Datasets
Models
Downloads: 1
Diff of
/analysis/data_analysis.ipynb
[000000]
..
[3f1788]
Switch to unified view
| a | b/analysis/data_analysis.ipynb | ||
|---|---|---|---|
| 1 | { |
||
| 2 | "cells": [ |
||
| 3 | { |
||
| 4 | "cell_type": "markdown", |
||
| 5 | "metadata": {}, |
||
| 6 | "source": [ |
||
| 7 | "# Dataset Preparation for Prediction of Imminent ICU Admission and Prolonged Stay" |
||
| 8 | ] |
||
| 9 | }, |
||
| 10 | { |
||
| 11 | "cell_type": "markdown", |
||
| 12 | "metadata": {}, |
||
| 13 | "source": [ |
||
| 14 | "## Imports & Inits" |
||
| 15 | ] |
||
| 16 | }, |
||
| 17 | { |
||
| 18 | "cell_type": "code", |
||
| 19 | "execution_count": 4, |
||
| 20 | "metadata": { |
||
| 21 | "ExecuteTime": { |
||
| 22 | "end_time": "2019-08-26T18:54:33.858025Z", |
||
| 23 | "start_time": "2019-08-26T18:54:33.683791Z" |
||
| 24 | } |
||
| 25 | }, |
||
| 26 | "outputs": [ |
||
| 27 | { |
||
| 28 | "name": "stdout", |
||
| 29 | "output_type": "stream", |
||
| 30 | "text": [ |
||
| 31 | "The autoreload extension is already loaded. To reload it, use:\n", |
||
| 32 | " %reload_ext autoreload\n" |
||
| 33 | ] |
||
| 34 | } |
||
| 35 | ], |
||
| 36 | "source": [ |
||
| 37 | "%load_ext autoreload\n", |
||
| 38 | "%autoreload 2" |
||
| 39 | ] |
||
| 40 | }, |
||
| 41 | { |
||
| 42 | "cell_type": "code", |
||
| 43 | "execution_count": 5, |
||
| 44 | "metadata": { |
||
| 45 | "ExecuteTime": { |
||
| 46 | "end_time": "2019-08-26T18:54:33.919510Z", |
||
| 47 | "start_time": "2019-08-26T18:54:33.887213Z" |
||
| 48 | } |
||
| 49 | }, |
||
| 50 | "outputs": [ |
||
| 51 | { |
||
| 52 | "data": { |
||
| 53 | "text/plain": [ |
||
| 54 | "{'workdir': PosixPath('../data/workdir'),\n", |
||
| 55 | " 'figdir': PosixPath('../data/results/figures'),\n", |
||
| 56 | " 'resultdir': PosixPath('../data/results'),\n", |
||
| 57 | " 'dataset_csv': PosixPath('../data/proc_dataset.csv'),\n", |
||
| 58 | " 'imminent_adm_cols': ['hadm_id', 'processed_note', 'imminent_adm_label'],\n", |
||
| 59 | " 'prolonged_stay_cols': ['hadm_id', 'processed_note', 'prolonged_stay_label'],\n", |
||
| 60 | " 'cols': ['hadm_id',\n", |
||
| 61 | " 'imminent_adm_label',\n", |
||
| 62 | " 'prolonged_stay_label',\n", |
||
| 63 | " 'processed_note',\n", |
||
| 64 | " 'charttime',\n", |
||
| 65 | " 'intime',\n", |
||
| 66 | " 'chartinterval'],\n", |
||
| 67 | " 'dates': ['charttime', 'intime'],\n", |
||
| 68 | " 'ia_thresh': {'lr': 0.45, 'rf': 0.27, 'gbm': 0.435, 'mlp': 0.2},\n", |
||
| 69 | " 'ps_thresh': {'lr': 0.39, 'rf': 0.36, 'gbm': 0.324, 'mlp': 0.27}}" |
||
| 70 | ] |
||
| 71 | }, |
||
| 72 | "execution_count": 5, |
||
| 73 | "metadata": {}, |
||
| 74 | "output_type": "execute_result" |
||
| 75 | } |
||
| 76 | ], |
||
| 77 | "source": [ |
||
| 78 | "import sys\n", |
||
| 79 | "sys.path.append('../')\n", |
||
| 80 | "\n", |
||
| 81 | "import math\n", |
||
| 82 | "import numpy as np\n", |
||
| 83 | "import pandas as pd\n", |
||
| 84 | "import spacy\n", |
||
| 85 | "\n", |
||
| 86 | "import seaborn as sns\n", |
||
| 87 | "sns.set(style = 'darkgrid')\n", |
||
| 88 | "\n", |
||
| 89 | "import matplotlib.pyplot as plt\n", |
||
| 90 | "%matplotlib inline\n", |
||
| 91 | "\n", |
||
| 92 | "from scipy import stats\n", |
||
| 93 | "from pathlib import Path\n", |
||
| 94 | "\n", |
||
| 95 | "from utils.splits import set_group_splits\n", |
||
| 96 | "from args import args\n", |
||
| 97 | "vars(args)" |
||
| 98 | ] |
||
| 99 | }, |
||
| 100 | { |
||
| 101 | "cell_type": "markdown", |
||
| 102 | "metadata": { |
||
| 103 | "heading_collapsed": true |
||
| 104 | }, |
||
| 105 | "source": [ |
||
| 106 | "## Stats" |
||
| 107 | ] |
||
| 108 | }, |
||
| 109 | { |
||
| 110 | "cell_type": "code", |
||
| 111 | "execution_count": null, |
||
| 112 | "metadata": { |
||
| 113 | "ExecuteTime": { |
||
| 114 | "end_time": "2019-07-17T18:48:22.330446Z", |
||
| 115 | "start_time": "2019-07-17T18:48:17.056668Z" |
||
| 116 | }, |
||
| 117 | "hidden": true |
||
| 118 | }, |
||
| 119 | "outputs": [], |
||
| 120 | "source": [ |
||
| 121 | "df = pd.read_csv(args.dataset_csv)\n", |
||
| 122 | "ia_df = df.loc[(df['imminent_adm_label'] != -1)][args.imminent_adm_cols].reset_index(drop=True)\n", |
||
| 123 | "ps_df = ori_df.loc[(ori_df['chartinterval'] != 0)][args.prolonged_stay_cols].reset_index(drop=True)" |
||
| 124 | ] |
||
| 125 | }, |
||
| 126 | { |
||
| 127 | "cell_type": "code", |
||
| 128 | "execution_count": null, |
||
| 129 | "metadata": { |
||
| 130 | "ExecuteTime": { |
||
| 131 | "end_time": "2019-07-17T18:48:22.402048Z", |
||
| 132 | "start_time": "2019-07-17T18:48:22.333813Z" |
||
| 133 | }, |
||
| 134 | "hidden": true |
||
| 135 | }, |
||
| 136 | "outputs": [], |
||
| 137 | "source": [ |
||
| 138 | "df['subject_id'].nunique(), df['hadm_id'].nunique()" |
||
| 139 | ] |
||
| 140 | }, |
||
| 141 | { |
||
| 142 | "cell_type": "code", |
||
| 143 | "execution_count": null, |
||
| 144 | "metadata": { |
||
| 145 | "ExecuteTime": { |
||
| 146 | "end_time": "2019-07-17T18:48:29.519915Z", |
||
| 147 | "start_time": "2019-07-17T18:48:29.443575Z" |
||
| 148 | }, |
||
| 149 | "hidden": true |
||
| 150 | }, |
||
| 151 | "outputs": [], |
||
| 152 | "source": [ |
||
| 153 | "ages = df.groupby(['subject_id'])[['admission_age']].first().to_numpy().reshape(-1)\n", |
||
| 154 | "ages[ages>100] = 100\n", |
||
| 155 | "print(f\"Median age: {ages.mean():0.1f}\")\n", |
||
| 156 | "print(f\"IQR: {np.percentile(ages, 25):0.1f} - {np.percentile(ages, 75):0.1f}\")" |
||
| 157 | ] |
||
| 158 | }, |
||
| 159 | { |
||
| 160 | "cell_type": "code", |
||
| 161 | "execution_count": null, |
||
| 162 | "metadata": { |
||
| 163 | "ExecuteTime": { |
||
| 164 | "end_time": "2019-07-17T18:48:53.210075Z", |
||
| 165 | "start_time": "2019-07-17T18:48:53.002656Z" |
||
| 166 | }, |
||
| 167 | "hidden": true |
||
| 168 | }, |
||
| 169 | "outputs": [], |
||
| 170 | "source": [ |
||
| 171 | "df['adm_to_icu_period'].describe().reset_index()" |
||
| 172 | ] |
||
| 173 | }, |
||
| 174 | { |
||
| 175 | "cell_type": "code", |
||
| 176 | "execution_count": null, |
||
| 177 | "metadata": { |
||
| 178 | "ExecuteTime": { |
||
| 179 | "end_time": "2019-07-17T18:49:21.918238Z", |
||
| 180 | "start_time": "2019-07-17T18:49:21.653850Z" |
||
| 181 | }, |
||
| 182 | "hidden": true |
||
| 183 | }, |
||
| 184 | "outputs": [], |
||
| 185 | "source": [ |
||
| 186 | "df.groupby(df['admission_type'])['hadm_id'].nunique().reset_index()" |
||
| 187 | ] |
||
| 188 | }, |
||
| 189 | { |
||
| 190 | "cell_type": "code", |
||
| 191 | "execution_count": null, |
||
| 192 | "metadata": { |
||
| 193 | "ExecuteTime": { |
||
| 194 | "end_time": "2019-07-17T18:49:22.411510Z", |
||
| 195 | "start_time": "2019-07-17T18:49:22.249868Z" |
||
| 196 | }, |
||
| 197 | "hidden": true |
