Datasets
Models
Downloads: 1
Diff of
/Model Buliding/final_notebook.ipynb
[000000]
..
[2629da]
Switch to unified view
| a | b/Model Buliding/final_notebook.ipynb | ||
|---|---|---|---|
| 1 | { |
||
| 2 | "cells": [ |
||
| 3 | { |
||
| 4 | "cell_type": "code", |
||
| 5 | "execution_count": 138, |
||
| 6 | "metadata": {}, |
||
| 7 | "outputs": [], |
||
| 8 | "source": [ |
||
| 9 | "import pandas as pd\n", |
||
| 10 | "import numpy as np\n", |
||
| 11 | "import matplotlib.pyplot as plt\n", |
||
| 12 | "from pandas.plotting import scatter_matrix\n", |
||
| 13 | "import seaborn as sns\n", |
||
| 14 | "import pickle\n", |
||
| 15 | "from sklearn.model_selection import train_test_split\n", |
||
| 16 | "from sklearn.preprocessing import StandardScaler\n", |
||
| 17 | "from sklearn.preprocessing import LabelEncoder\n", |
||
| 18 | "from sklearn.metrics import accuracy_score, classification_report\n", |
||
| 19 | "from sklearn.linear_model import LogisticRegression\n", |
||
| 20 | "# from sklearn.tree import DecisionTreeClassifier\n", |
||
| 21 | "# from sklearn.svm import SVC\n", |
||
| 22 | "# from sklearn.neighbors import KNeighborsClassifier\n", |
||
| 23 | "# from sklearn.ensemble import RandomForestClassifier\n", |
||
| 24 | "# from imblearn.over_sampling import SMOTE\n", |
||
| 25 | "# from sklearn.model_selection import GridSearchCV\n", |
||
| 26 | "import warnings\n", |
||
| 27 | "\n", |
||
| 28 | "# Ignore all warnings\n", |
||
| 29 | "warnings.filterwarnings(\"ignore\")" |
||
| 30 | ] |
||
| 31 | }, |
||
| 32 | { |
||
| 33 | "cell_type": "code", |
||
| 34 | "execution_count": 139, |
||
| 35 | "metadata": {}, |
||
| 36 | "outputs": [ |
||
| 37 | { |
||
| 38 | "data": { |
||
| 39 | "text/html": [ |
||
| 40 | "<div>\n", |
||
| 41 | "<style scoped>\n", |
||
| 42 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 43 | " vertical-align: middle;\n", |
||
| 44 | " }\n", |
||
| 45 | "\n", |
||
| 46 | " .dataframe tbody tr th {\n", |
||
| 47 | " vertical-align: top;\n", |
||
| 48 | " }\n", |
||
| 49 | "\n", |
||
| 50 | " .dataframe thead th {\n", |
||
| 51 | " text-align: right;\n", |
||
| 52 | " }\n", |
||
| 53 | "</style>\n", |
||
| 54 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 55 | " <thead>\n", |
||
| 56 | " <tr style=\"text-align: right;\">\n", |
||
| 57 | " <th></th>\n", |
||
| 58 | " <th>General_Health</th>\n", |
||
| 59 | " <th>Checkup</th>\n", |
||
| 60 | " <th>Exercise</th>\n", |
||
| 61 | " <th>Heart_Disease</th>\n", |
||
| 62 | " <th>Skin_Cancer</th>\n", |
||
| 63 | " <th>Other_Cancer</th>\n", |
||
| 64 | " <th>Depression</th>\n", |
||
| 65 | " <th>Diabetes</th>\n", |
||
| 66 | " <th>Arthritis</th>\n", |
||
| 67 | " <th>Sex</th>\n", |
||
| 68 | " <th>Age_Category</th>\n", |
||
| 69 | " <th>Height_(cm)</th>\n", |
||
| 70 | " <th>Weight_(kg)</th>\n", |
||
| 71 | " <th>BMI</th>\n", |
||
| 72 | " <th>Smoking_History</th>\n", |
||
| 73 | " <th>Alcohol_Consumption</th>\n", |
||
| 74 | " <th>Fruit_Consumption</th>\n", |
||
| 75 | " <th>Green_Vegetables_Consumption</th>\n", |
||
| 76 | " <th>FriedPotato_Consumption</th>\n", |
||
| 77 | " </tr>\n", |
||
| 78 | " </thead>\n", |
||
| 79 | " <tbody>\n", |
||
| 80 | " <tr>\n", |
||
| 81 | " <th>0</th>\n", |
||
| 82 | " <td>Poor</td>\n", |
||
| 83 | " <td>Within the past 2 years</td>\n", |
||
| 84 | " <td>No</td>\n", |
||
| 85 | " <td>No</td>\n", |
||
| 86 | " <td>No</td>\n", |
||
| 87 | " <td>No</td>\n", |
||
| 88 | " <td>No</td>\n", |
||
| 89 | " <td>No</td>\n", |
||
| 90 | " <td>Yes</td>\n", |
||
| 91 | " <td>Female</td>\n", |
||
| 92 | " <td>70-74</td>\n", |
||
| 93 | " <td>150.0</td>\n", |
||
| 94 | " <td>32.66</td>\n", |
||
| 95 | " <td>14.54</td>\n", |
||
| 96 | " <td>Yes</td>\n", |
||
| 97 | " <td>0.0</td>\n", |
||
| 98 | " <td>30.0</td>\n", |
||
| 99 | " <td>16.0</td>\n", |
||
| 100 | " <td>12.0</td>\n", |
||
| 101 | " </tr>\n", |
||
| 102 | " <tr>\n", |
||
| 103 | " <th>1</th>\n", |
||
| 104 | " <td>Very Good</td>\n", |
||
| 105 | " <td>Within the past year</td>\n", |
||
| 106 | " <td>No</td>\n", |
||
| 107 | " <td>Yes</td>\n", |
||
| 108 | " <td>No</td>\n", |
||
| 109 | " <td>No</td>\n", |
||
| 110 | " <td>No</td>\n", |
||
| 111 | " <td>Yes</td>\n", |
||
| 112 | " <td>No</td>\n", |
||
| 113 | " <td>Female</td>\n", |
||
| 114 | " <td>70-74</td>\n", |
||
| 115 | " <td>165.0</td>\n", |
||
| 116 | " <td>77.11</td>\n", |
||
| 117 | " <td>28.29</td>\n", |
||
| 118 | " <td>No</td>\n", |
||
| 119 | " <td>0.0</td>\n", |
||
| 120 | " <td>30.0</td>\n", |
||
| 121 | " <td>0.0</td>\n", |
||
| 122 | " <td>4.0</td>\n", |
||
| 123 | " </tr>\n", |
||
| 124 | " <tr>\n", |
||
| 125 | " <th>2</th>\n", |
||
| 126 | " <td>Very Good</td>\n", |
||
| 127 | " <td>Within the past year</td>\n", |
||
| 128 | " <td>Yes</td>\n", |
||
| 129 | " <td>No</td>\n", |
||
| 130 | " <td>No</td>\n", |
||
| 131 | " <td>No</td>\n", |
||
| 132 | " <td>No</td>\n", |
||
| 133 | " <td>Yes</td>\n", |
||
| 134 | " <td>No</td>\n", |
||
| 135 | " <td>Female</td>\n", |
||
| 136 | " <td>60-64</td>\n", |
||
| 137 | " <td>163.0</td>\n", |
||
| 138 | " <td>88.45</td>\n", |
||
| 139 | " <td>33.47</td>\n", |
||
| 140 | " <td>No</td>\n", |
||
| 141 | " <td>4.0</td>\n", |
||
| 142 | " <td>12.0</td>\n", |
||
| 143 | " <td>3.0</td>\n", |
||
| 144 | " <td>16.0</td>\n", |
||
| 145 | " </tr>\n", |
||
| 146 | " <tr>\n", |
||
| 147 | " <th>3</th>\n", |
