4hEjIJfRCRiFPwiIhGj4BcRiRgFv4hIxCj4RUQiRsEvIhIxCn4RkYhR8IuIRIyCX0QkYhJhFyDFs/4vzTxyx/+w4Y1NvO2Yacw570QqqyvCLktGia2dnfzsf5ezatNGDh4zlo++/XDGVVWHXZbkYO5emDc2mwLcAewLOLDA3b9lZuOARcBUYA0w1903D/ZejY2N3tTUVJA6o+KhHzzMzX9/O55xerp7qaypJFWZ4IYnrmXqEVPCLk/K3DOvv8bf/OJnZNzp7O2lMpHAgO+e8RHmTD047PIiy8yWunvjru2FHOrpBS5z98OB44CLzexw4ErgUXefDjya/VkKaM2Lr/H9Ly+ku7OHnu5eADrbOmnZ1MrXzryOQv3yl2ho6+7ms7/4Ge09PXT2Zj9fvb109PZy8eIH2dLZEXKFsquCBb+7r3X3P2YftwArgMnAWcDC7NMWAmcXqgYJPPjdX20P/P7coWVTK88/tSKEqmS0WLz6JfIdOjjwwP/q81VqinJy18ymAkcBvwf2dfe12a63CIaCcr1mvpk1mVlTc3NzMcoctV5/6U0y6Uze/nWvav/Knntj2zbae3py9nX29vLq1i3FLUh2q+DBb2a1wH3Ape6+rX+fB2MMOQ8W3H2Buze6e2NDQ0OhyxzVDn7nQSSS8Zx97s4Bh+1f5IpkNDl47FhqksmcfdWJJIeNn1DkimR3Chr8ZpYkCP2fuPv92eZ1ZjYp2z8JWF/IGgTOuvh04omBwR+LGRMPnMCMY6eFUJWMFqcfOp1kLPeBRSxmfOiwGUWuSHanYMFvZgbcCqxw9xv7dT0IXJh9fCHwQKFqkMD+h+7HFT+6hIqqFJU1FcRiRlVdJQ1TJnDd4q8R/KcS2TMViQR3nPMxxlRUUpNMEsOoSSapS1Vw+1l/RW0qFXaJsotCTuecDTwFPA/0DTBfRTDOfw9wIPAqwXTOTYO9l6Zzjoy2rW08ee8zbF63lUOPPIjG02cRj+c+UhMZrq7eXv77zy+zZusWDqiv57RDp1GZyD0EJMWRbzpnwYJ/JCn4RUSGL4x5/CIiUoK0ZIOISClqaYFFi2DVKpg+HebNg7q6EXlrBb+ISKl5+mk44wzIZKCtDWpq4MtfhsWLYfbsvX57DfWIiJSSlpYg9FtagtCH4Htfe2vrXm9CwS8iUkoWLQqO9HPJZIL+vaTgFxEpJatW7TjS31VbG6xevdebGFLwm9mhZlaRfTzHzC4xszF7vXUREdnZ9OnBmH4uNTUwbe+vtB/qEf99QNrMpgELgCnAnXu9dRER2dm8eRDLE82xWNC/l4Ya/Bl37wXOAb7t7pcDk/Z66yIisrO6umD2Tl3djiP/mpod7bW1e72JoU7n7DGz8wnW1vlwtk3XYouIFMLs2fDmm8GJ3NWrg+GdefNGJPRh6MH/GeBvgX9x91fM7GDgRyNSgYiIDFRbCxddVJC3HlLwu/tyM7uCYGE13P0V4N8KUpGIiBTUkILfzD4M/AeQAg42s1nAte7+kQLWVja6u3p4+v7fs+TXy6iuq+T9nziJGcdO03LHIlKShjrUcw1wLPAEgLsvM7NDClRTWdn01ma+dMLX2bphGx2tnVjM+PUPn+Ckc4/nK7d9QeEvIiVnqLN6etx96y5t+W/iGiH/fuF3aH59Ix2tnQB4xulq7+LJe3/HY3c+HXJ1IiIDDTX4XzSzC4C4mU03s28Dvy1gXWVh87otPPfkCtK96QF9nW1d3HvjL0KoSkRkcEMN/i8CRwBdBBdubQUuLVBNZWPTW1tIVuQfLdv45qA3FhMRCcVux/jNLA78l7ufDHyt8CWVj30PaqCnqzdv/5QZk4tYjYjI0Oz2iN/d00DGzPYpQj1lpXZMDSfNPZ5U5cBr2SqqKzj/Hz4aQlUiIoMb6qyeVuB5M3sE2L5snLtfUpCqysiXbp7Pxjc3s/x3K8mkM8QTcdK9GS68di6Npx4ZdnkiJc/dWbGhmea2NqaPH8/+dfVhlzTqDTX4789+yS4qqyv490f+kdXLXuH5J1dQUV3BCWc1MqZBfyCJ7M7KjRv4/EMPsL69jbgZ3ek0J045iG+efia1qVTY5Y1a5u5De6JZCjgs++NKd+8pWFW7aGxs9KampmJtTkSKYEtnB3MW3sq2rq6d2lPxOO+atD8/+ejckCobPcxsqbs37to+1PX45wCrgO8C3wNeMrP3jmSBIhIti158ge4cU6G702mefWstL23cEEJV0TDUoZ4bgFPdfSWAmR0G3AW8q1CFicjo9szrf6EznXtWXMyMP617i8PGTyhyVdEw1Hn8yb7QB3D3l9CyzCKyF8ZXVZNvQZOYGWMqKotaT5QMNfibzOw/s7ddnGNmtwAadBeRPTZv5juoTOQedHB33nvQ1OIWFCFDDf7PA8uBS7Jfy7NtIiJ7pHHSZM6ZcTjViR2DBzEzKhMJvnnamVTk+aUge29Is3rMrAbozF7M1Xc1b4W7txe4PmD4s3o2r9vCwqsX8fhdv6G7q4cZ757GRdd9nJknzihglSIyXO7OE6++wsI/Pcu61lbeue9+/M1RjUwfPz7s0kaFfLN6hhr8zwDvd/fW7M+1wMPufsIgr7kN+BCw3t1nZtuuAT4LNGefdpW7L97d9ocT/Ns2tjD/yMvY0ryNdM+OGQMVVSn+8d6vcOwHjxrS+4iIlLu9ms4JVPaFPkD2cfVuXnM7cHqO9pvcfVb2a7ehP1z33vgLtm1s2Sn0Abo6uvnm3/6AoV63ICIyWg01+NvM7Oi+H8ysEegY7AXu/iRQ9OUpH7vz6bwLp7VsauW1lW8WuSIRkdIy1LMnlwI/NbO+1JwEzNvDbf6dmX2KYFbQZe6+OdeTzGw+MB/gwAMPHPKb51obv997DtovIhIFgx7xm9kxZrafuy8BZgCLgB7gV8Are7C9m4FDgVnAWoILw3Jy9wXu3ujujQ0NDUPewPEfaSSejOfsS1YkOfDtWipZRKJtd0M9PwC6s4+PB64iWLZhM7BguBtz93Xunnb3DHALwX18R9R5V5xNZU3FgHvdVlSnmH/9J4nHc/9SEBGJit0Ff9zd+8bp5wEL3P0+d/8/wLThbszMJvX78RzgheG+x+5MPLCBb//uOo48+QgSyTiJVIKJB03gK7d+gdM+ffJIb04iynteIrP1n8ls/jyZ1h/gGd1tTcrH7sb442aWcPde4H1kx9yH8lozuwuYA0wws9eBq4E5ZjYLcGAN8Lk9K3twU942mev/+2o6Wjvo7uyhfnzdgL8ARPZUpnUBtH6HYNQzDV2/wdu+D2Nvx1K6B4OUvt0F/13A/5jZBoJZPE8BmNk0gvvu5uXu5+dovnVPitxTVbVVVNVWFXOTMsp5z/Js6Hf2a+0EB9/8OZj4G4LrG0VK16DB7+7/YmaPEsziedh3TIKPEdyAXSRSvP0n7Djttasu6H4GKk4sZkkiw7bb6Zzu/kyOtpcKU45IiUu/CWTydDpk1hezGpE9MtQLuEQEIPkOIN8tAR0S04tZjcgeUfCLDINVXwA5x/DjED8YS84sek0iw6XgFxkGi++Hjfk+WC1YDVAJVgWJadjYW8Iub8R472t458N49xKCy25kNNGC1yLDZBXHw8RnoOt/ILMREjMgeeSomDLsmTZ8y6XBSWpLAg5WDWO+g6W0su1ooeAX2QNmKaj8QNhljDjf8qUg9OkG78o2tuGbPwMTfoXF9wu1PhkZGuoREQC89y/Q/XtyTlf13uxUVhkNFPwiEuh9ESzfIEA3dC8pajlSOAp+EQnY2MH7YxOKU4cUnIJfRAKpY4CK3H1WhVXnWoVFypGCv4zpNpIykszi2NhvB9NTSfbrqILKD0Mq7y22pcxoVk+ZSafT3HvDL7jvpofYvG4rYybW81eXfohzv/IR4okyWxyspQUWLYJVq2D6dJg3D+rqwq4q0ix1DExYjLfdAd1/hPgErPrjkDpxVExXlYCVw1FjY2OjNzU1hV1GSfjGeTfxzENNdLXvmHlRUZ3imNOP4up7vxJiZcP09NNwxhmQyUBbG9TUQCwGixfD7NlhVycyKpjZUndv3LVdQz1l5OU/rRkQ+gBd7d0s+dUyVv3xzyFVNkwtLUHot7QEoQ/B97721tZw6xMZ5RT8ZeS3Dy6hp6s3Z19PZze/+fkfilzRHlq0KDjSzyWTCfpFpGAU/GXEMw55hubcy+hk76pVO470d9XWBqtXF7cekYhR8JeRd5/5LpKVuZcErqhOcdyHBgzllabp04Mx/VxqamDasG/nLCLDoOAvI29rPJRZJx9Bqmrn8E9VpZg5++3MOLZMAnPevOBEbi6xWNAvIgWj4C8z19x/OR/7+w9RXV9FPBGjuq6Kcy45g2sf+Gr5TLerqwtm79TV7Tjyr6nZ0V5bO+y39HQzmZZvk9n0GTJbrsC7nx3hosuPZ1rJtP2YzKaLyGz+It75uJZYFkDTOctWJpOhq72LiuoKYvmOnktda2twInf16mB4Z968PQv97mX45k+Dp4EuguOZCqi+gFj9FSNcdHnw9Jv4xnMh0wp0BI1WDclGbOz3sbxr8shokm86p/7rl6lYLEZVbVXYZeyd2lq46KK9egv3NL7lC+Dt/VozQAe034lXvh9LvWuvtlGOfMsVwb0C+t8f2Nuhewnefg9Wc0FotUn4yvRQUSSrewl4R57OzkguJezpDdDzLLlvCt8B7XcUuyQpMQp+KW+ZDYN0OqTfKlopJSOzOXv3rHz9m4pXi5QkBb+Ut+SM7Nh+LilIzSpmNaUhPnmQfUKwzyTSFPxS1iwxDZIz2Wk1ye2dcaz6E0WvKWwWq4bquUBljt5KrObiYpckJUYnd3fRsrmVZx99Hnc46n0zqR9X2NUiX13+GqufXcOYifXMOnlmSa6w2dXRxR//+3k6WjuZeeLbmHhgQ9gl7cTG3oxv/lvoeREsBhiQwMZ8G4vvH3Z5obC6K/DMZuh8GCwOxIK/Auq/jlW8O+zyJGQK/ix3545/+in3/PvPSSSD3dLb08vcr57Np64+d8TnyLdsbuWac65nZdNqYvEYhpGsSHDN/Zczc/bbR3Rbe+Pxu3/DjfO/TyxmuDu9PWlmn/NuLv/hF0imBhlHLiKL7YONvwvvWQm9yyE2DlInYIONc49yZklszA14+g3obgKrhNRsLJbnimmJlILN4zez24APAevdfWa2bRywCJgKrAHmuvvm3b1XMebx//K2R/nel35IZ1vXTu2V1RV84Vuf4YMXvW9Et3fZnKtZ/sxL9HbvvOhaZW0lP1zxTSZMHj+i29sTy595ia++/58GrAZaUZXiAxfO4Uvf+2xIlYnIUISxLPPtwOm7tF0JPOru04FHsz+XhB9fe++A0AfobO/iR9f+dES39ery11i5ZPWA0AdI96R58Hu/HtHt7ak7r7uf7o7uAe1dHd08fPvjtG1rz/EqESl1BQt+d38S2HXe2FnAwuzjhcDZhdr+cPT29NL8Wv5pgRve2ERPd8+Ibe/lZWuIJXLv+p6uHl787coR29beWLX0z/kWAyWRSvDm6ghOlRQZBYo9q2dfd1+bffwWsG++J5rZfDNrMrOm5ubmghYVT8RJ5Vn1EiBVkdw+7j8SxkzcByP3OQMzK4lhHoB9GvKf2O7t7mWfhvoiViMiIyW06ZwenFzIe4LB3Re4e6O7NzY0FHYWiZlx6qfnkEgNDPdkKsEHLjxpRE/uHnnyESQrc594TFWl+PDnTx2xbe2Nj15yJpU1FQPaLWYccuRUJk6ZEEJVIrK3ih3868xsEkD2+/oibz+vi667gMnT9tsp6CprKth/2n78zb9+fES3FY/Hueb+y6mqrSRZEfwCMDMqqiv4yBdOY+aJpXGBzQcuPIlZp7yDytod88ErqlPUj6vlH358SYiVicjeKOjqnGY2FXio36ye64GN7v5/zexKYJy7f3V371Os1Tm7u3p48qe/47E7n8LdOeWC93DS3BNIVRRmWuCGNzfx0M2/5oXfrGTC5HF8+POnccQJbyvItvZUJpNhyS+f5Ze3PUbblnbefebRnP7Xp1A7RtMCRUpdvlk9hZzOeRcwB5gArAOuBn4O3AMcCLxKMJ1ztwuHaFlmEZHhK/qyzO5+fp6ukZ0QLyIiw6K1ekREIkbBLyISMQp+EZGIUfCLiESMVueUkuKZLXj7PdD1BFg1Vv0xqPgAZqW3XLVIuVLwS8nw3r/gG8/N3jg9WDDPe5ogeReM/c9IL7MsMpI01CMlw7deDr6VvtAPGtuh+1m8fVFodYmMNgp+KQmeXhfcQYtMjt5OaP9xsUsSGbUU/FIaMlthsKEc31K0UkRGOwW/lIbEFPBcR/t9/UcUrxaRUU7BLyXBrAqqzwOqcvRWYrUXF7skkVFLs3qkYDy9AbqfBhxSJ2LxiYM+3+oux70FOh7MDvtY8Nr6b2Cpo4tRskgkKPhlxLk73nI9tN8Blv2IeS9e/XGs7sq8N7UxS2D7XIfXXgo9z4JVQeo4zPLfHU1Ehk/BLyPO2++B9p8A3eD9btbecTcen4LVfGLQ11t8IsRPK2yRIhGmMX4ZeW3fAzoGtnsHtN1MIW/+IyK7p+CXEeWehsza/E/IbAS68/eLSMEp+GWExcAGuy1jBaClF0TCpOCXEWVmUHUukOuEbAqqPoqZPnYiYdL/gTLirPZSSEwHq+7XWg2JQ7C6y8Iqq+x5pg3PtIZdhowCmtUjI85i1TD+p9D1KN7xEOBY1ZlQ8X6tsLkHvHsZvu1a6F0R/Jw4DKv/OpY6JuTKpFwp+KUgzBJQeRpWqWmZe8N7nsc3fQro3NHYuwLfdBGM+yGWeldotUn50lCPSAnzbf/GTqG/XSfe8q/FLkdGCQW/SIlyd+hpyv+Enhdw19RYGT4Fv0hJy728hcjeUPCLlCgzg9R7yBv+qWO0jpHsEQW/SAmz+iuy02L7h78FN6KvuyqssqTMKfhFSpglDsXG3wcV7ye4KC4JqTnYuHuw5NvDLk/KVCjTOc1sDdACpIFed28Mow6RcmCJQ7Cx3w27DBlFwpzHf7K7bwhx+yIikaShHhGRiAkr+B142MyWmtn8XE8ws/lm1mRmTc3NzUUuT0Rk9Aor+Ge7+9HAB4GLzey9uz7B3Re4e6O7NzY0NBS/QhGRUSqU4Hf3N7Lf1wM/A44Now4RkSgqevCbWY2Z1fU9Bk4FXih2HSIQ3DHMu57A2+7AOx/DvTfskkQKLoxZPfsCPzOzvu3f6e6/CqEOiTjvWYVv/jR4O3gPWBKogHG3YcnDi1tMSwssWgSrVsH06TBvHtTVFbcGiQwrhxtfNzY2elPTIItViQyTeze+/j3gmwd22j7YxCcxqypOMU8/DWecAZkMtLVBTQ3EYrB4McyeXZwaZFQys6W5rpPSdE6Jps6HyXvTd++Bzl8Wp46WliD0W1qC0Ifge197q+64JSNPwS+R5L2rwdvy9LbjPSuLU8iiRcGRfi6ZTNAvMsIU/BJJFt8P8g7lVEJ8/+IUsmrVjiP9XbW1werVxalDIkXBL9FUeUZwGWEeVvXh4tQxfXowpp9LTQ1Mm1acOiRSFPwSSRarx8Z8E6gkWPWS7PdK2Oc/sNi4gm3bM9vw9HrcM8HsnVie/w1jsaBfZITpZusSWVZ5MjQ8grffA+mXIX4IVj03GAYqAO99Gd/6j9CzDIhBrB6v/TKxxYvzz+qprS1ILRJtCn6JNIvvi9V9seDb8fRafONc8Fa2jzFlmmHbP5E56gpib74ZnMhdvToY3pk3T6EvBaPgFykCb70FvIOBJxY6ofVGfOJc7KKLwihNIkhj/CLF0PUYkG85iAz0ripmNRJxCn6RYrDB/rjOoD++pZgU/CLFUHkWO2YP7cLqITG9qOVItCn4RYrAai6EWAOQ3KWnEtvnG2QXLRQpCgW/SBFYrB6bcD9Unw82BqiE1HHYuIVYxUlhlycRo4FFkSKx2Fis/utQ//WwS5GI0xG/iEjEKPhFRCJGwS8iEjEKfhGRiFHwi4hETFncc9fMmoE2YEPYtZSgCWi/7Er7ZCDtk4GisE8OcveGXRvLIvgBzKwp102Do077ZSDtk4G0TwaK8j7RUI+ISMQo+EVEIqacgn9B2AWUKO2XgbRPBtI+GSiy+6RsxvhFRGRklNMRv4iIjAAFv4hIxJRF8JvZ6Wa20sxWm9mVYddTCsxsjZk9b2bLzKwp7HrCYGa3mdl6M3uhX9s4M3vEzFZlv48Ns8Yw5Nkv15jZG9nPyzIzOyPMGovJzKaY2eNmttzMXjSzL2XbI/tZKfngN7M48F3gg8DhwPlmdni4VZWMk919VlTnIgO3A6fv0nYl8Ki7Twcezf4cNbczcL8A3JT9vMxy98VFrilMvcBl7n44cBxwcTZDIvtZKfngB44FVrv7n929G7gbOCvkmqQEuPuTwKZdms8CFmYfLwTOLmZNpSDPfoksd1/r7n/MPm4BVgCTifBnpRyCfzLwWr+fX8+2RZ0DD5vZUjObH3YxJWRfd1+bffwWsG+YxZSYvzOz57JDQZEZ1ujPzKYCRwG/J8KflXIIfslttrsfTTAEdrGZvTfsgkqNB3OVNV85cDNwKDALWAvcEGo1ITCzWuA+4FJ339a/L2qflXII/jeAKf1+PiDbFmnu/kb2+3rgZwRDYgLrzGwSQPb7+pDrKQnuvs7d0+6eAW4hYp8XM0sShP5P3P3+bHNkPyvlEPxLgOlmdrCZpYDzgAdDrilUZlZjZnV9j4FTgRcGf1VkPAhcmH18IfBAiLWUjL6AyzqHCH1ezMyAW4EV7n5jv67IflbK4srd7NSzbwJx4DZ3/5dwKwqXmR1CcJQPkADujOI+MbO7gDkEy+uuA64Gfg7cAxwIvArMdfdInejMs1/mEAzzOLAG+Fy/8e1RzcxmA08BzwOZbPNVBOP8kfyslEXwi4jIyCmHoR4RERlBCn4RkYhR8IuIRIyCX0QkYhT8IiIRo+AXyTKzA8zsgexqjS+b2bey146IjCoKfhG2X+RzP/Dz7GqNhwG1wF5dH2FmiREoT2REKfhFAqcAne7+QwB3TwN/D/y1mf3BzI7oe6KZPWFmjdkrqG/L9j9rZmdl+z9tZg+a2WPAo2Y2ycyezK6D/4KZvSeMf6BIHwW/SOAIYGn/huxCXn8B/guYC9uXPpjk7k3A14DH3P1Y4GTg+uwSGgBHAx9z95OAC4Bfu/ss4EhgWcH/NSKDUPCL7N4TwMeyj+cC92YfnwpcaWbLss+pJLj8H+CRfpf/LwE+Y2bXAO/IrgkvEhoFv0hgOfCu/g1mVk8Q5EuAjWb2TmAesKjvKcBf9bur1YHuviLb19b3Ptkbo7yXYFXZ283sU4X9p4gMTsEvEngUqO4L5ewtP28Abnf3doKw/yqwj7s/l33Nr4EvZk8MY2ZH5XpjMzsIWOfutwD/STAMJBIaBb8I22/EcQ5wrpmtAl4COglWcYRgeOc8gtUc+/wzkASeM7MXsz/nMgf4k5k9S/AXw7dG/B8gMgxanVNEJGJ0xC8iEjEKfhGRiFHwi4hEjIJfRCRiFPwiIhGj4BcRiRgFv4hIxPx/GFp8h8IzitIAAAAASUVORK5CYII=\n",
422 |       "text/plain": [
423 |        "<Figure size 432x288 with 1 Axes>"
424 |       ]
425 |      },
426 |      "metadata": {
427 |       "needs_background": "light"
428 |      },
429 |      "output_type": "display_data"
430 |     }
431 |    ],
432 |    "source": [
433 |     "plt.scatter(df['Overs'], df['Scores'],c= kmeans.labels_.astype(float), s=50, alpha=1)\n",
434 |     "plt.scatter(centroids[:, 0], centroids[:, 1], c='red', s=50)\n",
435 |     "plt.xlabel('Overs')\n",
436 |     "plt.ylabel('Scores')\n",
437 |     "plt.show()"
438 |    ]
439 |   },
440 |   {
441 |    "cell_type": "code",
442 |    "execution_count": null,
443 |    "id": "attractive-national",
444 |    "metadata": {},
445 |    "outputs": [],
446 |    "source": []
447 |   }
448 |  ],
449 |  "metadata": {
450 |   "kernelspec": {
451 |    "display_name": "Python 3",
452 |    "language": "python",
453 |    "name": "python3"
454 |   },
455 |   "language_info": {
456 |    "codemirror_mode": {
457 |     "name": "ipython",
458 |     "version": 3
459 |    },
460 |    "file_extension": ".py",
461 |    "mimetype": "text/x-python",
462 |    "name": "python",
463 |    "nbconvert_exporter": "python",
464 |    "pygments_lexer": "ipython3",
465 |    "version": "3.8.8"
466 |   }
467 |  },
468 |  "nbformat": 4,
469 |  "nbformat_minor": 5
470 | }
471 | 


--------------------------------------------------------------------------------
/Decision_Tree.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |   "nbformat": 4,
  3 |   "nbformat_minor": 0,
  4 |   "metadata": {
  5 |     "colab": {
  6 |       "name": "Decision Tree.ipynb",
  7 |       "provenance": [],
  8 |       "authorship_tag": "ABX9TyOROAalO6i5bSeT2NjVmuLB",
  9 |       "include_colab_link": true
 10 |     },
 11 |     "kernelspec": {
 12 |       "name": "python3",
 13 |       "display_name": "Python 3"
 14 |     },
 15 |     "language_info": {
 16 |       "name": "python"
 17 |     }
 18 |   },
 19 |   "cells": [
 20 |     {
 21 |       "cell_type": "markdown",
 22 |       "metadata": {
 23 |         "id": "view-in-github",
 24 |         "colab_type": "text"
 25 |       },
 26 |       "source": [
 27 |         "<a href=\"https://colab.research.google.com/github/akpythonyt/ML-algorithms/blob/main/Decision_Tree.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
 28 |       ]
 29 |     },
 30 |     {
 31 |       "cell_type": "code",
 32 |       "execution_count": 3,
 33 |       "metadata": {
 34 |         "colab": {
 35 |           "base_uri": "https://localhost:8080/"
 36 |         },
 37 |         "id": "ex889e5uNZHJ",
 38 |         "outputId": "e3215fb7-e1db-40af-83de-f76ed01bca7f"
 39 |       },
 40 |       "outputs": [
 41 |         {
 42 |           "output_type": "execute_result",
 43 |           "data": {
 44 |             "text/plain": [
 45 |               "0    203\n",
 46 |               "1     96\n",
 47 |               "Name: DEATH_EVENT, dtype: int64"
 48 |             ]
 49 |           },
 50 |           "metadata": {},
 51 |           "execution_count": 3
 52 |         }
 53 |       ],
 54 |       "source": [
 55 |         "# importing libraries  \n",
 56 |         "import numpy as nm  \n",
 57 |         "import matplotlib.pyplot as mtp  \n",
 58 |         "import pandas as pd  \n",
 59 |         "  \n",
 60 |         "#importing datasets  \n",
 61 |         "data_set= pd.read_csv('/content/heart_failure_clinical_records_dataset.csv')  \n",
 62 |         "  \n",
 63 |         "#Extracting Independent and dependent Variable  \n",
 64 |         "data_set.DEATH_EVENT.value_counts()\n",
 65 |         "  \n"
 66 |       ]
 67 |     },
 68 |     {
 69 |       "cell_type": "code",
 70 |       "source": [
 71 |         "#feature allocation\n",
 72 |         "X=data_set.drop([\"DEATH_EVENT\"],axis=1)\n",
 73 |         "y=data_set[\"DEATH_EVENT\"]"
 74 |       ],
 75 |       "metadata": {
 76 |         "id": "azj_jpjyO80e"
 77 |       },
 78 |       "execution_count": 5,
 79 |       "outputs": []
 80 |     },
 81 |     {
 82 |       "cell_type": "code",
 83 |       "source": [
 84 |         "# Splitting the dataset into training and test set.  \n",
 85 |         "from sklearn.model_selection import train_test_split  \n",
 86 |         "x_train, x_test, y_train, y_test= train_test_split(X, y, test_size= 0.25, random_state=0)  "
 87 |       ],
 88 |       "metadata": {
 89 |         "id": "rxi68tNYO9OE"
 90 |       },
 91 |       "execution_count": 6,
 92 |       "outputs": []
 93 |     },
 94 |     {
 95 |       "cell_type": "code",
 96 |       "source": [
 97 |         ""
 98 |       ],
 99 |       "metadata": {
100 |         "id": "DhHNpvlNP2sV"
101 |       },
102 |       "execution_count": 3,
103 |       "outputs": []
104 |     },
105 |     {
106 |       "cell_type": "code",
107 |       "source": [
108 |         "#Fitting Decision Tree classifier to the training set  \n",
109 |         "from sklearn.tree import DecisionTreeClassifier  \n",
110 |         "classifier= DecisionTreeClassifier(criterion='entropy', random_state=0)  \n",
111 |         "classifier.fit(x_train, y_train)  "
112 |       ],
113 |       "metadata": {
114 |         "colab": {
115 |           "base_uri": "https://localhost:8080/"
116 |         },
117 |         "id": "wRd1hpbkPiK8",
118 |         "outputId": "0bb6e6b3-717c-48f7-ff64-8f98c5905488"
119 |       },
120 |       "execution_count": 10,
121 |       "outputs": [
122 |         {
123 |           "output_type": "execute_result",
124 |           "data": {
125 |             "text/plain": [
126 |               "DecisionTreeClassifier(criterion='entropy', random_state=0)"
127 |             ]
128 |           },
129 |           "metadata": {},
130 |           "execution_count": 10
131 |         }
132 |       ]
133 |     },
134 |     {
135 |       "cell_type": "code",
136 |       "source": [
137 |         "y_pred= classifier.predict(x_test)"
138 |       ],
139 |       "metadata": {
140 |         "id": "GuUiw3NgPoz0"
141 |       },
142 |       "execution_count": 11,
143 |       "outputs": []
144 |     },
145 |     {
146 |       "cell_type": "code",
147 |       "source": [
148 |         "print(y_pred)"
149 |       ],
150 |       "metadata": {
151 |         "colab": {
152 |           "base_uri": "https://localhost:8080/"
153 |         },
154 |         "id": "ndKQQVzFPwed",
155 |         "outputId": "bffd3833-a348-46ff-818d-a5c5462f09d4"
156 |       },
157 |       "execution_count": 16,
158 |       "outputs": [
159 |         {
160 |           "output_type": "stream",
161 |           "name": "stdout",
162 |           "text": [
163 |             "[0 1 1 0 0 0 1 0 1 0 0 1 1 0 0 1 0 0 0 0 1 1 0 0 1 0 1 0 0 0 0 1 1 0 0 1 0\n",
164 |             " 1 0 1 0 1 0 0 1 0 0 1 1 1 0 0 0 0 1 1 0 1 0 0 1 0 1 0 0 0 0 0 1 1 0 0 0 1\n",
165 |             " 0]\n"
166 |           ]
167 |         }
168 |       ]
169 |     },
170 |     {
171 |       "cell_type": "code",
172 |       "source": [
173 |         ""
174 |       ],
175 |       "metadata": {
176 |         "id": "OM2JwcQ7Q9B7"
177 |       },
178 |       "execution_count": 9,
179 |       "outputs": []
180 |     },
181 |     {
182 |       "cell_type": "code",
183 |       "source": [
184 |         "from sklearn.metrics import confusion_matrix  \n",
185 |         "cm= confusion_matrix(y_test, y_pred)  "
186 |       ],
187 |       "metadata": {
188 |         "id": "YbVRNx-DPzAp"
189 |       },
190 |       "execution_count": 12,
191 |       "outputs": []
192 |     },
193 |     {
194 |       "cell_type": "code",
195 |       "source": [
196 |         "print(cm)"
197 |       ],
198 |       "metadata": {
199 |         "colab": {
200 |           "base_uri": "https://localhost:8080/"
201 |         },
202 |         "id": "sHFHRZimQJst",
203 |         "outputId": "f8b62630-d901-439c-9245-eff9ae2a2271"
204 |       },
205 |       "execution_count": 13,
206 |       "outputs": [
207 |         {
208 |           "output_type": "stream",
209 |           "name": "stdout",
210 |           "text": [
211 |             "[[40  8]\n",
212 |             " [ 6 21]]\n"
213 |           ]
214 |         }
215 |       ]
216 |     },
217 |     {
218 |       "cell_type": "code",
219 |       "source": [
220 |         "from sklearn.metrics import accuracy_score\n",
221 |         "accuracy_score(y_test, y_pred)"
222 |       ],
223 |       "metadata": {
224 |         "colab": {
225 |           "base_uri": "https://localhost:8080/"
226 |         },
227 |         "id": "FlvctoxSQLQO",
228 |         "outputId": "3f730a8a-f038-4436-d044-011561a957e6"
229 |       },
230 |       "execution_count": 14,
231 |       "outputs": [
232 |         {
233 |           "output_type": "execute_result",
234 |           "data": {
235 |             "text/plain": [
236 |               "0.8133333333333334"
237 |             ]
238 |           },
239 |           "metadata": {},
240 |           "execution_count": 14
241 |         }
242 |       ]
243 |     },
244 |     {
245 |       "cell_type": "code",
246 |       "source": [
247 |         ""
248 |       ],
249 |       "metadata": {
250 |         "id": "kHL4j9jAQxPv"
251 |       },
252 |       "execution_count": null,
253 |       "outputs": []
254 |     }
255 |   ]
256 | }