||
| 198 | }, |
||
| 199 | "outputs": [], |
||
| 200 | "source": [ |
||
| 201 | "df.groupby(df['ethnicity'])['subject_id'].nunique().reset_index()" |
||
| 202 | ] |
||
| 203 | }, |
||
| 204 | { |
||
| 205 | "cell_type": "markdown", |
||
| 206 | "metadata": { |
||
| 207 | "hidden": true |
||
| 208 | }, |
||
| 209 | "source": [ |
||
| 210 | "Make sure average prevalence of random test sets is approximately same as real prevalence" |
||
| 211 | ] |
||
| 212 | }, |
||
| 213 | { |
||
| 214 | "cell_type": "code", |
||
| 215 | "execution_count": null, |
||
| 216 | "metadata": { |
||
| 217 | "ExecuteTime": { |
||
| 218 | "end_time": "2019-07-17T18:27:25.090684Z", |
||
| 219 | "start_time": "2019-07-17T18:27:05.095345Z" |
||
| 220 | }, |
||
| 221 | "hidden": true |
||
| 222 | }, |
||
| 223 | "outputs": [], |
||
| 224 | "source": [ |
||
| 225 | "ia_p = []\n", |
||
| 226 | "ps_p = []\n", |
||
| 227 | "\n", |
||
| 228 | "for seed in range(127, 227):\n", |
||
| 229 | " sdf = set_group_splits(ia_df.copy(), group_col='hadm_id', seed=seed)\n", |
||
| 230 | " test_size = len(sdf.loc[(sdf['split'] == 'test')])\n", |
||
| 231 | " test_pos = len(sdf.loc[(sdf['split'] == 'test') & (sdf['imminent_adm_label'] == 1)])\n", |
||
| 232 | " ia_p.append(test_pos/test_size) \n", |
||
| 233 | " \n", |
||
| 234 | " sdf = set_group_splits(ps_df.copy(), group_col='hadm_id', seed=seed)\n", |
||
| 235 | " test_size = len(sdf.loc[(sdf['split'] == 'test')])\n", |
||
| 236 | " test_pos = len(sdf.loc[(sdf['split'] == 'test') & (sdf['prolonged_stay_label'] == 1)])\n", |
||
| 237 | " ps_p.append(test_pos/test_size) \n", |
||
| 238 | " \n", |
||
| 239 | "\n", |
||
| 240 | "ia_p = np.array(ia_p)\n", |
||
| 241 | "ps_p = np.array(ps_p)\n", |
||
| 242 | "\n", |
||
| 243 | "print(f\"Prevalence of Imminent Admission: {(len(ia_df.loc[ia_df['imminent_adm_label'] == 1])/len(ia_df)):0.3f}\")\n", |
||
| 244 | "print(f\"Average of test set = {(ia_p.mean()):0.3f}, std = {(ia_p.std()):0.3f}\")\n", |
||
| 245 | "print(f\"Prevalence of Prolonged Stay: {(len(ps_df.loc[ps_df['prolonged_stay_label'] == 1])/len(ps_df)):0.3f}\")\n", |
||
| 246 | "print(f\"Average of test set = {(ps_p.mean()):0.3f}, std = {(ps_p.std()):0.3f}\")" |
||
| 247 | ] |
||
| 248 | }, |
||
| 249 | { |
||
| 250 | "cell_type": "code", |
||
| 251 | "execution_count": null, |
||
| 252 | "metadata": { |
||
| 253 | "ExecuteTime": { |
||
| 254 | "end_time": "2019-07-17T18:49:26.743454Z", |
||
| 255 | "start_time": "2019-07-17T18:49:26.652037Z" |
||
| 256 | }, |
||
| 257 | "hidden": true |
||
| 258 | }, |
||
| 259 | "outputs": [], |
||
| 260 | "source": [ |
||
| 261 | "print(f\"Average number of notes per admission for imminent admission: {ia_df.groupby('hadm_id').size().mean():0.2f}\")\n", |
||
| 262 | "print(f\"Average number of notes per admission for prolonged stay (and entire dataset): {ps_df.groupby('hadm_id').size().mean():0.2f}\")" |
||
| 263 | ] |
||
| 264 | }, |
||
| 265 | { |
||
| 266 | "cell_type": "code", |
||
| 267 | "execution_count": null, |
||
| 268 | "metadata": { |
||
| 269 | "ExecuteTime": { |
||
| 270 | "end_time": "2019-07-17T18:49:48.377622Z", |
||
| 271 | "start_time": "2019-07-17T18:49:48.020027Z" |
||
| 272 | }, |
||
| 273 | "hidden": true |
||
| 274 | }, |
||
| 275 | "outputs": [], |
||
| 276 | "source": [ |
||
| 277 | "df.groupby(df['deathtime'].apply(lambda x: True if pd.notnull(x) else False))['subject_id'].nunique().reset_index()" |
||
| 278 | ] |
||
| 279 | }, |
||
| 280 | { |
||
| 281 | "cell_type": "code", |
||
| 282 | "execution_count": null, |
||
| 283 | "metadata": { |
||
| 284 | "ExecuteTime": { |
||
| 285 | "end_time": "2019-07-17T18:49:49.030699Z", |
||
| 286 | "start_time": "2019-07-17T18:49:48.901279Z" |
||
| 287 | }, |
||
| 288 | "hidden": true |
||
| 289 | }, |
||
| 290 | "outputs": [], |
||
| 291 | "source": [ |
||
| 292 | "df.groupby(df['gender'])['subject_id'].nunique().reset_index()" |
||
| 293 | ] |
||
| 294 | }, |
||
| 295 | { |
||
| 296 | "cell_type": "markdown", |
||
| 297 | "metadata": { |
||
| 298 | "hidden": true |
||
| 299 | }, |
||
| 300 | "source": [ |
||
| 301 | "Distribution of notes by category" |
||
| 302 | ] |
||
| 303 | }, |
||
| 304 | { |
||
| 305 | "cell_type": "code", |
||
| 306 | "execution_count": null, |
||
| 307 | "metadata": { |
||
| 308 | "ExecuteTime": { |
||
| 309 | "end_time": "2019-07-17T18:49:51.015549Z", |
||
| 310 | "start_time": "2019-07-17T18:49:50.883550Z" |
||
| 311 | }, |
||
| 312 | "hidden": true |
||
| 313 | }, |
||
| 314 | "outputs": [], |
||
| 315 | "source": [ |
||
| 316 | "df.groupby(df['category']).size().reset_index()" |
||
| 317 | ] |
||
| 318 | }, |
||
| 319 | { |
||
| 320 | "cell_type": "markdown", |
||
| 321 | "metadata": { |
||
| 322 | "hidden": true |
||
| 323 | }, |
||
| 324 | "source": [ |
||
| 325 | "Distribution of notes by category for imminent admissions and delayed admissions" |
||
| 326 | ] |
||
| 327 | }, |
||
| 328 | { |
||
| 329 | "cell_type": "code", |
||
| 330 | "execution_count": null, |
||
| 331 | "metadata": { |
||
| 332 | "ExecuteTime": { |
||
| 333 | "end_time": "2019-07-17T18:40:35.638983Z", |
||
| 334 | "start_time": "2019-07-17T18:40:35.428118Z" |
||
| 335 | }, |
||
| 336 | "hidden": true |
||
| 337 | }, |
||
| 338 | "outputs": [], |
||
| 339 | "source": [ |
||
| 340 | "df.loc[(df['imminent_adm_label'] == 1)].groupby('category').size().reset_index()" |
||
| 341 | ] |
||
| 342 | }, |
||
| 343 | { |
||
| 344 | "cell_type": "code", |
||
| 345 | "execution_count": null, |
||
| 346 | "metadata": { |
||
| 347 | "ExecuteTime": { |
||
| 348 | "end_time": "2019-07-17T18:42:29.970948Z", |
||
| 349 | "start_time": "2019-07-17T18:42:29.704004Z" |
||
| 350 | }, |
||
| 351 | "hidden": true |
||
| 352 | }, |
||
| 353 | "outputs": [], |
||
| 354 | "source": [ |
||
| 355 | "df.loc[(df['imminent_adm_label'] == 0)].groupby('category').size().reset_index()" |
||
| 356 | ] |
||
| 357 | }, |
||
| 358 | { |
||
| 359 | "cell_type": "markdown", |
||
| 360 | "metadata": { |
||
| 361 | "hidden": true |
||
| 362 | }, |
||
| 363 | "source": [ |
||
| 364 | "Distribution of notes for prolonged stay and short stay" |
||
| 365 | ] |
||
| 366 | }, |
||
| 367 | { |
||
| 368 | "cell_type": "code", |
||
| 369 | "execution_count": null, |
||
| 370 | "metadata": { |
||
| 371 | "ExecuteTime": { |
||
| 372 | "end_time": "2019-07-17T18:42:30.199045Z", |
||
| 373 | "start_time": "2019-07-17T18:42:29.974531Z" |
||
| 374 | }, |
||
| 375 | "hidden": true |
||
| 376 | }, |
||
| 377 | "outputs": [], |
||
| 378 | "source": [ |
||
| 379 | "df.loc[(df['prolonged_stay_label'] == 1)].groupby('category').size().reset_index()" |
||
| 380 | ] |
||
| 381 | }, |
||
| 382 | { |
||
| 383 | "cell_type": "code", |
||
| 384 | "execution_count": null, |