||
| 148 | " <td>Poor</td>\n", |
||
| 149 | " <td>Within the past year</td>\n", |
||
| 150 | " <td>Yes</td>\n", |
||
| 151 | " <td>Yes</td>\n", |
||
| 152 | " <td>No</td>\n", |
||
| 153 | " <td>No</td>\n", |
||
| 154 | " <td>No</td>\n", |
||
| 155 | " <td>Yes</td>\n", |
||
| 156 | " <td>No</td>\n", |
||
| 157 | " <td>Male</td>\n", |
||
| 158 | " <td>75-79</td>\n", |
||
| 159 | " <td>180.0</td>\n", |
||
| 160 | " <td>93.44</td>\n", |
||
| 161 | " <td>28.73</td>\n", |
||
| 162 | " <td>No</td>\n", |
||
| 163 | " <td>0.0</td>\n", |
||
| 164 | " <td>30.0</td>\n", |
||
| 165 | " <td>30.0</td>\n", |
||
| 166 | " <td>8.0</td>\n", |
||
| 167 | " </tr>\n", |
||
| 168 | " <tr>\n", |
||
| 169 | " <th>4</th>\n", |
||
| 170 | " <td>Good</td>\n", |
||
| 171 | " <td>Within the past year</td>\n", |
||
| 172 | " <td>No</td>\n", |
||
| 173 | " <td>No</td>\n", |
||
| 174 | " <td>No</td>\n", |
||
| 175 | " <td>No</td>\n", |
||
| 176 | " <td>No</td>\n", |
||
| 177 | " <td>No</td>\n", |
||
| 178 | " <td>No</td>\n", |
||
| 179 | " <td>Male</td>\n", |
||
| 180 | " <td>80+</td>\n", |
||
| 181 | " <td>191.0</td>\n", |
||
| 182 | " <td>88.45</td>\n", |
||
| 183 | " <td>24.37</td>\n", |
||
| 184 | " <td>Yes</td>\n", |
||
| 185 | " <td>0.0</td>\n", |
||
| 186 | " <td>8.0</td>\n", |
||
| 187 | " <td>4.0</td>\n", |
||
| 188 | " <td>0.0</td>\n", |
||
| 189 | " </tr>\n", |
||
| 190 | " </tbody>\n", |
||
| 191 | "</table>\n", |
||
| 192 | "</div>" |
||
| 193 | ], |
||
| 194 | "text/plain": [ |
||
| 195 | " General_Health Checkup Exercise Heart_Disease Skin_Cancer \\\n", |
||
| 196 | "0 Poor Within the past 2 years No No No \n", |
||
| 197 | "1 Very Good Within the past year No Yes No \n", |
||
| 198 | "2 Very Good Within the past year Yes No No \n", |
||
| 199 | "3 Poor Within the past year Yes Yes No \n", |
||
| 200 | "4 Good Within the past year No No No \n", |
||
| 201 | "\n", |
||
| 202 | " Other_Cancer Depression Diabetes Arthritis Sex Age_Category \\\n", |
||
| 203 | "0 No No No Yes Female 70-74 \n", |
||
| 204 | "1 No No Yes No Female 70-74 \n", |
||
| 205 | "2 No No Yes No Female 60-64 \n", |
||
| 206 | "3 No No Yes No Male 75-79 \n", |
||
| 207 | "4 No No No No Male 80+ \n", |
||
| 208 | "\n", |
||
| 209 | " Height_(cm) Weight_(kg) BMI Smoking_History Alcohol_Consumption \\\n", |
||
| 210 | "0 150.0 32.66 14.54 Yes 0.0 \n", |
||
| 211 | "1 165.0 77.11 28.29 No 0.0 \n", |
||
| 212 | "2 163.0 88.45 33.47 No 4.0 \n", |
||
| 213 | "3 180.0 93.44 28.73 No 0.0 \n", |
||
| 214 | "4 191.0 88.45 24.37 Yes 0.0 \n", |
||
| 215 | "\n", |
||
| 216 | " Fruit_Consumption Green_Vegetables_Consumption FriedPotato_Consumption \n", |
||
| 217 | "0 30.0 16.0 12.0 \n", |
||
| 218 | "1 30.0 0.0 4.0 \n", |
||
| 219 | "2 12.0 3.0 16.0 \n", |
||
| 220 | "3 30.0 30.0 8.0 \n", |
||
| 221 | "4 8.0 4.0 0.0 " |
||
| 222 | ] |
||
| 223 | }, |
||
| 224 | "execution_count": 139, |
||
| 225 | "metadata": {}, |
||
| 226 | "output_type": "execute_result" |
||
| 227 | } |
||
| 228 | ], |
||
| 229 | "source": [ |
||
| 230 | "df = pd.read_csv(\"CVD_cleaned.csv\")\n", |
||
| 231 | "df.head()" |
||
| 232 | ] |
||
| 233 | }, |
||
| 234 | { |
||
| 235 | "cell_type": "code", |
||
| 236 | "execution_count": 140, |
||
| 237 | "metadata": {}, |
||
| 238 | "outputs": [ |
||
| 239 | { |
||
| 240 | "name": "stdout", |
||
| 241 | "output_type": "stream", |
||
| 242 | "text": [ |
||
| 243 | "<class 'pandas.core.frame.DataFrame'>\n", |
||
| 244 | "RangeIndex: 308854 entries, 0 to 308853\n", |
||
| 245 | "Data columns (total 19 columns):\n", |
||
| 246 | " # Column Non-Null Count Dtype \n", |
||
| 247 | "--- ------ -------------- ----- \n", |
||
| 248 | " 0 General_Health 308854 non-null object \n", |
||
| 249 | " 1 Checkup 308854 non-null object \n", |
||
| 250 | " 2 Exercise 308854 non-null object \n", |
||
| 251 | " 3 Heart_Disease 308854 non-null object \n", |
||
| 252 | " 4 Skin_Cancer 308854 non-null object \n", |
||
| 253 | " 5 Other_Cancer 308854 non-null object \n", |
||
| 254 | " 6 Depression 308854 non-null object \n", |
||
| 255 | " 7 Diabetes 308854 non-null object \n", |
||
| 256 | " 8 Arthritis 308854 non-null object \n", |
||
| 257 | " 9 Sex 308854 non-null object \n", |
||
| 258 | " 10 Age_Category 308854 non-null object \n", |
||
| 259 | " 11 Height_(cm) 308854 non-null float64\n", |
||
| 260 | " 12 Weight_(kg) 308854 non-null float64\n", |
||
| 261 | " 13 BMI 308854 non-null float64\n", |
||
| 262 | " 14 Smoking_History 308854 non-null object \n", |
||
| 263 | " 15 Alcohol_Consumption 308854 non-null float64\n", |
||
| 264 | " 16 Fruit_Consumption 308854 non-null float64\n", |
||
| 265 | " 17 Green_Vegetables_Consumption 308854 non-null float64\n", |
||
| 266 | " 18 FriedPotato_Consumption 308854 non-null float64\n", |
||
| 267 | "dtypes: float64(7), object(12)\n", |
||
| 268 | "memory usage: 44.8+ MB\n" |
||
| 269 | ] |
||
| 270 | } |
||
| 271 | ], |
||
| 272 | "source": [ |
||
| 273 | "df.info()" |
||
| 274 | ] |
||
| 275 | }, |
||
| 276 | { |
||
| 277 | "cell_type": "code", |
||
| 278 | "execution_count": 141, |
||
| 279 | "metadata": {}, |
||
| 280 | "outputs": [ |
||
| 281 | { |
||
| 282 | "data": { |
||
| 283 | "text/plain": [ |
||
| 284 | "Index(['General_Health', 'Checkup', 'Exercise', 'Heart_Disease', 'Skin_Cancer',\n", |
||
| 285 | " 'Other_Cancer', 'Depression', 'Diabetes', 'Arthritis', 'Sex',\n", |