--------------------------------------------------------------------------------
/Ensemble learning.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 80,
  6 |    "id": "proof-secretariat",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 81,
 16 |    "id": "frank-league",
 17 |    "metadata": {},
 18 |    "outputs": [
 19 |     {
 20 |      "data": {
 21 |       "text/html": [
 22 |        "<div>\n",
 23 |        "<style scoped>\n",
 24 |        "    .dataframe tbody tr th:only-of-type {\n",
 25 |        "        vertical-align: middle;\n",
 26 |        "    }\n",
 27 |        "\n",
 28 |        "    .dataframe tbody tr th {\n",
 29 |        "        vertical-align: top;\n",
 30 |        "    }\n",
 31 |        "\n",
 32 |        "    .dataframe thead th {\n",
 33 |        "        text-align: right;\n",
 34 |        "    }\n",
 35 |        "</style>\n",
 36 |        "<table border=\"1\" class=\"dataframe\">\n",
 37 |        "  <thead>\n",
 38 |        "    <tr style=\"text-align: right;\">\n",
 39 |        "      <th></th>\n",
 40 |        "      <th>Pregnancies</th>\n",
 41 |        "      <th>Glucose</th>\n",
 42 |        "      <th>BloodPressure</th>\n",
 43 |        "      <th>SkinThickness</th>\n",
 44 |        "      <th>Insulin</th>\n",
 45 |        "      <th>BMI</th>\n",
 46 |        "      <th>DiabetesPedigreeFunction</th>\n",
 47 |        "      <th>Age</th>\n",
 48 |        "      <th>Outcome</th>\n",
 49 |        "    </tr>\n",
 50 |        "  </thead>\n",
 51 |        "  <tbody>\n",
 52 |        "    <tr>\n",
 53 |        "      <th>0</th>\n",
 54 |        "      <td>6</td>\n",
 55 |        "      <td>148</td>\n",
 56 |        "      <td>72</td>\n",
 57 |        "      <td>35</td>\n",
 58 |        "      <td>0</td>\n",
 59 |        "      <td>33.6</td>\n",
 60 |        "      <td>0.627</td>\n",
 61 |        "      <td>50</td>\n",
 62 |        "      <td>1</td>\n",
 63 |        "    </tr>\n",
 64 |        "    <tr>\n",
 65 |        "      <th>1</th>\n",
 66 |        "      <td>1</td>\n",
 67 |        "      <td>85</td>\n",
 68 |        "      <td>66</td>\n",
 69 |        "      <td>29</td>\n",
 70 |        "      <td>0</td>\n",
 71 |        "      <td>26.6</td>\n",
 72 |        "      <td>0.351</td>\n",
 73 |        "      <td>31</td>\n",
 74 |        "      <td>0</td>\n",
 75 |        "    </tr>\n",
 76 |        "    <tr>\n",
 77 |        "      <th>2</th>\n",
 78 |        "      <td>8</td>\n",
 79 |        "      <td>183</td>\n",
 80 |        "      <td>64</td>\n",
 81 |        "      <td>0</td>\n",
 82 |        "      <td>0</td>\n",
 83 |        "      <td>23.3</td>\n",
 84 |        "      <td>0.672</td>\n",
 85 |        "      <td>32</td>\n",
 86 |        "      <td>1</td>\n",
 87 |        "    </tr>\n",
 88 |        "    <tr>\n",
 89 |        "      <th>3</th>\n",
 90 |        "      <td>1</td>\n",
 91 |        "      <td>89</td>\n",
 92 |        "      <td>66</td>\n",
 93 |        "      <td>23</td>\n",
 94 |        "      <td>94</td>\n",
 95 |        "      <td>28.1</td>\n",
 96 |        "      <td>0.167</td>\n",
 97 |        "      <td>21</td>\n",
 98 |        "      <td>0</td>\n",
 99 |        "    </tr>\n",
100 |        "    <tr>\n",
101 |        "      <th>4</th>\n",
102 |        "      <td>0</td>\n",
103 |        "      <td>137</td>\n",
104 |        "      <td>40</td>\n",
105 |        "      <td>35</td>\n",
106 |        "      <td>168</td>\n",
107 |        "      <td>43.1</td>\n",
108 |        "      <td>2.288</td>\n",
109 |        "      <td>33</td>\n",
110 |        "      <td>1</td>\n",
111 |        "    </tr>\n",
112 |        "    <tr>\n",
113 |        "      <th>...</th>\n",
114 |        "      <td>...</td>\n",
115 |        "      <td>...</td>\n",
116 |        "      <td>...</td>\n",
117 |        "      <td>...</td>\n",
118 |        "      <td>...</td>\n",
119 |        "      <td>...</td>\n",
120 |        "      <td>...</td>\n",
121 |        "      <td>...</td>\n",
122 |        "      <td>...</td>\n",
123 |        "    </tr>\n",
124 |        "    <tr>\n",
125 |        "      <th>763</th>\n",
126 |        "      <td>10</td>\n",
127 |        "      <td>101</td>\n",
128 |        "      <td>76</td>\n",
129 |        "      <td>48</td>\n",
130 |        "      <td>180</td>\n",
131 |        "      <td>32.9</td>\n",
132 |        "      <td>0.171</td>\n",
133 |        "      <td>63</td>\n",
134 |        "      <td>0</td>\n",
135 |        "    </tr>\n",
136 |        "    <tr>\n",
137 |        "      <th>764</th>\n",
138 |        "      <td>2</td>\n",
139 |        "      <td>122</td>\n",
140 |        "      <td>70</td>\n",
141 |        "      <td>27</td>\n",
142 |        "      <td>0</td>\n",
143 |        "      <td>36.8</td>\n",
144 |        "      <td>0.340</td>\n",
145 |        "      <td>27</td>\n",
146 |        "      <td>0</td>\n",
147 |        "    </tr>\n",
148 |        "    <tr>\n",
149 |        "      <th>765</th>\n",
150 |        "      <td>5</td>\n",
151 |        "      <td>121</td>\n",
152 |        "      <td>72</td>\n",
153 |        "      <td>23</td>\n",
154 |        "      <td>112</td>\n",
155 |        "      <td>26.2</td>\n",
156 |        "      <td>0.245</td>\n",
157 |        "      <td>30</td>\n",
158 |        "      <td>0</td>\n",
159 |        "    </tr>\n",
160 |        "    <tr>\n",
161 |        "      <th>766</th>\n",
162 |        "      <td>1</td>\n",
163 |        "      <td>126</td>\n",
164 |        "      <td>60</td>\n",
165 |        "      <td>0</td>\n",
166 |        "      <td>0</td>\n",
167 |        "      <td>30.1</td>\n",
168 |        "      <td>0.349</td>\n",
169 |        "      <td>47</td>\n",
170 |        "      <td>1</td>\n",
171 |        "    </tr>\n",
172 |        "    <tr>\n",
173 |        "      <th>767</th>\n",
174 |        "      <td>1</td>\n",
175 |        "      <td>93</td>\n",
176 |        "      <td>70</td>\n",
177 |        "      <td>31</td>\n",
178 |        "      <td>0</td>\n",
179 |        "      <td>30.4</td>\n",
180 |        "      <td>0.315</td>\n",
181 |        "      <td>23</td>\n",
182 |        "      <td>0</td>\n",
183 |        "    </tr>\n",
184 |        "  </tbody>\n",
185 |        "</table>\n",
186 |        "<p>768 rows × 9 columns</p>\n",
187 |        "</div>"
188 |       ],
189 |       "text/plain": [
190 |        "     Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin   BMI  \\\n",
191 |        "0              6      148             72             35        0  33.6   \n",
192 |        "1              1       85             66             29        0  26.6   \n",
193 |        "2              8      183             64              0        0  23.3   \n",
194 |        "3              1       89             66             23       94  28.1   \n",
195 |        "4              0      137             40             35      168  43.1   \n",
196 |        "..           ...      ...            ...            ...      ...   ...   \n",
197 |        "763           10      101             76             48      180  32.9   \n",
198 |        "764            2      122             70             27        0  36.8   \n",
199 |        "765            5      121             72             23      112  26.2   \n",
200 |        "766            1      126             60              0        0  30.1   \n",
201 |        "767            1       93             70             31        0  30.4   \n",
202 |        "\n",
203 |        "     DiabetesPedigreeFunction  Age  Outcome  \n",
204 |        "0                       0.627   50        1  \n",
205 |        "1                       0.351   31        0  \n",
206 |        "2                       0.672   32        1  \n",
207 |        "3                       0.167   21        0  \n",
208 |        "4                       2.288   33        1  \n",
209 |        "..                        ...  ...      ...  \n",
210 |        "763                     0.171   63        0  \n",
211 |        "764                     0.340   27        0  \n",
212 |        "765                     0.245   30        0  \n",
213 |        "766                     0.349   47        1  \n",
214 |        "767                     0.315   23        0  \n",
215 |        "\n",
216 |        "[768 rows x 9 columns]"
217 |       ]
218 |      },
219 |      "execution_count": 81,
220 |      "metadata": {},
221 |      "output_type": "execute_result"
222 |     }
223 |    ],
224 |    "source": [
225 |     "df=pd.read_csv('diabetes.csv')\n",
226 |     "df"
227 |    ]
228 |   },
229 |   {
230 |    "cell_type": "code",
231 |    "execution_count": 82,
232 |    "id": "electronic-oakland",
233 |    "metadata": {},
234 |    "outputs": [],
235 |    "source": [
236 |     "feature_cols = ['Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness','Insulin','BMI','DiabetesPedigreeFunction','Age']\n",
237 |     "X = df[feature_cols] #features\n",
238 |     "y = df.Outcome #outcomes or target"
239 |    ]
240 |   },
241 |   {
242 |    "cell_type": "code",
243 |    "execution_count": 83,
244 |    "id": "available-boards",
245 |    "metadata": {},
246 |    "outputs": [],
247 |    "source": [
248 |     "from sklearn.model_selection import train_test_split\n",
249 |     "X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.3)"
250 |    ]
251 |   },
252 |   {
253 |    "cell_type": "code",
254 |    "execution_count": 84,
255 |    "id": "proud-remainder",
256 |    "metadata": {},
257 |    "outputs": [],
258 |    "source": [
259 |     "from sklearn.naive_bayes import GaussianNB\n",
260 |     "from sklearn.tree import DecisionTreeClassifier\n",
261 |     "from sklearn.linear_model import LogisticRegression\n",
262 |     "from sklearn.metrics import accuracy_score\n",
263 |     "from sklearn.metrics import classification_report"
264 |    ]
265 |   },
266 |   {
267 |    "cell_type": "code",
268 |    "execution_count": 85,
269 |    "id": "burning-karma",
270 |    "metadata": {},
271 |    "outputs": [],
272 |    "source": [
273 |     "classifiers=[['Naive Bayes :', GaussianNB()],['LogisticRegression :', LogisticRegression(max_iter = 1000)], ['DecisionTree :',DecisionTreeClassifier()]]"
274 |    ]
275 |   },
276 |   {
277 |    "cell_type": "code",
278 |    "execution_count": 86,
279 |    "id": "daily-conference",
280 |    "metadata": {},
281 |    "outputs": [],
282 |    "source": [
283 |     "predictions_df = pd.DataFrame()\n",
284 |     "predictions_df['action'] = y_test"
285 |    ]
286 |   },
287 |   {
288 |    "cell_type": "code",
289 |    "execution_count": 87,
290 |    "id": "reasonable-ideal",
291 |    "metadata": {},
292 |    "outputs": [
293 |     {
294 |      "name": "stdout",
295 |      "output_type": "stream",
296 |      "text": [
297 |       "Naive Bayes : 0.70995670995671\n",
298 |       "LogisticRegression : 0.7445887445887446\n",
299 |       "DecisionTree : 0.6103896103896104\n"
300 |      ]
301 |     }
302 |    ],
303 |    "source": [
304 |     "for name,classifier in classifiers:\n",
305 |     "    classifier = classifier\n",
306 |     "    classifier.fit(X_train, y_train.ravel())\n",
307 |     "    predictions = classifier.predict(X_test)\n",
308 |     "    predictions_df[name.strip(\":\")] = predictions\n",
309 |     "    print(name, accuracy_score(y_test, predictions))"
310 |    ]
311 |   },
312 |   {
313 |    "cell_type": "code",
314 |    "execution_count": 95,
315 |    "id": "provincial-adventure",
316 |    "metadata": {},
317 |    "outputs": [
318 |     {
319 |      "data": {
320 |       "text/html": [
321 |        "<div>\n",
322 |        "<style scoped>\n",
323 |        "    .dataframe tbody tr th:only-of-type {\n",
324 |        "        vertical-align: middle;\n",
325 |        "    }\n",
326 |        "\n",
327 |        "    .dataframe tbody tr th {\n",
328 |        "        vertical-align: top;\n",
329 |        "    }\n",
330 |        "\n",
331 |        "    .dataframe thead th {\n",
332 |        "        text-align: right;\n",
333 |        "    }\n",
334 |        "</style>\n",
335 |        "<table border=\"1\" class=\"dataframe\">\n",
336 |        "  <thead>\n",
337 |        "    <tr style=\"text-align: right;\">\n",
338 |        "      <th></th>\n",
339 |        "      <th>action</th>\n",
340 |        "      <th>Naive Bayes</th>\n",
341 |        "      <th>LogisticRegression</th>\n",
342 |        "      <th>DecisionTree</th>\n",
343 |        "    </tr>\n",
344 |        "  </thead>\n",
345 |        "  <tbody>\n",
346 |        "    <tr>\n",
347 |        "      <th>574</th>\n",
348 |        "      <td>0</td>\n",
349 |        "      <td>1</td>\n",
350 |        "      <td>0</td>\n",
351 |        "      <td>0</td>\n",
352 |        "    </tr>\n",
353 |        "    <tr>\n",
354 |        "      <th>539</th>\n",
355 |        "      <td>1</td>\n",
356 |        "      <td>1</td>\n",
357 |        "      <td>1</td>\n",
358 |        "      <td>1</td>\n",
359 |        "    </tr>\n",
360 |        "    <tr>\n",
361 |        "      <th>613</th>\n",
362 |        "      <td>0</td>\n",
363 |        "      <td>0</td>\n",
364 |        "      <td>0</td>\n",
365 |        "      <td>0</td>\n",
366 |        "    </tr>\n",
367 |        "    <tr>\n",
368 |        "      <th>612</th>\n",
369 |        "      <td>1</td>\n",
370 |        "      <td>1</td>\n",
371 |        "      <td>1</td>\n",
372 |        "      <td>1</td>\n",
373 |        "    </tr>\n",
374 |        "    <tr>\n",
375 |        "      <th>122</th>\n",
376 |        "      <td>0</td>\n",
377 |        "      <td>0</td>\n",
378 |        "      <td>0</td>\n",
379 |        "      <td>0</td>\n",
380 |        "    </tr>\n",
381 |        "  </tbody>\n",
382 |        "</table>\n",
383 |        "</div>"
384 |       ],
385 |       "text/plain": [
386 |        "     action  Naive Bayes   LogisticRegression   DecisionTree \n",
387 |        "574       0             1                    0              0\n",
388 |        "539       1             1                    1              1\n",
389 |        "613       0             0                    0              0\n",
390 |        "612       1             1                    1              1\n",
391 |        "122       0             0                    0              0"
392 |       ]
393 |      },
394 |      "execution_count": 95,
395 |      "metadata": {},
396 |      "output_type": "execute_result"
397 |     }
398 |    ],
399 |    "source": [
400 |     "predictions_df.head()"
401 |    ]
402 |   },
403 |   {
404 |    "cell_type": "code",
405 |    "execution_count": null,
406 |    "id": "cutting-grade",
407 |    "metadata": {},
408 |    "outputs": [],
409 |    "source": []
410 |   },
411 |   {
412 |    "cell_type": "code",
413 |    "execution_count": 96,
414 |    "id": "defensive-secretariat",
415 |    "metadata": {},
416 |    "outputs": [
417 |     {
418 |      "name": "stdout",
419 |      "output_type": "stream",
420 |      "text": [
421 |       "[0 1 0 1 0 0 0 1 0 0 0 1 0 1 0 1 0 0 0 0 0 1 0 0 1 0 0 0 0 1 1 1 1 0 0 1 0\n",
422 |       " 0 0 0 0 0 0 0 1 1 0 0 0 0 0 0 0 0 1 0 0 0 0 1 1 0 0 0 0 0 0 1 1 0 0 0 1 0\n",
423 |       " 1 0 1 1 1 1 1 0 1 0 0 0 1 1 1 0 0 0 0 0 0 0 1 1 0 1 0 0 0 1 0 0 1 0 0 1 1\n",
424 |       " 0 1 1 1 0 1 0 0 1 0 0 1 1 0 0 1 0 1 0 0 0 0 0 1 1 0 0 0 0 0 0 0 1 0 1 0 1\n",
425 |       " 0 0 0 0 1 0 0 0 0 0 1 1 0 1 0 1 1 0 1 0 0 1 0 0 0 0 0 0 0 0 1 1 0 1 1 0 0\n",
426 |       " 1 0 0 0 0 0 0 1 0 0 1 1 0 1 1 1 0 0 0 0 0 1 0 0 0 0 1 0 0 0 0 1 1 1 0 1 0\n",
427 |       " 0 1 0 1 0 0 0 0 1]\n"
428 |      ]
429 |     },
430 |     {
431 |      "name": "stderr",
432 |      "output_type": "stream",
433 |      "text": [
434 |       "c:\\users\\admin\\appdata\\local\\programs\\python\\python38\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
435 |       "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
436 |       "\n",
437 |       "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
438 |       "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
439 |       "Please also refer to the documentation for alternative solver options:\n",
440 |       "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
441 |       "  n_iter_i = _check_optimize_result(\n"
442 |      ]
443 |     }
444 |    ],
445 |    "source": [
446 |     "from sklearn.ensemble import VotingClassifier\n",
447 |     "clf1 = GaussianNB()\n",
448 |     "clf2 = DecisionTreeClassifier()\n",
449 |     "clf3 = LogisticRegression()\n",
450 |     "\n",
451 |     "\n",
452 |     "    \n",
453 |     "eclf1 = VotingClassifier(estimators=[('Gaussian', clf1), ('DecisionTree', clf2), ('Logisitic', clf3)], voting='hard')\n",
454 |     "eclf1.fit(X_train, y_train)\n",
455 |     "predictions = eclf1.predict(X_test)\n",
456 |     "print(predictions)"
457 |    ]
458 |   },
459 |   {
460 |    "cell_type": "code",
461 |    "execution_count": null,
462 |    "id": "advisory-synthesis",
463 |    "metadata": {},
464 |    "outputs": [],
465 |    "source": []
466 |   },
467 |   {
468 |    "cell_type": "code",
469 |    "execution_count": null,
470 |    "id": "stopped-bibliography",
471 |    "metadata": {},
472 |    "outputs": [],
473 |    "source": []
474 |   },
475 |   {
476 |    "cell_type": "code",
477 |    "execution_count": null,
478 |    "id": "subjective-mainstream",
479 |    "metadata": {},
480 |    "outputs": [],
481 |    "source": []
482 |   },
483 |   {
484 |    "cell_type": "code",
485 |    "execution_count": 90,
486 |    "id": "bound-pastor",
487 |    "metadata": {},
488 |    "outputs": [
489 |     {
490 |      "name": "stdout",
491 |      "output_type": "stream",
492 |      "text": [
493 |       "Hard Voting Score  0\n"
494 |      ]
495 |     }
496 |    ],
497 |    "source": [
498 |     "# Voting Classifier with hard voting\n",
499 |     "vot_hard = VotingClassifier(estimators = classifiers, voting ='hard')\n",
500 |     "vot_hard.fit(X_train, y_train)\n",
501 |     "y_pred = vot_hard.predict(X_test)\n",
502 |     "  \n",
503 |     "# using accuracy_score metric to predict accuracy\n",
504 |     "score = accuracy_score(y_test, y_pred)\n",
505 |     "print(\"Hard Voting Score % d\" % score)"
506 |    ]
507 |   },
508 |   {
509 |    "cell_type": "code",
510 |    "execution_count": 91,
511 |    "id": "separate-compiler",
512 |    "metadata": {},
513 |    "outputs": [
514 |     {
515 |      "name": "stdout",
516 |      "output_type": "stream",
517 |      "text": [
518 |       "Soft Voting Score  0\n"
519 |      ]
520 |     }
521 |    ],
522 |    "source": [
523 |     "# Voting Classifier with soft voting\n",
524 |     "vot_soft = VotingClassifier(estimators = classifiers, voting ='soft')\n",
525 |     "vot_soft.fit(X_train, y_train)\n",
526 |     "y_pred = vot_soft.predict(X_test)\n",
527 |     "\n",
528 |     "score1 = accuracy_score(y_test, y_pred)\n",
529 |     "print(\"Soft Voting Score % d\" % score1)"
530 |    ]
531 |   },
532 |   {
533 |    "cell_type": "code",
534 |    "execution_count": 98,
535 |    "id": "african-athletics",
536 |    "metadata": {},
537 |    "outputs": [
538 |     {
539 |      "name": "stderr",
540 |      "output_type": "stream",
541 |      "text": [
542 |       "c:\\users\\admin\\appdata\\local\\programs\\python\\python38\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
543 |       "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
544 |       "\n",
545 |       "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
546 |       "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
547 |       "Please also refer to the documentation for alternative solver options:\n",
548 |       "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
549 |       "  n_iter_i = _check_optimize_result(\n",
550 |       "c:\\users\\admin\\appdata\\local\\programs\\python\\python38\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
551 |       "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
552 |       "\n",
553 |       "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
554 |       "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
555 |       "Please also refer to the documentation for alternative solver options:\n",
556 |       "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
557 |       "  n_iter_i = _check_optimize_result(\n",
558 |       "c:\\users\\admin\\appdata\\local\\programs\\python\\python38\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
559 |       "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
560 |       "\n",
561 |       "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
562 |       "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
563 |       "Please also refer to the documentation for alternative solver options:\n",
564 |       "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
565 |       "  n_iter_i = _check_optimize_result(\n",
566 |       "c:\\users\\admin\\appdata\\local\\programs\\python\\python38\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
567 |       "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
568 |       "\n",
569 |       "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
570 |       "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
571 |       "Please also refer to the documentation for alternative solver options:\n",
572 |       "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
573 |       "  n_iter_i = _check_optimize_result(\n",
574 |       "c:\\users\\admin\\appdata\\local\\programs\\python\\python38\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
575 |       "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
576 |       "\n",
577 |       "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
578 |       "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
579 |       "Please also refer to the documentation for alternative solver options:\n",
580 |       "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
581 |       "  n_iter_i = _check_optimize_result(\n",
582 |       "c:\\users\\admin\\appdata\\local\\programs\\python\\python38\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
583 |       "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
584 |       "\n",
585 |       "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
586 |       "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
587 |       "Please also refer to the documentation for alternative solver options:\n",
588 |       "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
589 |       "  n_iter_i = _check_optimize_result(\n",
590 |       "c:\\users\\admin\\appdata\\local\\programs\\python\\python38\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
591 |       "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
592 |       "\n",
593 |       "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
594 |       "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
595 |       "Please also refer to the documentation for alternative solver options:\n",
596 |       "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
597 |       "  n_iter_i = _check_optimize_result(\n",
598 |       "c:\\users\\admin\\appdata\\local\\programs\\python\\python38\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
599 |       "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
600 |       "\n",
601 |       "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
602 |       "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
603 |       "Please also refer to the documentation for alternative solver options:\n",
604 |       "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
605 |       "  n_iter_i = _check_optimize_result(\n",
606 |       "c:\\users\\admin\\appdata\\local\\programs\\python\\python38\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
607 |       "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
608 |       "\n",
609 |       "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
610 |       "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
611 |       "Please also refer to the documentation for alternative solver options:\n",
612 |       "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
613 |       "  n_iter_i = _check_optimize_result(\n",
614 |       "c:\\users\\admin\\appdata\\local\\programs\\python\\python38\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
615 |       "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
616 |       "\n",
617 |       "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
618 |       "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
619 |       "Please also refer to the documentation for alternative solver options:\n",
620 |       "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
621 |       "  n_iter_i = _check_optimize_result(\n"
622 |      ]
623 |     },
624 |     {
625 |      "name": "stdout",
626 |      "output_type": "stream",
627 |      "text": [
628 |       "[0.7597484276729559, 0.6983228511530398, 0.7729210342417889]\n"
629 |      ]
630 |     }
631 |    ],
632 |    "source": [
633 |     "\n",
634 |     "from sklearn.model_selection import cross_val_score\n",
635 |     "c = []\n",
636 |     "c.append(cross_val_score(clf1,X_train,y_train,scoring='accuracy',cv=10).mean())\n",
637 |     "c.append(cross_val_score(clf2,X_train,y_train,scoring='accuracy',cv=10).mean())\n",
638 |     "c.append(cross_val_score(clf3,X_train,y_train,scoring='accuracy',cv=10).mean())\n",
639 |     "print(c)"
640 |    ]
641 |   },
642 |   {
643 |    "cell_type": "code",
644 |    "execution_count": null,
645 |    "id": "differential-energy",
646 |    "metadata": {},
647 |    "outputs": [],
648 |    "source": []
649 |   }
650 |  ],
651 |  "metadata": {
652 |   "kernelspec": {
653 |    "display_name": "Python 3",
654 |    "language": "python",
655 |    "name": "python3"
656 |   },
657 |   "language_info": {
658 |    "codemirror_mode": {
659 |     "name": "ipython",
660 |     "version": 3
661 |    },
662 |    "file_extension": ".py",
663 |    "mimetype": "text/x-python",
664 |    "name": "python",
665 |    "nbconvert_exporter": "python",
666 |    "pygments_lexer": "ipython3",
667 |    "version": "3.8.8"
668 |   }
669 |  },
670 |  "nbformat": 4,
671 |  "nbformat_minor": 5
672 | }
673 | 


