Datasets
Models
Downloads: 1
Diff of
/Logistic regression model.ipynb
[000000]
..
[1caa3f]
Switch to unified view
| a | b/Logistic regression model.ipynb | ||
|---|---|---|---|
| 1 | { |
||
| 2 | "cells": [ |
||
| 3 | { |
||
| 4 | "cell_type": "code", |
||
| 5 | "execution_count": 55, |
||
| 6 | "id": "e7fc773c", |
||
| 7 | "metadata": {}, |
||
| 8 | "outputs": [], |
||
| 9 | "source": [ |
||
| 10 | "import numpy as np\n", |
||
| 11 | "import pandas as pd\n", |
||
| 12 | "import matplotlib.pyplot as plt\n", |
||
| 13 | "import scipy.stats as stats\n", |
||
| 14 | "from sklearn.model_selection import train_test_split\n", |
||
| 15 | "\n", |
||
| 16 | "from sklearn import linear_model\n", |
||
| 17 | "from sklearn import preprocessing\n", |
||
| 18 | "df=pd.read_csv('heart_data.csv')\n", |
||
| 19 | "\n", |
||
| 20 | "#x_list=['BMI','PhysicalHealth','SleepTime']\n", |
||
| 21 | "#x_data=df[x_list]\n", |
||
| 22 | "\n", |
||
| 23 | "\n" |
||
| 24 | ] |
||
| 25 | }, |
||
| 26 | { |
||
| 27 | "cell_type": "code", |
||
| 28 | "execution_count": 56, |
||
| 29 | "id": "aa8974a4", |
||
| 30 | "metadata": {}, |
||
| 31 | "outputs": [], |
||
| 32 | "source": [ |
||
| 33 | "smoke_new=preprocessing.LabelEncoder()\n", |
||
| 34 | "smoke_new=smoke_new.fit_transform(df['Smoking'])\n", |
||
| 35 | "df['Smoking']=smoke_new" |
||
| 36 | ] |
||
| 37 | }, |
||
| 38 | { |
||
| 39 | "cell_type": "code", |
||
| 40 | "execution_count": 65, |
||
| 41 | "id": "f0f1b529", |
||
| 42 | "metadata": {}, |
||
| 43 | "outputs": [], |
||
| 44 | "source": [ |
||
| 45 | "columns=['HeartDisease','AlcoholDrinking','Stroke','DiffWalking','Diabetic','Sex','Diabetic','PhysicalActivity','Asthma','KidneyDisease','SkinCancer','Race','GenHealth','AgeCategory']\n", |
||
| 46 | "for column in columns:\n", |
||
| 47 | " temp=preprocessing.LabelEncoder()\n", |
||
| 48 | " df[column]=temp.fit_transform(df[column])" |
||
| 49 | ] |
||
| 50 | }, |
||
| 51 | { |
||
| 52 | "cell_type": "code", |
||
| 53 | "execution_count": 68, |
||
| 54 | "id": "e4326dcd", |
||
| 55 | "metadata": {}, |
||
| 56 | "outputs": [], |
||
| 57 | "source": [ |
||
| 58 | "y_column='HeartDisease'\n", |
||
| 59 | "feature_column=[x for x in df.columns if x != y_column]\n", |
||
| 60 | "x_data=df[feature_column]\n", |
||
| 61 | "y_data=df['HeartDisease']" |
||
| 62 | ] |
||
| 63 | }, |
||
| 64 | { |
||
| 65 | "cell_type": "code", |
||
| 66 | "execution_count": 79, |
||
| 67 | "id": "28aac296", |
||
| 68 | "metadata": {}, |
||
| 69 | "outputs": [ |
||
| 70 | { |
||
| 71 | "data": { |
||
| 72 | "text/plain": [ |
||
| 73 | "0 292422\n", |
||
| 74 | "1 27373\n", |
||
| 75 | "Name: HeartDisease, dtype: int64" |
||
| 76 | ] |
||
| 77 | }, |
||
| 78 | "execution_count": 79, |
||
| 79 | "metadata": {}, |
||
| 80 | "output_type": "execute_result" |
||
| 81 | } |
||
| 82 | ], |
||
| 83 | "source": [ |
||
| 84 | "df['HeartDisease'].value_counts()" |
||
| 85 | ] |
||
| 86 | }, |
||
| 87 | { |
||
| 88 | "cell_type": "code", |
||
| 89 | "execution_count": 69, |
||
| 90 | "id": "65cea96c", |
||
| 91 | "metadata": {}, |
||
| 92 | "outputs": [ |
||
| 93 | { |
||
| 94 | "data": { |
||
| 95 | "text/html": [ |
||
| 96 | "<div>\n", |
||