||
| 286 | " 'Age_Category', 'Height_(cm)', 'Weight_(kg)', 'BMI', 'Smoking_History',\n", |
||
| 287 | " 'Alcohol_Consumption', 'Fruit_Consumption',\n", |
||
| 288 | " 'Green_Vegetables_Consumption', 'FriedPotato_Consumption'],\n", |
||
| 289 | " dtype='object')" |
||
| 290 | ] |
||
| 291 | }, |
||
| 292 | "execution_count": 141, |
||
| 293 | "metadata": {}, |
||
| 294 | "output_type": "execute_result" |
||
| 295 | } |
||
| 296 | ], |
||
| 297 | "source": [ |
||
| 298 | "df.columns" |
||
| 299 | ] |
||
| 300 | }, |
||
| 301 | { |
||
| 302 | "cell_type": "code", |
||
| 303 | "execution_count": 142, |
||
| 304 | "metadata": {}, |
||
| 305 | "outputs": [], |
||
| 306 | "source": [ |
||
| 307 | "df.drop(columns=['Skin_Cancer','Other_Cancer'],inplace = True)" |
||
| 308 | ] |
||
| 309 | }, |
||
| 310 | { |
||
| 311 | "cell_type": "code", |
||
| 312 | "execution_count": 143, |
||
| 313 | "metadata": {}, |
||
| 314 | "outputs": [ |
||
| 315 | { |
||
| 316 | "data": { |
||
| 317 | "text/plain": [ |
||
| 318 | "Diabetes\n", |
||
| 319 | "No 266037\n", |
||
| 320 | "Yes 42817\n", |
||
| 321 | "Name: count, dtype: int64" |
||
| 322 | ] |
||
| 323 | }, |
||
| 324 | "execution_count": 143, |
||
| 325 | "metadata": {}, |
||
| 326 | "output_type": "execute_result" |
||
| 327 | } |
||
| 328 | ], |
||
| 329 | "source": [ |
||
| 330 | "df['Diabetes'] = df['Diabetes'].replace({\n", |
||
| 331 | " 'Yes': 'Yes',\n", |
||
| 332 | " 'Yes, but female told only during pregnancy': 'Yes',\n", |
||
| 333 | " 'No': 'No',\n", |
||
| 334 | " 'No, pre-diabetes or borderline diabetes': 'No'\n", |
||
| 335 | "})\n", |
||
| 336 | "df['Diabetes'].value_counts()" |
||
| 337 | ] |
||
| 338 | }, |
||
| 339 | { |
||
| 340 | "cell_type": "code", |
||
| 341 | "execution_count": 144, |
||
| 342 | "metadata": {}, |
||
| 343 | "outputs": [], |
||
| 344 | "source": [ |
||
| 345 | "categorical_columns = df.select_dtypes(include=['object', 'category']).columns\n", |
||
| 346 | "numerical_columns = df.select_dtypes(include=['number'])" |
||
| 347 | ] |
||
| 348 | }, |
||
| 349 | { |
||
| 350 | "cell_type": "code", |
||
| 351 | "execution_count": 145, |
||
| 352 | "metadata": {}, |
||
| 353 | "outputs": [ |
||
| 354 | { |
||
| 355 | "data": { |
||
| 356 | "text/plain": [ |
||
| 357 | "obesity\n", |
||
| 358 | "Overweight 109866\n", |
||
| 359 | "Obesity 106738\n", |
||
| 360 | "Normal weight 87706\n", |
||
| 361 | "Underweight 4544\n", |
||
| 362 | "Name: count, dtype: int64" |
||
| 363 | ] |
||
| 364 | }, |
||
| 365 | "execution_count": 145, |
||
| 366 | "metadata": {}, |
||
| 367 | "output_type": "execute_result" |
||
| 368 | } |
||
| 369 | ], |
||
| 370 | "source": [ |
||
| 371 | "bins = [-float('inf'), 18.5, 24.9, 29.9, float('inf')]\n", |
||
| 372 | "labels = ['Underweight', 'Normal weight', 'Overweight', 'Obesity']\n", |
||
| 373 | "\n", |
||
| 374 | "# Create a new column 'obesity' based on BMI classification\n", |
||
| 375 | "df['obesity'] = pd.cut(df['BMI'], bins=bins, labels=labels)\n", |
||
| 376 | "df['obesity'].value_counts()" |
||
| 377 | ] |
||
| 378 | }, |
||
| 379 | { |
||
| 380 | "cell_type": "code", |
||
| 381 | "execution_count": 146, |
||
| 382 | "metadata": {}, |
||
| 383 | "outputs": [], |
||
| 384 | "source": [ |
||
| 385 | "label_encoders = {}\n", |
||
| 386 | "\n", |
||
| 387 | "# Apply Label Encoding to categorical columns\n", |
||
| 388 | "for column in categorical_columns:\n", |
||
| 389 | " df[column] = df[column].astype(str)\n", |
||
| 390 | " label_encoder = LabelEncoder() \n", |
||
| 391 | " df[column] = label_encoder.fit_transform(df[column])\n", |
||
| 392 | " label_encoders[column] = label_encoder \n" |
||
| 393 | ] |
||
| 394 | }, |
||
| 395 | { |
||
| 396 | "cell_type": "code", |
||
| 397 | "execution_count": 147, |
||
| 398 | "metadata": {}, |
||
| 399 | "outputs": [], |
||
| 400 | "source": [ |
||
| 401 | "with open('label_encoders.pkl', 'wb') as f:\n", |
||
| 402 | " pickle.dump(label_encoders, f)" |
||
| 403 | ] |
||
| 404 | }, |
||
| 405 | { |
||
| 406 | "cell_type": "code", |
||
| 407 | "execution_count": 148, |
||
| 408 | "metadata": {}, |
||
| 409 | "outputs": [ |
||
| 410 | { |
||
| 411 | "name": "stdout", |
||
| 412 | "output_type": "stream", |
||
| 413 | "text": [ |
||
| 414 | "Checkup Label Encoder Mappings:\n", |
||
| 415 | "0: No\n", |
||
| 416 | "1: Yes\n" |
||
| 417 | ] |
||
| 418 | } |
||
| 419 | ], |
||
| 420 | "source": [ |
||
| 421 | "if 'Heart_Disease' in label_encoders:\n", |
||
| 422 | " encoder = label_encoders['Heart_Disease']\n", |
||
| 423 | " mappings = dict(zip(encoder.transform(encoder.classes_), encoder.classes_))\n", |
||
| 424 | " print(\"Checkup Label Encoder Mappings:\")\n", |
||
| 425 | " for key, value in mappings.items():\n", |
||
| 426 | " print(f\"{key}: {value}\")\n", |
||
| 427 | "else:\n", |
||
| 428 | " print(\"Checkup column not found in label encoders.\")" |
||
| 429 | ] |
||
| 430 | }, |
||
| 431 | { |
||
| 432 | "cell_type": "code", |
||
| 433 | "execution_count": 149, |
||
| 434 | "metadata": {}, |
||
| 435 | "outputs": [ |
||
| 436 | { |
||
| 437 | "data": { |
||
| 438 | "text/plain": [ |
||
| 439 | "18" |
||
| 440 | ] |
||
| 441 | }, |
||
| 442 | "execution_count": 149, |
||
| 443 | "metadata": {}, |
||
| 444 | "output_type": "execute_result" |
||
| 445 | } |
||
| 446 | ], |
||