||
| 385 | "metadata": { |
||
| 386 | "ExecuteTime": { |
||
| 387 | "end_time": "2019-07-17T18:42:30.334632Z", |
||
| 388 | "start_time": "2019-07-17T18:42:30.202847Z" |
||
| 389 | }, |
||
| 390 | "hidden": true |
||
| 391 | }, |
||
| 392 | "outputs": [], |
||
| 393 | "source": [ |
||
| 394 | "df.loc[(df['prolonged_stay_label'] == 0)].groupby('category').size().reset_index()" |
||
| 395 | ] |
||
| 396 | }, |
||
| 397 | { |
||
| 398 | "cell_type": "code", |
||
| 399 | "execution_count": null, |
||
| 400 | "metadata": { |
||
| 401 | "ExecuteTime": { |
||
| 402 | "end_time": "2019-07-17T18:49:58.769470Z", |
||
| 403 | "start_time": "2019-07-17T18:49:58.658678Z" |
||
| 404 | }, |
||
| 405 | "hidden": true |
||
| 406 | }, |
||
| 407 | "outputs": [], |
||
| 408 | "source": [ |
||
| 409 | "df['icu_los'].describe().reset_index()" |
||
| 410 | ] |
||
| 411 | }, |
||
| 412 | { |
||
| 413 | "cell_type": "code", |
||
| 414 | "execution_count": null, |
||
| 415 | "metadata": { |
||
| 416 | "ExecuteTime": { |
||
| 417 | "end_time": "2019-07-17T18:52:01.571726Z", |
||
| 418 | "start_time": "2019-07-17T18:52:01.262084Z" |
||
| 419 | }, |
||
| 420 | "hidden": true |
||
| 421 | }, |
||
| 422 | "outputs": [], |
||
| 423 | "source": [ |
||
| 424 | "df['note'].apply(len).describe().reset_index()" |
||
| 425 | ] |
||
| 426 | }, |
||
| 427 | { |
||
| 428 | "cell_type": "code", |
||
| 429 | "execution_count": null, |
||
| 430 | "metadata": { |
||
| 431 | "ExecuteTime": { |
||
| 432 | "end_time": "2019-07-17T18:42:23.454748Z", |
||
| 433 | "start_time": "2019-07-17T18:42:23.043855Z" |
||
| 434 | }, |
||
| 435 | "hidden": true |
||
| 436 | }, |
||
| 437 | "outputs": [], |
||
| 438 | "source": [ |
||
| 439 | "df['charttime_to_icu_period'].describe().reset_index()" |
||
| 440 | ] |
||
| 441 | }, |
||
| 442 | { |
||
| 443 | "cell_type": "markdown", |
||
| 444 | "metadata": {}, |
||
| 445 | "source": [ |
||
| 446 | "## Plots" |
||
| 447 | ] |
||
| 448 | }, |
||
| 449 | { |
||
| 450 | "cell_type": "code", |
||
| 451 | "execution_count": 7, |
||
| 452 | "metadata": { |
||
| 453 | "ExecuteTime": { |
||
| 454 | "end_time": "2019-08-26T18:54:53.518650Z", |
||
| 455 | "start_time": "2019-08-26T18:54:50.602313Z" |
||
| 456 | } |
||
| 457 | }, |
||
| 458 | "outputs": [ |
||
| 459 | { |
||
| 460 | "data": { |
||
| 461 | "text/plain": [ |
||
| 462 | "Index(['subject_id', 'hadm_id', 'icustay_id', 'admission_type', 'admittime',\n", |
||
| 463 | " 'dischtime', 'intime', 'outtime', 'charttime', 'icu_los', 'deathtime',\n", |
||
| 464 | " 'adm_to_icu_period', 'charttime_to_icu_period', 'chartinterval',\n", |
||
| 465 | " 'ethnicity', 'dob', 'gender', 'admission_age', 'category',\n", |
||
| 466 | " 'imminent_adm_label', 'prolonged_stay_label', 'note', 'processed_note'],\n", |
||
| 467 | " dtype='object')" |
||
| 468 | ] |
||
| 469 | }, |
||
| 470 | "execution_count": 7, |
||
| 471 | "metadata": {}, |
||
| 472 | "output_type": "execute_result" |
||
| 473 | } |
||
| 474 | ], |
||
| 475 | "source": [ |
||
| 476 | "df = pd.read_csv(args.dataset_csv)\n", |
||
| 477 | "df.columns" |
||
| 478 | ] |
||
| 479 | }, |
||
| 480 | { |
||
| 481 | "cell_type": "code", |
||
| 482 | "execution_count": 11, |
||
| 483 | "metadata": { |
||
| 484 | "ExecuteTime": { |
||
| 485 | "end_time": "2019-08-26T18:56:35.688519Z", |
||
| 486 | "start_time": "2019-08-26T18:56:35.448942Z" |
||
| 487 | } |
||
| 488 | }, |
||
| 489 | "outputs": [ |
||
| 490 | { |
||
| 491 | "name": "stdout", |
||
| 492 | "output_type": "stream", |
||
| 493 | "text": [ |
||
| 494 | "Radiology\n", |
||
| 495 | "VEN DUP EXTEXT BIL (MAP/DVT)\n", |
||
| 496 | "[**2162-5-17**] 8:12 AM\n", |
||
| 497 | " [**Last Name (un) 1296**] DUP EXTEXT BIL (MAP/DVT) Clip # [**Clip Number (Radiology) 18833**]\n", |
||
| 498 | " Reason: eval for vein harvesting*****OR second case on [**2162-5-17**]******\n", |
||
| 499 | " Admitting Diagnosis: CORONARY ARTERY DISEASE\n", |
||
| 500 | " ______________________________________________________________________________\n", |
||
| 501 | " [**Hospital 2**] MEDICAL CONDITION:\n", |
||
| 502 | " 60 year old man pre-op for CABG\n", |
||
| 503 | " REASON FOR THIS EXAMINATION:\n", |
||
| 504 | " eval for vein harvesting*****OR second case on [**2162-5-17**]********\n", |
||
| 505 | " ______________________________________________________________________________\n", |
||
| 506 | " FINAL REPORT\n", |
||
| 507 | " HISTORY: A 60-year-old gentleman, preop for CABG. Search for conduit.\n", |
||
| 508 | "\n", |
||
| 509 | " TECHNIQUE: Venous mapping of the superficial veins in the lower extremities\n", |
||
| 510 | " was performed with [**Doctor Last Name 37**]-scale and Doppler ultrasound.\n", |
||
| 511 | "\n", |
||
| 512 | " FINDINGS: Right great saphenous vein is patent and compressible with\n", |
||
| 513 | " diameters ranging between 0.15 and 0.21 cm. The right small saphenous vein is\n", |
||
| 514 | " patent and compressible with diameters ranging between 0.14 and 0.20 cm.\n", |
||
| 515 | "\n", |
||
| 516 | " The left great saphenous vein presented with diameters ranging between 0.06\n", |
||
| 517 | " and 0.49 cm. It was not visualized below the calf. The left small saphenous\n", |
||
| 518 | " vein presented thick walled and calcified.\n", |
||
| 519 | "\n", |
||
| 520 | " COMPARISON: None available.\n", |
||
| 521 | "\n", |
||
| 522 | " IMPRESSION: Patent right great and small saphenous veins, with diameters\n", |
||
| 523 | " described above. Left great saphenous vein with small diameters below the mid\n", |
||
| 524 | " thigh and not visualized below the calf. The left small saphenous vein\n", |
||
| 525 | " presented with thick walls and calcifications.\n", |
||
| 526 | "\n", |
||
| 527 | "\n", |
||
| 528 | "\n" |
||
| 529 | ] |
||
| 530 | } |
||
| 531 | ], |
||
| 532 | "source": [ |
||
| 533 | "print(df.iloc[0]['note'])" |
||
| 534 | ] |
||
| 535 | }, |
||
| 536 | { |
||
| 537 | "cell_type": "code", |
||
| 538 | "execution_count": 12, |
||
| 539 | "metadata": { |
||
| 540 | "ExecuteTime": { |
||
| 541 | "end_time": "2019-08-26T18:56:41.114437Z", |
||
| 542 | "start_time": "2019-08-26T18:56:41.086224Z" |
||
| 543 | } |
||
| 544 | }, |
||
| 545 | "outputs": [ |
||
| 546 | { |
||
| 547 | "name": "stdout", |
||
| 548 | "output_type": "stream", |
||
| 549 | "text": [ |
||
| 550 | "Radiology \n", |
||
| 551 | " VEN DUP EXTEXT BIL ( MAP/DVT ) \n", |
||
| 552 | " [ * * 2162 - 5 - 17 * * ] 8:12 AM \n", |
||
| 553 | " [ * * Last Name ( un ) 1296 * * ] DUP EXTEXT BIL ( MAP/DVT ) Clip # [ * * Clip Number ( Radiology ) 18833 * * ] \n", |
||
| 554 | " Reason : eval for vein harvesting*****OR second case on [ * * 2162 - 5 - 17 * * ] * * * * * * \n", |
||
| 555 | " Admitting Diagnosis : CORONARY ARTERY DISEASE \n", |