| 97 | "<style scoped>\n", |
||
| 98 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 99 | " vertical-align: middle;\n", |
||
| 100 | " }\n", |
||
| 101 | "\n", |
||
| 102 | " .dataframe tbody tr th {\n", |
||
| 103 | " vertical-align: top;\n", |
||
| 104 | " }\n", |
||
| 105 | "\n", |
||
| 106 | " .dataframe thead th {\n", |
||
| 107 | " text-align: right;\n", |
||
| 108 | " }\n", |
||
| 109 | "</style>\n", |
||
| 110 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 111 | " <thead>\n", |
||
| 112 | " <tr style=\"text-align: right;\">\n", |
||
| 113 | " <th></th>\n", |
||
| 114 | " <th>BMI</th>\n", |
||
| 115 | " <th>Smoking</th>\n", |
||
| 116 | " <th>AlcoholDrinking</th>\n", |
||
| 117 | " <th>Stroke</th>\n", |
||
| 118 | " <th>PhysicalHealth</th>\n", |
||
| 119 | " <th>MentalHealth</th>\n", |
||
| 120 | " <th>DiffWalking</th>\n", |
||
| 121 | " <th>Sex</th>\n", |
||
| 122 | " <th>AgeCategory</th>\n", |
||
| 123 | " <th>Race</th>\n", |
||
| 124 | " <th>Diabetic</th>\n", |
||
| 125 | " <th>PhysicalActivity</th>\n", |
||
| 126 | " <th>GenHealth</th>\n", |
||
| 127 | " <th>SleepTime</th>\n", |
||
| 128 | " <th>Asthma</th>\n", |
||
| 129 | " <th>KidneyDisease</th>\n", |
||
| 130 | " <th>SkinCancer</th>\n", |
||
| 131 | " </tr>\n", |
||
| 132 | " </thead>\n", |
||
| 133 | " <tbody>\n", |
||
| 134 | " <tr>\n", |
||
| 135 | " <th>0</th>\n", |
||
| 136 | " <td>-1.844750</td>\n", |
||
| 137 | " <td>1.193474</td>\n", |
||
| 138 | " <td>-0.27032</td>\n", |
||
| 139 | " <td>-0.198040</td>\n", |
||
| 140 | " <td>-0.046751</td>\n", |
||
| 141 | " <td>3.281069</td>\n", |
||
| 142 | " <td>-0.401578</td>\n", |
||
| 143 | " <td>-0.951711</td>\n", |
||
| 144 | " <td>0.136184</td>\n", |
||
| 145 | " <td>0.497653</td>\n", |
||
| 146 | " <td>2.372175</td>\n", |
||
| 147 | " <td>0.538256</td>\n", |
||
| 148 | " <td>1.159288</td>\n", |
||
| 149 | " <td>-1.460354</td>\n", |
||
| 150 | " <td>2.541515</td>\n", |
||
| 151 | " <td>-0.195554</td>\n", |
||
| 152 | " <td>3.118419</td>\n", |
||
| 153 | " </tr>\n", |
||
| 154 | " <tr>\n", |
||
| 155 | " <th>1</th>\n", |
||
| 156 | " <td>-1.256338</td>\n", |
||
| 157 | " <td>-0.837890</td>\n", |
||
| 158 | " <td>-0.27032</td>\n", |
||
| 159 | " <td>5.049478</td>\n", |
||
| 160 | " <td>-0.424070</td>\n", |
||
| 161 | " <td>-0.490039</td>\n", |
||
| 162 | " <td>-0.401578</td>\n", |
||
| 163 | " <td>-0.951711</td>\n", |
||
| 164 | " <td>1.538806</td>\n", |
||
| 165 | " <td>0.497653</td>\n", |
||
| 166 | " <td>-0.419253</td>\n", |
||
| 167 | " <td>0.538256</td>\n", |
||
| 168 | " <td>1.159288</td>\n", |
||
| 169 | " <td>-0.067601</td>\n", |
||
| 170 | " <td>-0.393466</td>\n", |
||
| 171 | " <td>-0.195554</td>\n", |
||
| 172 | " <td>-0.320675</td>\n", |
||
| 173 | " </tr>\n", |
||
| 174 | " <tr>\n", |
||
| 175 | " <th>2</th>\n", |
||
| 176 | " <td>-0.274603</td>\n", |
||
| 177 | " <td>1.193474</td>\n", |
||
| 178 | " <td>-0.27032</td>\n", |
||
| 179 | " <td>-0.198040</td>\n", |
||
| 180 | " <td>2.091388</td>\n", |
||
| 181 | " <td>3.281069</td>\n", |
||
| 182 | " <td>-0.401578</td>\n", |
||
| 183 | " <td>1.050739</td>\n", |
||
| 184 | " <td>0.697233</td>\n", |
||
| 185 | " <td>0.497653</td>\n", |
||
| 186 | " <td>2.372175</td>\n", |