--------------------------------------------------------------------------------
/Hyper parameter tuning.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 69,
  6 |    "id": "97b98548",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd\n",
 11 |     "from sklearn.svm import SVC\n",
 12 |     "from sklearn.metrics import confusion_matrix, classification_report\n",
 13 |     "from sklearn.preprocessing import StandardScaler, LabelEncoder\n",
 14 |     "import seaborn as sns"
 15 |    ]
 16 |   },
 17 |   {
 18 |    "cell_type": "code",
 19 |    "execution_count": 90,
 20 |    "id": "84729c58",
 21 |    "metadata": {},
 22 |    "outputs": [
 23 |     {
 24 |      "data": {
 25 |       "text/html": [
 26 |        "<div>\n",
 27 |        "<style scoped>\n",
 28 |        "    .dataframe tbody tr th:only-of-type {\n",
 29 |        "        vertical-align: middle;\n",
 30 |        "    }\n",
 31 |        "\n",
 32 |        "    .dataframe tbody tr th {\n",
 33 |        "        vertical-align: top;\n",
 34 |        "    }\n",
 35 |        "\n",
 36 |        "    .dataframe thead th {\n",
 37 |        "        text-align: right;\n",
 38 |        "    }\n",
 39 |        "</style>\n",
 40 |        "<table border=\"1\" class=\"dataframe\">\n",
 41 |        "  <thead>\n",
 42 |        "    <tr style=\"text-align: right;\">\n",
 43 |        "      <th></th>\n",
 44 |        "      <th>fixed acidity</th>\n",
 45 |        "      <th>volatile acidity</th>\n",
 46 |        "      <th>citric acid</th>\n",
 47 |        "      <th>residual sugar</th>\n",
 48 |        "      <th>chlorides</th>\n",
 49 |        "      <th>free sulfur dioxide</th>\n",
 50 |        "      <th>total sulfur dioxide</th>\n",
 51 |        "      <th>density</th>\n",
 52 |        "      <th>pH</th>\n",
 53 |        "      <th>sulphates</th>\n",
 54 |        "      <th>alcohol</th>\n",
 55 |        "      <th>quality</th>\n",
 56 |        "    </tr>\n",
 57 |        "  </thead>\n",
 58 |        "  <tbody>\n",
 59 |        "    <tr>\n",
 60 |        "      <th>0</th>\n",
 61 |        "      <td>7.4</td>\n",
 62 |        "      <td>0.700</td>\n",
 63 |        "      <td>0.00</td>\n",
 64 |        "      <td>1.9</td>\n",
 65 |        "      <td>0.076</td>\n",
 66 |        "      <td>11.0</td>\n",
 67 |        "      <td>34.0</td>\n",
 68 |        "      <td>0.99780</td>\n",
 69 |        "      <td>3.51</td>\n",
 70 |        "      <td>0.56</td>\n",
 71 |        "      <td>9.4</td>\n",
 72 |        "      <td>5</td>\n",
 73 |        "    </tr>\n",
 74 |        "    <tr>\n",
 75 |        "      <th>1</th>\n",
 76 |        "      <td>7.8</td>\n",
 77 |        "      <td>0.880</td>\n",
 78 |        "      <td>0.00</td>\n",
 79 |        "      <td>2.6</td>\n",
 80 |        "      <td>0.098</td>\n",
 81 |        "      <td>25.0</td>\n",
 82 |        "      <td>67.0</td>\n",
 83 |        "      <td>0.99680</td>\n",
 84 |        "      <td>3.20</td>\n",
 85 |        "      <td>0.68</td>\n",
 86 |        "      <td>9.8</td>\n",
 87 |        "      <td>5</td>\n",
 88 |        "    </tr>\n",
 89 |        "    <tr>\n",
 90 |        "      <th>2</th>\n",
 91 |        "      <td>7.8</td>\n",
 92 |        "      <td>0.760</td>\n",
 93 |        "      <td>0.04</td>\n",
 94 |        "      <td>2.3</td>\n",
 95 |        "      <td>0.092</td>\n",
 96 |        "      <td>15.0</td>\n",
 97 |        "      <td>54.0</td>\n",
 98 |        "      <td>0.99700</td>\n",
 99 |        "      <td>3.26</td>\n",
100 |        "      <td>0.65</td>\n",
101 |        "      <td>9.8</td>\n",
102 |        "      <td>5</td>\n",
103 |        "    </tr>\n",
104 |        "    <tr>\n",
105 |        "      <th>3</th>\n",
106 |        "      <td>11.2</td>\n",
107 |        "      <td>0.280</td>\n",
108 |        "      <td>0.56</td>\n",
109 |        "      <td>1.9</td>\n",
110 |        "      <td>0.075</td>\n",
111 |        "      <td>17.0</td>\n",
112 |        "      <td>60.0</td>\n",
113 |        "      <td>0.99800</td>\n",
114 |        "      <td>3.16</td>\n",
115 |        "      <td>0.58</td>\n",
116 |        "      <td>9.8</td>\n",
117 |        "      <td>6</td>\n",
118 |        "    </tr>\n",
119 |        "    <tr>\n",
120 |        "      <th>4</th>\n",
121 |        "      <td>7.4</td>\n",
122 |        "      <td>0.700</td>\n",
123 |        "      <td>0.00</td>\n",
124 |        "      <td>1.9</td>\n",
125 |        "      <td>0.076</td>\n",
126 |        "      <td>11.0</td>\n",
127 |        "      <td>34.0</td>\n",
128 |        "      <td>0.99780</td>\n",
129 |        "      <td>3.51</td>\n",
130 |        "      <td>0.56</td>\n",
131 |        "      <td>9.4</td>\n",
132 |        "      <td>5</td>\n",
133 |        "    </tr>\n",
134 |        "    <tr>\n",
135 |        "      <th>...</th>\n",
136 |        "      <td>...</td>\n",
137 |        "      <td>...</td>\n",
138 |        "      <td>...</td>\n",
139 |        "      <td>...</td>\n",
140 |        "      <td>...</td>\n",
141 |        "      <td>...</td>\n",
142 |        "      <td>...</td>\n",
143 |        "      <td>...</td>\n",
144 |        "      <td>...</td>\n",
145 |        "      <td>...</td>\n",
146 |        "      <td>...</td>\n",
147 |        "      <td>...</td>\n",
148 |        "    </tr>\n",
149 |        "    <tr>\n",
150 |        "      <th>1594</th>\n",
151 |        "      <td>6.2</td>\n",
152 |        "      <td>0.600</td>\n",
153 |        "      <td>0.08</td>\n",
154 |        "      <td>2.0</td>\n",
155 |        "      <td>0.090</td>\n",
156 |        "      <td>32.0</td>\n",
157 |        "      <td>44.0</td>\n",
158 |        "      <td>0.99490</td>\n",
159 |        "      <td>3.45</td>\n",
160 |        "      <td>0.58</td>\n",
161 |        "      <td>10.5</td>\n",
162 |        "      <td>5</td>\n",
163 |        "    </tr>\n",
164 |        "    <tr>\n",
165 |        "      <th>1595</th>\n",
166 |        "      <td>5.9</td>\n",
167 |        "      <td>0.550</td>\n",
168 |        "      <td>0.10</td>\n",
169 |        "      <td>2.2</td>\n",
170 |        "      <td>0.062</td>\n",
171 |        "      <td>39.0</td>\n",
172 |        "      <td>51.0</td>\n",
173 |        "      <td>0.99512</td>\n",
174 |        "      <td>3.52</td>\n",
175 |        "      <td>0.76</td>\n",
176 |        "      <td>11.2</td>\n",
177 |        "      <td>6</td>\n",
178 |        "    </tr>\n",
179 |        "    <tr>\n",
180 |        "      <th>1596</th>\n",
181 |        "      <td>6.3</td>\n",
182 |        "      <td>0.510</td>\n",
183 |        "      <td>0.13</td>\n",
184 |        "      <td>2.3</td>\n",
185 |        "      <td>0.076</td>\n",
186 |        "      <td>29.0</td>\n",
187 |        "      <td>40.0</td>\n",
188 |        "      <td>0.99574</td>\n",
189 |        "      <td>3.42</td>\n",
190 |        "      <td>0.75</td>\n",
191 |        "      <td>11.0</td>\n",
192 |        "      <td>6</td>\n",
193 |        "    </tr>\n",
194 |        "    <tr>\n",
195 |        "      <th>1597</th>\n",
196 |        "      <td>5.9</td>\n",
197 |        "      <td>0.645</td>\n",
198 |        "      <td>0.12</td>\n",
199 |        "      <td>2.0</td>\n",
200 |        "      <td>0.075</td>\n",
201 |        "      <td>32.0</td>\n",
202 |        "      <td>44.0</td>\n",
203 |        "      <td>0.99547</td>\n",
204 |        "      <td>3.57</td>\n",
205 |        "      <td>0.71</td>\n",
206 |        "      <td>10.2</td>\n",
207 |        "      <td>5</td>\n",
208 |        "    </tr>\n",
209 |        "    <tr>\n",
210 |        "      <th>1598</th>\n",
211 |        "      <td>6.0</td>\n",
212 |        "      <td>0.310</td>\n",
213 |        "      <td>0.47</td>\n",
214 |        "      <td>3.6</td>\n",
215 |        "      <td>0.067</td>\n",
216 |        "      <td>18.0</td>\n",
217 |        "      <td>42.0</td>\n",
218 |        "      <td>0.99549</td>\n",
219 |        "      <td>3.39</td>\n",
220 |        "      <td>0.66</td>\n",
221 |        "      <td>11.0</td>\n",
222 |        "      <td>6</td>\n",
223 |        "    </tr>\n",
224 |        "  </tbody>\n",
225 |        "</table>\n",
226 |        "<p>1599 rows × 12 columns</p>\n",
227 |        "</div>"
228 |       ],
229 |       "text/plain": [
230 |        "      fixed acidity  volatile acidity  citric acid  residual sugar  chlorides  \\\n",
231 |        "0               7.4             0.700         0.00             1.9      0.076   \n",
232 |        "1               7.8             0.880         0.00             2.6      0.098   \n",
233 |        "2               7.8             0.760         0.04             2.3      0.092   \n",
234 |        "3              11.2             0.280         0.56             1.9      0.075   \n",
235 |        "4               7.4             0.700         0.00             1.9      0.076   \n",
236 |        "...             ...               ...          ...             ...        ...   \n",
237 |        "1594            6.2             0.600         0.08             2.0      0.090   \n",
238 |        "1595            5.9             0.550         0.10             2.2      0.062   \n",
239 |        "1596            6.3             0.510         0.13             2.3      0.076   \n",
240 |        "1597            5.9             0.645         0.12             2.0      0.075   \n",
241 |        "1598            6.0             0.310         0.47             3.6      0.067   \n",
242 |        "\n",
243 |        "      free sulfur dioxide  total sulfur dioxide  density    pH  sulphates  \\\n",
244 |        "0                    11.0                  34.0  0.99780  3.51       0.56   \n",
245 |        "1                    25.0                  67.0  0.99680  3.20       0.68   \n",
246 |        "2                    15.0                  54.0  0.99700  3.26       0.65   \n",
247 |        "3                    17.0                  60.0  0.99800  3.16       0.58   \n",
248 |        "4                    11.0                  34.0  0.99780  3.51       0.56   \n",
249 |        "...                   ...                   ...      ...   ...        ...   \n",
250 |        "1594                 32.0                  44.0  0.99490  3.45       0.58   \n",
251 |        "1595                 39.0                  51.0  0.99512  3.52       0.76   \n",
252 |        "1596                 29.0                  40.0  0.99574  3.42       0.75   \n",
253 |        "1597                 32.0                  44.0  0.99547  3.57       0.71   \n",
254 |        "1598                 18.0                  42.0  0.99549  3.39       0.66   \n",
255 |        "\n",
256 |        "      alcohol  quality  \n",
257 |        "0         9.4        5  \n",
258 |        "1         9.8        5  \n",
259 |        "2         9.8        5  \n",
260 |        "3         9.8        6  \n",
261 |        "4         9.4        5  \n",
262 |        "...       ...      ...  \n",
263 |        "1594     10.5        5  \n",
264 |        "1595     11.2        6  \n",
265 |        "1596     11.0        6  \n",
266 |        "1597     10.2        5  \n",
267 |        "1598     11.0        6  \n",
268 |        "\n",
269 |        "[1599 rows x 12 columns]"
270 |       ]
271 |      },
272 |      "execution_count": 90,
273 |      "metadata": {},
274 |      "output_type": "execute_result"
275 |     }
276 |    ],
277 |    "source": [
278 |     "wine=pd.read_csv('winequality-red.csv')\n",
279 |     "wine"
280 |    ]
281 |   },
282 |   {
283 |    "cell_type": "code",
284 |    "execution_count": 73,
285 |    "id": "9a898701",
286 |    "metadata": {},
287 |    "outputs": [
288 |     {
289 |      "data": {
290 |       "text/plain": [
291 |        "5    681\n",
292 |        "6    638\n",
293 |        "7    199\n",
294 |        "4     53\n",
295 |        "8     18\n",
296 |        "3     10\n",
297 |        "Name: quality, dtype: int64"
298 |       ]
299 |      },
300 |      "execution_count": 73,
301 |      "metadata": {},
302 |      "output_type": "execute_result"
303 |     }
304 |    ],
305 |    "source": [
306 |     "wine['quality'].value_counts()"
307 |    ]
308 |   },
309 |   {
310 |    "cell_type": "code",
311 |    "execution_count": 74,
312 |    "id": "b9dec75b",
313 |    "metadata": {},
314 |    "outputs": [
315 |     {
316 |      "name": "stdout",
317 |      "output_type": "stream",
318 |      "text": [
319 |       "<class 'pandas.core.frame.DataFrame'>\n",
320 |       "RangeIndex: 1599 entries, 0 to 1598\n",
321 |       "Data columns (total 12 columns):\n",
322 |       " #   Column                Non-Null Count  Dtype  \n",
323 |       "---  ------                --------------  -----  \n",
324 |       " 0   fixed acidity         1599 non-null   float64\n",
325 |       " 1   volatile acidity      1599 non-null   float64\n",
326 |       " 2   citric acid           1599 non-null   float64\n",
327 |       " 3   residual sugar        1599 non-null   float64\n",
328 |       " 4   chlorides             1599 non-null   float64\n",
329 |       " 5   free sulfur dioxide   1599 non-null   float64\n",
330 |       " 6   total sulfur dioxide  1599 non-null   float64\n",
331 |       " 7   density               1599 non-null   float64\n",
332 |       " 8   pH                    1599 non-null   float64\n",
333 |       " 9   sulphates             1599 non-null   float64\n",
334 |       " 10  alcohol               1599 non-null   float64\n",
335 |       " 11  quality               1599 non-null   int64  \n",
336 |       "dtypes: float64(11), int64(1)\n",
337 |       "memory usage: 150.0 KB\n"
338 |      ]
339 |     }
340 |    ],
341 |    "source": [
342 |     "wine.info()"
343 |    ]
344 |   },
345 |   {
346 |    "cell_type": "code",
347 |    "execution_count": 92,
348 |    "id": "687120f4",
349 |    "metadata": {},
350 |    "outputs": [],
351 |    "source": [
352 |     "#Making binary classificaion for the response variable.\n",
353 |     "#Dividing wine as good and bad by giving the limit for the quality\n",
354 |     "bins = (2, 6.5, 8)\n",
355 |     "group_names = ['bad', 'good']\n",
356 |     "wine['quality'] = pd.cut(wine['quality'], bins = bins, labels = group_names)"
357 |    ]
358 |   },
359 |   {
360 |    "cell_type": "code",
361 |    "execution_count": null,
362 |    "id": "3b0d693c",
363 |    "metadata": {},
364 |    "outputs": [],
365 |    "source": []
366 |   },
367 |   {
368 |    "cell_type": "code",
369 |    "execution_count": 93,
370 |    "id": "24b3198b",
371 |    "metadata": {},
372 |    "outputs": [],
373 |    "source": [
374 |     "#Now lets assign a labels to our quality variable\n",
375 |     "label_quality = LabelEncoder()\n",
376 |     "#Bad becomes 0 and good becomes 1 \n",
377 |     "wine['quality'] = label_quality.fit_transform(wine['quality'])"
378 |    ]
379 |   },
380 |   {
381 |    "cell_type": "code",
382 |    "execution_count": 77,
383 |    "id": "86f12402",
384 |    "metadata": {},
385 |    "outputs": [],
386 |    "source": []
387 |   },
388 |   {
389 |    "cell_type": "code",
390 |    "execution_count": 78,
391 |    "id": "d677b6b7",
392 |    "metadata": {},
393 |    "outputs": [
394 |     {
395 |      "data": {
396 |       "text/plain": [
397 |        "0    1382\n",
398 |        "1     217\n",
399 |        "Name: quality, dtype: int64"
400 |       ]
401 |      },
402 |      "execution_count": 78,
403 |      "metadata": {},
404 |      "output_type": "execute_result"
405 |     }
406 |    ],
407 |    "source": [
408 |     "wine['quality'].value_counts()"
409 |    ]
410 |   },
411 |   {
412 |    "cell_type": "code",
413 |    "execution_count": 79,
414 |    "id": "29aeab91",
415 |    "metadata": {},
416 |    "outputs": [
417 |     {
418 |      "name": "stderr",
419 |      "output_type": "stream",
420 |      "text": [
421 |       "c:\\users\\arun\\appdata\\local\\programs\\python\\python38\\lib\\site-packages\\seaborn\\_decorators.py:36: FutureWarning: Pass the following variable as a keyword arg: x. 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",
422 |       "  warnings.warn(\n"
423 |      ]
424 |     },
425 |     {
426 |      "data": {
427 |       "text/plain": [
428 |        "<AxesSubplot:xlabel='quality', ylabel='count'>"
429 |       ]
430 |      },
431 |      "execution_count": 79,
432 |      "metadata": {},
433 |      "output_type": "execute_result"
434 |     },
435 |     {
436 |      "data": {
437 |       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAEGCAYAAACUzrmNAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/YYfK9AAAACXBIWXMAAAsTAAALEwEAmpwYAAASA0lEQVR4nO3de7BdZ13/8feHhIIo0JYcKybREzWDU1EEzpSOjL/pUIW2KqkOdNpRCCUz8VK8oP74FZ2xDoqjY7UWL3UiDW0c7EUEG7WKnSLWC62clluhImdKIcm05EBCuXQqRr+/P/YT2aTn5DknnL33Sc/7NbMna32fZ6/9ZSbk02ettddOVSFJ0vE8YdINSJJWP8NCktRlWEiSugwLSVKXYSFJ6lo/6QZGYcOGDTU9PT3pNiTppHL33Xd/uqqmFhp7XIbF9PQ0s7Ozk25Dkk4qST6x2JinoSRJXYaFJKnLsJAkdY0sLJLsTnIwyb0LjP1Ckkqyoe0nyZuSzCX5YJLnDc3dnuRj7bV9VP1KkhY3ypXFdcB5xxaTbAZeDHxyqHw+sLW9dgLXtLmnA1cALwDOAq5IctoIe5YkLWBkYVFVdwCHFhi6CngdMPwEw23Anhq4Ezg1yTOBlwC3VdWhqjoM3MYCASRJGq2xXrNIsg04UFUfOGZoI7BvaH9/qy1WX+jYO5PMJpmdn59fwa4lSWMLiyRPAX4J+JVRHL+qdlXVTFXNTE0t+J0SSdIJGufK4luBLcAHkjwAbALuSfINwAFg89DcTa22WF2SNEZj+wZ3VX0I+Pqj+y0wZqrq00n2Aq9JciODi9kPV9WDSd4J/MbQRe0XA68fR7/P/797xvExOsnc/duvnHQL0kSM8tbZG4D3AM9Ksj/JjuNMvxW4H5gD/gT4KYCqOgT8GvDe9npDq0mSxmhkK4uquqQzPj20XcBli8zbDexe0eYkScviN7glSV2GhSSpy7CQJHUZFpKkLsNCktRlWEiSugwLSVKXYSFJ6jIsJEldhoUkqcuwkCR1GRaSpC7DQpLUZVhIkroMC0lSl2EhSeoyLCRJXYaFJKnLsJAkdRkWkqQuw0KS1DWysEiyO8nBJPcO1X47yb8n+WCSdyQ5dWjs9Unmknw0yUuG6ue12lySy0fVryRpcaNcWVwHnHdM7Tbg2VX1XcB/AK8HSHImcDHwHe09f5RkXZJ1wB8C5wNnApe0uZKkMRpZWFTVHcChY2p/X1VH2u6dwKa2vQ24sar+s6o+DswBZ7XXXFXdX1VfAm5scyVJYzTJaxavBv62bW8E9g2N7W+1xeqPkWRnktkks/Pz8yNoV5LWromERZJfBo4Ab12pY1bVrqqaqaqZqamplTqsJAlYP+4PTPIq4AeBc6uqWvkAsHlo2qZW4zh1SdKYjHVlkeQ84HXAS6vqkaGhvcDFSZ6UZAuwFfg34L3A1iRbkpzC4CL43nH2LEka4coiyQ3AOcCGJPuBKxjc/fQk4LYkAHdW1U9U1YeT3Ax8hMHpqcuq6r/bcV4DvBNYB+yuqg+PqmdJ0sJGFhZVdckC5WuPM/+NwBsXqN8K3LqCrUmSlslvcEuSugwLSVKXYSFJ6jIsJEldhoUkqcuwkCR1GRaSpC7DQpLUZVhIkroMC0lSl2EhSeoyLCRJXYaFJKnLsJAkdRkWkqQuw0KS1GVYSJK6DAtJUpdhIUnqMiwkSV2GhSSpa2RhkWR3koNJ7h2qnZ7ktiQfa3+e1upJ8qYkc0k+mOR5Q+/Z3uZ/LMn2UfUrSVrcKFcW1wHnHVO7HLi9qrYCt7d9gPOBre21E7gGBuECXAG8ADgLuOJowEiSxmdkYVFVdwCHjilvA65v29cDFw7V99TAncCpSZ4JvAS4raoOVdVh4DYeG0CSpBEb9zWLM6rqwbb9EHBG294I7Buat7/VFqs/RpKdSWaTzM7Pz69s15K0xk3sAndVFVAreLxdVTVTVTNTU1MrdVhJEuMPi0+100u0Pw+2+gFg89C8Ta22WF2SNEbjDou9wNE7mrYDtwzVX9nuijobeLidrnon8OIkp7UL2y9uNUnSGK0f1YGT3ACcA2xIsp/BXU2/CdycZAfwCeCiNv1W4AJgDngEuBSgqg4l+TXgvW3eG6rq2IvmkqQRG1lYVNUliwydu8DcAi5b5Di7gd0r2JokaZn8BrckqcuwkCR1GRaSpC7DQpLUZVhIkroMC0lSl2EhSeoyLCRJXYaFJKnLsJAkdRkWkqQuw0KS1GVYSJK6DAtJUpdhIUnqMiwkSV2GhSSpy7CQJHUZFpKkLsNCktRlWEiSuiYSFklem+TDSe5NckOSJyfZkuSuJHNJbkpySpv7pLY/18anJ9GzJK1lYw+LJBuBnwFmqurZwDrgYuC3gKuq6tuAw8CO9pYdwOFWv6rNkySN0aROQ60HvibJeuApwIPAi4C3tfHrgQvb9ra2Txs/N0nG16okaUlhkeT2pdSWoqoOAFcCn2QQEg8DdwOfraojbdp+YGPb3gjsa+890uY/Y4F+diaZTTI7Pz9/Iq1JkhZx3LBo1xJOBzYkOS3J6e01zZf/MV+WJKcxWC1sAb4R+FrgvBM51rCq2lVVM1U1MzU19dUeTpI0ZH1n/MeBn2Pwj/rdwNHTP58D/uAEP/P7gI9X1TxAkrcDLwROTbK+rR42AQfa/APAZmB/O231dOAzJ/jZkqQTcNyVRVVdXVVbgF+sqm+pqi3t9ZyqOtGw+CRwdpKntGsP5wIfAf4BeFmbsx24pW3vbfu08XdVVZ3gZ0uSTkBvZQFAVf1+ku8BpoffU1V7lvuBVXVXkrcB9wBHgPcBu4C/AW5M8uutdm17y7XAnyaZAw4xuHNKkjRGSwqLJH8KfCvwfuC/W7mAZYcFQFVdAVxxTPl+4KwF5j4KvPxEPkeStDKWFBbADHCmp38kaW1a6vcs7gW+YZSNSJJWr6WuLDYAH0nyb8B/Hi1W1UtH0pUkaVVZalj86iibkCStbku9G+ofR92IJGn1WurdUJ9ncPcTwCnAE4EvVtXTRtWYJGn1WOrK4qlHt9sX6bYBZ4+qKUnS6rLsp87WwF8CL1n5diRJq9FST0P9yNDuExh87+LRkXQkSVp1lno31A8NbR8BHmBwKkqStAYs9ZrFpaNuRJK0ei31x482JXlHkoPt9RdJNo26OUnS6rDUC9xvYfCo8G9sr79qNUnSGrDUsJiqqrdU1ZH2ug7w5+gkaY1Yalh8JsmPJVnXXj+Gv1YnSWvGUsPi1cBFwEPAgwx+se5VI+pJkrTKLPXW2TcA26vqMECS04ErGYSIJOlxbqkri+86GhQAVXUIeO5oWpIkrTZLDYsnJDnt6E5bWSx1VSJJOskt9R/83wHek+TP2/7LgTeOpiVJ0mqz1G9w70kyC7yolX6kqj4yurYkSavJkk8ltXBYkYBIcirwZuDZDH4n49XAR4GbgGkGz566qKoOt0eiXw1cADwCvKqq7lmJPiRJS7PsR5SvkKuBv6uqbweeA9wHXA7cXlVbgdvbPsD5wNb22glcM/52JWltG3tYJHk68H+AawGq6ktV9VkGT7G9vk27HriwbW8D9rTf0bgTODXJM8fatCStcZNYWWwB5oG3JHlfkjcn+VrgjKp6sM15CDijbW8E9g29f3+rfYUkO5PMJpmdn58fYfuStPZMIizWA88Drqmq5wJf5MunnIDBr/Hx5d/8XpKq2lVVM1U1MzXlY6skaSVNIiz2A/ur6q62/zYG4fGpo6eX2p8H2/gBYPPQ+ze1miRpTMYeFlX1ELAvybNa6VwGd1ntBba32nbglra9F3hlBs4GHh46XSVJGoNJfQv7p4G3JjkFuB+4lEFw3ZxkB/AJBg8uBLiVwW2zcwxunfVX+yRpzCYSFlX1fmBmgaFzF5hbwGWj7kmStLhJfc9CknQSMSwkSV2GhSSpy7CQJHUZFpKkLsNCktRlWEiSugwLSVKXYSFJ6jIsJEldhoUkqcuwkCR1GRaSpC7DQpLUZVhIkroMC0lSl2EhSeoyLCRJXYaFJKnLsJAkdRkWkqSuiYVFknVJ3pfkr9v+liR3JZlLclOSU1r9SW1/ro1PT6pnSVqrJrmy+FngvqH93wKuqqpvAw4DO1p9B3C41a9q8yRJYzSRsEiyCfgB4M1tP8CLgLe1KdcDF7btbW2fNn5umy9JGpNJrSx+D3gd8D9t/xnAZ6vqSNvfD2xs2xuBfQBt/OE2/ysk2ZlkNsns/Pz8CFuXpLVn7GGR5AeBg1V190oet6p2VdVMVc1MTU2t5KElac1bP4HPfCHw0iQXAE8GngZcDZyaZH1bPWwCDrT5B4DNwP4k64GnA58Zf9uStHaNfWVRVa+vqk1VNQ1cDLyrqn4U+AfgZW3aduCWtr237dPG31VVNcaWJWnNW03fs/h/wM8nmWNwTeLaVr8WeEar/zxw+YT6k6Q1axKnof5XVb0beHfbvh84a4E5jwIvH2tjkqSvsJpWFpKkVcqwkCR1GRaSpC7DQpLUZVhIkroMC0lSl2EhSeoyLCRJXYaFJKnLsJAkdRkWkqQuw0KS1GVYSJK6DAtJUpdhIUnqMiwkSV2GhSSpy7CQJHUZFpKkLsNCktRlWEiSutaP+wOTbAb2AGcABeyqqquTnA7cBEwDDwAXVdXhJAGuBi4AHgFeVVX3jLtvaTX55Bu+c9ItaBX6pl/50MiOPYmVxRHgF6rqTOBs4LIkZwKXA7dX1Vbg9rYPcD6wtb12AteMv2VJWtvGHhZV9eDRlUFVfR64D9gIbAOub9OuBy5s29uAPTVwJ3BqkmeOt2tJWtsmes0iyTTwXOAu4IyqerANPcTgNBUMgmTf0Nv2t9qxx9qZZDbJ7Pz8/OialqQ1aGJhkeTrgL8Afq6qPjc8VlXF4HrGklXVrqqaqaqZqampFexUkjSRsEjyRAZB8daqensrf+ro6aX258FWPwBsHnr7plaTJI3J2MOi3d10LXBfVf3u0NBeYHvb3g7cMlR/ZQbOBh4eOl0lSRqDsd86C7wQeAXwoSTvb7VfAn4TuDnJDuATwEVt7FYGt83OMbh19tKxditJGn9YVNU/A1lk+NwF5hdw2UibkiQdl9/gliR1GRaSpC7DQpLUZVhIkroMC0lSl2EhSeoyLCRJXYaFJKnLsJAkdRkWkqQuw0KS1GVYSJK6DAtJUpdhIUnqMiwkSV2GhSSpy7CQJHUZFpKkLsNCktRlWEiSugwLSVLXSRMWSc5L8tEkc0kun3Q/krSWnBRhkWQd8IfA+cCZwCVJzpxsV5K0dpwUYQGcBcxV1f1V9SXgRmDbhHuSpDVj/aQbWKKNwL6h/f3AC4YnJNkJ7Gy7X0jy0TH1thZsAD496SZWg1y5fdIt6LH8+3nUFflqj/DNiw2cLGHRVVW7gF2T7uPxKMlsVc1Mug9pIf79HI+T5TTUAWDz0P6mVpMkjcHJEhbvBbYm2ZLkFOBiYO+Ee5KkNeOkOA1VVUeSvAZ4J7AO2F1VH55wW2uJp/e0mvn3cwxSVZPuQZK0yp0sp6EkSRNkWEiSugwLHZePWdFqlGR3koNJ7p10L2uFYaFF+ZgVrWLXAedNuom1xLDQ8fiYFa1KVXUHcGjSfawlhoWOZ6HHrGycUC+SJsiwkCR1GRY6Hh+zIgkwLHR8PmZFEmBY6Diq6ghw9DEr9wE3+5gVrQZJbgDeAzwryf4kOybd0+Odj/uQJHW5spAkdRkWkqQuw0KS1GVYSJK6DAtJUpdhIU1AkumjT0xNMpPkTW37nCTfM9nupMc6KX5WVXo8q6pZYLbtngN8AfjXiTUkLcCVhbRMSX45yX8k+eckNyT5xSTvTjLTxjckeaBtTyf5pyT3tNdjVg1tNfHXSaaBnwBem+T9Sb43yceTPLHNe9rwvjROriykZUjyfAaPPfluBv//uQe4+zhvOQh8f1U9mmQrcAMws9DEqnogyR8DX6iqK9vnvRv4AeAv2+e+var+a0X+x0jL4MpCWp7vBd5RVY9U1efoPyvricCfJPkQ8OcMfkRqOd4MXNq2LwXessz3SyvClYW0Mo7w5f/4evJQ/bXAp4DntPFHl3PQqvqXdirrHGBdVfkzopoIVxbS8twBXJjka5I8FfihVn8AeH7bftnQ/KcDD1bV/wCvANZ1jv954KnH1PYAf4arCk2QYSEtQ1XdA9wEfAD4WwaPcQe4EvjJJO8DNgy95Y+A7Uk+AHw78MXOR/wV8MNHL3C32luB0xhc75AmwqfOSl+FJL/K0AXpEX3Gy4BtVfWKUX2G1OM1C2kVS/L7wPnABZPuRWubKwtJUpfXLCRJXYaFJKnLsJAkdRkWkqQuw0KS1PX/ASoTvN+6kVUJAAAAAElFTkSuQmCC\n",
438 |       "text/plain": [
439 |        "<Figure size 432x288 with 1 Axes>"
440 |       ]
441 |      },
442 |      "metadata": {
443 |       "needs_background": "light"
444 |      },
445 |      "output_type": "display_data"
446 |     }
447 |    ],
448 |    "source": [
449 |     "sns.countplot(wine['quality'])"
450 |    ]
451 |   },
452 |   {
453 |    "cell_type": "code",
454 |    "execution_count": 80,
455 |    "id": "09cc0e42",
456 |    "metadata": {},
457 |    "outputs": [],
458 |    "source": [
459 |     "#Now seperate the dataset as response variable and feature variabes\n",
460 |     "X = wine.drop('quality', axis = 1)\n",
461 |     "y = wine['quality']"
462 |    ]
463 |   },
464 |   {
465 |    "cell_type": "code",
466 |    "execution_count": 81,
467 |    "id": "065ef448",
468 |    "metadata": {},
469 |    "outputs": [],
470 |    "source": [
471 |     "#Train and Test splitting of data \n",
472 |     "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 42)"
473 |    ]
474 |   },
475 |   {
476 |    "cell_type": "code",
477 |    "execution_count": 82,
478 |    "id": "45f610f3",
479 |    "metadata": {},
480 |    "outputs": [],
481 |    "source": [
482 |     "#Applying Standard scaling to get optimized result\n",
483 |     "sc = StandardScaler()"
484 |    ]
485 |   },
486 |   {
487 |    "cell_type": "code",
488 |    "execution_count": 83,
489 |    "id": "bac4bfee",
490 |    "metadata": {},
491 |    "outputs": [],
492 |    "source": [
493 |     "X_train = sc.fit_transform(X_train)\n",
494 |     "X_test = sc.fit_transform(X_test)"
495 |    ]
496 |   },
497 |   {
498 |    "cell_type": "code",
499 |    "execution_count": 95,
500 |    "id": "9809c6c7",
501 |    "metadata": {},
502 |    "outputs": [
503 |     {
504 |      "data": {
505 |       "text/plain": [
506 |        "array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0,\n",
507 |        "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
508 |        "       0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
509 |        "       0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0,\n",
510 |        "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
511 |        "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
512 |        "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
513 |        "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0,\n",
514 |        "       0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
515 |        "       0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
516 |        "       0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
517 |        "       0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,\n",
518 |        "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0,\n",
519 |        "       0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
520 |        "       0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])"
521 |       ]
522 |      },
523 |      "execution_count": 95,
524 |      "metadata": {},
525 |      "output_type": "execute_result"
526 |     }
527 |    ],
528 |    "source": [
529 |     "svc = SVC()\n",
530 |     "svc.fit(X_train, y_train)\n",
531 |     "pred_svc = svc.predict(X_test)\n",
532 |     "pred_svc"
533 |    ]
534 |   },
535 |   {
536 |    "cell_type": "code",
537 |    "execution_count": 85,
538 |    "id": "89aed9c5",
539 |    "metadata": {},
540 |    "outputs": [
541 |     {
542 |      "name": "stdout",
543 |      "output_type": "stream",
544 |      "text": [
545 |       "              precision    recall  f1-score   support\n",
546 |       "\n",
547 |       "           0       0.88      0.98      0.93       273\n",
548 |       "           1       0.71      0.26      0.37        47\n",
549 |       "\n",
550 |       "    accuracy                           0.88       320\n",
551 |       "   macro avg       0.80      0.62      0.65       320\n",
552 |       "weighted avg       0.86      0.88      0.85       320\n",
553 |       "\n"
554 |      ]
555 |     }
556 |    ],
557 |    "source": [
558 |     "print(classification_report(y_test, pred_svc))"
559 |    ]
560 |   },
561 |   {
562 |    "cell_type": "code",
563 |    "execution_count": 86,
564 |    "id": "c4c95e6e",
565 |    "metadata": {},
566 |    "outputs": [],
567 |    "source": [
568 |     "#Finding best parameters for our SVC model\n",
569 |     "param = {\n",
570 |     "    'C': [0.1,0.8,0.9,1,1.1,1.2,1.3,1.4],\n",
571 |     "    'kernel':['linear', 'rbf'],\n",
572 |     "    'gamma' :[0.1,0.8,0.9,1,1.1,1.2,1.3,1.4]\n",
573 |     "}\n",
574 |     "grid_svc = GridSearchCV(svc, param_grid=param, scoring='accuracy', cv=10)"
575 |    ]
576 |   },
577 |   {
578 |    "cell_type": "code",
579 |    "execution_count": 87,
580 |    "id": "3a0d4b32",
581 |    "metadata": {},
582 |    "outputs": [
583 |     {
584 |      "data": {
585 |       "text/plain": [
586 |        "GridSearchCV(cv=10, estimator=SVC(),\n",
587 |        "             param_grid={'C': [0.1, 0.8, 0.9, 1, 1.1, 1.2, 1.3, 1.4],\n",
588 |        "                         'gamma': [0.1, 0.8, 0.9, 1, 1.1, 1.2, 1.3, 1.4],\n",
589 |        "                         'kernel': ['linear', 'rbf']},\n",
590 |        "             scoring='accuracy')"
591 |       ]
592 |      },
593 |      "execution_count": 87,
594 |      "metadata": {},
595 |      "output_type": "execute_result"
596 |     }
597 |    ],
598 |    "source": [
599 |     "grid_svc.fit(X_train, y_train)"
600 |    ]
601 |   },
602 |   {
603 |    "cell_type": "code",
604 |    "execution_count": 88,
605 |    "id": "4cd8c8d7",
606 |    "metadata": {},
607 |    "outputs": [
608 |     {
609 |      "data": {
610 |       "text/plain": [
611 |        "{'C': 1.2, 'gamma': 0.9, 'kernel': 'rbf'}"
612 |       ]
613 |      },
614 |      "execution_count": 88,
615 |      "metadata": {},
616 |      "output_type": "execute_result"
617 |     }
618 |    ],
619 |    "source": [
620 |     "#Best parameters for our svc model\n",
621 |     "grid_svc.best_params_"
622 |    ]
623 |   },
624 |   {
625 |    "cell_type": "code",
626 |    "execution_count": 89,
627 |    "id": "932f2eef",
628 |    "metadata": {},
629 |    "outputs": [
630 |     {
631 |      "name": "stdout",
632 |      "output_type": "stream",
633 |      "text": [
634 |       "              precision    recall  f1-score   support\n",
635 |       "\n",
636 |       "           0       0.90      0.99      0.94       273\n",
637 |       "           1       0.89      0.34      0.49        47\n",
638 |       "\n",
639 |       "    accuracy                           0.90       320\n",
640 |       "   macro avg       0.89      0.67      0.72       320\n",
641 |       "weighted avg       0.90      0.90      0.88       320\n",
642 |       "\n"
643 |      ]
644 |     }
645 |    ],
646 |    "source": [
647 |     "#Let's run our SVC again with the best parameters.\n",
648 |     "svc2 = SVC(C = 1.2, gamma =  0.9, kernel= 'rbf')\n",
649 |     "svc2.fit(X_train, y_train)\n",
650 |     "pred_svc2 = svc2.predict(X_test)\n",
651 |     "print(classification_report(y_test, pred_svc2))"
652 |    ]
653 |   },
654 |   {
655 |    "cell_type": "code",
656 |    "execution_count": null,
657 |    "id": "cda0622f",
658 |    "metadata": {},
659 |    "outputs": [],
660 |    "source": []
661 |   },
662 |   {
663 |    "cell_type": "code",
664 |    "execution_count": null,
665 |    "id": "e027a200",
666 |    "metadata": {},
667 |    "outputs": [],
668 |    "source": []
669 |   }
670 |  ],
671 |  "metadata": {
672 |   "kernelspec": {
673 |    "display_name": "Python 3 (ipykernel)",
674 |    "language": "python",
675 |    "name": "python3"
676 |   },
677 |   "language_info": {
678 |    "codemirror_mode": {
679 |     "name": "ipython",
680 |     "version": 3
681 |    },
682 |    "file_extension": ".py",
683 |    "mimetype": "text/x-python",
684 |    "name": "python",
685 |    "nbconvert_exporter": "python",
686 |    "pygments_lexer": "ipython3",
687 |    "version": "3.8.8"
688 |   }
689 |  },
690 |  "nbformat": 4,
691 |  "nbformat_minor": 5
692 | }
693 | 