||
| 556 | " _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ \n", |
||
| 557 | " [ * * Hospital 2 * * ] MEDICAL CONDITION : \n", |
||
| 558 | " 60 year old man pre-op for CABG \n", |
||
| 559 | " REASON FOR THIS EXAMINATION : \n", |
||
| 560 | " eval for vein harvesting*****OR second case on [ * * 2162 - 5 - 17 * * ] * * * * * * * * \n", |
||
| 561 | " _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ \n", |
||
| 562 | " FINAL REPORT \n", |
||
| 563 | " HISTORY : A 60-year-old gentleman , preop for CABG . Search for conduit . \n", |
||
| 564 | "\n", |
||
| 565 | " TECHNIQUE : Venous mapping of the superficial veins in the lower extremities \n", |
||
| 566 | " was performed with [ * * Doctor Last Name 37**]-scale and Doppler ultrasound . \n", |
||
| 567 | "\n", |
||
| 568 | " FINDINGS : Right great saphenous vein is patent and compressible with \n", |
||
| 569 | " diameters ranging between 0.15 and 0.21 cm . The right small saphenous vein is \n", |
||
| 570 | " patent and compressible with diameters ranging between 0.14 and 0.20 cm . \n", |
||
| 571 | "\n", |
||
| 572 | " The left great saphenous vein presented with diameters ranging between 0.06 \n", |
||
| 573 | " and 0.49 cm . It was not visualized below the calf . The left small saphenous \n", |
||
| 574 | " vein presented thick walled and calcified . \n", |
||
| 575 | "\n", |
||
| 576 | " COMPARISON : None available . \n", |
||
| 577 | "\n", |
||
| 578 | " IMPRESSION : Patent right great and small saphenous veins , with diameters \n", |
||
| 579 | " described above . Left great saphenous vein with small diameters below the mid \n", |
||
| 580 | " thigh and not visualized below the calf . The left small saphenous vein \n", |
||
| 581 | " presented with thick walls and calcifications . \n", |
||
| 582 | "\n", |
||
| 583 | "\n", |
||
| 584 | "\n" |
||
| 585 | ] |
||
| 586 | } |
||
| 587 | ], |
||
| 588 | "source": [ |
||
| 589 | "print(df.iloc[0]['processed_note'])" |
||
| 590 | ] |
||
| 591 | }, |
||
| 592 | { |
||
| 593 | "cell_type": "code", |
||
| 594 | "execution_count": null, |
||
| 595 | "metadata": {}, |
||
| 596 | "outputs": [], |
||
| 597 | "source": [] |
||
| 598 | }, |
||
| 599 | { |
||
| 600 | "cell_type": "code", |
||
| 601 | "execution_count": null, |
||
| 602 | "metadata": { |
||
| 603 | "ExecuteTime": { |
||
| 604 | "end_time": "2019-07-17T18:42:36.032162Z", |
||
| 605 | "start_time": "2019-07-17T18:42:36.008573Z" |
||
| 606 | } |
||
| 607 | }, |
||
| 608 | "outputs": [], |
||
| 609 | "source": [ |
||
| 610 | "intervals = ['-1 ≤ t ≤ 0']\n", |
||
| 611 | "intervals += [f'-{i+1} ≤ t ≤ -{i}' for i in range(1, 15)]\n", |
||
| 612 | "intervals.append('t ≤ -15')" |
||
| 613 | ] |
||
| 614 | }, |
||
| 615 | { |
||
| 616 | "cell_type": "markdown", |
||
| 617 | "metadata": {}, |
||
| 618 | "source": [ |
||
| 619 | "### Bar Plot of Notes Over Days" |
||
| 620 | ] |
||
| 621 | }, |
||
| 622 | { |
||
| 623 | "cell_type": "markdown", |
||
| 624 | "metadata": {}, |
||
| 625 | "source": [ |
||
| 626 | "#### All Notes" |
||
| 627 | ] |
||
| 628 | }, |
||
| 629 | { |
||
| 630 | "cell_type": "code", |
||
| 631 | "execution_count": null, |
||
| 632 | "metadata": { |
||
| 633 | "ExecuteTime": { |
||
| 634 | "end_time": "2019-07-17T18:42:38.585605Z", |
||
| 635 | "start_time": "2019-07-17T18:42:38.475792Z" |
||
| 636 | } |
||
| 637 | }, |
||
| 638 | "outputs": [], |
||
| 639 | "source": [ |
||
| 640 | "plot_df = pd.DataFrame(df.groupby(['chartinterval']).size(), columns=['n_notes'])\n", |
||
| 641 | "plot_df.reset_index(inplace=True, drop=True)\n", |
||
| 642 | "plot_df['days'] = intervals" |
||
| 643 | ] |
||
| 644 | }, |
||
| 645 | { |
||
| 646 | "cell_type": "code", |
||
| 647 | "execution_count": null, |
||
| 648 | "metadata": { |
||
| 649 | "ExecuteTime": { |
||
| 650 | "end_time": "2019-07-17T18:42:41.669474Z", |
||
| 651 | "start_time": "2019-07-17T18:42:40.376671Z" |
||
| 652 | } |
||
| 653 | }, |
||
| 654 | "outputs": [], |
||
| 655 | "source": [ |
||
| 656 | "fig, ax = plt.subplots(figsize=(15, 8))\n", |
||
| 657 | "sns.barplot(x='days', y='n_notes', data=plot_df, ax=ax)\n", |
||
| 658 | "ax.set_xticklabels(ax.get_xticklabels(),rotation=45, ha='right')\n", |
||
| 659 | "ax.set_xlabel('Time to ICU Admission (days)')\n", |
||
| 660 | "ax.set_ylabel('# notes')\n", |
||
| 661 | "for index, row in plot_df.iterrows():\n", |
||
| 662 | " ax.text(index, row['n_notes'], str(row['n_notes']), color='black', ha='center', va='bottom')" |
||
| 663 | ] |
||
| 664 | }, |
||
| 665 | { |
||
| 666 | "cell_type": "code", |
||
| 667 | "execution_count": null, |
||
| 668 | "metadata": { |
||
| 669 | "ExecuteTime": { |
||
| 670 | "end_time": "2019-06-27T00:38:13.014421Z", |
||
| 671 | "start_time": "2019-06-27T00:38:12.991010Z" |
||
| 672 | } |
||
| 673 | }, |
||
| 674 | "outputs": [], |
||
| 675 | "source": [ |
||
| 676 | "# fig.savefig(args.figdir/'note_bp.tif', dpi=300)" |
||
| 677 | ] |
||
| 678 | }, |
||
| 679 | { |
||
| 680 | "cell_type": "markdown", |
||
| 681 | "metadata": {}, |
||
| 682 | "source": [ |
||
| 683 | "#### By Category" |
||
| 684 | ] |
||
| 685 | }, |
||
| 686 | { |
||
| 687 | "cell_type": "code", |
||
| 688 | "execution_count": null, |
||
| 689 | "metadata": { |
||
| 690 | "ExecuteTime": { |
||
| 691 | "end_time": "2019-07-17T18:43:10.933200Z", |
||
| 692 | "start_time": "2019-07-17T18:43:10.805412Z" |
||
| 693 | } |
||
| 694 | }, |
||
| 695 | "outputs": [], |
||
| 696 | "source": [ |
||
| 697 | "def plot_intervals(ax, df, cat):\n", |
||
| 698 | " sns.barplot(x='days', y='n_notes', data=df, ax=ax)\n", |
||
| 699 | " ax.set_xticklabels(ax.get_xticklabels(),rotation=45, ha='right')\n", |
||
| 700 | " ax.set_xlabel('')\n", |
||
| 701 | " ax.set_ylabel('')\n", |
||
| 702 | " ax.set_title(f\"Note Category: {cat}\\n# notes: {df['n_notes'].sum()}\") \n", |
||
| 703 | "\n", |
||
| 704 | " for index, (_, row) in enumerate(df.iterrows()):\n", |
||
| 705 | " ax.text(index, row['n_notes'], str(row['n_notes']), color='black', ha='center', va='bottom') " |
||
| 706 | ] |
||
| 707 | }, |
||
| 708 | { |
||
| 709 | "cell_type": "code", |
||
| 710 | "execution_count": null, |
||
| 711 | "metadata": { |
||
| 712 | "ExecuteTime": { |
||
| 713 | "end_time": "2019-07-17T18:43:12.728434Z", |
||
| 714 | "start_time": "2019-07-17T18:43:12.610095Z" |
||
| 715 | } |
||
| 716 | }, |
||
| 717 | "outputs": [], |
||
| 718 | "source": [ |
||
| 719 | "plot_df = pd.DataFrame(df.groupby(['category', 'chartinterval']).size(), columns=['n_notes'])\n", |
||
| 720 | "plot_df.reset_index(inplace=True)\n", |
||
| 721 | "plot_df['days'] = plot_df['chartinterval'].apply(lambda x: intervals[x])\n", |
||
| 722 | "plot_df.drop(['chartinterval'], inplace=True, axis=1)" |