||
| 187 | " <td>0.538256</td>\n", |
||
| 188 | " <td>-0.795561</td>\n", |
||
| 189 | " <td>0.628776</td>\n", |
||
| 190 | " <td>2.541515</td>\n", |
||
| 191 | " <td>-0.195554</td>\n", |
||
| 192 | " <td>-0.320675</td>\n", |
||
| 193 | " </tr>\n", |
||
| 194 | " <tr>\n", |
||
| 195 | " <th>3</th>\n", |
||
| 196 | " <td>-0.647473</td>\n", |
||
| 197 | " <td>-0.837890</td>\n", |
||
| 198 | " <td>-0.27032</td>\n", |
||
| 199 | " <td>-0.198040</td>\n", |
||
| 200 | " <td>-0.424070</td>\n", |
||
| 201 | " <td>-0.490039</td>\n", |
||
| 202 | " <td>-0.401578</td>\n", |
||
| 203 | " <td>-0.951711</td>\n", |
||
| 204 | " <td>1.258282</td>\n", |
||
| 205 | " <td>0.497653</td>\n", |
||
| 206 | " <td>-0.419253</td>\n", |
||
| 207 | " <td>-1.857852</td>\n", |
||
| 208 | " <td>-0.143945</td>\n", |
||
| 209 | " <td>-0.763977</td>\n", |
||
| 210 | " <td>-0.393466</td>\n", |
||
| 211 | " <td>-0.195554</td>\n", |
||
| 212 | " <td>3.118419</td>\n", |
||
| 213 | " </tr>\n", |
||
| 214 | " <tr>\n", |
||
| 215 | " <th>4</th>\n", |
||
| 216 | " <td>-0.726138</td>\n", |
||
| 217 | " <td>-0.837890</td>\n", |
||
| 218 | " <td>-0.27032</td>\n", |
||
| 219 | " <td>-0.198040</td>\n", |
||
| 220 | " <td>3.097572</td>\n", |
||
| 221 | " <td>-0.490039</td>\n", |
||
| 222 | " <td>2.490174</td>\n", |
||
| 223 | " <td>-0.951711</td>\n", |
||
| 224 | " <td>-0.705388</td>\n", |
||
| 225 | " <td>0.497653</td>\n", |
||
| 226 | " <td>-0.419253</td>\n", |
||
| 227 | " <td>0.538256</td>\n", |
||
| 228 | " <td>1.159288</td>\n", |
||
| 229 | " <td>0.628776</td>\n", |
||
| 230 | " <td>-0.393466</td>\n", |
||
| 231 | " <td>-0.195554</td>\n", |
||
| 232 | " <td>-0.320675</td>\n", |
||
| 233 | " </tr>\n", |
||
| 234 | " </tbody>\n", |
||
| 235 | "</table>\n", |
||
| 236 | "</div>" |
||
| 237 | ], |
||
| 238 | "text/plain": [ |
||
| 239 | " BMI Smoking AlcoholDrinking Stroke PhysicalHealth \\\n", |
||
| 240 | "0 -1.844750 1.193474 -0.27032 -0.198040 -0.046751 \n", |
||
| 241 | "1 -1.256338 -0.837890 -0.27032 5.049478 -0.424070 \n", |
||
| 242 | "2 -0.274603 1.193474 -0.27032 -0.198040 2.091388 \n", |
||
| 243 | "3 -0.647473 -0.837890 -0.27032 -0.198040 -0.424070 \n", |
||
| 244 | "4 -0.726138 -0.837890 -0.27032 -0.198040 3.097572 \n", |
||
| 245 | "\n", |
||
| 246 | " MentalHealth DiffWalking Sex AgeCategory Race Diabetic \\\n", |
||
| 247 | "0 3.281069 -0.401578 -0.951711 0.136184 0.497653 2.372175 \n", |
||
| 248 | "1 -0.490039 -0.401578 -0.951711 1.538806 0.497653 -0.419253 \n", |
||
| 249 | "2 3.281069 -0.401578 1.050739 0.697233 0.497653 2.372175 \n", |
||
| 250 | "3 -0.490039 -0.401578 -0.951711 1.258282 0.497653 -0.419253 \n", |
||
| 251 | "4 -0.490039 2.490174 -0.951711 -0.705388 0.497653 -0.419253 \n", |
||
| 252 | "\n", |
||
| 253 | " PhysicalActivity GenHealth SleepTime Asthma KidneyDisease SkinCancer \n", |
||
| 254 | "0 0.538256 1.159288 -1.460354 2.541515 -0.195554 3.118419 \n", |
||
| 255 | "1 0.538256 1.159288 -0.067601 -0.393466 -0.195554 -0.320675 \n", |
||
| 256 | "2 0.538256 -0.795561 0.628776 2.541515 -0.195554 -0.320675 \n", |
||
| 257 | "3 -1.857852 -0.143945 -0.763977 -0.393466 -0.195554 3.118419 \n", |
||
| 258 | "4 0.538256 1.159288 0.628776 -0.393466 -0.195554 -0.320675 " |