--------------------------------------------------------------------------------
/KNN algorithm.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 2,
  6 |    "id": "romance-interstate",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "#importing libraries\n",
 11 |     "import matplotlib.pyplot as plt\n",
 12 |     "from sklearn import datasets\n",
 13 |     "from sklearn.model_selection import train_test_split \n",
 14 |     "from sklearn.neighbors import KNeighborsClassifier"
 15 |    ]
 16 |   },
 17 |   {
 18 |    "cell_type": "code",
 19 |    "execution_count": 3,
 20 |    "id": "knowing-suffering",
 21 |    "metadata": {},
 22 |    "outputs": [],
 23 |    "source": [
 24 |     "# load the data\n",
 25 |     "digits = datasets.load_digits()"
 26 |    ]
 27 |   },
 28 |   {
 29 |    "cell_type": "code",
 30 |    "execution_count": 9,
 31 |    "id": "unauthorized-release",
 32 |    "metadata": {},
 33 |    "outputs": [
 34 |     {
 35 |      "data": {
 36 |       "text/plain": [
 37 |        "5"
 38 |       ]
 39 |      },
 40 |      "execution_count": 9,
 41 |      "metadata": {},
 42 |      "output_type": "execute_result"
 43 |     }
 44 |    ],
 45 |    "source": [
 46 |     "digits.target[1700]"
 47 |    ]
 48 |   },
 49 |   {
 50 |    "cell_type": "code",
 51 |    "execution_count": 5,
 52 |    "id": "spoken-hepatitis",
 53 |    "metadata": {},
 54 |    "outputs": [],
 55 |    "source": [
 56 |     "#Features allocation\n",
 57 |     "Samplefeatures=digits.data\n",
 58 |     "labels=digits.target"
 59 |    ]
 60 |   },
 61 |   {
 62 |    "cell_type": "code",
 63 |    "execution_count": 10,
 64 |    "id": "nominated-edmonton",
 65 |    "metadata": {},
 66 |    "outputs": [
 67 |     {
 68 |      "data": {
 69 |       "text/plain": [
 70 |        "<matplotlib.image.AxesImage at 0x21793cfe8b0>"
 71 |       ]
 72 |      },
 73 |      "execution_count": 10,
 74 |      "metadata": {},
 75 |      "output_type": "execute_result"
 76 |     },
 77 |     {
 78 |      "data": {
 79 |       "image/png": "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\n",
 80 |       "text/plain": [
 81 |        "<Figure size 432x288 with 1 Axes>"
 82 |       ]
 83 |      },
 84 |      "metadata": {
 85 |       "needs_background": "light"
 86 |      },
 87 |      "output_type": "display_data"
 88 |     }
 89 |    ],
 90 |    "source": [
 91 |     "plt.imshow(digits.images[1700], cmap=plt.cm.gray_r, interpolation='nearest')"
 92 |    ]
 93 |   },
 94 |   {
 95 |    "cell_type": "code",
 96 |    "execution_count": 17,
 97 |    "id": "exclusive-groove",
 98 |    "metadata": {},
 99 |    "outputs": [],
100 |    "source": [
101 |     "# Split into training and test set\n",
102 |     "trainimg, testimg,trainlab,testlab = train_test_split(Samplefeatures, labels, test_size = 0.2, random_state=42)"
103 |    ]
104 |   },
105 |   {
106 |    "cell_type": "code",
107 |    "execution_count": 18,
108 |    "id": "broken-pakistan",
109 |    "metadata": {},
110 |    "outputs": [],
111 |    "source": [
112 |     "knn = KNeighborsClassifier(n_neighbors=7)"
113 |    ]
114 |   },
115 |   {
116 |    "cell_type": "code",
117 |    "execution_count": 19,
118 |    "id": "surprising-commodity",
119 |    "metadata": {},
120 |    "outputs": [
121 |     {
122 |      "data": {
123 |       "text/plain": [
124 |        "KNeighborsClassifier(n_neighbors=7)"
125 |       ]
126 |      },
127 |      "execution_count": 19,
128 |      "metadata": {},
129 |      "output_type": "execute_result"
130 |     }
131 |    ],
132 |    "source": [
133 |     "knn.fit(trainimg, trainlab)"
134 |    ]
135 |   },
136 |   {
137 |    "cell_type": "code",
138 |    "execution_count": 34,
139 |    "id": "contrary-moore",
140 |    "metadata": {},
141 |    "outputs": [
142 |     {
143 |      "data": {
144 |       "text/plain": [
145 |        "360"
146 |       ]
147 |      },
148 |      "execution_count": 34,
149 |      "metadata": {},
150 |      "output_type": "execute_result"
151 |     }
152 |    ],
153 |    "source": [
154 |     "len(testimg)"
155 |    ]
156 |   },
157 |   {
158 |    "cell_type": "code",
159 |    "execution_count": 35,
160 |    "id": "exterior-wallet",
161 |    "metadata": {},
162 |    "outputs": [
163 |     {
164 |      "data": {
165 |       "text/plain": [
166 |        "array([5])"
167 |       ]
168 |      },
169 |      "execution_count": 35,
170 |      "metadata": {},
171 |      "output_type": "execute_result"
172 |     }
173 |    ],
174 |    "source": [
175 |     "knn.predict(testimg[[359]])"
176 |    ]
177 |   },
178 |   {
179 |    "cell_type": "code",
180 |    "execution_count": 37,
181 |    "id": "hearing-event",
182 |    "metadata": {},
183 |    "outputs": [
184 |     {
185 |      "data": {
186 |       "text/plain": [
187 |        "5"
188 |       ]
189 |      },
190 |      "execution_count": 37,
191 |      "metadata": {},
192 |      "output_type": "execute_result"
193 |     }
194 |    ],
195 |    "source": [
196 |     "#original\n",
197 |     "testlab[359]"
198 |    ]
199 |   },
200 |   {
201 |    "cell_type": "code",
202 |    "execution_count": 39,
203 |    "id": "critical-replica",
204 |    "metadata": {},
205 |    "outputs": [
206 |     {
207 |      "name": "stdout",
208 |      "output_type": "stream",
209 |      "text": [
210 |       "0.9888888888888889\n"
211 |      ]
212 |     }
213 |    ],
214 |    "source": [
215 |     "#accuracy\n",
216 |     "print(knn.score(testimg,testlab))"
217 |    ]
218 |   },
219 |   {
220 |    "cell_type": "code",
221 |    "execution_count": null,
222 |    "id": "surprised-migration",
223 |    "metadata": {},
224 |    "outputs": [],
225 |    "source": []
226 |   }
227 |  ],
228 |  "metadata": {
229 |   "kernelspec": {
230 |    "display_name": "Python 3",
231 |    "language": "python",
232 |    "name": "python3"
233 |   },
234 |   "language_info": {
235 |    "codemirror_mode": {
236 |     "name": "ipython",
237 |     "version": 3
238 |    },
239 |    "file_extension": ".py",
240 |    "mimetype": "text/x-python",
241 |    "name": "python",
242 |    "nbconvert_exporter": "python",
243 |    "pygments_lexer": "ipython3",
244 |    "version": "3.8.8"
245 |   }
246 |  },
247 |  "nbformat": 4,
248 |  "nbformat_minor": 5
249 | }
250 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
 1 | MIT License
 2 | 
 3 | Copyright (c) 2021 AKpython
 4 | 
 5 | Permission is hereby granted, free of charge, to any person obtaining a copy
 6 | of this software and associated documentation files (the "Software"), to deal
 7 | in the Software without restriction, including without limitation the rights
 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 | 
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 | 
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.
22 | 


--------------------------------------------------------------------------------
/LP1.py:
--------------------------------------------------------------------------------
 1 | from pulp import *
 2 | # declare your variables
 3 | A = LpVariable("A", 100, 200)   # 100 <= A <= 200
 4 | B = LpVariable("B", 80, 170) # 80 <= B <= 170
 5 | # defines the problem: optimization - Maximization
 6 | prob = LpProblem("problem", LpMaximize)
 7 | 
 8 | 
 9 | # defines the constraints
10 | prob += A + B >=200
11 | prob += A<=200
12 | prob += A>=100
13 | prob += B>=80
14 | prob += B<=170
15 | 
16 | 
17 | # defines the objective function to maximize
18 | prob += 5000*B- 2000*A 
19 | 
20 | 
21 | # solve the problem
22 | status = prob.solve()
23 | print('printing status of the LP problem: ', LpStatus[status])
24 | 
25 | 
26 | # print the results A = 100, B = 170
27 | print('Value of model A car: ', value(A))
28 | print('Value of model B car: ', value(B))
29 | print('the optimal solution or say maximum profit: $', value(prob.objective))


--------------------------------------------------------------------------------
/Logistic regression.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "floral-reality",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "#Importing libraries\n",
 11 |     "import pandas as pd\n",
 12 |     "%matplotlib inline\n",
 13 |     "from sklearn.model_selection import train_test_split"
 14 |    ]
 15 |   },
 16 |   {
 17 |    "cell_type": "code",
 18 |    "execution_count": 2,
 19 |    "id": "undefined-submission",
 20 |    "metadata": {},
 21 |    "outputs": [
 22 |     {
 23 |      "data": {
 24 |       "text/html": [
 25 |        "<div>\n",
 26 |        "<style scoped>\n",
 27 |        "    .dataframe tbody tr th:only-of-type {\n",
 28 |        "        vertical-align: middle;\n",
 29 |        "    }\n",
 30 |        "\n",
 31 |        "    .dataframe tbody tr th {\n",
 32 |        "        vertical-align: top;\n",
 33 |        "    }\n",
 34 |        "\n",
 35 |        "    .dataframe thead th {\n",
 36 |        "        text-align: right;\n",
 37 |        "    }\n",
 38 |        "</style>\n",
 39 |        "<table border=\"1\" class=\"dataframe\">\n",
 40 |        "  <thead>\n",
 41 |        "    <tr style=\"text-align: right;\">\n",
 42 |        "      <th></th>\n",
 43 |        "      <th>Pregnancies</th>\n",
 44 |        "      <th>Glucose</th>\n",
 45 |        "      <th>BloodPressure</th>\n",
 46 |        "      <th>SkinThickness</th>\n",
 47 |        "      <th>Insulin</th>\n",
 48 |        "      <th>BMI</th>\n",
 49 |        "      <th>DiabetesPedigreeFunction</th>\n",
 50 |        "      <th>Age</th>\n",
 51 |        "      <th>Outcome</th>\n",
 52 |        "    </tr>\n",
 53 |        "  </thead>\n",
 54 |        "  <tbody>\n",
 55 |        "    <tr>\n",
 56 |        "      <th>0</th>\n",
 57 |        "      <td>6</td>\n",
 58 |        "      <td>148</td>\n",
 59 |        "      <td>72</td>\n",
 60 |        "      <td>35</td>\n",
 61 |        "      <td>0</td>\n",
 62 |        "      <td>33.6</td>\n",
 63 |        "      <td>0.627</td>\n",
 64 |        "      <td>50</td>\n",
 65 |        "      <td>1</td>\n",
 66 |        "    </tr>\n",
 67 |        "    <tr>\n",
 68 |        "      <th>1</th>\n",
 69 |        "      <td>1</td>\n",
 70 |        "      <td>85</td>\n",
 71 |        "      <td>66</td>\n",
 72 |        "      <td>29</td>\n",
 73 |        "      <td>0</td>\n",
 74 |        "      <td>26.6</td>\n",
 75 |        "      <td>0.351</td>\n",
 76 |        "      <td>31</td>\n",
 77 |        "      <td>0</td>\n",
 78 |        "    </tr>\n",
 79 |        "    <tr>\n",
 80 |        "      <th>2</th>\n",
 81 |        "      <td>8</td>\n",
 82 |        "      <td>183</td>\n",
 83 |        "      <td>64</td>\n",
 84 |        "      <td>0</td>\n",
 85 |        "      <td>0</td>\n",
 86 |        "      <td>23.3</td>\n",
 87 |        "      <td>0.672</td>\n",
 88 |        "      <td>32</td>\n",
 89 |        "      <td>1</td>\n",
 90 |        "    </tr>\n",
 91 |        "    <tr>\n",
 92 |        "      <th>3</th>\n",
 93 |        "      <td>1</td>\n",
 94 |        "      <td>89</td>\n",
 95 |        "      <td>66</td>\n",
 96 |        "      <td>23</td>\n",
 97 |        "      <td>94</td>\n",
 98 |        "      <td>28.1</td>\n",
 99 |        "      <td>0.167</td>\n",
100 |        "      <td>21</td>\n",
101 |        "      <td>0</td>\n",
102 |        "    </tr>\n",
103 |        "    <tr>\n",
104 |        "      <th>4</th>\n",
105 |        "      <td>0</td>\n",
106 |        "      <td>137</td>\n",
107 |        "      <td>40</td>\n",
108 |        "      <td>35</td>\n",
109 |        "      <td>168</td>\n",
110 |        "      <td>43.1</td>\n",
111 |        "      <td>2.288</td>\n",
112 |        "      <td>33</td>\n",
113 |        "      <td>1</td>\n",
114 |        "    </tr>\n",
115 |        "  </tbody>\n",
116 |        "</table>\n",
117 |        "</div>"
118 |       ],
119 |       "text/plain": [
120 |        "   Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin   BMI  \\\n",
121 |        "0            6      148             72             35        0  33.6   \n",
122 |        "1            1       85             66             29        0  26.6   \n",
123 |        "2            8      183             64              0        0  23.3   \n",
124 |        "3            1       89             66             23       94  28.1   \n",
125 |        "4            0      137             40             35      168  43.1   \n",
126 |        "\n",
127 |        "   DiabetesPedigreeFunction  Age  Outcome  \n",
128 |        "0                     0.627   50        1  \n",
129 |        "1                     0.351   31        0  \n",
130 |        "2                     0.672   32        1  \n",
131 |        "3                     0.167   21        0  \n",
132 |        "4                     2.288   33        1  "
133 |       ]
134 |      },
135 |      "execution_count": 2,
136 |      "metadata": {},
137 |      "output_type": "execute_result"
138 |     }
139 |    ],
140 |    "source": [
141 |     "df = pd.read_csv(\"diabetes.csv\")\n",
142 |     "df.head()"
143 |    ]
144 |   },
145 |   {
146 |    "cell_type": "code",
147 |    "execution_count": 3,
148 |    "id": "continuing-royal",
149 |    "metadata": {},
150 |    "outputs": [],
151 |    "source": [
152 |     "feature_cols = ['Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness','Insulin','BMI','DiabetesPedigreeFunction','Age']\n",
153 |     "X = df[feature_cols] # Features\n",
154 |     "y = df.Outcome # Target variable"
155 |    ]
156 |   },
157 |   {
158 |    "cell_type": "code",
159 |    "execution_count": null,
160 |    "id": "supposed-latter",
161 |    "metadata": {},
162 |    "outputs": [],
163 |    "source": []
164 |   },
165 |   {
166 |    "cell_type": "code",
167 |    "execution_count": 5,
168 |    "id": "administrative-aside",
169 |    "metadata": {},
170 |    "outputs": [],
171 |    "source": [
172 |     "X_train, X_test, y_train, y_test = train_test_split(X,y,train_size=0.7)"
173 |    ]
174 |   },
175 |   {
176 |    "cell_type": "code",
177 |    "execution_count": 6,
178 |    "id": "under-essence",
179 |    "metadata": {},
180 |    "outputs": [
181 |     {
182 |      "data": {
183 |       "text/plain": [
184 |        "450    0\n",
185 |        "742    0\n",
186 |        "304    0\n",
187 |        "667    1\n",
188 |        "500    0\n",
189 |        "      ..\n",
190 |        "164    1\n",
191 |        "576    0\n",
192 |        "315    0\n",
193 |        "68     0\n",
194 |        "631    0\n",
195 |        "Name: Outcome, Length: 231, dtype: int64"
196 |       ]
197 |      },
198 |      "execution_count": 6,
199 |      "metadata": {},
200 |      "output_type": "execute_result"
201 |     }
202 |    ],
203 |    "source": [
204 |     "y_test"
205 |    ]
206 |   },
207 |   {
208 |    "cell_type": "code",
209 |    "execution_count": 7,
210 |    "id": "fiscal-blake",
211 |    "metadata": {},
212 |    "outputs": [],
213 |    "source": [
214 |     "from sklearn.linear_model import LogisticRegression\n",
215 |     "model = LogisticRegression()"
216 |    ]
217 |   },
218 |   {
219 |    "cell_type": "code",
220 |    "execution_count": 8,
221 |    "id": "vulnerable-bradley",
222 |    "metadata": {},
223 |    "outputs": [
224 |     {
225 |      "name": "stderr",
226 |      "output_type": "stream",
227 |      "text": [
228 |       "c:\\users\\admin\\appdata\\local\\programs\\python\\python38\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
229 |       "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
230 |       "\n",
231 |       "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
232 |       "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
233 |       "Please also refer to the documentation for alternative solver options:\n",
234 |       "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
235 |       "  n_iter_i = _check_optimize_result(\n"
236 |      ]
237 |     },
238 |     {
239 |      "data": {
240 |       "text/plain": [
241 |        "LogisticRegression()"
242 |       ]
243 |      },
244 |      "execution_count": 8,
245 |      "metadata": {},
246 |      "output_type": "execute_result"
247 |     }
248 |    ],
249 |    "source": [
250 |     "\n",
251 |     "model.fit(X_train, y_train)"
252 |    ]
253 |   },
254 |   {
255 |    "cell_type": "code",
256 |    "execution_count": 11,
257 |    "id": "handmade-highlight",
258 |    "metadata": {},
259 |    "outputs": [],
260 |    "source": [
261 |     "y_predicted = model.predict(X_test)#Random value"
262 |    ]
263 |   },
264 |   {
265 |    "cell_type": "code",
266 |    "execution_count": 12,
267 |    "id": "steady-organization",
268 |    "metadata": {},
269 |    "outputs": [
270 |     {
271 |      "name": "stdout",
272 |      "output_type": "stream",
273 |      "text": [
274 |       "[0 0 0 0 0 0 0 0 0 0 0 1 0 0 1 1 1 1 0 0 0 0 1 0 0 0 1 0 0 0 0 0 0 0 0 0 0\n",
275 |       " 0 1 0 0 1 0 1 0 0 1 0 1 0 0 0 1 0 1 1 0 0 0 1 0 1 0 0 1 0 0 0 0 1 1 0 1 1\n",
276 |       " 0 1 0 1 1 0 0 1 1 1 0 1 0 0 0 1 0 0 0 0 1 0 1 1 0 1 1 0 0 0 0 0 1 0 0 0 0\n",
277 |       " 1 0 1 1 1 0 0 0 0 1 1 1 1 0 0 0 0 0 1 1 0 0 0 1 0 0 1 1 0 0 1 1 1 0 1 0 0\n",
278 |       " 0 0 0 0 0 0 1 0 1 0 1 0 0 0 1 0 1 0 0 0 1 0 0 0 1 0 0 0 1 0 0 0 0 1 0 1 0\n",
279 |       " 1 1 0 1 1 0 0 1 1 0 0 0 1 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 0\n",
280 |       " 0 1 0 1 0 0 0 0 0]\n"
281 |      ]
282 |     }
283 |    ],
284 |    "source": [
285 |     "print(y_predicted)"
286 |    ]
287 |   },
288 |   {
289 |    "cell_type": "code",
290 |    "execution_count": null,
291 |    "id": "excited-madison",
292 |    "metadata": {},
293 |    "outputs": [],
294 |    "source": []
295 |   },
296 |   {
297 |    "cell_type": "code",
298 |    "execution_count": 115,
299 |    "id": "sunrise-feelings",
300 |    "metadata": {},
301 |    "outputs": [
302 |     {
303 |      "data": {
304 |       "text/plain": [
305 |        "0.7965367965367965"
306 |       ]
307 |      },
308 |      "execution_count": 115,
309 |      "metadata": {},
310 |      "output_type": "execute_result"
311 |     }
312 |    ],
313 |    "source": [
314 |     "model.score(X_test,y_test)"
315 |    ]
316 |   },
317 |   {
318 |    "cell_type": "code",
319 |    "execution_count": null,
320 |    "id": "literary-jesus",
321 |    "metadata": {},
322 |    "outputs": [],
323 |    "source": []
324 |   },
325 |   {
326 |    "cell_type": "code",
327 |    "execution_count": null,
328 |    "id": "latin-stopping",
329 |    "metadata": {},
330 |    "outputs": [],
331 |    "source": []
332 |   }
333 |  ],
334 |  "metadata": {
335 |   "kernelspec": {
336 |    "display_name": "Python 3",
337 |    "language": "python",
338 |    "name": "python3"
339 |   },
340 |   "language_info": {
341 |    "codemirror_mode": {
342 |     "name": "ipython",
343 |     "version": 3
344 |    },
345 |    "file_extension": ".py",
346 |    "mimetype": "text/x-python",
347 |    "name": "python",
348 |    "nbconvert_exporter": "python",
349 |    "pygments_lexer": "ipython3",
350 |    "version": "3.8.8"
351 |   }
352 |  },
353 |  "nbformat": 4,
354 |  "nbformat_minor": 5
355 | }
356 | 