||
| 723 | ] |
||
| 724 | }, |
||
| 725 | { |
||
| 726 | "cell_type": "code", |
||
| 727 | "execution_count": null, |
||
| 728 | "metadata": { |
||
| 729 | "ExecuteTime": { |
||
| 730 | "end_time": "2019-07-17T18:43:26.011143Z", |
||
| 731 | "start_time": "2019-07-17T18:43:15.024678Z" |
||
| 732 | }, |
||
| 733 | "scrolled": false |
||
| 734 | }, |
||
| 735 | "outputs": [], |
||
| 736 | "source": [ |
||
| 737 | "fig, ax = plt.subplots(6, 2, figsize=(20, 50))\n", |
||
| 738 | "plot_intervals(ax[0][0], plot_df.loc[plot_df['category'] == 'Case Management ', ['n_notes', 'days']], 'Case Management')\n", |
||
| 739 | "plot_intervals(ax[0][1], plot_df.loc[plot_df['category'] == 'Consult', ['n_notes', 'days']], 'Consult')\n", |
||
| 740 | "\n", |
||
| 741 | "plot_intervals(ax[1][0], plot_df.loc[plot_df['category'] == 'General', ['n_notes', 'days']], 'General')\n", |
||
| 742 | "plot_intervals(ax[1][1], plot_df.loc[plot_df['category'] == 'Nursing', ['n_notes', 'days']], 'Nursing')\n", |
||
| 743 | "\n", |
||
| 744 | "plot_intervals(ax[2][0], plot_df.loc[plot_df['category'] == 'Nursing/other', ['n_notes', 'days']], 'Nursing/other')\n", |
||
| 745 | "plot_intervals(ax[2][1], plot_df.loc[plot_df['category'] == 'Nutrition', ['n_notes', 'days']], 'Nutrition')\n", |
||
| 746 | "\n", |
||
| 747 | "plot_intervals(ax[3][0], plot_df.loc[plot_df['category'] == 'Pharmacy', ['n_notes', 'days']], 'Pharmacy')\n", |
||
| 748 | "plot_intervals(ax[3][1], plot_df.loc[plot_df['category'] == 'Physician ', ['n_notes', 'days',]], 'Physician')\n", |
||
| 749 | "\n", |
||
| 750 | "plot_intervals(ax[4][0], plot_df.loc[plot_df['category'] == 'Radiology', ['n_notes', 'days']], 'Radiology')\n", |
||
| 751 | "plot_intervals(ax[4][1], plot_df.loc[plot_df['category'] == 'Rehab Services', ['n_notes', 'days']], 'Rehab Services')\n", |
||
| 752 | "\n", |
||
| 753 | "plot_intervals(ax[5][0], plot_df.loc[plot_df['category'] == 'Respiratory ', ['n_notes', 'days']], 'Respiratory')\n", |
||
| 754 | "plot_intervals(ax[5][1], plot_df.loc[plot_df['category'] == 'Social Work', ['n_notes', 'days']], 'Social Work')\n", |
||
| 755 | "\n", |
||
| 756 | "fig.text(0.5, 0.1, 'Time to ICU Admission (days)', ha='center')\n", |
||
| 757 | "fig.text(0.08, 0.5, '# notes', va='center', rotation='vertical')\n", |
||
| 758 | "\n", |
||
| 759 | "plt.subplots_adjust(hspace = 0.3)" |
||
| 760 | ] |
||
| 761 | }, |
||
| 762 | { |
||
| 763 | "cell_type": "code", |
||
| 764 | "execution_count": null, |
||
| 765 | "metadata": { |
||
| 766 | "ExecuteTime": { |
||
| 767 | "end_time": "2019-06-27T00:42:13.420913Z", |
||
| 768 | "start_time": "2019-06-27T00:42:13.395654Z" |
||
| 769 | } |
||
| 770 | }, |
||
| 771 | "outputs": [], |
||
| 772 | "source": [ |
||
| 773 | "# cats = sorted(list(df['category'].unique()))\n", |
||
| 774 | "\n", |
||
| 775 | "# n = 0\n", |
||
| 776 | "# fig, ax = plt.subplots(1, 1, figsize=(10, 8))\n", |
||
| 777 | "# plot_intervals(ax, plot_df.loc[plot_df['category'] == cats[n], ['n_notes', 'days']], cats[n])\n", |
||
| 778 | "# ax.set_xlabel('Time to ICU Admission (days)')\n", |
||
| 779 | "# ax.set_ylabel('# notes')" |
||
| 780 | ] |
||
| 781 | }, |
||
| 782 | { |
||
| 783 | "cell_type": "code", |
||
| 784 | "execution_count": null, |
||
| 785 | "metadata": { |
||
| 786 | "ExecuteTime": { |
||
| 787 | "end_time": "2019-06-26T19:55:34.228896Z", |
||
| 788 | "start_time": "2019-06-26T19:55:34.204962Z" |
||
| 789 | }, |
||
| 790 | "scrolled": false |
||
| 791 | }, |
||
| 792 | "outputs": [], |
||
| 793 | "source": [ |
||
| 794 | "# fig.savefig(args.figdir/'note_cats_bp.tif', dpi=300)" |
||
| 795 | ] |
||
| 796 | }, |
||
| 797 | { |
||
| 798 | "cell_type": "markdown", |
||
| 799 | "metadata": {}, |
||
| 800 | "source": [ |
||
| 801 | "### Note Chart Time to ICU Admission Period Histogram" |
||
| 802 | ] |
||
| 803 | }, |
||
| 804 | { |
||
| 805 | "cell_type": "markdown", |
||
| 806 | "metadata": {}, |
||
| 807 | "source": [ |
||
| 808 | "#### All Notes" |
||
| 809 | ] |
||
| 810 | }, |
||
| 811 | { |
||
| 812 | "cell_type": "code", |
||
| 813 | "execution_count": null, |
||
| 814 | "metadata": { |
||
| 815 | "ExecuteTime": { |
||
| 816 | "end_time": "2019-07-17T18:43:56.456943Z", |
||
| 817 | "start_time": "2019-07-17T18:43:56.330361Z" |
||
| 818 | } |
||
| 819 | }, |
||
| 820 | "outputs": [], |
||
| 821 | "source": [ |
||
| 822 | "plot_df = df[['category', 'charttime_to_icu_period']]" |
||
| 823 | ] |
||
| 824 | }, |
||
| 825 | { |
||
| 826 | "cell_type": "code", |
||
| 827 | "execution_count": null, |
||
| 828 | "metadata": { |
||
| 829 | "ExecuteTime": { |
||
| 830 | "end_time": "2019-07-17T18:44:05.284861Z", |
||
| 831 | "start_time": "2019-07-17T18:44:03.949948Z" |
||
| 832 | } |
||
| 833 | }, |
||
| 834 | "outputs": [], |
||
| 835 | "source": [ |
||
| 836 | "fig, ax = plt.subplots(figsize=(10, 8))\n", |
||
| 837 | "\n", |
||
| 838 | "sns.distplot(plot_df['charttime_to_icu_period'], kde=False, ax=ax, bins=80)\n", |
||
| 839 | "ax.set_xlabel('Period between Note Chart Time and ICU Admission Time (days)')\n", |
||
| 840 | "ax.set_ylabel('# notes')\n", |
||
| 841 | "ax.set_xlim(0, 60)\n", |
||
| 842 | "\n", |
||
| 843 | "# ax.text(ax.get_xlim()[1]*0.50, ax.get_ylim()[1]*0.80, f\"Min: {mdf['chart_icu_period'].min()}, Avg: {mdf['chart_icu_period'].mean(): 0.2f}, Max: {mdf['chart_icu_period'].max()}\", fontweight='bold', fontsize=15, ha='center', va='bottom')" |
||
| 844 | ] |
||
| 845 | }, |
||
| 846 | { |
||
| 847 | "cell_type": "code", |
||
| 848 | "execution_count": null, |
||
| 849 | "metadata": { |
||
| 850 | "ExecuteTime": { |
||
| 851 | "end_time": "2019-06-26T19:55:34.712151Z", |
||
| 852 | "start_time": "2019-06-26T19:55:34.686551Z" |
||
| 853 | } |
||
| 854 | }, |
||
| 855 | "outputs": [], |
||
| 856 | "source": [ |
||
| 857 | "# fig.savefig(args.figdir/'note_icu_period_hist.tif', dpi=300)" |
||
| 858 | ] |
||
| 859 | }, |
||
| 860 | { |
||
| 861 | "cell_type": "markdown", |
||
| 862 | "metadata": {}, |
||
| 863 | "source": [ |
||
| 864 | "#### By Category" |
||
| 865 | ] |
||
| 866 | }, |
||
| 867 | { |
||
| 868 | "cell_type": "code", |
||
| 869 | "execution_count": null, |
||
| 870 | "metadata": { |
||
| 871 | "ExecuteTime": { |
||
| 872 | "end_time": "2019-07-17T18:44:13.676427Z", |
||
| 873 | "start_time": "2019-07-17T18:44:13.571725Z" |
||
| 874 | } |
||
| 875 | }, |
||
| 876 | "outputs": [], |
||
| 877 | "source": [ |
||
| 878 | "def plot_period(ax, df, cat):\n", |
||
| 879 | " sns.distplot(df, kde=False, ax=ax, bins=10)\n", |
||
| 880 | " ax.set_xlabel('')\n", |
||
| 881 | " ax.set_ylabel('')\n", |
||
| 882 | " ax.set_title(f\"Note Category: {cat}\") " |
||
| 883 | ] |
||
| 884 | }, |
||
| 885 | { |
||
| 886 | "cell_type": "code", |
||