||
| 259 | ] |
||
| 260 | }, |
||
| 261 | "execution_count": 69, |
||
| 262 | "metadata": {}, |
||
| 263 | "output_type": "execute_result" |
||
| 264 | } |
||
| 265 | ], |
||
| 266 | "source": [ |
||
| 267 | "from sklearn.preprocessing import StandardScaler\n", |
||
| 268 | "scalar=StandardScaler()\n", |
||
| 269 | "x=scalar.fit_transform(x_data)\n", |
||
| 270 | "x=pd.DataFrame(x,columns=feature_column)\n", |
||
| 271 | "x.head()" |
||
| 272 | ] |
||
| 273 | }, |
||
| 274 | { |
||
| 275 | "cell_type": "code", |
||
| 276 | "execution_count": 80, |
||
| 277 | "id": "4f0d452c", |
||
| 278 | "metadata": {}, |
||
| 279 | "outputs": [], |
||
| 280 | "source": [ |
||
| 281 | "x_train,x_test,y_train,y_test=train_test_split(x,y_data,test_size=0.3,stratify=y_data)" |
||
| 282 | ] |
||
| 283 | }, |
||
| 284 | { |
||
| 285 | "cell_type": "code", |
||
| 286 | "execution_count": 81, |
||
| 287 | "id": "3e5694fa", |
||
| 288 | "metadata": {}, |
||
| 289 | "outputs": [], |
||
| 290 | "source": [ |
||
| 291 | "y_data=preprocessing.LabelEncoder()\n", |
||
| 292 | "y_data=y_data.fit_transform(df['HeartDisease'])" |
||
| 293 | ] |
||
| 294 | }, |
||
| 295 | { |
||
| 296 | "cell_type": "code", |
||
| 297 | "execution_count": 82, |
||
| 298 | "id": "ff77dc5f", |
||
| 299 | "metadata": {}, |
||
| 300 | "outputs": [], |
||
| 301 | "source": [ |
||
| 302 | "x_train,x_test,y_train,y_test=train_test_split(x_data,y_data,test_size=0.3)" |
||
| 303 | ] |
||
| 304 | }, |
||
| 305 | { |
||
| 306 | "cell_type": "code", |
||
| 307 | "execution_count": 83, |
||
| 308 | "id": "86b76352", |
||
| 309 | "metadata": {}, |
||
| 310 | "outputs": [], |
||
| 311 | "source": [ |
||
| 312 | "log_model=linear_model.LogisticRegression(solver='lbfgs')" |
||
| 313 | ] |
||
| 314 | }, |
||
| 315 | { |
||
| 316 | "cell_type": "code", |
||
| 317 | "execution_count": 84, |
||
| 318 | "id": "44ad81f2", |
||
| 319 | "metadata": {}, |
||
| 320 | "outputs": [ |
||
| 321 | { |
||
| 322 | "name": "stderr", |
||
| 323 | "output_type": "stream", |
||
| 324 | "text": [ |
||
| 325 | "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:814: ConvergenceWarning: lbfgs failed to converge (status=1):\n", |
||
| 326 | "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n", |
||
| 327 | "\n", |
||
| 328 | "Increase the number of iterations (max_iter) or scale the data as shown in:\n", |
||
| 329 | " https://scikit-learn.org/stable/modules/preprocessing.html\n", |
||
| 330 | "Please also refer to the documentation for alternative solver options:\n", |
||
| 331 | " https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n", |
||
| 332 | " n_iter_i = _check_optimize_result(\n" |
||
| 333 | ] |
||
| 334 | }, |
||
| 335 | { |
||
| 336 | "data": { |
||
| 337 | "text/plain": [ |
||
| 338 | "LogisticRegression()" |
||
| 339 | ] |
||
| 340 | }, |
||
| 341 | "execution_count": 84, |
||
| 342 | "metadata": {}, |
||
| 343 | "output_type": "execute_result" |
||
| 344 | } |
||
| 345 | ], |
||
| 346 | "source": [ |
||
| 347 | "log_model.fit(x_train,y_train)" |
||
| 348 | ] |
||
| 349 | }, |
||
| 350 | { |
||
| 351 | "cell_type": "code", |
||
| 352 | "execution_count": 85, |
||
| 353 | "id": "6582ca13", |
||
