Commit 57ff8482acc06369382eab4063a66356e6258929
1 parent
1ba50105eb
Exists in
main
Update data_loading.ipynb
Showing 1 changed file with 29 additions and 74 deletions Side-by-side Diff
python-notebook/data_loading.ipynb
View file @
57ff848
| ... | ... | @@ -279,68 +279,36 @@ |
| 279 | 279 | }, |
| 280 | 280 | { |
| 281 | 281 | "cell_type": "code", |
| 282 | - "execution_count": 108, | |
| 282 | + "execution_count": 110, | |
| 283 | 283 | "metadata": {}, |
| 284 | 284 | "outputs": [ |
| 285 | 285 | { |
| 286 | 286 | "name": "stdout", |
| 287 | 287 | "output_type": "stream", |
| 288 | 288 | "text": [ |
| 289 | - " index user local_date hour walked\n", | |
| 290 | - "0 0 1 2015-07-22 8 2\n", | |
| 291 | - "1 3 1 2015-07-22 18 2\n", | |
| 292 | - "2 10 1 2015-07-22 19 2\n", | |
| 293 | - "3 30 1 2015-07-23 8 2\n", | |
| 294 | - "4 50 1 2015-07-23 9 2\n", | |
| 295 | - " user local_date hour walked\n", | |
| 296 | - "0 1 2015-07-22 0 1.0\n", | |
| 297 | - "1 1 2015-07-22 1 1.0\n", | |
| 298 | - "2 1 2015-07-22 2 1.0\n", | |
| 299 | - "3 1 2015-07-22 3 1.0\n", | |
| 300 | - "4 1 2015-07-22 4 1.0\n", | |
| 301 | - "5 1 2015-07-22 5 1.0\n", | |
| 302 | - "6 1 2015-07-22 6 1.0\n", | |
| 303 | - "7 1 2015-07-22 7 1.0\n", | |
| 304 | - "8 1 2015-07-22 8 2.0\n", | |
| 305 | - "9 1 2015-07-22 9 1.0\n", | |
| 306 | - "10 1 2015-07-22 10 1.0\n", | |
| 307 | - "11 1 2015-07-22 11 1.0\n", | |
| 308 | - "12 1 2015-07-22 12 1.0\n", | |
| 309 | - "13 1 2015-07-22 13 1.0\n", | |
| 310 | - "14 1 2015-07-22 14 1.0\n", | |
| 311 | - "15 1 2015-07-22 15 1.0\n", | |
| 312 | - "16 1 2015-07-22 16 1.0\n", | |
| 313 | - "17 1 2015-07-22 17 1.0\n", | |
| 314 | - "18 1 2015-07-22 18 2.0\n", | |
| 315 | - "19 1 2015-07-22 19 2.0\n", | |
| 316 | - "20 1 2015-07-22 20 1.0\n", | |
| 317 | - "21 1 2015-07-22 21 1.0\n", | |
| 318 | - "22 1 2015-07-22 22 1.0\n", | |
| 319 | - "23 1 2015-07-22 23 1.0\n", | |
| 320 | - "24 1 2015-07-23 0 1.0\n", | |
| 321 | - "25 1 2015-07-23 1 1.0\n", | |
| 322 | - "26 1 2015-07-23 2 1.0\n", | |
| 323 | - "27 1 2015-07-23 3 1.0\n", | |
| 324 | - "28 1 2015-07-23 4 1.0\n", | |
| 325 | - "29 1 2015-07-23 5 1.0\n", | |
| 326 | - "30 1 2015-07-23 6 1.0\n", | |
| 327 | - "31 1 2015-07-23 7 1.0\n", | |
| 328 | - "32 1 2015-07-23 8 2.0\n", | |
| 329 | - "33 1 2015-07-23 9 2.0\n", | |
| 330 | - "34 1 2015-07-23 10 1.0\n", | |
| 331 | - "35 1 2015-07-23 11 1.0\n", | |
| 332 | - "36 1 2015-07-23 12 1.0\n", | |
| 333 | - "37 1 2015-07-23 13 1.0\n", | |
| 334 | - "38 1 2015-07-23 14 1.0\n", | |
| 335 | - "39 1 2015-07-23 15 1.0\n", | |
| 336 | - "40 1 2015-07-23 16 1.0\n", | |
| 337 | - "41 1 2015-07-23 17 1.0\n", | |
| 338 | - "42 1 2015-07-23 18 1.0\n", | |
| 339 | - "43 1 2015-07-23 19 1.0\n", | |
| 340 | - "44 1 2015-07-23 20 1.0\n", | |
| 341 | - "45 1 2015-07-23 21 1.0\n", | |
| 342 | - "46 1 2015-07-23 22 1.0\n", | |
| 343 | - "47 1 2015-07-23 23 1.0\n" | |
| 289 | + " index user local_date threehour walked\n", | |
| 290 | + "0 0 1 2015-07-22 2 2\n", | |
| 291 | + "1 3 1 2015-07-22 6 2\n", | |
| 292 | + "2 30 1 2015-07-23 2 2\n", | |