| 887 | "execution_count": null, |
||
| 888 | "metadata": { |
||
| 889 | "ExecuteTime": { |
||
| 890 | "end_time": "2019-07-17T18:45:21.689010Z", |
||
| 891 | "start_time": "2019-07-17T18:45:12.353337Z" |
||
| 892 | }, |
||
| 893 | "scrolled": false |
||
| 894 | }, |
||
| 895 | "outputs": [], |
||
| 896 | "source": [ |
||
| 897 | "fig, ax = plt.subplots(6, 2, figsize=(20, 50))\n", |
||
| 898 | "plot_period(ax[0][0], plot_df.loc[plot_df['category'] == 'Case Management ', ['charttime_to_icu_period']], 'Case Management')\n", |
||
| 899 | "plot_period(ax[0][1], plot_df.loc[plot_df['category'] == 'Consult', ['charttime_to_icu_period']], 'Consult')\n", |
||
| 900 | "\n", |
||
| 901 | "plot_period(ax[1][0], plot_df.loc[plot_df['category'] == 'General', ['charttime_to_icu_period']], 'General')\n", |
||
| 902 | "plot_period(ax[1][1], plot_df.loc[plot_df['category'] == 'Nursing', ['charttime_to_icu_period']], 'Nursing')\n", |
||
| 903 | "\n", |
||
| 904 | "plot_period(ax[2][0], plot_df.loc[plot_df['category'] == 'Nursing/other', ['charttime_to_icu_period']], 'Nursing/other')\n", |
||
| 905 | "plot_period(ax[2][1], plot_df.loc[plot_df['category'] == 'Nutrition', ['charttime_to_icu_period']], 'Nutrition')\n", |
||
| 906 | "\n", |
||
| 907 | "plot_period(ax[3][0], plot_df.loc[plot_df['category'] == 'Pharmacy', ['charttime_to_icu_period']], 'Pharmacy')\n", |
||
| 908 | "plot_period(ax[3][1], plot_df.loc[plot_df['category'] == 'Physician ', ['charttime_to_icu_period',]], 'Physician')\n", |
||
| 909 | "\n", |
||
| 910 | "plot_period(ax[4][0], plot_df.loc[plot_df['category'] == 'Radiology', ['charttime_to_icu_period']], 'Radiology')\n", |
||
| 911 | "plot_period(ax[4][1], plot_df.loc[plot_df['category'] == 'Rehab Services', ['charttime_to_icu_period']], 'Rehab Services')\n", |
||
| 912 | "\n", |
||
| 913 | "plot_period(ax[5][0], plot_df.loc[plot_df['category'] == 'Respiratory ', ['charttime_to_icu_period']], 'Respiratory')\n", |
||
| 914 | "plot_period(ax[5][1], plot_df.loc[plot_df['category'] == 'Social Work', ['charttime_to_icu_period']], 'Social Work')\n", |
||
| 915 | "\n", |
||
| 916 | "fig.text(0.5, 0.11, 'Period between Note Chart Time and ICU Admission Time (days)', ha='center')\n", |
||
| 917 | "fig.text(0.08, 0.5, '# notes', va='center', rotation='vertical')\n", |
||
| 918 | "\n", |
||
| 919 | "plt.subplots_adjust(hspace = 0.1)" |
||
| 920 | ] |
||
| 921 | }, |
||
| 922 | { |
||
| 923 | "cell_type": "code", |
||
| 924 | "execution_count": null, |
||
| 925 | "metadata": { |
||
| 926 | "ExecuteTime": { |
||
| 927 | "end_time": "2019-06-27T00:43:24.745337Z", |
||
| 928 | "start_time": "2019-06-27T00:43:24.720208Z" |
||
| 929 | } |
||
| 930 | }, |
||
| 931 | "outputs": [], |
||
| 932 | "source": [ |
||
| 933 | "# cats = sorted(list(df['category'].unique()))\n", |
||
| 934 | "\n", |
||
| 935 | "# n = 0\n", |
||
| 936 | "# fig, ax = plt.subplots(1, 1, figsize=(10, 8))\n", |
||
| 937 | "# plot_period(ax, plot_df.loc[plot_df['category'] == cats[n], ['chart_icu_period']], cats[n])\n", |
||
| 938 | "# ax.set_xlabel('Time to ICU Admission (days)')\n", |
||
| 939 | "# ax.set_ylabel('# notes')" |
||
| 940 | ] |
||
| 941 | }, |
||
| 942 | { |
||
| 943 | "cell_type": "code", |
||
| 944 | "execution_count": null, |
||
| 945 | "metadata": { |
||
| 946 | "ExecuteTime": { |
||
| 947 | "end_time": "2019-06-26T19:35:38.476961Z", |
||
| 948 | "start_time": "2019-06-26T19:35:38.451886Z" |
||
| 949 | }, |
||
| 950 | "scrolled": false |
||
| 951 | }, |
||
| 952 | "outputs": [], |
||
| 953 | "source": [ |
||
| 954 | "# fig.savefig(args.figdir/'note_cat_icu_period_hist.tif', dpi=300)" |
||
| 955 | ] |
||
| 956 | }, |
||
| 957 | { |
||
| 958 | "cell_type": "markdown", |
||
| 959 | "metadata": {}, |
||
| 960 | "source": [ |
||
| 961 | "### Hospital Admission to ICU Admission Period Histogram" |
||
| 962 | ] |
||
| 963 | }, |
||
| 964 | { |
||
| 965 | "cell_type": "code", |
||
| 966 | "execution_count": null, |
||
| 967 | "metadata": { |
||
| 968 | "ExecuteTime": { |
||
| 969 | "end_time": "2019-07-17T18:45:44.547021Z", |
||
| 970 | "start_time": "2019-07-17T18:45:44.519812Z" |
||
| 971 | } |
||
| 972 | }, |
||
| 973 | "outputs": [], |
||
| 974 | "source": [ |
||
| 975 | "plot_df = df[['adm_to_icu_period']]" |
||
| 976 | ] |
||
| 977 | }, |
||
| 978 | { |
||
| 979 | "cell_type": "code", |
||
| 980 | "execution_count": null, |
||
| 981 | "metadata": { |
||
| 982 | "ExecuteTime": { |
||
| 983 | "end_time": "2019-07-17T18:45:46.580796Z", |
||
| 984 | "start_time": "2019-07-17T18:45:45.217784Z" |
||
| 985 | } |
||
| 986 | }, |
||
| 987 | "outputs": [], |
||
| 988 | "source": [ |
||
| 989 | "fig, ax = plt.subplots(figsize=(10, 8))\n", |
||
| 990 | "\n", |
||
| 991 | "sns.distplot(plot_df, kde=False, ax=ax, bins=80)\n", |
||
| 992 | "ax.set_xlabel('Time between hospital admission and ICU admission (days)')\n", |
||
| 993 | "ax.set_ylabel('# notes')\n", |
||
| 994 | "ax.set_xlim(0, 70)\n", |
||
| 995 | "# ax.text(ax.get_xlim()[1]*0.50, ax.get_ylim()[1]*0.80, f\"Min: {mdf['adm_icu_period'].min()}, Avg: {mdf['adm_icu_period'].mean(): 0.2f}, Max: {mdf['adm_icu_period'].max()}\", fontweight='bold', fontsize=15, ha='center', va='bottom') " |
||
| 996 | ] |
||
| 997 | }, |
||
| 998 | { |
||
| 999 | "cell_type": "code", |
||
| 1000 | "execution_count": null, |
||
| 1001 | "metadata": {}, |
||
| 1002 | "outputs": [], |
||
| 1003 | "source": [ |
||
| 1004 | "# fig.savefig(args.figdir/'adm_icu_period_hist.tif', dpi=300)" |
||
| 1005 | ] |
||
| 1006 | }, |
||
| 1007 | { |
||
| 1008 | "cell_type": "markdown", |
||
| 1009 | "metadata": {}, |
||
| 1010 | "source": [ |
||
| 1011 | "### Note Length Histogram" |
||
| 1012 | ] |
||
| 1013 | }, |
||
| 1014 | { |
||
| 1015 | "cell_type": "code", |
||
| 1016 | "execution_count": null, |
||
| 1017 | "metadata": { |
||
| 1018 | "ExecuteTime": { |
||
| 1019 | "end_time": "2019-07-17T18:45:50.860829Z", |
||
| 1020 | "start_time": "2019-07-17T18:45:49.137114Z" |
||
| 1021 | } |
||
| 1022 | }, |
||
| 1023 | "outputs": [], |
||
| 1024 | "source": [ |
||
| 1025 | "fig, ax = plt.subplots(figsize=(10, 8))\n", |
||
| 1026 | "sns.distplot(df['note'].apply(len), kde=False, ax=ax, bins=100)\n", |
||
| 1027 | "ax.set_xlabel('Length of Note (characters)')\n", |
||
| 1028 | "ax.set_ylabel('# notes')" |
||
| 1029 | ] |
||
| 1030 | }, |
||
| 1031 | { |
||
| 1032 | "cell_type": "code", |
||
| 1033 | "execution_count": null, |
||
| 1034 | "metadata": { |
||
| 1035 | "ExecuteTime": { |
||
| 1036 | "end_time": "2019-06-26T19:59:38.291139Z", |
||
| 1037 | "start_time": "2019-06-26T19:59:38.267860Z" |
||
| 1038 | } |
||
| 1039 | }, |
||
| 1040 | "outputs": [], |
||
| 1041 | "source": [ |
||
| 1042 | "# fig.savefig(args.figdir/'note_len_hist.tif', dpi=300)" |