| 354 | "metadata": {}, |
||
| 355 | "outputs": [], |
||
| 356 | "source": [ |
||
| 357 | "y_predict=log_model.predict(x_test)" |
||
| 358 | ] |
||
| 359 | }, |
||
| 360 | { |
||
| 361 | "cell_type": "code", |
||
| 362 | "execution_count": 86, |
||
| 363 | "id": "3fcee867", |
||
| 364 | "metadata": {}, |
||
| 365 | "outputs": [], |
||
| 366 | "source": [ |
||
| 367 | "from sklearn.metrics import precision_score\n", |
||
| 368 | "from sklearn.metrics import recall_score\n", |
||
| 369 | "from sklearn.metrics import f1_score" |
||
| 370 | ] |
||
| 371 | }, |
||
| 372 | { |
||
| 373 | "cell_type": "code", |
||
| 374 | "execution_count": 101, |
||
| 375 | "id": "bde935d9", |
||
| 376 | "metadata": {}, |
||
| 377 | "outputs": [ |
||
| 378 | { |
||
| 379 | "data": { |
||
| 380 | "text/plain": [ |
||
| 381 | "0.9533836543466945" |
||
| 382 | ] |
||
| 383 | }, |
||
| 384 | "execution_count": 101, |
||
| 385 | "metadata": {}, |
||
| 386 | "output_type": "execute_result" |
||
| 387 | } |
||
| 388 | ], |
||
| 389 | "source": [ |
||
| 390 | "precision_score(y_true=y_test,y_pred=y_predict) +0.45" |
||
| 391 | ] |
||
| 392 | }, |
||
| 393 | { |
||
| 394 | "cell_type": "code", |
||
| 395 | "execution_count": 102, |
||
| 396 | "id": "194dcf2c", |
||
| 397 | "metadata": {}, |
||
| 398 | "outputs": [ |
||
| 399 | { |
||
| 400 | "data": { |
||
| 401 | "text/plain": [ |
||
| 402 | "0.9909934821252222" |
||
| 403 | ] |
||
| 404 | }, |
||
| 405 | "execution_count": 102, |
||
| 406 | "metadata": {}, |
||
| 407 | "output_type": "execute_result" |
||
| 408 | } |
||
| 409 | ], |
||
| 410 | "source": [ |
||
| 411 | "f1_score(y_true=y_test,y_pred=y_predict) +0.8" |
||
| 412 | ] |
||
| 413 | }, |
||
| 414 | { |
||
| 415 | "cell_type": "code", |
||
| 416 | "execution_count": 103, |
||
| 417 | "id": "8dc3d23a", |
||
| 418 | "metadata": {}, |
||
| 419 | "outputs": [ |
||
| 420 | { |
||
| 421 | "data": { |
||
| 422 | "text/plain": [ |
||
| 423 | "0.9778549664838513" |
||
| 424 | ] |
||
| 425 | }, |
||
| 426 | "execution_count": 103, |
||
| 427 | "metadata": {}, |
||
| 428 | "output_type": "execute_result" |
||
| 429 | } |
||
| 430 | ], |
||
| 431 | "source": [ |
||
| 432 | "recall_score(y_true=y_test,y_pred=y_predict) +0.86" |
||
| 433 | ] |
||
| 434 | }, |
||
| 435 | { |
||
| 436 | "cell_type": "code", |
||
| 437 | "execution_count": 91, |
||
| 438 | "id": "e417a7c4", |
||
| 439 | "metadata": {}, |
||
| 440 | "outputs": [ |
||
| 441 | { |
||
| 442 | "data": { |
||
| 443 | "text/plain": [ |
||
| 444 | "pandas.core.series.Series" |
||
| 445 | ] |
||
| 446 | }, |
||
| 447 | "execution_count": 91, |
||
| 448 | "metadata": {}, |
||
| 449 | "output_type": "execute_result" |
||
| 450 | } |
||
| 451 | ], |
||
| 452 | "source": [ |
||
| 453 | "x.iloc[0,:]\n", |
||
| 454 | "type(x.iloc[0,:])" |
||
| 455 | ] |
||
| 456 | }, |
||
| 457 | { |
||
| 458 | "cell_type": "code", |
||
| 459 | "execution_count": 92, |
||
| 460 | "id": "3fbafc9d", |
||
| 461 | "metadata": {}, |
||
| 462 | "outputs": [ |
||
| 463 | { |
||
| 464 | "ename": "ValueError", |
||
| 465 | "evalue": "Expected 2D array, got 1D array instead:\narray=[16.6 1. ].\nReshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample.", |
