Spaces:
Runtime error
Runtime error
File size: 14,632 Bytes
6005162 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 |
{
"cells": [
{
"cell_type": "markdown",
"id": "c2f352ed",
"metadata": {},
"source": [
"# Dataset\n",
"\n",
"https://www.kaggle.com/datasets/andrewmvd/autism-screening-on-adults"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "dff0477d",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd \n",
"from sklearn.ensemble import RandomForestClassifier\n",
"import pickle \n",
"import numpy as np"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "53a8cd69",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" A1_Score A2_Score A3_Score A4_Score A5_Score A6_Score A7_Score \\\n",
"0 1 1 1 1 0 0 1 \n",
"1 1 1 0 1 0 0 0 \n",
"2 1 1 0 1 1 0 1 \n",
"3 1 1 0 1 0 0 1 \n",
"4 1 0 0 0 0 0 0 \n",
"\n",
" A8_Score A9_Score A10_Score age gender ethnicity jundice austim \\\n",
"0 1 0 0 26.0 f White-European no no \n",
"1 1 0 1 24.0 m Latino no yes \n",
"2 1 1 1 27.0 m Latino yes yes \n",
"3 1 0 1 35.0 f White-European no yes \n",
"4 1 0 0 40.0 f ? no no \n",
"\n",
" contry_of_res used_app_before result age_desc relation Class/ASD \n",
"0 United States no 6.0 18 and more Self NO \n",
"1 Brazil no 5.0 18 and more Self NO \n",
"2 Spain no 8.0 18 and more Parent YES \n",
"3 United States no 6.0 18 and more Self NO \n",
"4 Egypt no 2.0 18 and more ? NO \n"
]
}
],
"source": [
"pd.set_option('display.max_columns', None)\n",
"pd.set_option('display.max_rows', None)\n",
"df_autism = pd.read_csv('autism_screening.csv')\n",
"print(df_autism.head())"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "367014f4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 704 entries, 0 to 703\n",
"Data columns (total 21 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 A1_Score 704 non-null int64 \n",
" 1 A2_Score 704 non-null int64 \n",
" 2 A3_Score 704 non-null int64 \n",
" 3 A4_Score 704 non-null int64 \n",
" 4 A5_Score 704 non-null int64 \n",
" 5 A6_Score 704 non-null int64 \n",
" 6 A7_Score 704 non-null int64 \n",
" 7 A8_Score 704 non-null int64 \n",
" 8 A9_Score 704 non-null int64 \n",
" 9 A10_Score 704 non-null int64 \n",
" 10 age 702 non-null float64\n",
" 11 gender 704 non-null object \n",
" 12 ethnicity 704 non-null object \n",
" 13 jundice 704 non-null object \n",
" 14 austim 704 non-null object \n",
" 15 contry_of_res 704 non-null object \n",
" 16 used_app_before 704 non-null object \n",
" 17 result 704 non-null float64\n",
" 18 age_desc 704 non-null object \n",
" 19 relation 704 non-null object \n",
" 20 Class/ASD 704 non-null object \n",
"dtypes: float64(2), int64(10), object(9)\n",
"memory usage: 115.6+ KB\n"
]
}
],
"source": [
"df_autism.info()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "67d026a5",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['A1_Score', 'A2_Score', 'A3_Score', 'A4_Score', 'A5_Score', 'A6_Score',\n",
" 'A7_Score', 'A8_Score', 'A9_Score', 'A10_Score', 'age', 'gender',\n",
" 'ethnicity', 'jundice', 'austim', 'contry_of_res', 'used_app_before',\n",
" 'result', 'age_desc', 'relation', 'Class/ASD'],\n",
" dtype='object')"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_autism.columns"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "c34f87cb",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"A1_Score 0\n",
"A2_Score 0\n",
"A3_Score 0\n",
"A4_Score 0\n",
"A5_Score 0\n",
"A6_Score 0\n",
"A7_Score 0\n",
"A8_Score 0\n",
"A9_Score 0\n",
"A10_Score 0\n",
"age 17.0\n",
"gender f\n",
"ethnicity ?\n",
"jundice no\n",
"austim no\n",
"contry_of_res Afghanistan\n",
"used_app_before no\n",
"result 0.0\n",
"age_desc 18 and more\n",
"relation ?\n",
"Class/ASD NO\n",
"dtype: object"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_autism.min()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "7346223c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"A1_Score 1\n",
"A2_Score 1\n",
"A3_Score 1\n",
"A4_Score 1\n",
"A5_Score 1\n",
"A6_Score 1\n",
"A7_Score 1\n",
"A8_Score 1\n",
"A9_Score 1\n",
"A10_Score 1\n",
"age 383.0\n",
"gender m\n",
"ethnicity others\n",
"jundice yes\n",
"austim yes\n",
"contry_of_res Viet Nam\n",
"used_app_before yes\n",
"result 10.0\n",
"age_desc 18 and more\n",
"relation Self\n",
"Class/ASD YES\n",