||
| 1043 | ] |
||
| 1044 | }, |
||
| 1045 | { |
||
| 1046 | "cell_type": "markdown", |
||
| 1047 | "metadata": {}, |
||
| 1048 | "source": [ |
||
| 1049 | "### Imminent ICU Prediction Class Distribution" |
||
| 1050 | ] |
||
| 1051 | }, |
||
| 1052 | { |
||
| 1053 | "cell_type": "code", |
||
| 1054 | "execution_count": null, |
||
| 1055 | "metadata": { |
||
| 1056 | "ExecuteTime": { |
||
| 1057 | "end_time": "2019-07-17T18:53:53.526861Z", |
||
| 1058 | "start_time": "2019-07-17T18:53:53.429558Z" |
||
| 1059 | } |
||
| 1060 | }, |
||
| 1061 | "outputs": [], |
||
| 1062 | "source": [ |
||
| 1063 | "desc = ['Unused', 'Delayed Admission', 'Imminent Admission']" |
||
| 1064 | ] |
||
| 1065 | }, |
||
| 1066 | { |
||
| 1067 | "cell_type": "markdown", |
||
| 1068 | "metadata": {}, |
||
| 1069 | "source": [ |
||
| 1070 | "#### Without Admissions" |
||
| 1071 | ] |
||
| 1072 | }, |
||
| 1073 | { |
||
| 1074 | "cell_type": "code", |
||
| 1075 | "execution_count": null, |
||
| 1076 | "metadata": { |
||
| 1077 | "ExecuteTime": { |
||
| 1078 | "end_time": "2019-07-17T18:53:54.551036Z", |
||
| 1079 | "start_time": "2019-07-17T18:53:54.423540Z" |
||
| 1080 | } |
||
| 1081 | }, |
||
| 1082 | "outputs": [], |
||
| 1083 | "source": [ |
||
| 1084 | "plot_df = pd.DataFrame(df.groupby(['imminent_adm_label']).size(), columns=['n_notes']).reset_index()\n", |
||
| 1085 | "plot_df['imminent_adm_label'] = desc\n", |
||
| 1086 | "plot_df = plot_df.reindex([2, 1, 0])\n", |
||
| 1087 | "plot_df.reset_index(inplace=True, drop=True)" |
||
| 1088 | ] |
||
| 1089 | }, |
||
| 1090 | { |
||
| 1091 | "cell_type": "code", |
||
| 1092 | "execution_count": null, |
||
| 1093 | "metadata": { |
||
| 1094 | "ExecuteTime": { |
||
| 1095 | "end_time": "2019-07-17T18:53:55.840770Z", |
||
| 1096 | "start_time": "2019-07-17T18:53:54.913513Z" |
||
| 1097 | } |
||
| 1098 | }, |
||
| 1099 | "outputs": [], |
||
| 1100 | "source": [ |
||
| 1101 | "fig, ax = plt.subplots(figsize=(10, 8))\n", |
||
| 1102 | "sns.barplot(x='imminent_adm_label', y='n_notes', data=plot_df, ax=ax)\n", |
||
| 1103 | "ax.set_xlabel('Imminent Class Label')\n", |
||
| 1104 | "ax.set_ylabel('# notes')\n", |
||
| 1105 | "for index, row in plot_df.iterrows():\n", |
||
| 1106 | " ax.text(index+0.05, row['n_notes']+50, str(row['n_notes']), color='black', ha='right', va='bottom')" |
||
| 1107 | ] |
||
| 1108 | }, |
||
| 1109 | { |
||
| 1110 | "cell_type": "code", |
||
| 1111 | "execution_count": null, |
||
| 1112 | "metadata": { |
||
| 1113 | "ExecuteTime": { |
||
| 1114 | "end_time": "2019-06-27T01:07:18.818779Z", |
||
| 1115 | "start_time": "2019-06-27T01:07:18.795768Z" |
||
| 1116 | } |
||
| 1117 | }, |
||
| 1118 | "outputs": [], |
||
| 1119 | "source": [ |
||
| 1120 | "# fig.savefig(args.figdir/'imminent_label_bp.tif', dpi=300)" |
||
| 1121 | ] |
||
| 1122 | }, |
||
| 1123 | { |
||
| 1124 | "cell_type": "markdown", |
||
| 1125 | "metadata": {}, |
||
| 1126 | "source": [ |
||
| 1127 | "#### With Admissions" |
||
| 1128 | ] |
||
| 1129 | }, |
||
| 1130 | { |
||
| 1131 | "cell_type": "code", |
||
| 1132 | "execution_count": null, |
||
| 1133 | "metadata": { |
||
| 1134 | "ExecuteTime": { |
||
| 1135 | "end_time": "2019-07-17T18:54:20.657113Z", |
||
| 1136 | "start_time": "2019-07-17T18:54:20.298763Z" |
||
| 1137 | } |
||
| 1138 | }, |
||
| 1139 | "outputs": [], |
||
| 1140 | "source": [ |
||
| 1141 | "p1 = pd.DataFrame(df.groupby(['imminent_adm_label']).size(), columns=['n_notes']).reset_index()\n", |
||
| 1142 | "p2 = df.groupby(['imminent_adm_label'])['hadm_id'].nunique().reset_index()\n", |
||
| 1143 | "p = p1.merge(p2, on=['imminent_adm_label'])" |
||
| 1144 | ] |
||
| 1145 | }, |
||
| 1146 | { |
||
| 1147 | "cell_type": "code", |
||
| 1148 | "execution_count": null, |
||
| 1149 | "metadata": { |
||
| 1150 | "ExecuteTime": { |
||
| 1151 | "end_time": "2019-07-17T18:54:20.757964Z", |
||
| 1152 | "start_time": "2019-07-17T18:54:20.660979Z" |
||
| 1153 | } |
||
| 1154 | }, |
||
| 1155 | "outputs": [], |
||
| 1156 | "source": [ |
||
| 1157 | "p['imminent_adm_label'] = desc" |
||
| 1158 | ] |
||
| 1159 | }, |
||
| 1160 | { |
||
| 1161 | "cell_type": "code", |
||
| 1162 | "execution_count": null, |
||
| 1163 | "metadata": { |
||
| 1164 | "ExecuteTime": { |
||
| 1165 | "end_time": "2019-07-17T18:54:21.287840Z", |
||
| 1166 | "start_time": "2019-07-17T18:54:21.204792Z" |
||
| 1167 | } |
||
| 1168 | }, |
||
| 1169 | "outputs": [], |
||
| 1170 | "source": [ |
||
| 1171 | "p = p.reindex([2,1,0])\n", |
||
| 1172 | "p.reset_index(inplace=True, drop=True)\n", |
||
| 1173 | "p" |
||
| 1174 | ] |
||
| 1175 | }, |
||
| 1176 | { |
||
| 1177 | "cell_type": "code", |
||
| 1178 | "execution_count": null, |
||
| 1179 | "metadata": { |
||
| 1180 | "ExecuteTime": { |
||
| 1181 | "end_time": "2019-07-17T18:54:29.367296Z", |
||
| 1182 | "start_time": "2019-07-17T18:54:29.263198Z" |
||
| 1183 | } |
||
| 1184 | }, |
||
| 1185 | "outputs": [], |
||
| 1186 | "source": [ |
||
| 1187 | "plot_df = p.copy()\n", |
||
| 1188 | "plot_df.rename(columns={'hadm_id':'# Admissions', 'n_notes':'# Notes'}, inplace=True)\n", |
||
| 1189 | "plot_df = pd.melt(plot_df, id_vars='imminent_adm_label', var_name='Legend', value_name='counts')" |
||
| 1190 | ] |
||
| 1191 | }, |
||
| 1192 | { |
||
| 1193 | "cell_type": "code", |
||
| 1194 | "execution_count": null, |
||
| 1195 | "metadata": { |
||
| 1196 | "ExecuteTime": { |
||
| 1197 | "end_time": "2019-07-17T18:54:35.592328Z", |
||
| 1198 | "start_time": "2019-07-17T18:54:34.576044Z" |
||
| 1199 | } |
||
| 1200 | }, |
||
| 1201 | "outputs": [], |
||
| 1202 | "source": [ |
||
| 1203 | "fig, ax = plt.subplots(figsize=(10, 8))\n", |
||
| 1204 | "\n", |
||
| 1205 | "sns.barplot(x='imminent_adm_label', y='counts', hue='Legend', data=plot_df, ax=ax)\n", |
||
| 1206 | "ax.set_xticklabels(ax.get_xticklabels(), ha='right')\n", |
||
| 1207 | "ax.set_xlabel('Imminent Class Label')\n", |
||
| 1208 | "ax.set_ylabel('# notes')\n", |
||
| 1209 | "\n", |
||
| 1210 | "for index, row in plot_df.iterrows():\n", |
||
| 1211 | " if index < len(plot_df)//2:\n", |
||
| 1212 | " ax.text(index-0.13, row['counts']+50, str(row['counts']), color='black', ha='right', va='bottom')\n", |
||
| 1213 | " else:\n", |
||
| 1214 | " ax.text(index % (len(plot_df)//2)+0.25, row['counts']+50, str(row['counts']), color='black', ha='right', va='bottom')" |
||
| 1215 | ] |
||
| 1216 | }, |
||
| 1217 | { |
||
| 1218 | "cell_type": "code", |
||
| 1219 | "execution_count": null, |
||
| 1220 | "metadata": {}, |
||
| 1221 | "outputs": [], |
||
| 1222 | "source": [ |
||
| 1223 | "# fig.savefig(args.figdir/'imminent_label_adms_bp.tif', dpi=300)" |
||
| 1224 | ] |
||
| 1225 | }, |
||
| 1226 | { |
||
| 1227 | "cell_type": "markdown", |
||