--------------------------------------------------------------------------------
/Salary prediction ( Linear Regression ).ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 3,
  6 |    "id": "lined-aquatic",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import numpy as np # linear algebra\n",
 11 |     "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)"
 12 |    ]
 13 |   },
 14 |   {
 15 |    "cell_type": "code",
 16 |    "execution_count": 4,
 17 |    "id": "several-wagon",
 18 |    "metadata": {},
 19 |    "outputs": [
 20 |     {
 21 |      "data": {
 22 |       "text/html": [
 23 |        "<div>\n",
 24 |        "<style scoped>\n",
 25 |        "    .dataframe tbody tr th:only-of-type {\n",
 26 |        "        vertical-align: middle;\n",
 27 |        "    }\n",
 28 |        "\n",
 29 |        "    .dataframe tbody tr th {\n",
 30 |        "        vertical-align: top;\n",
 31 |        "    }\n",
 32 |        "\n",
 33 |        "    .dataframe thead th {\n",
 34 |        "        text-align: right;\n",
 35 |        "    }\n",
 36 |        "</style>\n",
 37 |        "<table border=\"1\" class=\"dataframe\">\n",
 38 |        "  <thead>\n",
 39 |        "    <tr style=\"text-align: right;\">\n",
 40 |        "      <th></th>\n",
 41 |        "      <th>YearsExperience</th>\n",
 42 |        "      <th>Salary</th>\n",
 43 |        "    </tr>\n",
 44 |        "  </thead>\n",
 45 |        "  <tbody>\n",
 46 |        "    <tr>\n",
 47 |        "      <th>0</th>\n",
 48 |        "      <td>1.1</td>\n",
 49 |        "      <td>39343.0</td>\n",
 50 |        "    </tr>\n",
 51 |        "    <tr>\n",
 52 |        "      <th>1</th>\n",
 53 |        "      <td>1.3</td>\n",
 54 |        "      <td>46205.0</td>\n",
 55 |        "    </tr>\n",
 56 |        "    <tr>\n",
 57 |        "      <th>2</th>\n",
 58 |        "      <td>1.5</td>\n",
 59 |        "      <td>37731.0</td>\n",
 60 |        "    </tr>\n",
 61 |        "    <tr>\n",
 62 |        "      <th>3</th>\n",
 63 |        "      <td>2.0</td>\n",
 64 |        "      <td>43525.0</td>\n",
 65 |        "    </tr>\n",
 66 |        "    <tr>\n",
 67 |        "      <th>4</th>\n",
 68 |        "      <td>2.2</td>\n",
 69 |        "      <td>39891.0</td>\n",
 70 |        "    </tr>\n",
 71 |        "    <tr>\n",
 72 |        "      <th>5</th>\n",
 73 |        "      <td>2.9</td>\n",
 74 |        "      <td>56642.0</td>\n",
 75 |        "    </tr>\n",
 76 |        "    <tr>\n",
 77 |        "      <th>6</th>\n",
 78 |        "      <td>3.0</td>\n",
 79 |        "      <td>60150.0</td>\n",
 80 |        "    </tr>\n",
 81 |        "    <tr>\n",
 82 |        "      <th>7</th>\n",
 83 |        "      <td>3.2</td>\n",
 84 |        "      <td>54445.0</td>\n",
 85 |        "    </tr>\n",
 86 |        "    <tr>\n",
 87 |        "      <th>8</th>\n",
 88 |        "      <td>3.2</td>\n",
 89 |        "      <td>64445.0</td>\n",
 90 |        "    </tr>\n",
 91 |        "    <tr>\n",
 92 |        "      <th>9</th>\n",
 93 |        "      <td>3.7</td>\n",
 94 |        "      <td>57189.0</td>\n",
 95 |        "    </tr>\n",
 96 |        "    <tr>\n",
 97 |        "      <th>10</th>\n",
 98 |        "      <td>3.9</td>\n",
 99 |        "      <td>63218.0</td>\n",
100 |        "    </tr>\n",
101 |        "    <tr>\n",
102 |        "      <th>11</th>\n",
103 |        "      <td>4.0</td>\n",
104 |        "      <td>55794.0</td>\n",
105 |        "    </tr>\n",
106 |        "    <tr>\n",
107 |        "      <th>12</th>\n",
108 |        "      <td>4.0</td>\n",
109 |        "      <td>56957.0</td>\n",
110 |        "    </tr>\n",
111 |        "    <tr>\n",
112 |        "      <th>13</th>\n",
113 |        "      <td>4.1</td>\n",
114 |        "      <td>57081.0</td>\n",
115 |        "    </tr>\n",
116 |        "    <tr>\n",
117 |        "      <th>14</th>\n",
118 |        "      <td>4.5</td>\n",
119 |        "      <td>61111.0</td>\n",
120 |        "    </tr>\n",
121 |        "    <tr>\n",
122 |        "      <th>15</th>\n",
123 |        "      <td>4.9</td>\n",
124 |        "      <td>67938.0</td>\n",
125 |        "    </tr>\n",
126 |        "    <tr>\n",
127 |        "      <th>16</th>\n",
128 |        "      <td>5.1</td>\n",
129 |        "      <td>66029.0</td>\n",
130 |        "    </tr>\n",
131 |        "    <tr>\n",
132 |        "      <th>17</th>\n",
133 |        "      <td>5.3</td>\n",
134 |        "      <td>83088.0</td>\n",
135 |        "    </tr>\n",
136 |        "    <tr>\n",
137 |        "      <th>18</th>\n",
138 |        "      <td>5.9</td>\n",
139 |        "      <td>81363.0</td>\n",
140 |        "    </tr>\n",
141 |        "    <tr>\n",
142 |        "      <th>19</th>\n",
143 |        "      <td>6.0</td>\n",
144 |        "      <td>93940.0</td>\n",
145 |        "    </tr>\n",
146 |        "    <tr>\n",
147 |        "      <th>20</th>\n",
148 |        "      <td>6.8</td>\n",
149 |        "      <td>91738.0</td>\n",
150 |        "    </tr>\n",
151 |        "    <tr>\n",
152 |        "      <th>21</th>\n",
153 |        "      <td>7.1</td>\n",
154 |        "      <td>98273.0</td>\n",
155 |        "    </tr>\n",
156 |        "    <tr>\n",
157 |        "      <th>22</th>\n",
158 |        "      <td>7.9</td>\n",
159 |        "      <td>101302.0</td>\n",
160 |        "    </tr>\n",
161 |        "    <tr>\n",
162 |        "      <th>23</th>\n",
163 |        "      <td>8.2</td>\n",
164 |        "      <td>113812.0</td>\n",
165 |        "    </tr>\n",
166 |        "    <tr>\n",
167 |        "      <th>24</th>\n",
168 |        "      <td>8.7</td>\n",
169 |        "      <td>109431.0</td>\n",
170 |        "    </tr>\n",
171 |        "    <tr>\n",
172 |        "      <th>25</th>\n",
173 |        "      <td>9.0</td>\n",
174 |        "      <td>105582.0</td>\n",
175 |        "    </tr>\n",
176 |        "    <tr>\n",
177 |        "      <th>26</th>\n",
178 |        "      <td>9.5</td>\n",
179 |        "      <td>116969.0</td>\n",
180 |        "    </tr>\n",
181 |        "    <tr>\n",
182 |        "      <th>27</th>\n",
183 |        "      <td>9.6</td>\n",
184 |        "      <td>112635.0</td>\n",
185 |        "    </tr>\n",
186 |        "    <tr>\n",
187 |        "      <th>28</th>\n",
188 |        "      <td>10.3</td>\n",
189 |        "      <td>122391.0</td>\n",
190 |        "    </tr>\n",
191 |        "    <tr>\n",
192 |        "      <th>29</th>\n",
193 |        "      <td>10.5</td>\n",
194 |        "      <td>121872.0</td>\n",
195 |        "    </tr>\n",
196 |        "  </tbody>\n",
197 |        "</table>\n",
198 |        "</div>"
199 |       ],
200 |       "text/plain": [
201 |        "    YearsExperience    Salary\n",
202 |        "0               1.1   39343.0\n",
203 |        "1               1.3   46205.0\n",
204 |        "2               1.5   37731.0\n",
205 |        "3               2.0   43525.0\n",
206 |        "4               2.2   39891.0\n",
207 |        "5               2.9   56642.0\n",
208 |        "6               3.0   60150.0\n",
209 |        "7               3.2   54445.0\n",
210 |        "8               3.2   64445.0\n",
211 |        "9               3.7   57189.0\n",
212 |        "10              3.9   63218.0\n",
213 |        "11              4.0   55794.0\n",
214 |        "12              4.0   56957.0\n",
215 |        "13              4.1   57081.0\n",
216 |        "14              4.5   61111.0\n",
217 |        "15              4.9   67938.0\n",
218 |        "16              5.1   66029.0\n",
219 |        "17              5.3   83088.0\n",
220 |        "18              5.9   81363.0\n",
221 |        "19              6.0   93940.0\n",
222 |        "20              6.8   91738.0\n",
223 |        "21              7.1   98273.0\n",
224 |        "22              7.9  101302.0\n",
225 |        "23              8.2  113812.0\n",
226 |        "24              8.7  109431.0\n",
227 |        "25              9.0  105582.0\n",
228 |        "26              9.5  116969.0\n",
229 |        "27              9.6  112635.0\n",
230 |        "28             10.3  122391.0\n",
231 |        "29             10.5  121872.0"
232 |       ]
233 |      },
234 |      "execution_count": 4,
235 |      "metadata": {},
236 |      "output_type": "execute_result"
237 |     }
238 |    ],
239 |    "source": [
240 |     "data = pd.read_csv('Salary_data.csv')\n",
241 |     "data"
242 |    ]
243 |   },
244 |   {
245 |    "cell_type": "code",
246 |    "execution_count": 5,
247 |    "id": "reduced-journalism",
248 |    "metadata": {},
249 |    "outputs": [],
250 |    "source": [
251 |     "x = data.YearsExperience.values.reshape(-1,1)\n",
252 |     "y = data.Salary.values.reshape(-1,1)"
253 |    ]
254 |   },
255 |   {
256 |    "cell_type": "code",
257 |    "execution_count": 6,
258 |    "id": "consistent-parent",
259 |    "metadata": {},
260 |    "outputs": [],
261 |    "source": [
262 |     "from sklearn.model_selection import train_test_split\n",
263 |     "X_train, X_test, y_train, y_test = train_test_split(x, y, test_size = 0.3, random_state = 0)"
264 |    ]
265 |   },
266 |   {
267 |    "cell_type": "code",
268 |    "execution_count": 7,
269 |    "id": "handmade-rogers",
270 |    "metadata": {},
271 |    "outputs": [],
272 |    "source": [
273 |     "from sklearn.linear_model import LinearRegression"
274 |    ]
275 |   },
276 |   {
277 |    "cell_type": "code",
278 |    "execution_count": 9,
279 |    "id": "invalid-natural",
280 |    "metadata": {},
281 |    "outputs": [],
282 |    "source": [
283 |     "model= LinearRegression()"
284 |    ]
285 |   },
286 |   {
287 |    "cell_type": "code",
288 |    "execution_count": 10,
289 |    "id": "sealed-composition",
290 |    "metadata": {},
291 |    "outputs": [
292 |     {
293 |      "data": {
294 |       "text/plain": [
295 |        "LinearRegression()"
296 |       ]
297 |      },
298 |      "execution_count": 10,
299 |      "metadata": {},
300 |      "output_type": "execute_result"
301 |     }
302 |    ],
303 |    "source": [
304 |     "model.fit(x,y)"
305 |    ]
306 |   },
307 |   {
308 |    "cell_type": "code",
309 |    "execution_count": 12,
310 |    "id": "thorough-rabbit",
311 |    "metadata": {},
312 |    "outputs": [
313 |     {
314 |      "name": "stdout",
315 |      "output_type": "stream",
316 |      "text": [
317 |       "63592\n"
318 |      ]
319 |     }
320 |    ],
321 |    "source": [
322 |     "next_salary = model.predict([[4.0]])\n",
323 |     "print(int(next_salary))\n"
324 |    ]
325 |   },
326 |   {
327 |    "cell_type": "code",
328 |    "execution_count": 13,
329 |    "id": "decimal-effectiveness",
330 |    "metadata": {},
331 |    "outputs": [
332 |     {
333 |      "data": {
334 |       "text/plain": [
335 |        "0.941799590058557"
336 |       ]
337 |      },
338 |      "execution_count": 13,
339 |      "metadata": {},
340 |      "output_type": "execute_result"
341 |     }
342 |    ],
343 |    "source": [
344 |     "model.score(X_train,y_train)"
345 |    ]
346 |   },
347 |   {
348 |    "cell_type": "code",
349 |    "execution_count": null,
350 |    "id": "billion-portuguese",
351 |    "metadata": {},
352 |    "outputs": [],
353 |    "source": []
354 |   }
355 |  ],
356 |  "metadata": {
357 |   "kernelspec": {
358 |    "display_name": "Python 3",
359 |    "language": "python",
360 |    "name": "python3"
361 |   },
362 |   "language_info": {
363 |    "codemirror_mode": {
364 |     "name": "ipython",
365 |     "version": 3
366 |    },
367 |    "file_extension": ".py",
368 |    "mimetype": "text/x-python",
369 |    "name": "python",
370 |    "nbconvert_exporter": "python",
371 |    "pygments_lexer": "ipython3",
372 |    "version": "3.8.8"
373 |   }
374 |  },
375 |  "nbformat": 4,
376 |  "nbformat_minor": 5
377 | }
378 | 


--------------------------------------------------------------------------------
/Salary_Data.csv:
--------------------------------------------------------------------------------
 1 | YearsExperience,Salary
 2 | 1.1,39343.00
 3 | 1.3,46205.00
 4 | 1.5,37731.00
 5 | 2.0,43525.00
 6 | 2.2,39891.00
 7 | 2.9,56642.00
 8 | 3.0,60150.00
 9 | 3.2,54445.00
10 | 3.2,64445.00
11 | 3.7,57189.00
12 | 3.9,63218.00
13 | 4.0,55794.00
14 | 4.0,56957.00
15 | 4.1,57081.00
16 | 4.5,61111.00
17 | 4.9,67938.00
18 | 5.1,66029.00
19 | 5.3,83088.00
20 | 5.9,81363.00
21 | 6.0,93940.00
22 | 6.8,91738.00
23 | 7.1,98273.00
24 | 7.9,101302.00
25 | 8.2,113812.00
26 | 8.7,109431.00
27 | 9.0,105582.00
28 | 9.5,116969.00
29 | 9.6,112635.00
30 | 10.3,122391.00
31 | 10.5,121872.00
32 | 


--------------------------------------------------------------------------------
/Sample scores.csv:
--------------------------------------------------------------------------------
 1 | Overs,Scores
 2 | 1,15
 3 | 2,10
 4 | 3,17
 5 | 4,10
 6 | 5,12
 7 | 6,20
 8 | 7,100
 9 | 8,7
10 | 9,8
11 | 10,11
12 | 11,100
13 | 12,14
14 | 13,3
15 | 14,100
16 | 15,11
17 | 16,13
18 | 17,100
19 | 18,16
20 | 19,26
21 | 20,30
22 | 