"dtype: object"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_autism.max()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "4c90720b",
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" A1_Score A2_Score A3_Score A4_Score A5_Score A6_Score A7_Score \\\n",
"0 1 1 1 1 0 0 1 \n",
"1 1 1 0 1 0 0 0 \n",
"2 1 1 0 1 1 0 1 \n",
"3 1 1 0 1 0 0 1 \n",
"4 1 0 0 0 0 0 0 \n",
"\n",
" A8_Score A9_Score A10_Score age gender ethnicity jundice austim \\\n",
"0 1 0 0 26.0 f White-European no no \n",
"1 1 0 1 24.0 m Latino no yes \n",
"2 1 1 1 27.0 m Latino yes yes \n",
"3 1 0 1 35.0 f White-European no yes \n",
"4 1 0 0 40.0 f ? no no \n",
"\n",
" contry_of_res used_app_before result age_desc relation Class/ASD \n",
"0 United States no 6.0 18 and more Self NO \n",
"1 Brazil no 5.0 18 and more Self NO \n",
"2 Spain no 8.0 18 and more Parent YES \n",
"3 United States no 6.0 18 and more Self NO \n",
"4 Egypt no 2.0 18 and more ? NO \n"
]
}
],
"source": [
"pd.set_option('display.max_columns', None)\n",
"pd.set_option('display.max_rows', None)\n",
"df_autism = pd.read_csv('autism_screening.csv')\n",
"df_autism = df_autism[['A1_Score', 'A2_Score', 'A3_Score', 'A4_Score', 'A5_Score', 'A6_Score', 'A7_Score', 'A8_Score', 'A9_Score', 'A10_Score', 'age', 'gender', 'ethnicity', 'jundice', 'austim', 'contry_of_res', 'used_app_before', 'result', 'age_desc', 'relation', 'Class/ASD']].copy()\n",
"print(df_autism.head())"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "0da534fb",
"metadata": {},
"outputs": [],
"source": [
"df_autism = df_autism.dropna()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "025d840c",
"metadata": {},
"outputs": [],
"source": [
"df_autism['gender'] = np.where(df_autism['gender']=='m', 1, 0)\n",
"df_autism['jundice'] = np.where(df_autism['jundice']=='yes', 1, 0)\n",
"df_autism['austim'] = np.where(df_autism['austim']=='yes', 1, 0)\n",
"df_autism['Class/ASD'] = np.where(df_autism['Class/ASD']=='YES', 1, 0)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "0f4d322a",
"metadata": {},
"outputs": [],
"source": [
"df = df_autism.drop(['ethnicity', 'contry_of_res', 'used_app_before', 'result', 'age_desc', 'relation'], axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "1f7ceaee",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" A1_Score A2_Score A3_Score A4_Score A5_Score A6_Score A7_Score \\\n",
"0 1 1 1 1 0 0 1 \n",
"1 1 1 0 1 0 0 0 \n",
"2 1 1 0 1 1 0 1 \n",
"3 1 1 0 1 0 0 1 \n",
"4 1 0 0 0 0 0 0 \n",
"\n",
" A8_Score A9_Score A10_Score age gender jundice austim Class/ASD \n",
"0 1 0 0 26.0 0 0 0 0 \n",
"1 1 0 1 24.0 1 0 1 0 \n",
"2 1 1 1 27.0 1 1 1 1 \n",
"3 1 0 1 35.0 0 0 1 0 \n",
"4 1 0 0 40.0 0 0 0 0 \n"
]
}
],
"source": [
"print(df.head())"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "56bf3c6d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"Int64Index: 702 entries, 0 to 703\n",
"Data columns (total 15 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 A1_Score 702 non-null int64 \n",
" 1 A2_Score 702 non-null int64 \n",
" 2 A3_Score 702 non-null int64 \n",
" 3 A4_Score 702 non-null int64 \n",
" 4 A5_Score 702 non-null int64 \n",
" 5 A6_Score 702 non-null int64 \n",
" 6 A7_Score 702 non-null int64 \n",
" 7 A8_Score 702 non-null int64 \n",
" 8 A9_Score 702 non-null int64 \n",
" 9 A10_Score 702 non-null int64 \n",
" 10 age 702 non-null float64\n",
" 11 gender 702 non-null int32 \n",
" 12 jundice 702 non-null int32 \n",
" 13 austim 702 non-null int32 \n",
" 14 Class/ASD 702 non-null int32 \n",
"dtypes: float64(1), int32(4), int64(10)\n",
"memory usage: 76.8 KB\n"
]
}
],
"source": [
"df.info()"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "79794484",
"metadata": {},
"outputs": [],
"source": [
"X = df.drop('Class/ASD', axis=1)\n",
"Y = df['Class/ASD']"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "d505ff04",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"RandomForestClassifier()"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"clf = RandomForestClassifier()\n",
"clf.fit(X, Y)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "f64b8440",
"metadata": {},
"outputs": [],
"source": [
"pickle.dump(clf, open('autism_clf.pkl', 'wb'))"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.12"
},
"vscode": {
"interpreter": {
"hash": "a07fda4108288eac30d110fb6c0835906d2e1f106803cd94f31ab0c859b7a7bd"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|