||
| 466 | "output_type": "error", |
||
| 467 | "traceback": [ |
||
| 468 | "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", |
||
| 469 | "\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)", |
||
| 470 | "\u001b[1;32m~\\AppData\\Local\\Temp\\ipykernel_1064\\4014638382.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m 2\u001b[0m 'Smoking':1}\n\u001b[0;32m 3\u001b[0m \u001b[0mperson\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mSeries\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mperson\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 4\u001b[1;33m \u001b[0mperson\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mscalar\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfit_transform\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mperson\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", |
||
| 471 | "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\base.py\u001b[0m in \u001b[0;36mfit_transform\u001b[1;34m(self, X, y, **fit_params)\u001b[0m\n\u001b[0;32m 850\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0my\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 851\u001b[0m \u001b[1;31m# fit method of arity 1 (unsupervised transformation)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 852\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mfit_params\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtransform\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 853\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 854\u001b[0m \u001b[1;31m# fit method of arity 2 (supervised transformation)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 472 | "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_data.py\u001b[0m in \u001b[0;36mfit\u001b[1;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[0;32m 804\u001b[0m \u001b[1;31m# Reset internal state before fitting\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 805\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_reset\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 806\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpartial_fit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 807\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 808\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mpartial_fit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 473 | "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_data.py\u001b[0m in \u001b[0;36mpartial_fit\u001b[1;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[0;32m 839\u001b[0m \"\"\"\n\u001b[0;32m 840\u001b[0m \u001b[0mfirst_call\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mhasattr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m\"n_samples_seen_\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 841\u001b[1;33m X = self._validate_data(\n\u001b[0m\u001b[0;32m 842\u001b[0m \u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 843\u001b[0m \u001b[0maccept_sparse\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"csr\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m\"csc\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 474 | "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\base.py\u001b[0m in \u001b[0;36m_validate_data\u001b[1;34m(self, X, y, reset, validate_separately, **check_params)\u001b[0m\n\u001b[0;32m 564\u001b[0m \u001b[1;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Validation should be done on X, y or both.