--------------------------------------------------------------------------------
/Weather prediction (NaiveBayes algorithm ).ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 3,
  6 |    "id": "public-horizontal",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 8,
 16 |    "id": "spread-fairy",
 17 |    "metadata": {},
 18 |    "outputs": [
 19 |     {
 20 |      "data": {
 21 |       "text/html": [
 22 |        "<div>\n",
 23 |        "<style scoped>\n",
 24 |        "    .dataframe tbody tr th:only-of-type {\n",
 25 |        "        vertical-align: middle;\n",
 26 |        "    }\n",
 27 |        "\n",
 28 |        "    .dataframe tbody tr th {\n",
 29 |        "        vertical-align: top;\n",
 30 |        "    }\n",
 31 |        "\n",
 32 |        "    .dataframe thead th {\n",
 33 |        "        text-align: right;\n",
 34 |        "    }\n",
 35 |        "</style>\n",
 36 |        "<table border=\"1\" class=\"dataframe\">\n",
 37 |        "  <thead>\n",
 38 |        "    <tr style=\"text-align: right;\">\n",
 39 |        "      <th></th>\n",
 40 |        "      <th>Outlook</th>\n",
 41 |        "      <th>Temp</th>\n",
 42 |        "      <th>Humidity</th>\n",
 43 |        "      <th>Windy</th>\n",
 44 |        "      <th>Play</th>\n",
 45 |        "    </tr>\n",
 46 |        "  </thead>\n",
 47 |        "  <tbody>\n",
 48 |        "    <tr>\n",
 49 |        "      <th>0</th>\n",
 50 |        "      <td>Rainy</td>\n",
 51 |        "      <td>Hot</td>\n",
 52 |        "      <td>High</td>\n",
 53 |        "      <td>f</td>\n",
 54 |        "      <td>no</td>\n",
 55 |        "    </tr>\n",
 56 |        "    <tr>\n",
 57 |        "      <th>1</th>\n",
 58 |        "      <td>Rainy</td>\n",
 59 |        "      <td>Hot</td>\n",
 60 |        "      <td>High</td>\n",
 61 |        "      <td>t</td>\n",
 62 |        "      <td>no</td>\n",
 63 |        "    </tr>\n",
 64 |        "    <tr>\n",
 65 |        "      <th>2</th>\n",
 66 |        "      <td>Overcast</td>\n",
 67 |        "      <td>Hot</td>\n",
 68 |        "      <td>High</td>\n",
 69 |        "      <td>f</td>\n",
 70 |        "      <td>yes</td>\n",
 71 |        "    </tr>\n",
 72 |        "    <tr>\n",
 73 |        "      <th>3</th>\n",
 74 |        "      <td>Sunny</td>\n",
 75 |        "      <td>Mild</td>\n",
 76 |        "      <td>High</td>\n",
 77 |        "      <td>f</td>\n",
 78 |        "      <td>yes</td>\n",
 79 |        "    </tr>\n",
 80 |        "    <tr>\n",
 81 |        "      <th>4</th>\n",
 82 |        "      <td>Sunny</td>\n",
 83 |        "      <td>Cool</td>\n",
 84 |        "      <td>Normal</td>\n",
 85 |        "      <td>f</td>\n",
 86 |        "      <td>yes</td>\n",
 87 |        "    </tr>\n",
 88 |        "    <tr>\n",
 89 |        "      <th>5</th>\n",
 90 |        "      <td>Sunny</td>\n",
 91 |        "      <td>Cool</td>\n",
 92 |        "      <td>Normal</td>\n",
 93 |        "      <td>t</td>\n",
 94 |        "      <td>no</td>\n",
 95 |        "    </tr>\n",
 96 |        "    <tr>\n",
 97 |        "      <th>6</th>\n",
 98 |        "      <td>Overcast</td>\n",
 99 |        "      <td>Cool</td>\n",
100 |        "      <td>Normal</td>\n",
101 |        "      <td>t</td>\n",
102 |        "      <td>yes</td>\n",
103 |        "    </tr>\n",
104 |        "    <tr>\n",
105 |        "      <th>7</th>\n",
106 |        "      <td>Rainy</td>\n",
107 |        "      <td>Mild</td>\n",
108 |        "      <td>High</td>\n",
109 |        "      <td>f</td>\n",
110 |        "      <td>no</td>\n",
111 |        "    </tr>\n",
112 |        "    <tr>\n",
113 |        "      <th>8</th>\n",
114 |        "      <td>Rainy</td>\n",
115 |        "      <td>Cool</td>\n",
116 |        "      <td>Normal</td>\n",
117 |        "      <td>f</td>\n",
118 |        "      <td>yes</td>\n",
119 |        "    </tr>\n",
120 |        "    <tr>\n",
121 |        "      <th>9</th>\n",
122 |        "      <td>Sunny</td>\n",
123 |        "      <td>Mild</td>\n",
124 |        "      <td>Normal</td>\n",
125 |        "      <td>f</td>\n",
126 |        "      <td>yes</td>\n",
127 |        "    </tr>\n",
128 |        "    <tr>\n",
129 |        "      <th>10</th>\n",
130 |        "      <td>Rainy</td>\n",
131 |        "      <td>Mild</td>\n",
132 |        "      <td>Normal</td>\n",
133 |        "      <td>t</td>\n",
134 |        "      <td>yes</td>\n",
135 |        "    </tr>\n",
136 |        "    <tr>\n",
137 |        "      <th>11</th>\n",
138 |        "      <td>Overcast</td>\n",
139 |        "      <td>Mild</td>\n",
140 |        "      <td>High</td>\n",
141 |        "      <td>t</td>\n",
142 |        "      <td>yes</td>\n",
143 |        "    </tr>\n",
144 |        "    <tr>\n",
145 |        "      <th>12</th>\n",
146 |        "      <td>Overcast</td>\n",
147 |        "      <td>Hot</td>\n",
148 |        "      <td>Normal</td>\n",
149 |        "      <td>f</td>\n",
150 |        "      <td>yes</td>\n",
151 |        "    </tr>\n",
152 |        "    <tr>\n",
153 |        "      <th>13</th>\n",
154 |        "      <td>Sunny</td>\n",
155 |        "      <td>Mild</td>\n",
156 |        "      <td>High</td>\n",
157 |        "      <td>t</td>\n",
158 |        "      <td>no</td>\n",
159 |        "    </tr>\n",
160 |        "  </tbody>\n",
161 |        "</table>\n",
162 |        "</div>"
163 |       ],
164 |       "text/plain": [
165 |        "     Outlook  Temp Humidity Windy Play\n",
166 |        "0      Rainy   Hot     High     f   no\n",
167 |        "1      Rainy   Hot     High     t   no\n",
168 |        "2   Overcast   Hot     High     f  yes\n",
169 |        "3      Sunny  Mild     High     f  yes\n",
170 |        "4      Sunny  Cool   Normal     f  yes\n",
171 |        "5      Sunny  Cool   Normal     t   no\n",
172 |        "6   Overcast  Cool   Normal     t  yes\n",
173 |        "7      Rainy  Mild     High     f   no\n",
174 |        "8      Rainy  Cool   Normal     f  yes\n",
175 |        "9      Sunny  Mild   Normal     f  yes\n",
176 |        "10     Rainy  Mild   Normal     t  yes\n",
177 |        "11  Overcast  Mild     High     t  yes\n",
178 |        "12  Overcast   Hot   Normal     f  yes\n",
179 |        "13     Sunny  Mild     High     t   no"
180 |       ]
181 |      },
182 |      "execution_count": 8,
183 |      "metadata": {},
184 |      "output_type": "execute_result"
185 |     }
186 |    ],
187 |    "source": [
188 |     "df = pd.read_csv(\"new_dataset.csv\")\n",
189 |     "df"
190 |    ]
191 |   },
192 |   {
193 |    "cell_type": "code",
194 |    "execution_count": 1,
195 |    "id": "popular-kennedy",
196 |    "metadata": {},
197 |    "outputs": [],
198 |    "source": [
199 |     "#NaiveBayes project (Weather Prediction)\n",
200 |     "#Required Modules\n",
201 |     "import pandas as pd\n",
202 |     "from sklearn.preprocessing import LabelEncoder\n",
203 |     "from sklearn.naive_bayes import GaussianNB"
204 |    ]
205 |   },
206 |   {
207 |    "cell_type": "code",
208 |    "execution_count": 2,
209 |    "id": "touched-packet",
210 |    "metadata": {},
211 |    "outputs": [
212 |     {
213 |      "data": {
214 |       "text/html": [
215 |        "<div>\n",
216 |        "<style scoped>\n",
217 |        "    .dataframe tbody tr th:only-of-type {\n",
218 |        "        vertical-align: middle;\n",
219 |        "    }\n",
220 |        "\n",
221 |        "    .dataframe tbody tr th {\n",
222 |        "        vertical-align: top;\n",
223 |        "    }\n",
224 |        "\n",
225 |        "    .dataframe thead th {\n",
226 |        "        text-align: right;\n",
227 |        "    }\n",
228 |        "</style>\n",
229 |        "<table border=\"1\" class=\"dataframe\">\n",
230 |        "  <thead>\n",
231 |        "    <tr style=\"text-align: right;\">\n",
232 |        "      <th></th>\n",
233 |        "      <th>Outlook</th>\n",
234 |        "      <th>Temp</th>\n",
235 |        "      <th>Humidity</th>\n",
236 |        "      <th>Windy</th>\n",
237 |        "      <th>Play</th>\n",
238 |        "    </tr>\n",
239 |        "  </thead>\n",
240 |        "  <tbody>\n",
241 |        "    <tr>\n",
242 |        "      <th>0</th>\n",
243 |        "      <td>Rainy</td>\n",
244 |        "      <td>Hot</td>\n",
245 |        "      <td>High</td>\n",
246 |        "      <td>f</td>\n",
247 |        "      <td>no</td>\n",
248 |        "    </tr>\n",
249 |        "    <tr>\n",
250 |        "      <th>1</th>\n",
251 |        "      <td>Rainy</td>\n",
252 |        "      <td>Hot</td>\n",
253 |        "      <td>High</td>\n",
254 |        "      <td>t</td>\n",
255 |        "      <td>no</td>\n",
256 |        "    </tr>\n",
257 |        "    <tr>\n",
258 |        "      <th>2</th>\n",
259 |        "      <td>Overcast</td>\n",
260 |        "      <td>Hot</td>\n",
261 |        "      <td>High</td>\n",
262 |        "      <td>f</td>\n",
263 |        "      <td>yes</td>\n",
264 |        "    </tr>\n",
265 |        "    <tr>\n",
266 |        "      <th>3</th>\n",
267 |        "      <td>Sunny</td>\n",
268 |        "      <td>Mild</td>\n",
269 |        "      <td>High</td>\n",
270 |        "      <td>f</td>\n",
271 |        "      <td>yes</td>\n",
272 |        "    </tr>\n",
273 |        "    <tr>\n",
274 |        "      <th>4</th>\n",
275 |        "      <td>Sunny</td>\n",
276 |        "      <td>Cool</td>\n",
277 |        "      <td>Normal</td>\n",
278 |        "      <td>f</td>\n",
279 |        "      <td>yes</td>\n",
280 |        "    </tr>\n",
281 |        "    <tr>\n",
282 |        "      <th>5</th>\n",
283 |        "      <td>Sunny</td>\n",
284 |        "      <td>Cool</td>\n",
285 |        "      <td>Normal</td>\n",
286 |        "      <td>t</td>\n",
287 |        "      <td>no</td>\n",
288 |        "    </tr>\n",
289 |        "    <tr>\n",
290 |        "      <th>6</th>\n",
291 |        "      <td>Overcast</td>\n",
292 |        "      <td>Cool</td>\n",
293 |        "      <td>Normal</td>\n",
294 |        "      <td>t</td>\n",
295 |        "      <td>yes</td>\n",
296 |        "    </tr>\n",
297 |        "    <tr>\n",
298 |        "      <th>7</th>\n",
299 |        "      <td>Rainy</td>\n",
300 |        "      <td>Mild</td>\n",
301 |        "      <td>High</td>\n",
302 |        "      <td>f</td>\n",
303 |        "      <td>no</td>\n",
304 |        "    </tr>\n",
305 |        "    <tr>\n",
306 |        "      <th>8</th>\n",
307 |        "      <td>Rainy</td>\n",
308 |        "      <td>Cool</td>\n",
309 |        "      <td>Normal</td>\n",
310 |        "      <td>f</td>\n",
311 |        "      <td>yes</td>\n",
312 |        "    </tr>\n",
313 |        "    <tr>\n",
314 |        "      <th>9</th>\n",
315 |        "      <td>Sunny</td>\n",
316 |        "      <td>Mild</td>\n",
317 |        "      <td>Normal</td>\n",
318 |        "      <td>f</td>\n",
319 |        "      <td>yes</td>\n",
320 |        "    </tr>\n",
321 |        "    <tr>\n",
322 |        "      <th>10</th>\n",
323 |        "      <td>Rainy</td>\n",
324 |        "      <td>Mild</td>\n",
325 |        "      <td>Normal</td>\n",
326 |        "      <td>t</td>\n",
327 |        "      <td>yes</td>\n",
328 |        "    </tr>\n",
329 |        "    <tr>\n",
330 |        "      <th>11</th>\n",
331 |        "      <td>Overcast</td>\n",
332 |        "      <td>Mild</td>\n",
333 |        "      <td>High</td>\n",
334 |        "      <td>t</td>\n",
335 |        "      <td>yes</td>\n",
336 |        "    </tr>\n",
337 |        "    <tr>\n",
338 |        "      <th>12</th>\n",
339 |        "      <td>Overcast</td>\n",
340 |        "      <td>Hot</td>\n",
341 |        "      <td>Normal</td>\n",
342 |        "      <td>f</td>\n",
343 |        "      <td>yes</td>\n",
344 |        "    </tr>\n",
345 |        "    <tr>\n",
346 |        "      <th>13</th>\n",
347 |        "      <td>Sunny</td>\n",
348 |        "      <td>Mild</td>\n",
349 |        "      <td>High</td>\n",
350 |        "      <td>t</td>\n",
351 |        "      <td>no</td>\n",
352 |        "    </tr>\n",
353 |        "  </tbody>\n",
354 |        "</table>\n",
355 |        "</div>"
356 |       ],
357 |       "text/plain": [
358 |        "     Outlook  Temp Humidity Windy Play\n",
359 |        "0      Rainy   Hot     High     f   no\n",
360 |        "1      Rainy   Hot     High     t   no\n",
361 |        "2   Overcast   Hot     High     f  yes\n",
362 |        "3      Sunny  Mild     High     f  yes\n",
363 |        "4      Sunny  Cool   Normal     f  yes\n",
364 |        "5      Sunny  Cool   Normal     t   no\n",
365 |        "6   Overcast  Cool   Normal     t  yes\n",
366 |        "7      Rainy  Mild     High     f   no\n",
367 |        "8      Rainy  Cool   Normal     f  yes\n",
368 |        "9      Sunny  Mild   Normal     f  yes\n",
369 |        "10     Rainy  Mild   Normal     t  yes\n",
370 |        "11  Overcast  Mild     High     t  yes\n",
371 |        "12  Overcast   Hot   Normal     f  yes\n",
372 |        "13     Sunny  Mild     High     t   no"
373 |       ]
374 |      },
375 |      "execution_count": 2,
376 |      "metadata": {},
377 |      "output_type": "execute_result"
378 |     }
379 |    ],
380 |    "source": [
381 |     "#Reading CSV files\n",
382 |     "df = pd.read_csv(\"new_dataset.csv\")\n",
383 |     "df"
384 |    ]
385 |   },
386 |   {
387 |    "cell_type": "code",
388 |    "execution_count": 3,
389 |    "id": "forbidden-ottawa",
390 |    "metadata": {},
391 |    "outputs": [],
392 |    "source": [
393 |     "#Encoding the strings to Numericals\n",
394 |     "outlook_at=LabelEncoder()\n",
395 |     "Temp_at=LabelEncoder()\n",
396 |     "Hum_at=LabelEncoder()\n",
397 |     "win_at=LabelEncoder()"
398 |    ]
399 |   },
400 |   {
401 |    "cell_type": "code",
402 |    "execution_count": 5,
403 |    "id": "supposed-radar",
404 |    "metadata": {},
405 |    "outputs": [
406 |     {
407 |      "data": {
408 |       "text/plain": [
409 |        "0      no\n",
410 |        "1      no\n",
411 |        "2     yes\n",
412 |        "3     yes\n",
413 |        "4     yes\n",
414 |        "5      no\n",
415 |        "6     yes\n",
416 |        "7      no\n",
417 |        "8     yes\n",
418 |        "9     yes\n",
419 |        "10    yes\n",
420 |        "11    yes\n",
421 |        "12    yes\n",
422 |        "13     no\n",
423 |        "Name: Play, dtype: object"
424 |       ]
425 |      },
426 |      "execution_count": 5,
427 |      "metadata": {},
428 |      "output_type": "execute_result"
429 |     }
430 |    ],
431 |    "source": [
432 |     "#Dropping the target variable and make it is as newframe\n",
433 |     "inputs=df.drop('Play',axis='columns')\n",
434 |     "target=df['Play']\n",
435 |     "target"
436 |    ]
437 |   },
438 |   {
439 |    "cell_type": "code",
440 |    "execution_count": 6,
441 |    "id": "double-rwanda",
442 |    "metadata": {},
443 |    "outputs": [
444 |     {
445 |      "data": {
446 |       "text/html": [
447 |        "<div>\n",
448 |        "<style scoped>\n",
449 |        "    .dataframe tbody tr th:only-of-type {\n",
450 |        "        vertical-align: middle;\n",
451 |        "    }\n",
452 |        "\n",
453 |        "    .dataframe tbody tr th {\n",
454 |        "        vertical-align: top;\n",
455 |        "    }\n",
456 |        "\n",
457 |        "    .dataframe thead th {\n",
458 |        "        text-align: right;\n",
459 |        "    }\n",
460 |        "</style>\n",
461 |        "<table border=\"1\" class=\"dataframe\">\n",
462 |        "  <thead>\n",
463 |        "    <tr style=\"text-align: right;\">\n",
464 |        "      <th></th>\n",
465 |        "      <th>Outlook</th>\n",
466 |        "      <th>Temp</th>\n",
467 |        "      <th>Humidity</th>\n",
468 |        "      <th>Windy</th>\n",
469 |        "      <th>outlook_n</th>\n",
470 |        "      <th>Temp_n</th>\n",
471 |        "      <th>Hum_n</th>\n",
472 |        "      <th>win_n</th>\n",
473 |        "    </tr>\n",
474 |        "  </thead>\n",
475 |        "  <tbody>\n",
476 |        "    <tr>\n",
477 |        "      <th>0</th>\n",
478 |        "      <td>Rainy</td>\n",
479 |        "      <td>Hot</td>\n",
480 |        "      <td>High</td>\n",
481 |        "      <td>f</td>\n",
482 |        "      <td>1</td>\n",
483 |        "      <td>1</td>\n",
484 |        "      <td>0</td>\n",
485 |        "      <td>0</td>\n",
486 |        "    </tr>\n",
487 |        "    <tr>\n",
488 |        "      <th>1</th>\n",
489 |        "      <td>Rainy</td>\n",
490 |        "      <td>Hot</td>\n",
491 |        "      <td>High</td>\n",
492 |        "      <td>t</td>\n",
493 |        "      <td>1</td>\n",
494 |        "      <td>1</td>\n",
495 |        "      <td>0</td>\n",
496 |        "      <td>1</td>\n",
497 |        "    </tr>\n",
498 |        "    <tr>\n",
499 |        "      <th>2</th>\n",
500 |        "      <td>Overcast</td>\n",
501 |        "      <td>Hot</td>\n",
502 |        "      <td>High</td>\n",
503 |        "      <td>f</td>\n",
504 |        "      <td>0</td>\n",
505 |        "      <td>1</td>\n",
506 |        "      <td>0</td>\n",
507 |        "      <td>0</td>\n",
508 |        "    </tr>\n",
509 |        "    <tr>\n",
510 |        "      <th>3</th>\n",
511 |        "      <td>Sunny</td>\n",
512 |        "      <td>Mild</td>\n",
513 |        "      <td>High</td>\n",
514 |        "      <td>f</td>\n",
515 |        "      <td>2</td>\n",
516 |        "      <td>2</td>\n",
517 |        "      <td>0</td>\n",
518 |        "      <td>0</td>\n",
519 |        "    </tr>\n",
520 |        "    <tr>\n",
521 |        "      <th>4</th>\n",
522 |        "      <td>Sunny</td>\n",
523 |        "      <td>Cool</td>\n",
524 |        "      <td>Normal</td>\n",
525 |        "      <td>f</td>\n",
526 |        "      <td>2</td>\n",
527 |        "      <td>0</td>\n",
528 |        "      <td>1</td>\n",
529 |        "      <td>0</td>\n",
530 |        "    </tr>\n",
531 |        "    <tr>\n",
532 |        "      <th>5</th>\n",
533 |        "      <td>Sunny</td>\n",
534 |        "      <td>Cool</td>\n",
535 |        "      <td>Normal</td>\n",
536 |        "      <td>t</td>\n",
537 |        "      <td>2</td>\n",
538 |        "      <td>0</td>\n",
539 |        "      <td>1</td>\n",
540 |        "      <td>1</td>\n",
541 |        "    </tr>\n",
542 |        "    <tr>\n",
543 |        "      <th>6</th>\n",
544 |        "      <td>Overcast</td>\n",
545 |        "      <td>Cool</td>\n",
546 |        "      <td>Normal</td>\n",
547 |        "      <td>t</td>\n",
548 |        "      <td>0</td>\n",
549 |        "      <td>0</td>\n",
550 |        "      <td>1</td>\n",
551 |        "      <td>1</td>\n",
552 |        "    </tr>\n",
553 |        "    <tr>\n",
554 |        "      <th>7</th>\n",
555 |        "      <td>Rainy</td>\n",
556 |        "      <td>Mild</td>\n",
557 |        "      <td>High</td>\n",
558 |        "      <td>f</td>\n",
559 |        "      <td>1</td>\n",
560 |        "      <td>2</td>\n",
561 |        "      <td>0</td>\n",
562 |        "      <td>0</td>\n",
563 |        "    </tr>\n",
564 |        "    <tr>\n",
565 |        "      <th>8</th>\n",
566 |        "      <td>Rainy</td>\n",
567 |        "      <td>Cool</td>\n",
568 |        "      <td>Normal</td>\n",
569 |        "      <td>f</td>\n",
570 |        "      <td>1</td>\n",
571 |        "      <td>0</td>\n",
572 |        "      <td>1</td>\n",
573 |        "      <td>0</td>\n",
574 |        "    </tr>\n",
575 |        "    <tr>\n",
576 |        "      <th>9</th>\n",
577 |        "      <td>Sunny</td>\n",
578 |        "      <td>Mild</td>\n",
579 |        "      <td>Normal</td>\n",
580 |        "      <td>f</td>\n",
581 |        "      <td>2</td>\n",
582 |        "      <td>2</td>\n",
583 |        "      <td>1</td>\n",
584 |        "      <td>0</td>\n",
585 |        "    </tr>\n",
586 |        "    <tr>\n",
587 |        "      <th>10</th>\n",
588 |        "      <td>Rainy</td>\n",
589 |        "      <td>Mild</td>\n",
590 |        "      <td>Normal</td>\n",
591 |        "      <td>t</td>\n",
592 |        "      <td>1</td>\n",
593 |        "      <td>2</td>\n",
594 |        "      <td>1</td>\n",
595 |        "      <td>1</td>\n",
596 |        "    </tr>\n",
597 |        "    <tr>\n",
598 |        "      <th>11</th>\n",
599 |        "      <td>Overcast</td>\n",
600 |        "      <td>Mild</td>\n",
601 |        "      <td>High</td>\n",
602 |        "      <td>t</td>\n",
603 |        "      <td>0</td>\n",
604 |        "      <td>2</td>\n",
605 |        "      <td>0</td>\n",
606 |        "      <td>1</td>\n",
607 |        "    </tr>\n",
608 |        "    <tr>\n",
609 |        "      <th>12</th>\n",
610 |        "      <td>Overcast</td>\n",
611 |        "      <td>Hot</td>\n",
612 |        "      <td>Normal</td>\n",
613 |        "      <td>f</td>\n",
614 |        "      <td>0</td>\n",
615 |        "      <td>1</td>\n",
616 |        "      <td>1</td>\n",
617 |        "      <td>0</td>\n",
618 |        "    </tr>\n",
619 |        "    <tr>\n",
620 |        "      <th>13</th>\n",
621 |        "      <td>Sunny</td>\n",
622 |        "      <td>Mild</td>\n",
623 |        "      <td>High</td>\n",
624 |        "      <td>t</td>\n",
625 |        "      <td>2</td>\n",
626 |        "      <td>2</td>\n",
627 |        "      <td>0</td>\n",
628 |        "      <td>1</td>\n",
629 |        "    </tr>\n",
630 |        "  </tbody>\n",
631 |        "</table>\n",
632 |        "</div>"
633 |       ],
634 |       "text/plain": [
635 |        "     Outlook  Temp Humidity Windy  outlook_n  Temp_n  Hum_n  win_n\n",
636 |        "0      Rainy   Hot     High     f          1       1      0      0\n",
637 |        "1      Rainy   Hot     High     t          1       1      0      1\n",
638 |        "2   Overcast   Hot     High     f          0       1      0      0\n",
639 |        "3      Sunny  Mild     High     f          2       2      0      0\n",
640 |        "4      Sunny  Cool   Normal     f          2       0      1      0\n",
641 |        "5      Sunny  Cool   Normal     t          2       0      1      1\n",
642 |        "6   Overcast  Cool   Normal     t          0       0      1      1\n",
643 |        "7      Rainy  Mild     High     f          1       2      0      0\n",
644 |        "8      Rainy  Cool   Normal     f          1       0      1      0\n",
645 |        "9      Sunny  Mild   Normal     f          2       2      1      0\n",
646 |        "10     Rainy  Mild   Normal     t          1       2      1      1\n",
647 |        "11  Overcast  Mild     High     t          0       2      0      1\n",
648 |        "12  Overcast   Hot   Normal     f          0       1      1      0\n",
649 |        "13     Sunny  Mild     High     t          2       2      0      1"
650 |       ]
651 |      },
652 |      "execution_count": 6,
653 |      "metadata": {},
654 |      "output_type": "execute_result"
655 |     }
656 |    ],
657 |    "source": [
658 |     "#Creating the new dataframe\n",
659 |     "inputs['outlook_n']= outlook_at.fit_transform(inputs['Outlook'])\n",
660 |     "inputs['Temp_n']= outlook_at.fit_transform(inputs['Temp'])\n",
661 |     "inputs['Hum_n']= outlook_at.fit_transform(inputs['Humidity'])\n",
662 |     "inputs['win_n']= outlook_at.fit_transform(inputs['Windy'])\n",
663 |     "inputs"
664 |    ]
665 |   },
666 |   {
667 |    "cell_type": "code",
668 |    "execution_count": 7,
669 |    "id": "indoor-satellite",
670 |    "metadata": {},
671 |    "outputs": [
672 |     {
673 |      "data": {
674 |       "text/html": [
675 |        "<div>\n",
676 |        "<style scoped>\n",
677 |        "    .dataframe tbody tr th:only-of-type {\n",
678 |        "        vertical-align: middle;\n",
679 |        "    }\n",
680 |        "\n",
681 |        "    .dataframe tbody tr th {\n",
682 |        "        vertical-align: top;\n",
683 |        "    }\n",
684 |        "\n",
685 |        "    .dataframe thead th {\n",
686 |        "        text-align: right;\n",
687 |        "    }\n",
688 |        "</style>\n",
689 |        "<table border=\"1\" class=\"dataframe\">\n",
690 |        "  <thead>\n",
691 |        "    <tr style=\"text-align: right;\">\n",
692 |        "      <th></th>\n",
693 |        "      <th>outlook_n</th>\n",
694 |        "      <th>Temp_n</th>\n",
695 |        "      <th>Hum_n</th>\n",
696 |        "      <th>win_n</th>\n",
697 |        "    </tr>\n",
698 |        "  </thead>\n",
699 |        "  <tbody>\n",
700 |        "    <tr>\n",
701 |        "      <th>0</th>\n",
702 |        "      <td>1</td>\n",
703 |        "      <td>1</td>\n",
704 |        "      <td>0</td>\n",
705 |        "      <td>0</td>\n",
706 |        "    </tr>\n",
707 |        "    <tr>\n",
708 |        "      <th>1</th>\n",
709 |        "      <td>1</td>\n",
710 |        "      <td>1</td>\n",
711 |        "      <td>0</td>\n",
712 |        "      <td>1</td>\n",
713 |        "    </tr>\n",
714 |        "    <tr>\n",
715 |        "      <th>2</th>\n",
716 |        "      <td>0</td>\n",
717 |        "      <td>1</td>\n",
718 |        "      <td>0</td>\n",
719 |        "      <td>0</td>\n",
720 |        "    </tr>\n",
721 |        "    <tr>\n",
722 |        "      <th>3</th>\n",
723 |        "      <td>2</td>\n",
724 |        "      <td>2</td>\n",
725 |        "      <td>0</td>\n",
726 |        "      <td>0</td>\n",
727 |        "    </tr>\n",
728 |        "    <tr>\n",
729 |        "      <th>4</th>\n",
730 |        "      <td>2</td>\n",
731 |        "      <td>0</td>\n",
732 |        "      <td>1</td>\n",
733 |        "      <td>0</td>\n",
734 |        "    </tr>\n",
735 |        "    <tr>\n",
736 |        "      <th>5</th>\n",
737 |        "      <td>2</td>\n",
738 |        "      <td>0</td>\n",
739 |        "      <td>1</td>\n",
740 |        "      <td>1</td>\n",
741 |        "    </tr>\n",
742 |        "    <tr>\n",
743 |        "      <th>6</th>\n",
744 |        "      <td>0</td>\n",
745 |        "      <td>0</td>\n",
746 |        "      <td>1</td>\n",
747 |        "      <td>1</td>\n",
748 |        "    </tr>\n",
749 |        "    <tr>\n",
750 |        "      <th>7</th>\n",
751 |        "      <td>1</td>\n",
752 |        "      <td>2</td>\n",
753 |        "      <td>0</td>\n",
754 |        "      <td>0</td>\n",
755 |        "    </tr>\n",
756 |        "    <tr>\n",
757 |        "      <th>8</th>\n",
758 |        "      <td>1</td>\n",
759 |        "      <td>0</td>\n",
760 |        "      <td>1</td>\n",
761 |        "      <td>0</td>\n",
762 |        "    </tr>\n",
763 |        "    <tr>\n",
764 |        "      <th>9</th>\n",
765 |        "      <td>2</td>\n",
766 |        "      <td>2</td>\n",
767 |        "      <td>1</td>\n",
768 |        "      <td>0</td>\n",
769 |        "    </tr>\n",
770 |        "    <tr>\n",
771 |        "      <th>10</th>\n",
772 |        "      <td>1</td>\n",
773 |        "      <td>2</td>\n",
774 |        "      <td>1</td>\n",
775 |        "      <td>1</td>\n",
776 |        "    </tr>\n",
777 |        "    <tr>\n",
778 |        "      <th>11</th>\n",
779 |        "      <td>0</td>\n",
780 |        "      <td>2</td>\n",
781 |        "      <td>0</td>\n",
782 |        "      <td>1</td>\n",
783 |        "    </tr>\n",
784 |        "    <tr>\n",
785 |        "      <th>12</th>\n",
786 |        "      <td>0</td>\n",
787 |        "      <td>1</td>\n",
788 |        "      <td>1</td>\n",
789 |        "      <td>0</td>\n",
790 |        "    </tr>\n",
791 |        "    <tr>\n",
792 |        "      <th>13</th>\n",
793 |        "      <td>2</td>\n",
794 |        "      <td>2</td>\n",
795 |        "      <td>0</td>\n",
796 |        "      <td>1</td>\n",
797 |        "    </tr>\n",
798 |        "  </tbody>\n",
799 |        "</table>\n",
800 |        "</div>"
801 |       ],
802 |       "text/plain": [
803 |        "    outlook_n  Temp_n  Hum_n  win_n\n",
804 |        "0           1       1      0      0\n",
805 |        "1           1       1      0      1\n",
806 |        "2           0       1      0      0\n",
807 |        "3           2       2      0      0\n",
808 |        "4           2       0      1      0\n",
809 |        "5           2       0      1      1\n",
810 |        "6           0       0      1      1\n",
811 |        "7           1       2      0      0\n",
812 |        "8           1       0      1      0\n",
813 |        "9           2       2      1      0\n",
814 |        "10          1       2      1      1\n",
815 |        "11          0       2      0      1\n",
816 |        "12          0       1      1      0\n",
817 |        "13          2       2      0      1"
818 |       ]
819 |      },
820 |      "execution_count": 7,
821 |      "metadata": {},
822 |      "output_type": "execute_result"
823 |     }
824 |    ],
825 |    "source": [
826 |     "#Dropping the string values\n",
827 |     "inputs_n=inputs.drop(['Outlook','Temp','Humidity','Windy'],axis='columns')\n",
828 |     "inputs_n"
829 |    ]
830 |   },
831 |   {
832 |    "cell_type": "code",
833 |    "execution_count": 8,
834 |    "id": "functional-rebecca",
835 |    "metadata": {},
836 |    "outputs": [
837 |     {
838 |      "data": {
839 |       "text/plain": [
840 |        "GaussianNB()"
841 |       ]
842 |      },
843 |      "execution_count": 8,
844 |      "metadata": {},
845 |      "output_type": "execute_result"
846 |     }
847 |    ],
848 |    "source": [
849 |     "#Applying the Gaussian naivebayes\n",
850 |     "classifier = GaussianNB()\n",
851 |     "classifier.fit(inputs_n,target)"
852 |    ]
853 |   },
854 |   {
855 |    "cell_type": "code",
856 |    "execution_count": 9,
857 |    "id": "hybrid-program",
858 |    "metadata": {},
859 |    "outputs": [
860 |     {
861 |      "data": {
862 |       "text/plain": [
863 |        "0.8571428571428571"
864 |       ]
865 |      },
866 |      "execution_count": 9,
867 |      "metadata": {},
868 |      "output_type": "execute_result"
869 |     }
870 |    ],
871 |    "source": [
872 |     "#85% accuracy \n",
873 |     "classifier.score(inputs_n,target)"
874 |    ]
875 |   },
876 |   {
877 |    "cell_type": "code",
878 |    "execution_count": 10,
879 |    "id": "coordinated-sector",
880 |    "metadata": {},
881 |    "outputs": [
882 |     {
883 |      "data": {
884 |       "text/plain": [
885 |        "array(['yes'], dtype='<U3')"
886 |       ]
887 |      },
888 |      "execution_count": 10,
889 |      "metadata": {},
890 |      "output_type": "execute_result"
891 |     }
892 |    ],
893 |    "source": [
894 |     "#Prediction\n",
895 |     "classifier.predict([[0,0,0,1]])"
896 |    ]
897 |   },
898 |   {
899 |    "cell_type": "code",
900 |    "execution_count": null,
901 |    "id": "false-melbourne",
902 |    "metadata": {},
903 |    "outputs": [],
904 |    "source": []
905 |   }
906 |  ],
907 |  "metadata": {
908 |   "kernelspec": {
909 |    "display_name": "Python 3",
910 |    "language": "python",
911 |    "name": "python3"
912 |   },
913 |   "language_info": {
914 |    "codemirror_mode": {
915 |     "name": "ipython",
916 |     "version": 3
917 |    },
918 |    "file_extension": ".py",
919 |    "mimetype": "text/x-python",
920 |    "name": "python",
921 |    "nbconvert_exporter": "python",
922 |    "pygments_lexer": "ipython3",
923 |    "version": "3.8.8"
924 |   }
925 |  },
926 |  "nbformat": 4,
927 |  "nbformat_minor": 5
928 | }
929 | 


--------------------------------------------------------------------------------
/adboost algorithm.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 2,
  6 |    "id": "9700d31f",
  7 |    "metadata": {},
  8 |    "outputs": [
  9 |     {
 10 |      "name": "stdout",
 11 |      "output_type": "stream",
 12 |      "text": [
 13 |       "Accuracy: 0.806 (0.041)\n"
 14 |      ]
 15 |     }
 16 |    ],
 17 |    "source": [
 18 |     "# evaluate adaboost algorithm for classification\n",
 19 |     "from numpy import mean\n",
 20 |     "from numpy import std\n",
 21 |     "from sklearn.datasets import make_classification\n",
 22 |     "from sklearn.model_selection import cross_val_score\n",
 23 |     "from sklearn.model_selection import RepeatedStratifiedKFold\n",
 24 |     "from sklearn.ensemble import AdaBoostClassifier\n",
 25 |     "# define dataset\n",
 26 |     "X, y = make_classification(n_samples=1000, n_features=20, n_informative=15, n_redundant=5, random_state=6)\n",
 27 |     "# define the model\n",
 28 |     "model = AdaBoostClassifier()\n",
 29 |     "# evaluate the model\n",
 30 |     "cv = RepeatedStratifiedKFold(n_splits=10, n_repeats=3, random_state=1)\n",
 31 |     "n_scores = cross_val_score(model, X, y, scoring='accuracy', cv=cv, n_jobs=-1, error_score='raise')\n",
 32 |     "# report performance\n",
 33 |     "print('Accuracy: %.3f (%.3f)' % (mean(n_scores), std(n_scores)))"
 34 |    ]
 35 |   },
 36 |   {
 37 |    "cell_type": "code",
 38 |    "execution_count": 3,
 39 |    "id": "a4e73d5e",
 40 |    "metadata": {},
 41 |    "outputs": [
 42 |     {
 43 |      "name": "stdout",
 44 |      "output_type": "stream",
 45 |      "text": [
 46 |       "Predicted Class: 0\n"
 47 |      ]
 48 |     }
 49 |    ],
 50 |    "source": [
 51 |     "\n",
 52 |     "# make predictions using adaboost for classification\n",
 53 |     "from sklearn.datasets import make_classification\n",
 54 |     "from sklearn.ensemble import AdaBoostClassifier\n",
 55 |     "# define dataset\n",
 56 |     "X, y = make_classification(n_samples=1000, n_features=20, n_informative=15, n_redundant=5, random_state=6)\n",
 57 |     "# define the model\n",
 58 |     "model = AdaBoostClassifier()\n",
 59 |     "# fit the model on the whole dataset\n",
 60 |     "model.fit(X, y)\n",
 61 |     "# make a single prediction\n",
 62 |     "row = [[-3.47224758,1.95378146,0.04875169,-0.91592588,-3.54022468,1.96405547,-7.72564954,-2.64787168,-1.81726906,-1.67104974,2.33762043,-4.30273117,0.4839841,-1.28253034,-10.6704077,-0.7641103,-3.58493721,2.07283886,0.08385173,0.91461126]]\n",
 63 |     "yhat = model.predict(row)\n",
 64 |     "print('Predicted Class: %d' % yhat[0])"
 65 |    ]
 66 |   },
 67 |   {
 68 |    "cell_type": "code",
 69 |    "execution_count": null,
 70 |    "id": "a7cfacad",
 71 |    "metadata": {},
 72 |    "outputs": [],
 73 |    "source": []
 74 |   },
 75 |   {
 76 |    "cell_type": "code",
 77 |    "execution_count": 5,
 78 |    "id": "705cab32",
 79 |    "metadata": {},
 80 |    "outputs": [],
 81 |    "source": [
 82 |     "#Adaboost\n",
 83 |     "# This Python 3 environment comes with many helpful analytics libraries installed\n",
 84 |     "# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n",
 85 |     "# For example, here's several helpful packages to load in \n",
 86 |     "\n",
 87 |     "import numpy as np # linear algebra\n",
 88 |     "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
 89 |     "\n"
 90 |    ]
 91 |   },
 92 |   {
 93 |    "cell_type": "code",
 94 |    "execution_count": 28,
 95 |    "id": "bb7d1261",
 96 |    "metadata": {},
 97 |    "outputs": [
 98 |     {
 99 |      "data": {
100 |       "text/plain": [
101 |        "array(['Iris-setosa', 'Iris-versicolor', 'Iris-virginica'], dtype=object)"
102 |       ]
103 |      },
104 |      "execution_count": 28,
105 |      "metadata": {},
106 |      "output_type": "execute_result"
107 |     }
108 |    ],
109 |    "source": [
110 |     "iris = pd.read_csv('Iris.csv')\n",
111 |     "iris['Species'].unique()"
112 |    ]
113 |   },
114 |   {
115 |    "cell_type": "code",
116 |    "execution_count": 30,
117 |    "id": "0390a09a",
118 |    "metadata": {},
119 |    "outputs": [
120 |     {
121 |      "data": {
122 |       "text/plain": [
123 |        "(150, 6)"
124 |       ]
125 |      },
126 |      "execution_count": 30,
127 |      "metadata": {},
128 |      "output_type": "execute_result"
129 |     }
130 |    ],
131 |    "source": [
132 |     "iris.shape"
133 |    ]
134 |   },
135 |   {
136 |    "cell_type": "code",
137 |    "execution_count": 8,
138 |    "id": "13fb1fc9",
139 |    "metadata": {},
140 |    "outputs": [
141 |     {
142 |      "data": {
143 |       "text/html": [
144 |        "<div>\n",
145 |        "<style scoped>\n",
146 |        "    .dataframe tbody tr th:only-of-type {\n",
147 |        "        vertical-align: middle;\n",
148 |        "    }\n",
149 |        "\n",
150 |        "    .dataframe tbody tr th {\n",
151 |        "        vertical-align: top;\n",
152 |        "    }\n",
153 |        "\n",
154 |        "    .dataframe thead th {\n",
155 |        "        text-align: right;\n",
156 |        "    }\n",
157 |        "</style>\n",
158 |        "<table border=\"1\" class=\"dataframe\">\n",
159 |        "  <thead>\n",
160 |        "    <tr style=\"text-align: right;\">\n",
161 |        "      <th></th>\n",
162 |        "      <th>SepalLengthCm</th>\n",
163 |        "      <th>SepalWidthCm</th>\n",
164 |        "      <th>PetalLengthCm</th>\n",
165 |        "      <th>PetalWidthCm</th>\n",
166 |        "    </tr>\n",
167 |        "  </thead>\n",
168 |        "  <tbody>\n",
169 |        "    <tr>\n",
170 |        "      <th>0</th>\n",
171 |        "      <td>5.1</td>\n",
172 |        "      <td>3.5</td>\n",
173 |        "      <td>1.4</td>\n",
174 |        "      <td>0.2</td>\n",
175 |        "    </tr>\n",
176 |        "    <tr>\n",
177 |        "      <th>1</th>\n",
178 |        "      <td>4.9</td>\n",
179 |        "      <td>3.0</td>\n",
180 |        "      <td>1.4</td>\n",
181 |        "      <td>0.2</td>\n",
182 |        "    </tr>\n",
183 |        "    <tr>\n",
184 |        "      <th>2</th>\n",
185 |        "      <td>4.7</td>\n",
186 |        "      <td>3.2</td>\n",
187 |        "      <td>1.3</td>\n",
188 |        "      <td>0.2</td>\n",
189 |        "    </tr>\n",
190 |        "    <tr>\n",
191 |        "      <th>3</th>\n",
192 |        "      <td>4.6</td>\n",
193 |        "      <td>3.1</td>\n",
194 |        "      <td>1.5</td>\n",
195 |        "      <td>0.2</td>\n",
196 |        "    </tr>\n",
197 |        "    <tr>\n",
198 |        "      <th>4</th>\n",
199 |        "      <td>5.0</td>\n",
200 |        "      <td>3.6</td>\n",
201 |        "      <td>1.4</td>\n",
202 |        "      <td>0.2</td>\n",
203 |        "    </tr>\n",
204 |        "  </tbody>\n",
205 |        "</table>\n",
206 |        "</div>"
207 |       ],
208 |       "text/plain": [
209 |        "   SepalLengthCm  SepalWidthCm  PetalLengthCm  PetalWidthCm\n",
210 |        "0            5.1           3.5            1.4           0.2\n",
211 |        "1            4.9           3.0            1.4           0.2\n",
212 |        "2            4.7           3.2            1.3           0.2\n",
213 |        "3            4.6           3.1            1.5           0.2\n",
214 |        "4            5.0           3.6            1.4           0.2"
215 |       ]
216 |      },
217 |      "execution_count": 8,
218 |      "metadata": {},
219 |      "output_type": "execute_result"
220 |     }
221 |    ],
222 |    "source": [
223 |     "X = iris[['SepalLengthCm','SepalWidthCm','PetalLengthCm','PetalWidthCm']]\n",
224 |     "\n",
225 |     "X.head()"
226 |    ]
227 |   },
228 |   {
229 |    "cell_type": "code",
230 |    "execution_count": 9,
231 |    "id": "100396f2",
232 |    "metadata": {},
233 |    "outputs": [
234 |     {
235 |      "data": {
236 |       "text/plain": [
237 |        "0    Iris-setosa\n",
238 |        "1    Iris-setosa\n",
239 |        "2    Iris-setosa\n",
240 |        "3    Iris-setosa\n",
241 |        "4    Iris-setosa\n",
242 |        "Name: Species, dtype: object"
243 |       ]
244 |      },
245 |      "execution_count": 9,
246 |      "metadata": {},
247 |      "output_type": "execute_result"
248 |     }
249 |    ],
250 |    "source": [
251 |     "y = iris['Species']\n",
252 |     "\n",
253 |     "y.head()"
254 |    ]
255 |   },
256 |   {
257 |    "cell_type": "code",
258 |    "execution_count": 10,
259 |    "id": "689d29bf",
260 |    "metadata": {},
261 |    "outputs": [],
262 |    "source": [
263 |     "from sklearn.preprocessing import LabelEncoder\n",
264 |     "\n",
265 |     "le=LabelEncoder()\n",
266 |     "\n",
267 |     "y=le.fit_transform(y)"
268 |    ]
269 |   },
270 |   {
271 |    "cell_type": "code",
272 |    "execution_count": 11,
273 |    "id": "1e35285c",
274 |    "metadata": {},
275 |    "outputs": [
276 |     {
277 |      "data": {
278 |       "text/plain": [
279 |        "array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
280 |        "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
281 |        "       0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
282 |        "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
283 |        "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
284 |        "       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
285 |        "       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])"
286 |       ]
287 |      },
288 |      "execution_count": 11,
289 |      "metadata": {},
290 |      "output_type": "execute_result"
291 |     }
292 |    ],
293 |    "source": [
294 |     "y"
295 |    ]
296 |   },
297 |   {
298 |    "cell_type": "code",
299 |    "execution_count": 12,
300 |    "id": "2e7751ff",
301 |    "metadata": {},
302 |    "outputs": [],
303 |    "source": [
304 |     "# Import train_test_split function\n",
305 |     "from sklearn.model_selection import train_test_split\n",
306 |     "\n",
307 |     "# Split dataset into training set and test set\n",
308 |     "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)"
309 |    ]
310 |   },
311 |   {
312 |    "cell_type": "code",
313 |    "execution_count": 14,
314 |    "id": "2f35d717",
315 |    "metadata": {},
316 |    "outputs": [],
317 |    "source": [
318 |     "# Import the AdaBoost classifier\n",
319 |     "from sklearn.ensemble import AdaBoostClassifier\n",
320 |     "\n",
321 |     "\n",
322 |     "# Create adaboost classifer object\n",
323 |     "abc = AdaBoostClassifier(n_estimators=50, learning_rate=1, random_state=0)\n",
324 |     "\n",
325 |     "# Train Adaboost Classifer\n",
326 |     "model1 = abc.fit(X_train, y_train)\n",
327 |     "\n",
328 |     "\n",
329 |     "#Predict the response for test dataset\n",
330 |     "y_pred = model1.predict(X_test)"
331 |    ]
332 |   },
333 |   {
334 |    "cell_type": "code",
335 |    "execution_count": 16,
336 |    "id": "2c447ea7",
337 |    "metadata": {},
338 |    "outputs": [
339 |     {
340 |      "name": "stdout",
341 |      "output_type": "stream",
342 |      "text": [
343 |       "AdaBoost Classifier Model Accuracy: 0.9333333333333333\n"
344 |      ]
345 |     }
346 |    ],
347 |    "source": [
348 |     "#import scikit-learn metrics module for accuracy calculation\n",
349 |     "from sklearn.metrics import accuracy_score\n",
350 |     "\n",
351 |     "\n",
352 |     "# calculate and print model accuracy\n",
353 |     "print(\"AdaBoost Classifier Model Accuracy:\", accuracy_score(y_test, y_pred))"
354 |    ]
355 |   },
356 |   {
357 |    "cell_type": "code",
358 |    "execution_count": 15,
359 |    "id": "e8ffad25",
360 |    "metadata": {},
361 |    "outputs": [
362 |     {
363 |      "data": {
364 |       "text/plain": [
365 |        "array([1, 2, 1, 0, 2, 2, 1, 2, 1, 1, 1, 0, 2, 1, 0, 2, 1, 1, 2, 1, 1, 1,\n",
366 |        "       0, 0, 0, 0, 0, 1, 1, 2, 1, 0, 1, 2, 2, 1, 2, 2, 0, 2, 2, 1, 1, 1,\n",
367 |        "       2])"
368 |       ]
369 |      },
370 |      "execution_count": 15,
371 |      "metadata": {},
372 |      "output_type": "execute_result"
373 |     }
374 |    ],
375 |    "source": [
376 |     "y_pred"
377 |    ]
378 |   },
379 |   {
380 |    "cell_type": "code",
381 |    "execution_count": null,
382 |    "id": "fc852e82",
383 |    "metadata": {},
384 |    "outputs": [],
385 |    "source": []
386 |   }
387 |  ],
388 |  "metadata": {
389 |   "kernelspec": {
390 |    "display_name": "Python 3 (ipykernel)",
391 |    "language": "python",
392 |    "name": "python3"
393 |   },
394 |   "language_info": {
395 |    "codemirror_mode": {
396 |     "name": "ipython",
397 |     "version": 3
398 |    },
399 |    "file_extension": ".py",
400 |    "mimetype": "text/x-python",
401 |    "name": "python",
402 |    "nbconvert_exporter": "python",
403 |    "pygments_lexer": "ipython3",
404 |    "version": "3.8.8"
405 |   }
406 |  },
407 |  "nbformat": 4,
408 |  "nbformat_minor": 5
409 | }
410 | 