| 293 | + "3 50 1 2015-07-23 3 2\n", | |
| 294 | + "4 58 1 2015-07-23 5 2\n", | |
| 295 | + " user local_date threehour walked\n", | |
| 296 | + "0 1 2015-07-22 0 1.0\n", | |
| 297 | + "1 1 2015-07-22 1 1.0\n", | |
| 298 | + "2 1 2015-07-22 2 2.0\n", | |
| 299 | + "3 1 2015-07-22 3 1.0\n", | |
| 300 | + "4 1 2015-07-22 4 1.0\n", | |
| 301 | + "5 1 2015-07-22 5 1.0\n", | |
| 302 | + "6 1 2015-07-22 6 2.0\n", | |
| 303 | + "7 1 2015-07-22 7 1.0\n", | |
| 304 | + "8 1 2015-07-23 0 1.0\n", | |
| 305 | + "9 1 2015-07-23 1 1.0\n", | |
| 306 | + "10 1 2015-07-23 2 2.0\n", | |
| 307 | + "11 1 2015-07-23 3 2.0\n", | |
| 308 | + "12 1 2015-07-23 4 1.0\n", | |
| 309 | + "13 1 2015-07-23 5 2.0\n", | |
| 310 | + "14 1 2015-07-23 6 1.0\n", | |
| 311 | + "15 1 2015-07-23 7 1.0\n" | |
| 344 | 312 | ] |
| 345 | 313 | } |
| 346 | 314 | ], |
| 347 | 315 | |
| ... | ... | @@ -381,28 +349,15 @@ |
| 381 | 349 | "measured_hour = product_df(walk_by_hours[[\"user\", \"local_date\"]], hours[[\"hour\"]])\n", |
| 382 | 350 | "measured_threehour = product_df(walk_by_threehours[[\"user\", \"local_date\"]], threehours[[\"threehour\"]])\n", |
| 383 | 351 | "\n", |
| 384 | - "\n", | |
| 385 | - "\n", | |
| 386 | - "print(walk_by_threehours)\n", | |
| 387 | - "\n", | |
| 352 | + "# pad the hourly walk data (fill in missing hours with 1s)\n", | |
| 388 | 353 | "padded_hours = walk_by_hours.merge(measured_hour, on=[\"user\", \"local_date\", \"hour\"], how=\"right\")\n", |
| 389 | 354 | "padded_hours = padded_hours[[\"user\", \"local_date\", \"hour\", \"walked\"]]\n", |
| 390 | 355 | "padded_hours = padded_hours.fillna(1)\n", |
| 391 | 356 | "\n", |
| 392 | - "padded_threehours = walk_by_threehours.merge(measured_threehour, on=[\"user\", \"local_date\", \"hour\"], how=\"right\")\n", | |
| 393 | - "padded_threehours = padded_threehours[[\"user\", \"local_date\", \"hour\", \"walked\"]]\n", | |
| 394 | - "padded_threehours = padded_threehours.fillna(1)\n", | |
| 395 | - "\n", | |
| 396 | - "print(padded_threehours)\n", | |
| 397 | - "\n", | |
| 398 | - "# walk_by_hour = consecutive_minutes.groupby([\"user\", \"local_date\", \"hour\"])[\"add_count\"].sum().reset_index()\n", | |
| 399 | - "# walk_by_threehour = consecutive_minutes.groupby([\"user\", \"local_date\", \"threehour\"])[\"add_count\"].sum().reset_index()\n", | |
| 400 | - "\n", | |
| 401 | - "# walk_by_hour[\"walked\"] = 1\n", | |
| 402 | - "# walk_by_threehour[\"walked\"] = 1\n", | |
| 403 | - "\n", | |
| 404 | - "\n", | |
| 405 | - "# hours2 = walk_by_hour.merge(hours, left_on=\"hour\", right_on=\"hour\", how=\"right\")\n" | |
| 357 | + "# pad the walk data with 3 hours unit (fill in missing hours with 1s)\n", | |
| 358 | + "padded_threehours = walk_by_threehours.merge(measured_threehour, on=[\"user\", \"local_date\", \"threehour\"], how=\"right\")\n", | |
| 359 | + "padded_threehours = padded_threehours[[\"user\", \"local_date\", \"threehour\", \"walked\"]]\n", | |
| 360 | + "padded_threehours = padded_threehours.fillna(1)" | |
| 406 | 361 | ] |
| 407 | 362 | }, |
| 408 | 363 | { |