| 447 | "source": [ |
||
| 448 | "len(df.columns.tolist())" |
||
| 449 | ] |
||
| 450 | }, |
||
| 451 | { |
||
| 452 | "cell_type": "code", |
||
| 453 | "execution_count": 150, |
||
| 454 | "metadata": {}, |
||
| 455 | "outputs": [ |
||
| 456 | { |
||
| 457 | "data": { |
||
| 458 | "text/plain": [ |
||
| 459 | "Diabetes\n", |
||
| 460 | "0 266037\n", |
||
| 461 | "1 42817\n", |
||
| 462 | "Name: count, dtype: int64" |
||
| 463 | ] |
||
| 464 | }, |
||
| 465 | "execution_count": 150, |
||
| 466 | "metadata": {}, |
||
| 467 | "output_type": "execute_result" |
||
| 468 | } |
||
| 469 | ], |
||
| 470 | "source": [ |
||
| 471 | "df['Diabetes'].value_counts()" |
||
| 472 | ] |
||
| 473 | }, |
||
| 474 | { |
||
| 475 | "cell_type": "code", |
||
| 476 | "execution_count": 151, |
||
| 477 | "metadata": {}, |
||
| 478 | "outputs": [], |
||
| 479 | "source": [ |
||
| 480 | "y_heart_disease = df['Heart_Disease']\n", |
||
| 481 | "y_diabetes = df['Diabetes']\n", |
||
| 482 | "y_obesity = df['obesity']\n", |
||
| 483 | "X_train = df.drop(columns=['Heart_Disease','Diabetes','obesity'])\n" |
||
| 484 | ] |
||
| 485 | }, |
||
| 486 | { |
||
| 487 | "cell_type": "code", |
||
| 488 | "execution_count": 152, |
||
| 489 | "metadata": {}, |
||
| 490 | "outputs": [], |
||
| 491 | "source": [ |
||
| 492 | "# Feature scaling (Standardizing the data)\n", |
||
| 493 | "# scaler = StandardScaler()\n", |
||
| 494 | "# X_scaled = scaler.fit_transform(X)\n", |
||
| 495 | "\n", |
||
| 496 | "# X_resampled, y_resampled = smote.fit_resample(X_scaled, y)\n", |
||
| 497 | "X_train_ht, X_test_ht, y_train_ht, y_test_ht = train_test_split(X_train,y_heart_disease,test_size= 0.2)\n", |
||
| 498 | "X_train_dt, X_test_dt, y_train_dt, y_test_dt = train_test_split(X_train,y_diabetes,test_size= 0.2)\n", |
||
| 499 | "X_train_ob, X_test_ob, y_train_ob, y_test_ob = train_test_split(X_train,y_obesity,test_size= 0.2)" |
||
| 500 | ] |
||
| 501 | }, |
||
| 502 | { |
||
| 503 | "cell_type": "code", |
||
| 504 | "execution_count": 154, |
||
| 505 | "metadata": {}, |
||
| 506 | "outputs": [ |
||
| 507 | { |
||
| 508 | "data": { |
||
| 509 | "text/plain": [ |
||
| 510 | "Index(['General_Health', 'Checkup', 'Exercise', 'Depression', 'Arthritis',\n", |
||
| 511 | " 'Sex', 'Age_Category', 'Height_(cm)', 'Weight_(kg)', 'BMI',\n", |
||
| 512 | " 'Smoking_History', 'Alcohol_Consumption', 'Fruit_Consumption',\n", |
||
| 513 | " 'Green_Vegetables_Consumption', 'FriedPotato_Consumption'],\n", |
||
| 514 | " dtype='object')" |
||
| 515 | ] |
||
| 516 | }, |
||
| 517 | "execution_count": 154, |
||
| 518 | "metadata": {}, |
||
| 519 | "output_type": "execute_result" |
||
| 520 | } |
||
| 521 | ], |
||
| 522 | "source": [ |
||
| 523 | "X_train_dt.columns" |
||
| 524 | ] |
||
| 525 | }, |
||
| 526 | { |
||
| 527 | "cell_type": "code", |
||
| 528 | "execution_count": 155, |
||
| 529 | "metadata": {}, |
||
| 530 | "outputs": [ |
||
| 531 | { |
||
| 532 | "name": "stdout", |
||
| 533 | "output_type": "stream", |
||
| 534 | "text": [ |
||
| 535 | "Accuracy: 0.9201\n", |
||
| 536 | " precision recall f1-score support\n", |
||
| 537 | "\n", |
||
| 538 | " 0 0.92 1.00 0.96 56850\n", |
||
| 539 | " 1 0.33 0.00 0.01 4921\n", |
||
| 540 | "\n", |
||
| 541 | " accuracy 0.92 61771\n", |
||
| 542 | " macro avg 0.63 0.50 0.48 61771\n", |
||
| 543 | "weighted avg 0.87 0.92 0.88 61771\n", |
||
| 544 | "\n" |
||
| 545 | ] |
||
| 546 | } |
||
| 547 | ], |
||
| 548 | "source": [ |
||
| 549 | "### Logistic Regression\n", |
||
| 550 | "lr_ht = LogisticRegression()\n", |
||
| 551 | "lr_ht.fit(X_train_ht,y_train_ht)\n", |
||
| 552 | "y_pred_ht = lr_ht.predict(X_test_ht)\n", |
||
| 553 | "print(f\"Accuracy: {accuracy_score(y_test_ht, y_pred_ht):.4f}\")\n", |
||
| 554 | "print(classification_report(y_test_ht, y_pred_ht))" |
||
| 555 | ] |
||
| 556 | }, |
||
| 557 | { |
||
| 558 | "cell_type": "code", |
||
| 559 | "execution_count": 156, |
||
| 560 | "metadata": {}, |
||
| 561 | "outputs": [ |
||
| 562 | { |
||
| 563 | "name": "stdout", |
||
| 564 | "output_type": "stream", |
||
| 565 | "text": [ |
||
| 566 | "Accuracy: 0.8609\n", |
||
| 567 | " precision recall f1-score support\n", |
||
| 568 | "\n", |
||
| 569 | " 0 0.86 0.99 0.92 53194\n", |
||
| 570 | " 1 0.49 0.04 0.07 8577\n", |
||
| 571 | "\n", |
||
| 572 | " accuracy 0.86 61771\n", |
||
| 573 | " macro avg 0.68 0.52 0.50 61771\n", |
||
| 574 | "weighted avg 0.81 0.86 0.81 61771\n", |
||
| 575 | "\n" |
||
| 576 | ] |
||
| 577 | } |
||
| 578 | ], |
||
| 579 | "source": [ |
||
| 580 | "### Logistic Regression\n", |
||
| 581 | "lr_dt = LogisticRegression()\n", |
||
| 582 | "lr_dt.fit(X_train_dt,y_train_dt)\n", |
||
| 583 | "y_pred_dt = lr_dt.predict(X_test_dt)\n", |
||
| 584 | "print(f\"Accuracy: {accuracy_score(y_test_dt, y_pred_dt):.4f}\")\n", |
||
| 585 | "print(classification_report(y_test_dt, y_pred_dt))" |
||
| 586 | ] |
||
| 587 | }, |
||
| 588 | { |
||
| 589 | "cell_type": "code", |
||
| 590 | "execution_count": 157, |
||
| 591 | "metadata": {}, |
||
| 592 | "outputs": [ |
||
| 593 | { |
||
| 594 | "name": "stdout", |
||
| 595 | "output_type": "stream", |
||
| 596 | "text": [ |
||
| 597 | "Accuracy: 0.9732\n", |
||
| 598 | " precision recall f1-score support\n", |
||
| 599 | "\n", |
||
| 600 | "Normal weight 0.97 0.97 0.97 17380\n", |
||
| 601 | " Obesity 0.99 0.99 0.99 21321\n", |