--------------------------------------------------------------------------------
/airline-passenger-traffic(1).csv:
--------------------------------------------------------------------------------
  1 | 1949-01,112
  2 | 1949-02,118
  3 | 1949-03,132
  4 | 1949-04,129
  5 | 1949-05,121
  6 | 1949-06,135
  7 | 1949-07,148
  8 | 1949-08,148
  9 | 1949-09,136
 10 | 1949-10,119
 11 | 1949-11,104
 12 | 1949-12,118
 13 | 1950-01,115
 14 | 1950-02,126
 15 | 1950-03,141
 16 | 1950-04,135
 17 | 1950-05,125
 18 | 1950-06,149
 19 | 1950-07,170
 20 | 1950-08,170
 21 | 1950-09,158
 22 | 1950-10,133
 23 | 1950-11,114
 24 | 1950-12,140
 25 | 1951-01,145
 26 | 1951-02,150
 27 | 1951-03,178
 28 | 1951-04,163
 29 | 1951-05,172
 30 | 1951-06,
 31 | 1951-07,
 32 | 1951-08,199
 33 | 1951-09,184
 34 | 1951-10,162
 35 | 1951-11,146
 36 | 1951-12,166
 37 | 1952-01,171
 38 | 1952-02,180
 39 | 1952-03,193
 40 | 1952-04,181
 41 | 1952-05,183
 42 | 1952-06,218
 43 | 1952-07,230
 44 | 1952-08,242
 45 | 1952-09,209
 46 | 1952-10,191
 47 | 1952-11,172
 48 | 1952-12,194
 49 | 1953-01,196
 50 | 1953-02,196
 51 | 1953-03,236
 52 | 1953-04,235
 53 | 1953-05,229
 54 | 1953-06,243
 55 | 1953-07,264
 56 | 1953-08,272
 57 | 1953-09,237
 58 | 1953-10,211
 59 | 1953-11,180
 60 | 1953-12,201
 61 | 1954-01,204
 62 | 1954-02,188
 63 | 1954-03,235
 64 | 1954-04,227
 65 | 1954-05,234
 66 | 1954-06,
 67 | 1954-07,302
 68 | 1954-08,293
 69 | 1954-09,259
 70 | 1954-10,229
 71 | 1954-11,203
 72 | 1954-12,229
 73 | 1955-01,242
 74 | 1955-02,233
 75 | 1955-03,267
 76 | 1955-04,269
 77 | 1955-05,270
 78 | 1955-06,315
 79 | 1955-07,364
 80 | 1955-08,347
 81 | 1955-09,312
 82 | 1955-10,274
 83 | 1955-11,237
 84 | 1955-12,278
 85 | 1956-01,284
 86 | 1956-02,277
 87 | 1956-03,317
 88 | 1956-04,313
 89 | 1956-05,318
 90 | 1956-06,374
 91 | 1956-07,413
 92 | 1956-08,405
 93 | 1956-09,355
 94 | 1956-10,306
 95 | 1956-11,271
 96 | 1956-12,306
 97 | 1957-01,315
 98 | 1957-02,301
 99 | 1957-03,356
100 | 1957-04,348
101 | 1957-05,355
102 | 1957-06,422
103 | 1957-07,465
104 | 1957-08,467
105 | 1957-09,404
106 | 1957-10,347
107 | 1957-11,305
108 | 1957-12,336
109 | 1958-01,340
110 | 1958-02,318
111 | 1958-03,362
112 | 1958-04,348
113 | 1958-05,363
114 | 1958-06,435
115 | 1958-07,491
116 | 1958-08,505
117 | 1958-09,404
118 | 1958-10,359
119 | 1958-11,310
120 | 1958-12,337
121 | 1959-01,360
122 | 1959-02,342
123 | 1959-03,406
124 | 1959-04,396
125 | 1959-05,420
126 | 1959-06,472
127 | 1959-07,548
128 | 1959-08,559
129 | 1959-09,463
130 | 1959-10,407
131 | 1959-11,362
132 | 1959-12,405
133 | 1960-01,417
134 | 1960-02,391
135 | 1960-03,
136 | 1960-04,461
137 | 1960-05,472
138 | 1960-06,535
139 | 1960-07,622
140 | 1960-08,606
141 | 1960-09,508
142 | 1960-10,461
143 | 1960-11,390
144 | 1960-12,432
145 | 


--------------------------------------------------------------------------------
/car data.csv:
--------------------------------------------------------------------------------
  1 | Car_Name,Year,Selling_Price,Present_Price,Kms_Driven,Fuel_Type,Seller_Type,Transmission,Owner
  2 | ritz,2014,3.35,5.59,27000,Petrol,Dealer,Manual,0
  3 | sx4,2013,4.75,9.54,43000,Diesel,Dealer,Manual,0
  4 | ciaz,2017,7.25,9.85,6900,Petrol,Dealer,Manual,0
  5 | wagon r,2011,2.85,4.15,5200,Petrol,Dealer,Manual,0
  6 | swift,2014,4.6,6.87,42450,Diesel,Dealer,Manual,0
  7 | vitara brezza,2018,9.25,9.83,2071,Diesel,Dealer,Manual,0
  8 | ciaz,2015,6.75,8.12,18796,Petrol,Dealer,Manual,0
  9 | s cross,2015,6.5,8.61,33429,Diesel,Dealer,Manual,0
 10 | ciaz,2016,8.75,8.89,20273,Diesel,Dealer,Manual,0
 11 | ciaz,2015,7.45,8.92,42367,Diesel,Dealer,Manual,0
 12 | alto 800,2017,2.85,3.6,2135,Petrol,Dealer,Manual,0
 13 | ciaz,2015,6.85,10.38,51000,Diesel,Dealer,Manual,0
 14 | ciaz,2015,7.5,9.94,15000,Petrol,Dealer,Automatic,0
 15 | ertiga,2015,6.1,7.71,26000,Petrol,Dealer,Manual,0
 16 | dzire,2009,2.25,7.21,77427,Petrol,Dealer,Manual,0
 17 | ertiga,2016,7.75,10.79,43000,Diesel,Dealer,Manual,0
 18 | ertiga,2015,7.25,10.79,41678,Diesel,Dealer,Manual,0
 19 | ertiga,2016,7.75,10.79,43000,Diesel,Dealer,Manual,0
 20 | wagon r,2015,3.25,5.09,35500,CNG,Dealer,Manual,0
 21 | sx4,2010,2.65,7.98,41442,Petrol,Dealer,Manual,0
 22 | alto k10,2016,2.85,3.95,25000,Petrol,Dealer,Manual,0
 23 | ignis,2017,4.9,5.71,2400,Petrol,Dealer,Manual,0
 24 | sx4,2011,4.4,8.01,50000,Petrol,Dealer,Automatic,0
 25 | alto k10,2014,2.5,3.46,45280,Petrol,Dealer,Manual,0
 26 | wagon r,2013,2.9,4.41,56879,Petrol,Dealer,Manual,0
 27 | swift,2011,3,4.99,20000,Petrol,Dealer,Manual,0
 28 | swift,2013,4.15,5.87,55138,Petrol,Dealer,Manual,0
 29 | swift,2017,6,6.49,16200,Petrol,Individual,Manual,0
 30 | alto k10,2010,1.95,3.95,44542,Petrol,Dealer,Manual,0
 31 | ciaz,2015,7.45,10.38,45000,Diesel,Dealer,Manual,0
 32 | ritz,2012,3.1,5.98,51439,Diesel,Dealer,Manual,0
 33 | ritz,2011,2.35,4.89,54200,Petrol,Dealer,Manual,0
 34 | swift,2014,4.95,7.49,39000,Diesel,Dealer,Manual,0
 35 | ertiga,2014,6,9.95,45000,Diesel,Dealer,Manual,0
 36 | dzire,2014,5.5,8.06,45000,Diesel,Dealer,Manual,0
 37 | sx4,2011,2.95,7.74,49998,CNG,Dealer,Manual,0
 38 | dzire,2015,4.65,7.2,48767,Petrol,Dealer,Manual,0
 39 | 800,2003,0.35,2.28,127000,Petrol,Individual,Manual,0
 40 | alto k10,2016,3,3.76,10079,Petrol,Dealer,Manual,0
 41 | sx4,2003,2.25,7.98,62000,Petrol,Dealer,Manual,0
 42 | baleno,2016,5.85,7.87,24524,Petrol,Dealer,Automatic,0
 43 | alto k10,2014,2.55,3.98,46706,Petrol,Dealer,Manual,0
 44 | sx4,2008,1.95,7.15,58000,Petrol,Dealer,Manual,0
 45 | dzire,2014,5.5,8.06,45780,Diesel,Dealer,Manual,0
 46 | omni,2012,1.25,2.69,50000,Petrol,Dealer,Manual,0
 47 | ciaz,2014,7.5,12.04,15000,Petrol,Dealer,Automatic,0
 48 | ritz,2013,2.65,4.89,64532,Petrol,Dealer,Manual,0
 49 | wagon r,2006,1.05,4.15,65000,Petrol,Dealer,Manual,0
 50 | ertiga,2015,5.8,7.71,25870,Petrol,Dealer,Manual,0
 51 | ciaz,2017,7.75,9.29,37000,Petrol,Dealer,Automatic,0
 52 | fortuner,2012,14.9,30.61,104707,Diesel,Dealer,Automatic,0
 53 | fortuner,2015,23,30.61,40000,Diesel,Dealer,Automatic,0
 54 | innova,2017,18,19.77,15000,Diesel,Dealer,Automatic,0
 55 | fortuner,2013,16,30.61,135000,Diesel,Individual,Automatic,0
 56 | innova,2005,2.75,10.21,90000,Petrol,Individual,Manual,0
 57 | corolla altis,2009,3.6,15.04,70000,Petrol,Dealer,Automatic,0
 58 | etios cross,2015,4.5,7.27,40534,Petrol,Dealer,Manual,0
 59 | corolla altis,2010,4.75,18.54,50000,Petrol,Dealer,Manual,0
 60 | etios g,2014,4.1,6.8,39485,Petrol,Dealer,Manual,1
 61 | fortuner,2014,19.99,35.96,41000,Diesel,Dealer,Automatic,0
 62 | corolla altis,2013,6.95,18.61,40001,Petrol,Dealer,Manual,0
 63 | etios cross,2015,4.5,7.7,40588,Petrol,Dealer,Manual,0
 64 | fortuner,2014,18.75,35.96,78000,Diesel,Dealer,Automatic,0
 65 | fortuner,2015,23.5,35.96,47000,Diesel,Dealer,Automatic,0
 66 | fortuner,2017,33,36.23,6000,Diesel,Dealer,Automatic,0
 67 | etios liva,2014,4.75,6.95,45000,Diesel,Dealer,Manual,0
 68 | innova,2017,19.75,23.15,11000,Petrol,Dealer,Automatic,0
 69 | fortuner,2010,9.25,20.45,59000,Diesel,Dealer,Manual,0
 70 | corolla altis,2011,4.35,13.74,88000,Petrol,Dealer,Manual,0
 71 | corolla altis,2016,14.25,20.91,12000,Petrol,Dealer,Manual,0
 72 | etios liva,2014,3.95,6.76,71000,Diesel,Dealer,Manual,0
 73 | corolla altis,2011,4.5,12.48,45000,Diesel,Dealer,Manual,0
 74 | corolla altis,2013,7.45,18.61,56001,Petrol,Dealer,Manual,0
 75 | etios liva,2011,2.65,5.71,43000,Petrol,Dealer,Manual,0
 76 | etios cross,2014,4.9,8.93,83000,Diesel,Dealer,Manual,0
 77 | etios g,2015,3.95,6.8,36000,Petrol,Dealer,Manual,0
 78 | corolla altis,2013,5.5,14.68,72000,Petrol,Dealer,Manual,0
 79 | corolla,2004,1.5,12.35,135154,Petrol,Dealer,Automatic,0
 80 | corolla altis,2010,5.25,22.83,80000,Petrol,Dealer,Automatic,0
 81 | fortuner,2012,14.5,30.61,89000,Diesel,Dealer,Automatic,0
 82 | corolla altis,2016,14.73,14.89,23000,Diesel,Dealer,Manual,0
 83 | etios gd,2015,4.75,7.85,40000,Diesel,Dealer,Manual,0
 84 | innova,2017,23,25.39,15000,Diesel,Dealer,Automatic,0
 85 | innova,2015,12.5,13.46,38000,Diesel,Dealer,Manual,0
 86 | innova,2005,3.49,13.46,197176,Diesel,Dealer,Manual,0
 87 | camry,2006,2.5,23.73,142000,Petrol,Individual,Automatic,3
 88 | land cruiser,2010,35,92.6,78000,Diesel,Dealer,Manual,0
 89 | corolla altis,2012,5.9,13.74,56000,Petrol,Dealer,Manual,0
 90 | etios liva,2013,3.45,6.05,47000,Petrol,Dealer,Manual,0
 91 | etios g,2014,4.75,6.76,40000,Petrol,Dealer,Manual,0
 92 | corolla altis,2009,3.8,18.61,62000,Petrol,Dealer,Manual,0
 93 | innova,2014,11.25,16.09,58242,Diesel,Dealer,Manual,0
 94 | innova,2005,3.51,13.7,75000,Petrol,Dealer,Manual,0
 95 | fortuner,2015,23,30.61,40000,Diesel,Dealer,Automatic,0
 96 | corolla altis,2008,4,22.78,89000,Petrol,Dealer,Automatic,0
 97 | corolla altis,2012,5.85,18.61,72000,Petrol,Dealer,Manual,0
 98 | innova,2016,20.75,25.39,29000,Diesel,Dealer,Automatic,0
 99 | corolla altis,2017,17,18.64,8700,Petrol,Dealer,Manual,0
100 | corolla altis,2013,7.05,18.61,45000,Petrol,Dealer,Manual,0
101 | fortuner,2010,9.65,20.45,50024,Diesel,Dealer,Manual,0
102 | Royal Enfield Thunder 500,2016,1.75,1.9,3000,Petrol,Individual,Manual,0
103 | UM Renegade Mojave,2017,1.7,1.82,1400,Petrol,Individual,Manual,0
104 | KTM RC200,2017,1.65,1.78,4000,Petrol,Individual,Manual,0
105 | Bajaj Dominar 400,2017,1.45,1.6,1200,Petrol,Individual,Manual,0
106 | Royal Enfield Classic 350,2017,1.35,1.47,4100,Petrol,Individual,Manual,0
107 | KTM RC390,2015,1.35,2.37,21700,Petrol,Individual,Manual,0
108 | Hyosung GT250R,2014,1.35,3.45,16500,Petrol,Individual,Manual,1
109 | Royal Enfield Thunder 350,2013,1.25,1.5,15000,Petrol,Individual,Manual,0
110 | Royal Enfield Thunder 350,2016,1.2,1.5,18000,Petrol,Individual,Manual,0
111 | Royal Enfield Classic 350,2017,1.2,1.47,11000,Petrol,Individual,Manual,0
112 | KTM RC200,2016,1.2,1.78,6000,Petrol,Individual,Manual,0
113 | Royal Enfield Thunder 350,2016,1.15,1.5,8700,Petrol,Individual,Manual,0
114 | KTM 390 Duke ,2014,1.15,2.4,7000,Petrol,Individual,Manual,0
115 | Mahindra Mojo XT300,2016,1.15,1.4,35000,Petrol,Individual,Manual,0
116 | Royal Enfield Classic 350,2015,1.15,1.47,17000,Petrol,Individual,Manual,0
117 | Royal Enfield Classic 350,2015,1.11,1.47,17500,Petrol,Individual,Manual,0
118 | Royal Enfield Classic 350,2013,1.1,1.47,33000,Petrol,Individual,Manual,0
119 | Royal Enfield Thunder 500,2015,1.1,1.9,14000,Petrol,Individual,Manual,0
120 | Royal Enfield Classic 350,2015,1.1,1.47,26000,Petrol,Individual,Manual,0
121 | Royal Enfield Thunder 500,2013,1.05,1.9,5400,Petrol,Individual,Manual,0
122 | Bajaj Pulsar RS200,2016,1.05,1.26,5700,Petrol,Individual,Manual,0
123 | Royal Enfield Thunder 350,2011,1.05,1.5,6900,Petrol,Individual,Manual,0
124 | Royal Enfield Bullet 350,2016,1.05,1.17,6000,Petrol,Individual,Manual,0
125 | Royal Enfield Classic 350,2013,1,1.47,46500,Petrol,Individual,Manual,0
126 | Royal Enfield Classic 500,2012,0.95,1.75,11500,Petrol,Individual,Manual,0
127 | Royal Enfield Classic 500,2009,0.9,1.75,40000,Petrol,Individual,Manual,0
128 | Bajaj Avenger 220,2017,0.9,0.95,1300,Petrol,Individual,Manual,0
129 | Bajaj Avenger 150,2016,0.75,0.8,7000,Petrol,Individual,Manual,0
130 | Honda CB Hornet 160R,2017,0.8,0.87,3000,Petrol,Individual,Manual,0
131 | Yamaha FZ S V 2.0,2017,0.78,0.84,5000,Petrol,Individual,Manual,0
132 | Honda CB Hornet 160R,2017,0.75,0.87,11000,Petrol,Individual,Manual,0
133 | Yamaha FZ 16,2015,0.75,0.82,18000,Petrol,Individual,Manual,0
134 | Bajaj Avenger 220,2017,0.75,0.95,3500,Petrol,Individual,Manual,0
135 | Bajaj Avenger 220,2016,0.72,0.95,500,Petrol,Individual,Manual,0
136 | TVS Apache RTR 160,2017,0.65,0.81,11800,Petrol,Individual,Manual,0
137 | Bajaj Pulsar 150,2015,0.65,0.74,5000,Petrol,Individual,Manual,0
138 | Honda CBR 150,2014,0.65,1.2,23500,Petrol,Individual,Manual,0
139 | Hero Extreme,2013,0.65,0.787,16000,Petrol,Individual,Manual,0
140 | Honda CB Hornet 160R,2016,0.6,0.87,15000,Petrol,Individual,Manual,0
141 | Bajaj Avenger 220 dtsi,2015,0.6,0.95,16600,Petrol,Individual,Manual,0
142 | Honda CBR 150,2013,0.6,1.2,32000,Petrol,Individual,Manual,0
143 | Bajaj Avenger 150 street,2016,0.6,0.8,20000,Petrol,Individual,Manual,0
144 | Yamaha FZ  v 2.0,2015,0.6,0.84,29000,Petrol,Individual,Manual,0
145 | Yamaha FZ  v 2.0,2016,0.6,0.84,25000,Petrol,Individual,Manual,0
146 | Bajaj Pulsar  NS 200,2014,0.6,0.99,25000,Petrol,Individual,Manual,0
147 | TVS Apache RTR 160,2012,0.6,0.81,19000,Petrol,Individual,Manual,0
148 | Hero Extreme,2014,0.55,0.787,15000,Petrol,Individual,Manual,0
149 | Yamaha FZ S V 2.0,2015,0.55,0.84,58000,Petrol,Individual,Manual,0
150 | Bajaj Pulsar 220 F,2010,0.52,0.94,45000,Petrol,Individual,Manual,0
151 | Bajaj Pulsar 220 F,2016,0.51,0.94,24000,Petrol,Individual,Manual,0
152 | TVS Apache RTR 180,2011,0.5,0.826,6000,Petrol,Individual,Manual,0
153 | Hero Passion X pro,2016,0.5,0.55,31000,Petrol,Individual,Manual,0
154 | Bajaj Pulsar NS 200,2012,0.5,0.99,13000,Petrol,Individual,Manual,0
155 | Bajaj Pulsar NS 200,2013,0.5,0.99,45000,Petrol,Individual,Manual,0
156 | Yamaha Fazer ,2014,0.5,0.88,8000,Petrol,Individual,Manual,0
157 | Honda Activa 4G,2017,0.48,0.51,4300,Petrol,Individual,Automatic,0
158 | TVS Sport ,2017,0.48,0.52,15000,Petrol,Individual,Manual,0
159 | Yamaha FZ S V 2.0,2015,0.48,0.84,23000,Petrol,Individual,Manual,0
160 | Honda Dream Yuga ,2017,0.48,0.54,8600,Petrol,Individual,Manual,0
161 | Honda Activa 4G,2017,0.45,0.51,4000,Petrol,Individual,Automatic,0
162 | Bajaj Avenger Street 220,2011,0.45,0.95,24000,Petrol,Individual,Manual,0
163 | TVS Apache RTR 180,2014,0.45,0.826,23000,Petrol,Individual,Manual,0
164 | Bajaj Pulsar NS 200,2012,0.45,0.99,14500,Petrol,Individual,Manual,0
165 | Bajaj Avenger 220 dtsi,2010,0.45,0.95,27000,Petrol,Individual,Manual,0
166 | Hero Splender iSmart,2016,0.45,0.54,14000,Petrol,Individual,Manual,0
167 | Activa 3g,2016,0.45,0.54,500,Petrol,Individual,Automatic,0
168 | Hero Passion Pro,2016,0.45,0.55,1000,Petrol,Individual,Manual,0
169 | TVS Apache RTR 160,2014,0.42,0.81,42000,Petrol,Individual,Manual,0
170 | Honda CB Trigger,2013,0.42,0.73,12000,Petrol,Individual,Manual,0
171 | Hero Splender iSmart,2015,0.4,0.54,14000,Petrol,Individual,Manual,0
172 | Yamaha FZ S ,2012,0.4,0.83,5500,Petrol,Individual,Manual,0
173 | Hero Passion Pro,2015,0.4,0.55,6700,Petrol,Individual,Manual,0
174 | Bajaj Pulsar 135 LS,2014,0.4,0.64,13700,Petrol,Individual,Manual,0
175 | Activa 4g,2017,0.4,0.51,1300,Petrol,Individual,Automatic,0
176 | Honda CB Unicorn,2015,0.38,0.72,38600,Petrol,Individual,Manual,0
177 | Hero Honda CBZ extreme,2011,0.38,0.787,75000,Petrol,Individual,Manual,0
178 | Honda Karizma,2011,0.35,1.05,30000,Petrol,Individual,Manual,0
179 | Honda Activa 125,2016,0.35,0.57,24000,Petrol,Individual,Automatic,0
180 | TVS Jupyter,2014,0.35,0.52,19000,Petrol,Individual,Automatic,0
181 | Honda Karizma,2010,0.31,1.05,213000,Petrol,Individual,Manual,0
182 | Hero Honda Passion Pro,2012,0.3,0.51,60000,Petrol,Individual,Manual,0
183 | Hero Splender Plus,2016,0.3,0.48,50000,Petrol,Individual,Manual,0
184 | Honda CB Shine,2013,0.3,0.58,30000,Petrol,Individual,Manual,0
185 | Bajaj Discover 100,2013,0.27,0.47,21000,Petrol,Individual,Manual,0
186 | Bajaj Pulsar 150,2008,0.25,0.75,26000,Petrol,Individual,Manual,1
187 | Suzuki Access 125,2008,0.25,0.58,1900,Petrol,Individual,Automatic,0
188 | TVS Wego,2010,0.25,0.52,22000,Petrol,Individual,Automatic,0
189 | Honda CB twister,2013,0.25,0.51,32000,Petrol,Individual,Manual,0
190 | Hero Glamour,2013,0.25,0.57,18000,Petrol,Individual,Manual,0
191 | Hero Super Splendor,2005,0.2,0.57,55000,Petrol,Individual,Manual,0
192 | Bajaj Pulsar 150,2008,0.2,0.75,60000,Petrol,Individual,Manual,0
193 | Bajaj Discover 125,2012,0.2,0.57,25000,Petrol,Individual,Manual,1
194 | Hero Hunk,2007,0.2,0.75,49000,Petrol,Individual,Manual,1
195 | Hero  Ignitor Disc,2013,0.2,0.65,24000,Petrol,Individual,Manual,1
196 | Hero  CBZ Xtreme,2008,0.2,0.787,50000,Petrol,Individual,Manual,0
197 | Bajaj  ct 100,2015,0.18,0.32,35000,Petrol,Individual,Manual,0
198 | Activa 3g,2008,0.17,0.52,500000,Petrol,Individual,Automatic,0
199 | Honda CB twister,2010,0.16,0.51,33000,Petrol,Individual,Manual,0
200 | Bajaj Discover 125,2011,0.15,0.57,35000,Petrol,Individual,Manual,1
201 | Honda CB Shine,2007,0.12,0.58,53000,Petrol,Individual,Manual,0
202 | Bajaj Pulsar 150,2006,0.1,0.75,92233,Petrol,Individual,Manual,0
203 | i20,2010,3.25,6.79,58000,Diesel,Dealer,Manual,1
204 | grand i10,2015,4.4,5.7,28200,Petrol,Dealer,Manual,0
205 | i10,2011,2.95,4.6,53460,Petrol,Dealer,Manual,0
206 | eon,2015,2.75,4.43,28282,Petrol,Dealer,Manual,0
207 | grand i10,2016,5.25,5.7,3493,Petrol,Dealer,Manual,1
208 | xcent,2017,5.75,7.13,12479,Petrol,Dealer,Manual,0
209 | grand i10,2015,5.15,5.7,34797,Petrol,Dealer,Automatic,0
210 | i20,2017,7.9,8.1,3435,Petrol,Dealer,Manual,0
211 | grand i10,2015,4.85,5.7,21125,Diesel,Dealer,Manual,0
212 | i10,2012,3.1,4.6,35775,Petrol,Dealer,Manual,0
213 | elantra,2015,11.75,14.79,43535,Diesel,Dealer,Manual,0
214 | creta,2016,11.25,13.6,22671,Petrol,Dealer,Manual,0
215 | i20,2011,2.9,6.79,31604,Petrol,Dealer,Manual,0
216 | grand i10,2017,5.25,5.7,20114,Petrol,Dealer,Manual,0
217 | verna,2012,4.5,9.4,36100,Petrol,Dealer,Manual,0
218 | eon,2016,2.9,4.43,12500,Petrol,Dealer,Manual,0
219 | eon,2016,3.15,4.43,15000,Petrol,Dealer,Manual,0
220 | verna,2014,6.45,9.4,45078,Petrol,Dealer,Manual,0
221 | verna,2012,4.5,9.4,36000,Petrol,Dealer,Manual,0
222 | eon,2017,3.5,4.43,38488,Petrol,Dealer,Manual,0
223 | i20,2013,4.5,6.79,32000,Petrol,Dealer,Automatic,0
224 | i20,2014,6,7.6,77632,Diesel,Dealer,Manual,0
225 | verna,2015,8.25,9.4,61381,Diesel,Dealer,Manual,0
226 | verna,2013,5.11,9.4,36198,Petrol,Dealer,Automatic,0
227 | i10,2011,2.7,4.6,22517,Petrol,Dealer,Manual,0
228 | grand i10,2015,5.25,5.7,24678,Petrol,Dealer,Manual,0
229 | i10,2011,2.55,4.43,57000,Petrol,Dealer,Manual,0
230 | verna,2012,4.95,9.4,60000,Diesel,Dealer,Manual,0
231 | i20,2012,3.1,6.79,52132,Diesel,Dealer,Manual,0
232 | verna,2013,6.15,9.4,45000,Diesel,Dealer,Manual,0
233 | verna,2017,9.25,9.4,15001,Petrol,Dealer,Manual,0
234 | elantra,2015,11.45,14.79,12900,Petrol,Dealer,Automatic,0
235 | grand i10,2013,3.9,5.7,53000,Diesel,Dealer,Manual,0
236 | grand i10,2015,5.5,5.7,4492,Petrol,Dealer,Manual,0
237 | verna,2017,9.1,9.4,15141,Petrol,Dealer,Manual,0
238 | eon,2016,3.1,4.43,11849,Petrol,Dealer,Manual,0
239 | creta,2015,11.25,13.6,68000,Diesel,Dealer,Manual,0
240 | verna,2013,4.8,9.4,60241,Petrol,Dealer,Manual,0
241 | eon,2012,2,4.43,23709,Petrol,Dealer,Manual,0
242 | verna,2012,5.35,9.4,32322,Diesel,Dealer,Manual,0
243 | xcent,2015,4.75,7.13,35866,Petrol,Dealer,Manual,1
244 | xcent,2014,4.4,7.13,34000,Petrol,Dealer,Manual,0
245 | i20,2016,6.25,7.6,7000,Petrol,Dealer,Manual,0
246 | verna,2013,5.95,9.4,49000,Diesel,Dealer,Manual,0
247 | verna,2012,5.2,9.4,71000,Diesel,Dealer,Manual,0
248 | i20,2012,3.75,6.79,35000,Petrol,Dealer,Manual,0
249 | verna,2015,5.95,9.4,36000,Petrol,Dealer,Manual,0
250 | i10,2013,4,4.6,30000,Petrol,Dealer,Manual,0
251 | i20,2016,5.25,7.6,17000,Petrol,Dealer,Manual,0
252 | creta,2016,12.9,13.6,35934,Diesel,Dealer,Manual,0
253 | city,2013,5,9.9,56701,Petrol,Dealer,Manual,0
254 | brio,2015,5.4,6.82,31427,Petrol,Dealer,Automatic,0
255 | city,2014,7.2,9.9,48000,Diesel,Dealer,Manual,0
256 | city,2013,5.25,9.9,54242,Petrol,Dealer,Manual,0
257 | brio,2012,3,5.35,53675,Petrol,Dealer,Manual,0
258 | city,2016,10.25,13.6,49562,Petrol,Dealer,Manual,0
259 | city,2015,8.5,13.6,40324,Petrol,Dealer,Manual,0
260 | city,2015,8.4,13.6,25000,Petrol,Dealer,Manual,0
261 | amaze,2014,3.9,7,36054,Petrol,Dealer,Manual,0
262 | city,2016,9.15,13.6,29223,Petrol,Dealer,Manual,0
263 | brio,2016,5.5,5.97,5600,Petrol,Dealer,Manual,0
264 | amaze,2015,4,5.8,40023,Petrol,Dealer,Manual,0
265 | jazz,2016,6.6,7.7,16002,Petrol,Dealer,Manual,0
266 | amaze,2015,4,7,40026,Petrol,Dealer,Manual,0
267 | jazz,2017,6.5,8.7,21200,Petrol,Dealer,Manual,0
268 | amaze,2014,3.65,7,35000,Petrol,Dealer,Manual,0
269 | city,2016,8.35,9.4,19434,Diesel,Dealer,Manual,0
270 | brio,2017,4.8,5.8,19000,Petrol,Dealer,Manual,0
271 | city,2015,6.7,10,18828,Petrol,Dealer,Manual,0
272 | city,2011,4.1,10,69341,Petrol,Dealer,Manual,0
273 | city,2009,3,10,69562,Petrol,Dealer,Manual,0
274 | city,2015,7.5,10,27600,Petrol,Dealer,Manual,0
275 | jazz,2010,2.25,7.5,61203,Petrol,Dealer,Manual,0
276 | brio,2014,5.3,6.8,16500,Petrol,Dealer,Manual,0
277 | city,2016,10.9,13.6,30753,Petrol,Dealer,Automatic,0
278 | city,2015,8.65,13.6,24800,Petrol,Dealer,Manual,0
279 | city,2015,9.7,13.6,21780,Petrol,Dealer,Manual,0
280 | jazz,2016,6,8.4,4000,Petrol,Dealer,Manual,0
281 | city,2014,6.25,13.6,40126,Petrol,Dealer,Manual,0
282 | brio,2015,5.25,5.9,14465,Petrol,Dealer,Manual,0
283 | city,2006,2.1,7.6,50456,Petrol,Dealer,Manual,0
284 | city,2014,8.25,14,63000,Diesel,Dealer,Manual,0
285 | city,2016,8.99,11.8,9010,Petrol,Dealer,Manual,0
286 | brio,2013,3.5,5.9,9800,Petrol,Dealer,Manual,0
287 | jazz,2016,7.4,8.5,15059,Petrol,Dealer,Automatic,0
288 | jazz,2016,5.65,7.9,28569,Petrol,Dealer,Manual,0
289 | amaze,2015,5.75,7.5,44000,Petrol,Dealer,Automatic,0
290 | city,2015,8.4,13.6,34000,Petrol,Dealer,Manual,0
291 | city,2016,10.11,13.6,10980,Petrol,Dealer,Manual,0
292 | amaze,2014,4.5,6.4,19000,Petrol,Dealer,Manual,0
293 | brio,2015,5.4,6.1,31427,Petrol,Dealer,Manual,0
294 | jazz,2016,6.4,8.4,12000,Petrol,Dealer,Manual,0
295 | city,2010,3.25,9.9,38000,Petrol,Dealer,Manual,0
296 | amaze,2014,3.75,6.8,33019,Petrol,Dealer,Manual,0
297 | city,2015,8.55,13.09,60076,Diesel,Dealer,Manual,0
298 | city,2016,9.5,11.6,33988,Diesel,Dealer,Manual,0
299 | brio,2015,4,5.9,60000,Petrol,Dealer,Manual,0
300 | city,2009,3.35,11,87934,Petrol,Dealer,Manual,0
301 | city,2017,11.5,12.5,9000,Diesel,Dealer,Manual,0
302 | brio,2016,5.3,5.9,5464,Petrol,Dealer,Manual,0
303 | 