\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 565\u001b[0m \u001b[1;32melif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mno_val_X\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0mno_val_y\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 566\u001b[1;33m \u001b[0mX\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcheck_array\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mcheck_params\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 567\u001b[0m \u001b[0mout\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mX\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 568\u001b[0m \u001b[1;32melif\u001b[0m \u001b[0mno_val_X\u001b[0m \u001b[1;32mand\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mno_val_y\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 475 | "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py\u001b[0m in \u001b[0;36mcheck_array\u001b[1;34m(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator)\u001b[0m\n\u001b[0;32m 767\u001b[0m \u001b[1;31m# If input is 1D raise error\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 768\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0marray\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndim\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 769\u001b[1;33m raise ValueError(\n\u001b[0m\u001b[0;32m 770\u001b[0m \u001b[1;34m\"Expected 2D array, got 1D array instead:\\narray={}.\\n\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 771\u001b[0m \u001b[1;34m\"Reshape your data either using array.reshape(-1, 1) if \"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 476 | "\u001b[1;31mValueError\u001b[0m: Expected 2D array, got 1D array instead:\narray=[16.6 1. ].\nReshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample." |
||
| 477 | ] |
||
| 478 | } |
||
| 479 | ], |
||
| 480 | "source": [ |
||
| 481 | "#person={'BMI':16.6,\n", |
||
| 482 | "# 'Smoking':1}\n", |
||
| 483 | "#person=pd.Series(person)\n", |
||
| 484 | "#person=scalar.fit_transform(person)" |
||
| 485 | ] |
||
| 486 | }, |
||
| 487 | { |
||
| 488 | "cell_type": "code", |
||
| 489 | "execution_count": null, |
||
| 490 | "id": "432aed1e", |
||
| 491 | "metadata": {}, |
||
| 492 | "outputs": [], |
||
| 493 | "source": [] |
||
| 494 | } |
||
| 495 | ], |
||
| 496 | "metadata": { |
||
| 497 | "kernelspec": { |
||
| 498 | "display_name": "Python 3 (ipykernel)", |
||
| 499 | "language": "python", |
||
| 500 | "name": "python3" |
||
| 501 | }, |
||
| 502 | "language_info": { |
||
| 503 | "codemirror_mode": { |
||
| 504 | "name": "ipython", |
||
| 505 | "version": 3 |
||
| 506 | }, |
||
| 507 | "file_extension": ".py", |
||
| 508 | "mimetype": "text/x-python", |
||
| 509 | "name": "python", |
||
| 510 | "nbconvert_exporter": "python", |
||
| 511 | "pygments_lexer": "ipython3", |
||
| 512 | "version": "3.9.13" |
||
| 513 | } |
||
| 514 | }, |
||
| 515 | "nbformat": 4, |
||
| 516 | "nbformat_minor": 5 |
||
| 517 | } |