||
| 602 | " Overweight 0.98 0.98 0.98 22138\n", |
||
| 603 | " Underweight 0.63 0.65 0.64 932\n", |
||
| 604 | "\n", |
||
| 605 | " accuracy 0.97 61771\n", |
||
| 606 | " macro avg 0.89 0.89 0.89 61771\n", |
||
| 607 | " weighted avg 0.97 0.97 0.97 61771\n", |
||
| 608 | "\n" |
||
| 609 | ] |
||
| 610 | } |
||
| 611 | ], |
||
| 612 | "source": [ |
||
| 613 | "### Logistic Regression\n", |
||
| 614 | "lr_ob = LogisticRegression()\n", |
||
| 615 | "lr_ob.fit(X_train_ob,y_train_ob)\n", |
||
| 616 | "y_pred_ob = lr_ob.predict(X_test_ob)\n", |
||
| 617 | "print(f\"Accuracy: {accuracy_score(y_test_ob, y_pred_ob):.4f}\")\n", |
||
| 618 | "print(classification_report(y_test_ob, y_pred_ob))" |
||
| 619 | ] |
||
| 620 | }, |
||
| 621 | { |
||
| 622 | "cell_type": "code", |
||
| 623 | "execution_count": 158, |
||
| 624 | "metadata": {}, |
||
| 625 | "outputs": [ |
||
| 626 | { |
||
| 627 | "name": "stdout", |
||
| 628 | "output_type": "stream", |
||
| 629 | "text": [ |
||
| 630 | "Accuracy: 0.9732\n", |
||
| 631 | " precision recall f1-score support\n", |
||
| 632 | "\n", |
||
| 633 | "Normal weight 0.97 0.97 0.97 17380\n", |
||
| 634 | " Obesity 0.99 0.99 0.99 21321\n", |
||
| 635 | " Overweight 0.98 0.98 0.98 22138\n", |
||
| 636 | " Underweight 0.63 0.65 0.64 932\n", |
||
| 637 | "\n", |
||
| 638 | " accuracy 0.97 61771\n", |
||
| 639 | " macro avg 0.89 0.89 0.89 61771\n", |
||
| 640 | " weighted avg 0.97 0.97 0.97 61771\n", |
||
| 641 | "\n" |
||
| 642 | ] |
||
| 643 | } |
||
| 644 | ], |
||
| 645 | "source": [ |
||
| 646 | "### Logistic Regression\n", |
||
| 647 | "lr_ob = LogisticRegression()\n", |
||
| 648 | "lr_ob.fit(X_train_ob,y_train_ob)\n", |
||
| 649 | "y_pred_ob = lr_ob.predict(X_test_ob)\n", |
||
| 650 | "print(f\"Accuracy: {accuracy_score(y_test_ob, y_pred_ob):.4f}\")\n", |
||
| 651 | "print(classification_report(y_test_ob, y_pred_ob))" |
||
| 652 | ] |
||
| 653 | }, |
||
| 654 | { |
||
| 655 | "cell_type": "code", |
||
| 656 | "execution_count": null, |
||
| 657 | "metadata": {}, |
||
| 658 | "outputs": [], |
||
| 659 | "source": [] |
||
| 660 | }, |
||
| 661 | { |
||
| 662 | "cell_type": "code", |
||
| 663 | "execution_count": 159, |
||
| 664 | "metadata": {}, |
||
| 665 | "outputs": [ |
||
| 666 | { |
||
| 667 | "name": "stdout", |
||
| 668 | "output_type": "stream", |
||
| 669 | "text": [ |
||
| 670 | "Model saved to lr_ht.pkl\n" |
||
| 671 | ] |
||
| 672 | } |
||
| 673 | ], |
||
| 674 | "source": [ |
||
| 675 | "model_filename = 'lr_ht.pkl'\n", |
||
| 676 | "with open(model_filename, 'wb') as file:\n", |
||
| 677 | " pickle.dump(lr_ht, file)\n", |
||
| 678 | "\n", |
||
| 679 | "print(f\"Model saved to {model_filename}\")" |
||
| 680 | ] |
||
| 681 | }, |
||
| 682 | { |
||
| 683 | "cell_type": "code", |
||
| 684 | "execution_count": 160, |
||
| 685 | "metadata": {}, |
||
| 686 | "outputs": [ |
||
| 687 | { |
||
| 688 | "name": "stdout", |
||
| 689 | "output_type": "stream", |
||
| 690 | "text": [ |
||
| 691 | "Model saved to lr_dt.pkl\n" |
||
| 692 | ] |
||
| 693 | } |
||
| 694 | ], |
||
| 695 | "source": [ |
||
| 696 | "model_filename = 'lr_dt.pkl'\n", |
||
| 697 | "with open(model_filename, 'wb') as file:\n", |
||
| 698 | " pickle.dump(lr_dt, file)\n", |
||
| 699 | "\n", |
||
| 700 | "print(f\"Model saved to {model_filename}\")" |
||
| 701 | ] |
||
| 702 | }, |
||
| 703 | { |
||
| 704 | "cell_type": "code", |
||
| 705 | "execution_count": 161, |
||
| 706 | "metadata": {}, |
||
| 707 | "outputs": [ |
||
| 708 | { |
||
| 709 | "name": "stdout", |
||
| 710 | "output_type": "stream", |
||
| 711 | "text": [ |
||
| 712 | "Model saved to lr_ob.pkl\n" |
||
| 713 | ] |
||
| 714 | } |
||
| 715 | ], |
||
| 716 | "source": [ |
||
| 717 | "model_filename = 'lr_ob.pkl'\n", |
||
| 718 | "with open(model_filename, 'wb') as file:\n", |
||
| 719 | " pickle.dump(lr_ob, file)\n", |
||
| 720 | "\n", |
||
| 721 | "print(f\"Model saved to {model_filename}\")" |
||
| 722 | ] |
||
| 723 | }, |
||
| 724 | { |
||
| 725 | "cell_type": "code", |
||
| 726 | "execution_count": 112, |
||
| 727 | "metadata": {}, |
||
| 728 | "outputs": [ |
||
| 729 | { |
||
| 730 | "name": "stdout", |
||
| 731 | "output_type": "stream", |
||
| 732 | "text": [ |
||
| 733 | "Loaded Model Accuracy: 0.9727\n" |
||
| 734 | ] |
||
| 735 | } |
||
| 736 | ], |
||
| 737 | "source": [ |
||
| 738 | "with open(model_filename, 'rb') as file:\n", |
||
| 739 | " loaded_model = pickle.load(file)\n", |
||
| 740 | "\n", |
||
| 741 | "# Now you can use loaded_model to make predictions\n", |
||
| 742 | "y_pred_loaded = loaded_model.predict(X_test_ob)\n", |
||
| 743 | "print(f\"Loaded Model Accuracy: {accuracy_score(y_test_ob, y_pred_loaded):.4f}\")" |
||
| 744 | ] |
||
| 745 | }, |
||
| 746 | { |
||
| 747 | "cell_type": "code", |
||
| 748 | "execution_count": 113, |
||
| 749 | "metadata": {}, |
||
| 750 | "outputs": [ |
||
| 751 | { |
||
| 752 | "data": { |
||
| 753 | "text/plain": [ |
||
| 754 | "Index(['General_Health', 'Checkup', 'Exercise', 'Skin_Cancer', 'Other_Cancer',\n", |
||
| 755 | " 'Depression', 'Arthritis', 'Sex', 'Age_Category', 'Height_(cm)',\n", |
||
| 756 | " 'Weight_(kg)', 'BMI', 'Smoking_History', 'Alcohol_Consumption',\n", |
||
| 757 | " 'Fruit_Consumption', 'Green_Vegetables_Consumption',\n", |
||
| 758 | " 'FriedPotato_Consumption'],\n", |
||
| 759 | " dtype='object')" |
||