--------------------------------------------------------------------------------
/hm-recommender.ipynb:
--------------------------------------------------------------------------------
1 | {"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-04-13T11:59:47.200163Z","iopub.execute_input":"2022-04-13T11:59:47.200668Z","iopub.status.idle":"2022-04-13T11:59:47.230047Z","shell.execute_reply.started":"2022-04-13T11:59:47.200543Z","shell.execute_reply":"2022-04-13T11:59:47.229075Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\nimport os\nimport warnings\nwarnings.filterwarnings(\"ignore\")","metadata":{"execution":{"iopub.status.busy":"2022-04-13T11:59:47.231711Z","iopub.execute_input":"2022-04-13T11:59:47.232622Z","iopub.status.idle":"2022-04-13T11:59:47.236528Z","shell.execute_reply.started":"2022-04-13T11:59:47.232583Z","shell.execute_reply":"2022-04-13T11:59:47.235708Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"customers=pd.read_csv('../input/h-and-m-personalized-fashion-recommendations/customers.csv')\ncustomers.describe()","metadata":{"execution":{"iopub.status.busy":"2022-04-13T11:59:47.237707Z","iopub.execute_input":"2022-04-13T11:59:47.237947Z","iopub.status.idle":"2022-04-13T11:59:53.367629Z","shell.execute_reply.started":"2022-04-13T11:59:47.237919Z","shell.execute_reply":"2022-04-13T11:59:53.366776Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"transactions_train=pd.read_csv('../input/h-and-m-personalized-fashion-recommendations/transactions_train.csv')\ntransactions_train['article_id']","metadata":{"execution":{"iopub.status.busy":"2022-04-13T11:59:53.369787Z","iopub.execute_input":"2022-04-13T11:59:53.370012Z","iopub.status.idle":"2022-04-13T12:01:02.469793Z","shell.execute_reply.started":"2022-04-13T11:59:53.369963Z","shell.execute_reply":"2022-04-13T12:01:02.468622Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"transactionsdata=pd.read_csv('../input/h-and-m-personalized-fashion-recommendations/transactions_train.csv',dtype={'article_id': str})","metadata":{"execution":{"iopub.status.busy":"2022-04-13T12:01:02.471617Z","iopub.execute_input":"2022-04-13T12:01:02.471928Z","iopub.status.idle":"2022-04-13T12:01:45.90164Z","shell.execute_reply.started":"2022-04-13T12:01:02.471887Z","shell.execute_reply":"2022-04-13T12:01:45.90082Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"transactionsdata","metadata":{"execution":{"iopub.status.busy":"2022-04-13T12:01:45.903367Z","iopub.execute_input":"2022-04-13T12:01:45.904106Z","iopub.status.idle":"2022-04-13T12:01:45.926837Z","shell.execute_reply.started":"2022-04-13T12:01:45.904041Z","shell.execute_reply":"2022-04-13T12:01:45.925833Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data=transactionsdata.drop(['t_dat', 'price','sales_channel_id'], axis=1)","metadata":{"execution":{"iopub.status.busy":"2022-04-13T12:01:45.928363Z","iopub.execute_input":"2022-04-13T12:01:45.928975Z","iopub.status.idle":"2022-04-13T12:01:46.653996Z","shell.execute_reply.started":"2022-04-13T12:01:45.928925Z","shell.execute_reply":"2022-04-13T12:01:46.653202Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data","metadata":{"execution":{"iopub.status.busy":"2022-04-13T12:01:46.655546Z","iopub.execute_input":"2022-04-13T12:01:46.655839Z","iopub.status.idle":"2022-04-13T12:01:46.668097Z","shell.execute_reply.started":"2022-04-13T12:01:46.655802Z","shell.execute_reply":"2022-04-13T12:01:46.667195Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import random","metadata":{"execution":{"iopub.status.busy":"2022-04-13T12:01:46.669817Z","iopub.execute_input":"2022-04-13T12:01:46.670243Z","iopub.status.idle":"2022-04-13T12:01:46.678833Z","shell.execute_reply.started":"2022-04-13T12:01:46.670201Z","shell.execute_reply":"2022-04-13T12:01:46.678284Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"top_12_items = transactionsdata.groupby('article_id')['customer_id'].nunique().sort_values(ascending=False).head(12).index.tolist()\ntop_12_items","metadata":{"execution":{"iopub.status.busy":"2022-04-13T12:01:46.680816Z","iopub.execute_input":"2022-04-13T12:01:46.681228Z","iopub.status.idle":"2022-04-13T12:02:13.344562Z","shell.execute_reply.started":"2022-04-13T12:01:46.681191Z","shell.execute_reply":"2022-04-13T12:02:13.34203Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ss=pd.read_csv('../input/h-and-m-personalized-fashion-recommendations/sample_submission.csv')","metadata":{"execution":{"iopub.status.busy":"2022-04-13T12:44:10.531825Z","iopub.execute_input":"2022-04-13T12:44:10.532274Z","iopub.status.idle":"2022-04-13T12:44:10.547507Z","shell.execute_reply.started":"2022-04-13T12:44:10.532239Z","shell.execute_reply":"2022-04-13T12:44:10.546212Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ss","metadata":{"execution":{"iopub.status.busy":"2022-04-13T12:44:10.95877Z","iopub.execute_input":"2022-04-13T12:44:10.959718Z","iopub.status.idle":"2022-04-13T12:44:10.977886Z","shell.execute_reply.started":"2022-04-13T12:44:10.959665Z","shell.execute_reply":"2022-04-13T12:44:10.976699Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ss['prediction'] =  ' '.join(top_12_items)\n","metadata":{"execution":{"iopub.status.busy":"2022-04-13T12:03:19.844987Z","iopub.execute_input":"2022-04-13T12:03:19.845289Z","iopub.status.idle":"2022-04-13T12:03:19.862627Z","shell.execute_reply.started":"2022-04-13T12:03:19.845256Z","shell.execute_reply":"2022-04-13T12:03:19.861594Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ss.to_csv('submission.csv', index=False)\nss.shape","metadata":{"execution":{"iopub.status.busy":"2022-04-13T12:43:55.805007Z","iopub.execute_input":"2022-04-13T12:43:55.805734Z","iopub.status.idle":"2022-04-13T12:43:55.818214Z","shell.execute_reply.started":"2022-04-13T12:43:55.805686Z","shell.execute_reply":"2022-04-13T12:43:55.817226Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}


--------------------------------------------------------------------------------
/overfitting-vs-underfitting-simple-explanation.ipynb:
--------------------------------------------------------------------------------
1 | {"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"* > 1- Underfits, when the training loss is way more significant than the testing loss.\n* > 2- Overfits, when the training loss is way smaller than the testing loss.\n* > 3- Performs very well when the training loss and the testing loss are very close.**","metadata":{}},{"cell_type":"markdown","source":"# Packages","metadata":{}},{"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import Sequential,load_model\nfrom keras.layers import Conv2D,MaxPooling2D,SpatialDropout2D,Flatten,Dropout,Dense\nfrom keras.preprocessing import image\nimport tensorflow as tf\nimport matplotlib.pyplot as plt\nimport cv2\nimport numpy as np\nimport os\n","metadata":{"execution":{"iopub.status.busy":"2022-07-27T13:43:46.152269Z","iopub.execute_input":"2022-07-27T13:43:46.152679Z","iopub.status.idle":"2022-07-27T13:43:46.158540Z","shell.execute_reply.started":"2022-07-27T13:43:46.152647Z","shell.execute_reply":"2022-07-27T13:43:46.157406Z"},"trusted":true},"execution_count":30,"outputs":[]},{"cell_type":"markdown","source":"# Data scaling ","metadata":{}},{"cell_type":"code","source":"#Normalization\ntrain=ImageDataGenerator(rescale=1/255)\ntest=ImageDataGenerator(rescale=1/255)","metadata":{"execution":{"iopub.status.busy":"2022-07-27T13:44:04.950608Z","iopub.execute_input":"2022-07-27T13:44:04.951018Z","iopub.status.idle":"2022-07-27T13:44:04.956784Z","shell.execute_reply.started":"2022-07-27T13:44:04.950986Z","shell.execute_reply":"2022-07-27T13:44:04.955450Z"},"trusted":true},"execution_count":31,"outputs":[]},{"cell_type":"markdown","source":"# Data preparation","metadata":{}},{"cell_type":"code","source":"traindataset=train.flow_from_directory('../input/pizza-dataset/pizza_not_pizza/Train',\n                                      target_size=(224,224),\n                                       batch_size=16,\n                                       class_mode='binary')\ntestdataset=train.flow_from_directory('../input/pizza-dataset/pizza_not_pizza/Test',\n                                      target_size=(224,224),\n                                       batch_size=16,\n                                       class_mode='binary')","metadata":{"execution":{"iopub.status.busy":"2022-07-27T13:44:51.279725Z","iopub.execute_input":"2022-07-27T13:44:51.280120Z","iopub.status.idle":"2022-07-27T13:44:51.602476Z","shell.execute_reply.started":"2022-07-27T13:44:51.280091Z","shell.execute_reply":"2022-07-27T13:44:51.601562Z"},"trusted":true},"execution_count":32,"outputs":[{"name":"stdout","text":"Found 1474 images belonging to 2 classes.\nFound 492 images belonging to 2 classes.\n","output_type":"stream"}]},{"cell_type":"markdown","source":"# CNN model","metadata":{}},{"cell_type":"code","source":"model=Sequential()\nmodel.add(Conv2D(32,(3,3),activation='relu',input_shape=(224,224,3)))#filters #Kernalsize #RELU\nmodel.add(MaxPooling2D() )\nmodel.add(Conv2D(32,(3,3),activation='relu'))\nmodel.add(MaxPooling2D() )\nmodel.add(Conv2D(32,(3,3),activation='relu'))\nmodel.add(MaxPooling2D() )\nmodel.add(Flatten())\nmodel.add(Dense(100,activation='relu'))\nmodel.add(Dense(1,activation='sigmoid'))","metadata":{"execution":{"iopub.status.busy":"2022-07-27T13:45:23.765242Z","iopub.execute_input":"2022-07-27T13:45:23.765623Z","iopub.status.idle":"2022-07-27T13:45:23.842837Z","shell.execute_reply.started":"2022-07-27T13:45:23.765591Z","shell.execute_reply":"2022-07-27T13:45:23.841917Z"},"trusted":true},"execution_count":33,"outputs":[]},{"cell_type":"code","source":"\nmodel.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])","metadata":{"execution":{"iopub.status.busy":"2022-07-27T13:45:33.305982Z","iopub.execute_input":"2022-07-27T13:45:33.306375Z","iopub.status.idle":"2022-07-27T13:45:33.317316Z","shell.execute_reply.started":"2022-07-27T13:45:33.306344Z","shell.execute_reply":"2022-07-27T13:45:33.316450Z"},"trusted":true},"execution_count":34,"outputs":[]},{"cell_type":"markdown","source":"# Training","metadata":{}},{"cell_type":"code","source":"model_saved=model.fit_generator(\n        traindataset,\n        epochs=7)","metadata":{"execution":{"iopub.status.busy":"2022-07-27T13:45:43.757598Z","iopub.execute_input":"2022-07-27T13:45:43.757992Z","iopub.status.idle":"2022-07-27T13:48:41.975555Z","shell.execute_reply.started":"2022-07-27T13:45:43.757958Z","shell.execute_reply":"2022-07-27T13:48:41.974458Z"},"trusted":true},"execution_count":35,"outputs":[{"name":"stderr","text":"/opt/conda/lib/python3.7/site-packages/keras/engine/training.py:1972: UserWarning: `Model.fit_generator` is deprecated and will be removed in a future version. Please use `Model.fit`, which supports generators.\n  warnings.warn('`Model.fit_generator` is deprecated and '\n","output_type":"stream"},{"name":"stdout","text":"Epoch 1/7\n93/93 [==============================] - 28s 288ms/step - loss: 0.7196 - accuracy: 0.5543\nEpoch 2/7\n93/93 [==============================] - 25s 270ms/step - loss: 0.6220 - accuracy: 0.6682\nEpoch 3/7\n93/93 [==============================] - 25s 265ms/step - loss: 0.5642 - accuracy: 0.7103\nEpoch 4/7\n93/93 [==============================] - 25s 269ms/step - loss: 0.4936 - accuracy: 0.7673\nEpoch 5/7\n93/93 [==============================] - 25s 264ms/step - loss: 0.4625 - accuracy: 0.7788\nEpoch 6/7\n93/93 [==============================] - 25s 269ms/step - loss: 0.3812 - accuracy: 0.8304\nEpoch 7/7\n93/93 [==============================] - 25s 267ms/step - loss: 0.3009 - accuracy: 0.8752\n","output_type":"stream"}]},{"cell_type":"markdown","source":"# Evaluation","metadata":{}},{"cell_type":"code","source":"prediction=model.predict(testdataset)","metadata":{"execution":{"iopub.status.busy":"2022-07-27T13:53:43.872718Z","iopub.execute_input":"2022-07-27T13:53:43.873065Z","iopub.status.idle":"2022-07-27T13:53:48.207364Z","shell.execute_reply.started":"2022-07-27T13:53:43.873038Z","shell.execute_reply":"2022-07-27T13:53:48.206515Z"},"trusted":true},"execution_count":48,"outputs":[]},{"cell_type":"code","source":"result=prediction[0]\nprint(result)","metadata":{"execution":{"iopub.status.busy":"2022-07-27T13:49:51.927990Z","iopub.execute_input":"2022-07-27T13:49:51.928901Z","iopub.status.idle":"2022-07-27T13:49:51.936127Z","shell.execute_reply.started":"2022-07-27T13:49:51.928848Z","shell.execute_reply":"2022-07-27T13:49:51.934479Z"},"trusted":true},"execution_count":38,"outputs":[{"name":"stdout","text":"[0.9787929]\n","output_type":"stream"}]},{"cell_type":"code","source":"score = model.evaluate(testdataset,verbose=0)\nprint('Test loss:', score[0])\nprint('Test accuracy:', score[1])","metadata":{"execution":{"iopub.status.busy":"2022-07-27T13:54:11.083538Z","iopub.execute_input":"2022-07-27T13:54:11.083921Z","iopub.status.idle":"2022-07-27T13:54:15.488750Z","shell.execute_reply.started":"2022-07-27T13:54:11.083888Z","shell.execute_reply":"2022-07-27T13:54:15.487836Z"},"trusted":true},"execution_count":50,"outputs":[{"name":"stdout","text":"Test loss: 0.5352293848991394\nTest accuracy: 0.7560975551605225\n","output_type":"stream"}]},{"cell_type":"code","source":"score = model.evaluate(traindataset,verbose=0)\nprint('Train loss:', score[0])\nprint('Train accuracy:', score[1])","metadata":{"execution":{"iopub.status.busy":"2022-07-27T13:54:50.260134Z","iopub.execute_input":"2022-07-27T13:54:50.260489Z","iopub.status.idle":"2022-07-27T13:55:01.990069Z","shell.execute_reply.started":"2022-07-27T13:54:50.260460Z","shell.execute_reply":"2022-07-27T13:55:01.988902Z"},"trusted":true},"execution_count":52,"outputs":[{"name":"stdout","text":"Train loss: 0.1777476817369461\nTrain accuracy: 0.9423337578773499\n","output_type":"stream"}]},{"cell_type":"markdown","source":"**Here Train loss is smaller than testing loss,It means we got overfitting issues!For balancing this loss you should add more data variations on both sides**","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}


--------------------------------------------------------------------------------
/price-elasticity.ipynb:
--------------------------------------------------------------------------------
1 | {"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-09-30T04:16:29.358192Z","iopub.execute_input":"2022-09-30T04:16:29.358836Z","iopub.status.idle":"2022-09-30T04:16:29.377678Z","shell.execute_reply.started":"2022-09-30T04:16:29.358775Z","shell.execute_reply":"2022-09-30T04:16:29.375892Z"},"trusted":true},"execution_count":1,"outputs":[{"name":"stdout","text":"/kaggle/input/productsales/sales.csv\n","output_type":"stream"}]},{"cell_type":"code","source":"pip install pyspark","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from pyspark.sql import SparkSession\n\nspark = SparkSession \\\n    .builder \\\n    .appName(\"Python Spark\") \\\n    .config(\"spark.some.config.option\", \"some-value\") \\\n    .getOrCreate()","metadata":{"execution":{"iopub.status.busy":"2022-09-30T04:17:23.806424Z","iopub.execute_input":"2022-09-30T04:17:23.807625Z","iopub.status.idle":"2022-09-30T04:17:24.788719Z","shell.execute_reply.started":"2022-09-30T04:17:23.807544Z","shell.execute_reply":"2022-09-30T04:17:24.787503Z"},"trusted":true},"execution_count":4,"outputs":[{"name":"stdout","text":"22/09/30 04:17:24 WARN SparkSession: Using an existing Spark session; only runtime SQL configurations will take effect.\n","output_type":"stream"}]},{"cell_type":"code","source":"from pyspark.sql.window import Window\nfrom pyspark.sql.functions import lag\nfrom pyspark.sql.functions import col\ndf = spark.read.csv(\"../input/productsales/sales.csv\", header=True, inferSchema=True)","metadata":{"execution":{"iopub.status.busy":"2022-09-30T04:17:58.073876Z","iopub.execute_input":"2022-09-30T04:17:58.074319Z","iopub.status.idle":"2022-09-30T04:17:58.453147Z","shell.execute_reply.started":"2022-09-30T04:17:58.074279Z","shell.execute_reply":"2022-09-30T04:17:58.452209Z"},"trusted":true},"execution_count":7,"outputs":[]},{"cell_type":"code","source":"win = Window.partitionBy('id').orderBy('Discount_price')\ndf1=df.withColumn('perc_price_change', (df.Discount_price - lag(df['Discount_price']).over(win))/100)\ndf1=df1.withColumn('perc_demand_change',(df.Impression-lag(df['Impression']).over(win))/100)","metadata":{"execution":{"iopub.status.busy":"2022-09-30T04:17:53.485363Z","iopub.execute_input":"2022-09-30T04:17:53.485734Z","iopub.status.idle":"2022-09-30T04:17:53.674901Z","shell.execute_reply.started":"2022-09-30T04:17:53.485703Z","shell.execute_reply":"2022-09-30T04:17:53.673857Z"},"trusted":true},"execution_count":6,"outputs":[]},{"cell_type":"code","source":"df1.select(\"Discount_price\",\"perc_price_change\",\"Impression\",\"perc_demand_change\").show()","metadata":{"execution":{"iopub.status.busy":"2022-09-30T04:18:12.192034Z","iopub.execute_input":"2022-09-30T04:18:12.192403Z","iopub.status.idle":"2022-09-30T04:18:13.388488Z","shell.execute_reply.started":"2022-09-30T04:18:12.192372Z","shell.execute_reply":"2022-09-30T04:18:13.387205Z"},"trusted":true},"execution_count":8,"outputs":[{"name":"stdout","text":"+--------------+-------------------+----------+------------------+\n|Discount_price|  perc_price_change|Impression|perc_demand_change|\n+--------------+-------------------+----------+------------------+\n|          96.6|               null|         1|              null|\n|        106.99|             0.1039|         1|               0.0|\n|        174.99| 0.6800000000000002|         1|               0.0|\n|        179.99|               0.05|         5|              0.04|\n|        184.99|               0.05|         1|             -0.04|\n|         189.0|0.04009999999999991|         1|               0.0|\n|         199.0|                0.1|         2|              0.01|\n|         219.0|                0.2|         1|             -0.01|\n|         229.0|                0.1|         1|               0.0|\n+--------------+-------------------+----------+------------------+\n\n","output_type":"stream"}]},{"cell_type":"code","source":"df2=df1.withColumn(\"price_elasticiy\", df1.perc_demand_change /df1.perc_price_change)\ndf3=df2.select(\"Discount_price\",\"perc_price_change\",\"Impression\",\"perc_demand_change\",'price_elasticiy')\ndf3.show()\n","metadata":{"execution":{"iopub.status.busy":"2022-09-30T04:18:49.646406Z","iopub.execute_input":"2022-09-30T04:18:49.646805Z","iopub.status.idle":"2022-09-30T04:18:50.114716Z","shell.execute_reply.started":"2022-09-30T04:18:49.646771Z","shell.execute_reply":"2022-09-30T04:18:50.113517Z"},"trusted":true},"execution_count":11,"outputs":[{"name":"stdout","text":"+--------------+-------------------+----------+------------------+--------------------+\n|Discount_price|  perc_price_change|Impression|perc_demand_change|     price_elasticiy|\n+--------------+-------------------+----------+------------------+--------------------+\n|          96.6|               null|         1|              null|                null|\n|        106.99|             0.1039|         1|               0.0|                 0.0|\n|        174.99| 0.6800000000000002|         1|               0.0|                 0.0|\n|        179.99|               0.05|         5|              0.04|  0.7999999999999999|\n|        184.99|               0.05|         1|             -0.04| -0.7999999999999999|\n|         189.0|0.04009999999999991|         1|               0.0|                 0.0|\n|         199.0|                0.1|         2|              0.01| 0.09999999999999999|\n|         219.0|                0.2|         1|             -0.01|-0.04999999999999...|\n|         229.0|                0.1|         1|               0.0|                 0.0|\n+--------------+-------------------+----------+------------------+--------------------+\n\n","output_type":"stream"}]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}


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