| 760 | ] |
||
| 761 | }, |
||
| 762 | "execution_count": 113, |
||
| 763 | "metadata": {}, |
||
| 764 | "output_type": "execute_result" |
||
| 765 | } |
||
| 766 | ], |
||
| 767 | "source": [ |
||
| 768 | "X_test_ob.columns" |
||
| 769 | ] |
||
| 770 | }, |
||
| 771 | { |
||
| 772 | "cell_type": "code", |
||
| 773 | "execution_count": null, |
||
| 774 | "metadata": {}, |
||
| 775 | "outputs": [], |
||
| 776 | "source": [] |
||
| 777 | }, |
||
| 778 | { |
||
| 779 | "cell_type": "code", |
||
| 780 | "execution_count": 114, |
||
| 781 | "metadata": {}, |
||
| 782 | "outputs": [ |
||
| 783 | { |
||
| 784 | "data": { |
||
| 785 | "text/plain": [ |
||
| 786 | "['General_Health',\n", |
||
| 787 | " 'Checkup',\n", |
||
| 788 | " 'Exercise',\n", |
||
| 789 | " 'Heart_Disease',\n", |
||
| 790 | " 'Skin_Cancer',\n", |
||
| 791 | " 'Other_Cancer',\n", |
||
| 792 | " 'Depression',\n", |
||
| 793 | " 'Diabetes',\n", |
||
| 794 | " 'Arthritis',\n", |
||
| 795 | " 'Sex',\n", |
||
| 796 | " 'Age_Category',\n", |
||
| 797 | " 'Smoking_History']" |
||
| 798 | ] |
||
| 799 | }, |
||
| 800 | "execution_count": 114, |
||
| 801 | "metadata": {}, |
||
| 802 | "output_type": "execute_result" |
||
| 803 | } |
||
| 804 | ], |
||
| 805 | "source": [ |
||
| 806 | "categorical_columns.tolist()" |
||
| 807 | ] |
||
| 808 | }, |
||
| 809 | { |
||
| 810 | "cell_type": "code", |
||
| 811 | "execution_count": 115, |
||
| 812 | "metadata": {}, |
||
| 813 | "outputs": [ |
||
| 814 | { |
||
| 815 | "name": "stdout", |
||
| 816 | "output_type": "stream", |
||
| 817 | "text": [ |
||
| 818 | "Encoded Input DataFrame:\n" |
||
| 819 | ] |
||
| 820 | }, |
||
| 821 | { |
||
| 822 | "data": { |
||
| 823 | "text/html": [ |
||
| 824 | "<div>\n", |
||
| 825 | "<style scoped>\n", |
||
| 826 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 827 | " vertical-align: middle;\n", |
||
| 828 | " }\n", |
||
| 829 | "\n", |
||
| 830 | " .dataframe tbody tr th {\n", |
||
| 831 | " vertical-align: top;\n", |
||
| 832 | " }\n", |
||
| 833 | "\n", |
||
| 834 | " .dataframe thead th {\n", |
||
| 835 | " text-align: right;\n", |
||
| 836 | " }\n", |
||
| 837 | "</style>\n", |
||
| 838 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 839 | " <thead>\n", |
||
| 840 | " <tr style=\"text-align: right;\">\n", |
||
| 841 | " <th></th>\n", |
||
| 842 | " <th>General_Health</th>\n", |
||
| 843 | " <th>Checkup</th>\n", |
||
| 844 | " <th>Exercise</th>\n", |
||
| 845 | " <th>Depression</th>\n", |
||
| 846 | " <th>Arthritis</th>\n", |
||
| 847 | " <th>Sex</th>\n", |
||
| 848 | " <th>Age_Category</th>\n", |
||
| 849 | " <th>Height_(cm)</th>\n", |
||
| 850 | " <th>Weight_(kg)</th>\n", |
||
| 851 | " <th>BMI</th>\n", |
||
| 852 | " <th>Smoking_History</th>\n", |
||
| 853 | " <th>Alcohol_Consumption</th>\n", |
||
| 854 | " <th>Fruit_Consumption</th>\n", |
||
| 855 | " <th>Green_Vegetables_Consumption</th>\n", |
||
| 856 | " <th>FriedPotato_Consumption</th>\n", |
||
| 857 | " </tr>\n", |
||
| 858 | " </thead>\n", |
||
| 859 | " <tbody>\n", |
||
| 860 | " <tr>\n", |
||
| 861 | " <th>0</th>\n", |
||
| 862 | " <td>3</td>\n", |
||
| 863 | " <td>2</td>\n", |
||
| 864 | " <td>0</td>\n", |
||
| 865 | " <td>0</td>\n", |
||
| 866 | " <td>1</td>\n", |
||
| 867 | " <td>0</td>\n", |
||
| 868 | " <td>10</td>\n", |
||
| 869 | " <td>150</td>\n", |
||
| 870 | " <td>32.66</td>\n", |
||
| 871 | " <td>14.34</td>\n", |
||
| 872 | " <td>1</td>\n", |
||
| 873 | " <td>0.0</td>\n", |
||
| 874 | " <td>30.0</td>\n", |
||
| 875 | " <td>16</td>\n", |
||
| 876 | " <td>12</td>\n", |
||
| 877 | " </tr>\n", |
||
| 878 | " </tbody>\n", |
||
| 879 | "</table>\n", |
||
| 880 | "</div>" |
||
| 881 | ], |
||
| 882 | "text/plain": [ |
||
| 883 | " General_Health Checkup Exercise Depression Arthritis Sex \\\n", |
||
| 884 | "0 3 2 0 0 1 0 \n", |
||
| 885 | "\n", |
||
| 886 | " Age_Category Height_(cm) Weight_(kg) BMI Smoking_History \\\n", |
||
| 887 | "0 10 150 32.66 14.34 1 \n", |
||
| 888 | "\n", |
||
| 889 | " Alcohol_Consumption Fruit_Consumption Green_Vegetables_Consumption \\\n", |
||
| 890 | "0 0.0 30.0 16 \n", |
||
| 891 | "\n", |
||
| 892 | " FriedPotato_Consumption \n", |
||
| 893 | "0 12 " |
||
| 894 | ] |
||
| 895 | }, |
||
| 896 | "execution_count": 115, |
||
| 897 | "metadata": {}, |
||
| 898 | "output_type": "execute_result" |
||
| 899 | } |
||
| 900 | ], |
||
| 901 | "source": [ |
||
| 902 | "# Define the columns\n", |
||
| 903 | "columns = ['General_Health', 'Checkup', 'Exercise', 'Depression', 'Arthritis',\n", |
||
| 904 | " 'Sex', 'Age_Category', 'Height_(cm)', 'Weight_(kg)', 'BMI',\n", |
||
| 905 | " 'Smoking_History', 'Alcohol_Consumption', 'Fruit_Consumption',\n", |
||
| 906 | " 'Green_Vegetables_Consumption', 'FriedPotato_Consumption']\n", |
||
| 907 | "\n", |
||
| 908 | "# Define the input values for each column (replace these with actual values)\n", |
||
| 909 | "input_values = {\n", |
||
| 910 | " 'General_Health': 'Poor', # Example values\n", |
||
| 911 | " 'Checkup': 'Within the past 2 years',\n", |
||
| 912 | " 'Exercise': 'No',\n", |
||
| 913 | " 'Depression': 'No',\n", |
||
| 914 | " 'Arthritis': 'Yes',\n", |
||
| 915 | " 'Sex': 'Female',\n", |
||
| 916 | " 'Age_Category': '70-74',\n", |
||
| 917 | " 'Height_(cm)': 150, # Example numerical values\n", |
||
| 918 | " 'Weight_(kg)': 32.66,\n", |
||
| 919 | " 'BMI': 14.34,\n", |
||
| 920 | " 'Smoking_History': 'Yes',\n", |
||
| 921 | " 'Alcohol_Consumption': 0.0,\n", |
||
| 922 | " 'Fruit_Consumption': 30.0,\n", |
||
| 923 | " 'Green_Vegetables_Consumption': 16,\n", |
||
| 924 | " 'FriedPotato_Consumption': 12\n", |
||
| 925 | "}\n", |
||
| 926 | "\n", |
||
| 927 | "# Create a DataFrame from input values\n", |
||
| 928 | "input_df = pd.DataFrame([input_values])\n", |
||
| 929 | "\n", |
||
| 930 | "# Encode categorical columns using the same LabelEncoders you used during training\n", |
||
| 931 | "for column in categorical_columns:\n", |
||
| 932 | " if column in input_df.columns:\n", |
||
| 933 | " # Transform the input values using the stored encoder\n", |
||
| 934 | " input_df[column] = label_encoders[column].transform(input_df[column].astype(str))\n", |
||
| 935 | "\n", |
||
| 936 | "# Display the input DataFrame after encoding\n", |
||
| 937 | "print(\"Encoded Input DataFrame:\")\n", |
||
| 938 | "input_df\n" |
||
| 939 | ] |
||
| 940 | }, |
||
| 941 | { |
||
| 942 | "cell_type": "code", |
||
| 943 | "execution_count": 116, |
||
| 944 | "metadata": {}, |
||
| 945 | "outputs": [ |
||
| 946 | { |
||
| 947 | "ename": "ValueError", |
||
| 948 | "evalue": "The feature names should match those that were passed during fit.\nFeature names seen at fit time, yet now missing:\n- Other_Cancer\n- Skin_Cancer\n", |
||
| 949 | "output_type": "error", |
||
| 950 | "traceback": [ |
||
| 951 | "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", |
||
| 952 | "\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)", |
||
| 953 | "Cell \u001b[1;32mIn[116], line 5\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[38;5;66;03m# Prepare input for prediction (make sure to drop any non-feature columns if necessary)\u001b[39;00m\n\u001b[0;32m 2\u001b[0m \u001b[38;5;66;03m# X_input = input_df[columns]\u001b[39;00m\n\u001b[0;32m 3\u001b[0m \n\u001b[0;32m 4\u001b[0m \u001b[38;5;66;03m# Make the prediction\u001b[39;00m\n\u001b[1;32m----> 5\u001b[0m prediction \u001b[38;5;241m=\u001b[39m loaded_model\u001b[38;5;241m.\u001b[39mpredict(input_df)\n\u001b[0;32m 7\u001b[0m \u001b[38;5;66;03m# Output the prediction\u001b[39;00m\n\u001b[0;32m 8\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPredicted Class: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mprediction[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n", |
||
| 954 | "File \u001b[1;32mc:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_base.py:351\u001b[0m, in \u001b[0;36mLinearClassifierMixin.predict\u001b[1;34m(self, X)\u001b[0m\n\u001b[0;32m 337\u001b[0m \u001b[39m\u001b[39m\u001b[39m\"\"\"\u001b[39;00m\n\u001b[0;32m 338\u001b[0m \u001b[39mPredict class labels for samples in X.\u001b[39;00m\n\u001b[0;32m 339\u001b[0m \n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 348\u001b[0m \u001b[39m Vector containing the class labels for each sample.\u001b[39;00m\n\u001b[0;32m 349\u001b[0m \u001b[39m\"\"\"\u001b[39;00m\n\u001b[0;32m 350\u001b[0m xp, _ \u001b[39m=\u001b[39m get_namespace(X)\n\u001b[1;32m--> 351\u001b[0m scores \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mdecision_function(X)\n\u001b[0;32m 352\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mlen\u001b[39m(scores\u001b[39m.\u001b[39mshape) \u001b[39m==\u001b[39m \u001b[39m1\u001b[39m:\n\u001b[0;32m 353\u001b[0m indices \u001b[39m=\u001b[39m xp\u001b[39m.\u001b[39mastype(scores \u001b[39m>\u001b[39m \u001b[39m0\u001b[39m, \u001b[39mint\u001b[39m)\n", |
||
| 955 | "File \u001b[1;32mc:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_base.py:332\u001b[0m, in \u001b[0;36mLinearClassifierMixin.decision_function\u001b[1;34m(self, X)\u001b[0m\n\u001b[0;32m 329\u001b[0m check_is_fitted(\u001b[39mself\u001b[39m)\n\u001b[0;32m 330\u001b[0m xp, _ \u001b[39m=\u001b[39m get_namespace(X)\n\u001b[1;32m--> 332\u001b[0m X \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_validate_data(X, accept_sparse\u001b[39m=\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mcsr\u001b[39m\u001b[39m\"\u001b[39m, reset\u001b[39m=\u001b[39m\u001b[39mFalse\u001b[39;00m)\n\u001b[0;32m 333\u001b[0m scores \u001b[39m=\u001b[39m safe_sparse_dot(X, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mcoef_\u001b[39m.\u001b[39mT, dense_output\u001b[39m=\u001b[39m\u001b[39mTrue\u001b[39;00m) \u001b[39m+\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mintercept_\n\u001b[0;32m 334\u001b[0m \u001b[39mreturn\u001b[39;00m xp\u001b[39m.\u001b[39mreshape(scores, (\u001b[39m-\u001b[39m\u001b[39m1\u001b[39m,)) \u001b[39mif\u001b[39;00m scores\u001b[39m.\u001b[39mshape[\u001b[39m1\u001b[39m] \u001b[39m==\u001b[39m \u001b[39m1\u001b[39m \u001b[39melse\u001b[39;00m scores\n", |
||
| 956 | "File \u001b[1;32mc:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\base.py:608\u001b[0m, in \u001b[0;36mBaseEstimator._validate_data\u001b[1;34m(self, X, y, reset, validate_separately, cast_to_ndarray, **check_params)\u001b[0m\n\u001b[0;32m 537\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m_validate_data\u001b[39m(\n\u001b[0;32m 538\u001b[0m \u001b[39mself\u001b[39m,\n\u001b[0;32m 539\u001b[0m X\u001b[39m=\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mno_validation\u001b[39m\u001b[39m\"\u001b[39m,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 544\u001b[0m \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mcheck_params,\n\u001b[0;32m 545\u001b[0m ):\n\u001b[0;32m 546\u001b[0m \u001b[39m \u001b[39m\u001b[39m\"\"\"Validate input data and set or check the `n_features_in_` attribute.\u001b[39;00m\n\u001b[0;32m 547\u001b[0m \n\u001b[0;32m 548\u001b[0m \u001b[39m Parameters\u001b[39;00m\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 606\u001b[0m \u001b[39m validated.\u001b[39;00m\n\u001b[0;32m 607\u001b[0m \u001b[39m \"\"\"\u001b[39;00m\n\u001b[1;32m--> 608\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_check_feature_names(X, reset\u001b[39m=\u001b[39mreset)\n\u001b[0;32m 610\u001b[0m \u001b[39mif\u001b[39;00m y \u001b[39mis\u001b[39;00m \u001b[39mNone\u001b[39;00m \u001b[39mand\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_get_tags()[\u001b[39m\"\u001b[39m\u001b[39mrequires_y\u001b[39m\u001b[39m\"\u001b[39m]:\n\u001b[0;32m 611\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\n\u001b[0;32m 612\u001b[0m \u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mThis \u001b[39m\u001b[39m{\u001b[39;00m\u001b[39mself\u001b[39m\u001b[39m.\u001b[39m\u001b[39m__class__\u001b[39m\u001b[39m.\u001b[39m\u001b[39m__name__\u001b[39m\u001b[39m}\u001b[39;00m\u001b[39m estimator \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m 613\u001b[0m \u001b[39m\"\u001b[39m\u001b[39mrequires y to be passed, but the target y is None.\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m 614\u001b[0m )\n", |
||
| 957 | "File \u001b[1;32mc:\\ProgramData\\anaconda3\\Lib\\site-packages\\sklearn\\base.py:535\u001b[0m, in \u001b[0;36mBaseEstimator._check_feature_names\u001b[1;34m(self, X, reset)\u001b[0m\n\u001b[0;32m 530\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m missing_names \u001b[39mand\u001b[39;00m \u001b[39mnot\u001b[39;00m unexpected_names:\n\u001b[0;32m 531\u001b[0m message \u001b[39m+\u001b[39m\u001b[39m=\u001b[39m (\n\u001b[0;32m 532\u001b[0m \u001b[39m\"\u001b[39m\u001b[39mFeature names must be in the same order as they were in fit.\u001b[39m\u001b[39m\\n\u001b[39;00m\u001b[39m\"\u001b[39m\n\u001b[0;32m 533\u001b[0m )\n\u001b[1;32m--> 535\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(message)\n", |
||
| 958 | "\u001b[1;31mValueError\u001b[0m: The feature names should match those that were passed during fit.\nFeature names seen at fit time, yet now missing:\n- Other_Cancer\n- Skin_Cancer\n" |
||
| 959 | ] |
||
| 960 | } |
||
| 961 | ], |
||
| 962 | "source": [ |
||
| 963 | "# Prepare input for prediction (make sure to drop any non-feature columns if necessary)\n", |
||
| 964 | "# X_input = input_df[columns]\n", |
||
| 965 | "\n", |
||
| 966 | "# Make the prediction\n", |
||
| 967 | "prediction = loaded_model.predict(input_df)\n", |
||
| 968 | "\n", |
||
| 969 | "# Output the prediction\n", |
||
| 970 | "print(f\"Predicted Class: {prediction[0]}\")" |
||
| 971 | ] |
||
| 972 | }, |
||
| 973 | { |
||
| 974 | "cell_type": "code", |
||
| 975 | "execution_count": null, |
||
| 976 | "metadata": {}, |
||
| 977 | "outputs": [ |
||
| 978 | { |
||
| 979 | "data": { |
||
| 980 | "text/plain": [ |
||
| 981 | "array(['Underweight'], dtype=object)" |
||
| 982 | ] |
||
| 983 | }, |
||
| 984 | "execution_count": 65, |
||
| 985 | "metadata": {}, |
||
| 986 | "output_type": "execute_result" |
||
| 987 | } |
||
| 988 | ], |
||
| 989 | "source": [ |
||
| 990 | "prediction" |
||
| 991 | ] |
||
| 992 | }, |
||
| 993 | { |
||
| 994 | "cell_type": "code", |
||
| 995 | "execution_count": null, |
||
| 996 | "metadata": {}, |
||
| 997 | "outputs": [ |
||
| 998 | { |
||
| 999 | "data": { |
||
| 1000 | "text/plain": [ |
||
| 1001 | "array([[0.90208773, 0.01696106, 0.06855007, 0.01240114]])" |
||
| 1002 | ] |
||
| 1003 | }, |
||
| 1004 | "execution_count": 70, |
||
| 1005 | "metadata": {}, |
||
| 1006 | "output_type": "execute_result" |
||
| 1007 | } |
||
| 1008 | ], |
||
| 1009 | "source": [ |
||
| 1010 | "model_filename = 'lr_dt.pkl'\n", |
||
| 1011 | "\n", |
||
| 1012 | "with open(model_filename, 'rb') as file:\n", |
||
| 1013 | " loaded_model_lr_dt = pickle.load(file)\n", |
||
| 1014 | "y_pred_loaded = loaded_model_lr_dt.predict_proba(input_df)\n", |
||
| 1015 | "y_pred_loaded" |
||
| 1016 | ] |
||
| 1017 | }, |
||
| 1018 | { |
||
| 1019 | "cell_type": "code", |
||
| 1020 | "execution_count": null, |
||
| 1021 | "metadata": {}, |
||
| 1022 | "outputs": [], |
||
| 1023 | "source": [ |
||
| 1024 | "df" |
||
| 1025 | ] |
||
| 1026 | } |
||
| 1027 | ], |
||
| 1028 | "metadata": { |
||
| 1029 | "kernelspec": { |
||
| 1030 | "display_name": "Python 3.12.4 ('base')", |
||
| 1031 | "language": "python", |
||
| 1032 | "name": "python3" |
||
| 1033 | }, |
||
| 1034 | "language_info": { |
||
| 1035 | "codemirror_mode": { |
||
| 1036 | "name": "ipython", |
||
| 1037 | "version": 3 |
||
| 1038 | }, |
||
| 1039 | "file_extension": ".py", |
||
| 1040 | "mimetype": "text/x-python", |
||
| 1041 | "name": "python", |
||
| 1042 | "nbconvert_exporter": "python", |
||
| 1043 | "pygments_lexer": "ipython3", |
||
| 1044 | "version": "3.12.4" |
||
| 1045 | }, |
||
| 1046 | "orig_nbformat": 4, |
||
| 1047 | "vscode": { |
||
| 1048 | "interpreter": { |
||
| 1049 | "hash": "3c06e3e46abf38078fe4dac36a0085ec2b134ebbd73dd076183d243eeca6918f" |
||
| 1050 | } |
||
| 1051 | } |
||
| 1052 | }, |
||
| 1053 | "nbformat": 4, |
||
| 1054 | "nbformat_minor": 2 |
||
| 1055 | } |