| 1228 | "metadata": {}, |
||
| 1229 | "source": [ |
||
| 1230 | "### Prolonged Stay Class Distribution" |
||
| 1231 | ] |
||
| 1232 | }, |
||
| 1233 | { |
||
| 1234 | "cell_type": "code", |
||
| 1235 | "execution_count": null, |
||
| 1236 | "metadata": { |
||
| 1237 | "ExecuteTime": { |
||
| 1238 | "end_time": "2019-07-17T19:00:53.843117Z", |
||
| 1239 | "start_time": "2019-07-17T19:00:53.541066Z" |
||
| 1240 | } |
||
| 1241 | }, |
||
| 1242 | "outputs": [], |
||
| 1243 | "source": [ |
||
| 1244 | "desc = ['Short Stay', 'Prolonged Stay']" |
||
| 1245 | ] |
||
| 1246 | }, |
||
| 1247 | { |
||
| 1248 | "cell_type": "markdown", |
||
| 1249 | "metadata": {}, |
||
| 1250 | "source": [ |
||
| 1251 | "#### Without Admissions" |
||
| 1252 | ] |
||
| 1253 | }, |
||
| 1254 | { |
||
| 1255 | "cell_type": "code", |
||
| 1256 | "execution_count": null, |
||
| 1257 | "metadata": { |
||
| 1258 | "ExecuteTime": { |
||
| 1259 | "end_time": "2019-07-17T19:01:08.738416Z", |
||
| 1260 | "start_time": "2019-07-17T19:01:08.586921Z" |
||
| 1261 | } |
||
| 1262 | }, |
||
| 1263 | "outputs": [], |
||
| 1264 | "source": [ |
||
| 1265 | "plot_df = pd.DataFrame(df.groupby(['prolonged_stay_label']).size(), columns=['n_notes']).reset_index()\n", |
||
| 1266 | "plot_df['prolonged_stay_label'] = desc\n", |
||
| 1267 | "plot_df = plot_df.reindex([1, 0])\n", |
||
| 1268 | "plot_df.reset_index(inplace=True, drop=True)\n", |
||
| 1269 | "plot_df" |
||
| 1270 | ] |
||
| 1271 | }, |
||
| 1272 | { |
||
| 1273 | "cell_type": "code", |
||
| 1274 | "execution_count": null, |
||
| 1275 | "metadata": { |
||
| 1276 | "ExecuteTime": { |
||
| 1277 | "end_time": "2019-07-17T19:01:18.296482Z", |
||
| 1278 | "start_time": "2019-07-17T19:01:17.775519Z" |
||
| 1279 | } |
||
| 1280 | }, |
||
| 1281 | "outputs": [], |
||
| 1282 | "source": [ |
||
| 1283 | "fig, ax = plt.subplots(figsize=(10, 8))\n", |
||
| 1284 | "sns.barplot(x='prolonged_stay_label', y='n_notes', data=plot_df, ax=ax)\n", |
||
| 1285 | "ax.set_xlabel('5 Day Discharge Class Label')\n", |
||
| 1286 | "ax.set_ylabel('# notes')\n", |
||
| 1287 | "for index, row in plot_df.iterrows():\n", |
||
| 1288 | " ax.text(index+0.05, row['n_notes']+50, str(row['n_notes']), color='black', ha='right', va='bottom')" |
||
| 1289 | ] |
||
| 1290 | }, |
||
| 1291 | { |
||
| 1292 | "cell_type": "code", |
||
| 1293 | "execution_count": null, |
||
| 1294 | "metadata": { |
||
| 1295 | "ExecuteTime": { |
||
| 1296 | "end_time": "2019-06-30T21:09:10.237355Z", |
||
| 1297 | "start_time": "2019-06-30T21:09:10.163Z" |
||
| 1298 | } |
||
| 1299 | }, |
||
| 1300 | "outputs": [], |
||
| 1301 | "source": [ |
||
| 1302 | "# fig.savefig(args.figdir/'discharge_label_bp.tif', dpi=300)" |
||
| 1303 | ] |
||
| 1304 | }, |
||
| 1305 | { |
||
| 1306 | "cell_type": "markdown", |
||
| 1307 | "metadata": {}, |
||
| 1308 | "source": [ |
||
| 1309 | "#### With Admissions" |
||
| 1310 | ] |
||
| 1311 | }, |
||
| 1312 | { |
||
| 1313 | "cell_type": "code", |
||
| 1314 | "execution_count": null, |
||
| 1315 | "metadata": { |
||
| 1316 | "ExecuteTime": { |
||
| 1317 | "end_time": "2019-07-17T19:01:34.791633Z", |
||
| 1318 | "start_time": "2019-07-17T19:01:34.568783Z" |
||
| 1319 | } |
||
| 1320 | }, |
||
| 1321 | "outputs": [], |
||
| 1322 | "source": [ |
||
| 1323 | "p1 = pd.DataFrame(df.groupby(['prolonged_stay_label']).size(), columns=['n_notes']).reset_index()\n", |
||
| 1324 | "p2 = df.groupby(['prolonged_stay_label'])['hadm_id'].nunique().reset_index()\n", |
||
| 1325 | "p = p1.merge(p2, on=['prolonged_stay_label'])\n", |
||
| 1326 | "p['prolonged_stay_label'] = desc\n", |
||
| 1327 | "p = p.reindex([1,0])\n", |
||
| 1328 | "p.reset_index(inplace=True, drop=True)\n", |
||
| 1329 | "p" |
||
| 1330 | ] |
||
| 1331 | }, |
||
| 1332 | { |
||
| 1333 | "cell_type": "code", |
||
| 1334 | "execution_count": null, |
||
| 1335 | "metadata": { |
||
| 1336 | "ExecuteTime": { |
||
| 1337 | "end_time": "2019-07-17T19:01:42.249351Z", |
||
| 1338 | "start_time": "2019-07-17T19:01:42.137270Z" |
||
| 1339 | } |
||
| 1340 | }, |
||
| 1341 | "outputs": [], |
||
| 1342 | "source": [ |
||
| 1343 | "plot_df = p.copy()\n", |
||
| 1344 | "plot_df.rename(columns={'hadm_id':'# Admissions', 'n_notes':'# Notes'}, inplace=True)\n", |
||
| 1345 | "plot_df = pd.melt(plot_df, id_vars='prolonged_stay_label', var_name='Legend', value_name='counts')" |
||
| 1346 | ] |
||
| 1347 | }, |
||
| 1348 | { |
||
| 1349 | "cell_type": "code", |
||
| 1350 | "execution_count": null, |
||
| 1351 | "metadata": { |
||
| 1352 | "ExecuteTime": { |
||
| 1353 | "end_time": "2019-07-17T19:01:47.756030Z", |
||
| 1354 | "start_time": "2019-07-17T19:01:47.553253Z" |
||
| 1355 | } |
||
| 1356 | }, |
||
| 1357 | "outputs": [], |
||
| 1358 | "source": [ |
||
| 1359 | "fig, ax = plt.subplots(figsize=(10, 8))\n", |
||
| 1360 | "\n", |
||
| 1361 | "sns.barplot(x='prolonged_stay_label', y='counts', hue='Legend', data=plot_df, ax=ax)\n", |
||
| 1362 | "ax.set_xticklabels(ax.get_xticklabels(), ha='right')\n", |
||
| 1363 | "ax.set_xlabel('5 Day Discharge Class Label')\n", |
||
| 1364 | "ax.set_ylabel('# notes')\n", |
||
| 1365 | "\n", |
||
| 1366 | "for index, row in plot_df.iterrows():\n", |
||
| 1367 | " if index < len(plot_df)//2:\n", |
||
| 1368 | " ax.text(index-0.13, row['counts']+50, str(row['counts']), color='black', ha='right', va='bottom')\n", |
||
| 1369 | " else:\n", |
||
| 1370 | " ax.text(index % (len(plot_df)//2)+0.25, row['counts']+50, str(row['counts']), color='black', ha='right', va='bottom')" |
||
| 1371 | ] |
||
| 1372 | }, |
||
| 1373 | { |
||
| 1374 | "cell_type": "code", |
||
| 1375 | "execution_count": null, |
||
| 1376 | "metadata": {}, |
||
| 1377 | "outputs": [], |
||
| 1378 | "source": [ |
||
| 1379 | "# fig.savefig(args.figdir/'discharge_label_adms_bp.tif', dpi=300)" |
||
| 1380 | ] |
||
| 1381 | } |
||
| 1382 | ], |
||
| 1383 | "metadata": { |
||
| 1384 | "kernelspec": { |
||
| 1385 | "display_name": "Python 3", |
||
| 1386 | "language": "python", |
||
| 1387 | "name": "python3" |
||
| 1388 | }, |
||
| 1389 | "language_info": { |
||
| 1390 | "codemirror_mode": { |
||
| 1391 | "name": "ipython", |
||
| 1392 | "version": 3 |
||
| 1393 | }, |
||
| 1394 | "file_extension": ".py", |
||
| 1395 | "mimetype": "text/x-python", |
||
| 1396 | "name": "python", |
||
| 1397 | "nbconvert_exporter": "python", |
||
| 1398 | "pygments_lexer": "ipython3", |
||
| 1399 | "version": "3.7.4" |
||
| 1400 | }, |
||
| 1401 | "toc": { |
||
| 1402 | "base_numbering": 1, |
||
| 1403 | "nav_menu": {}, |
||
| 1404 | "number_sections": true, |
||
| 1405 | "sideBar": true, |
||
| 1406 | "skip_h1_title": true, |
||
| 1407 | "title_cell": "Table of Contents", |
||
| 1408 | "title_sidebar": "Contents", |
||
| 1409 | "toc_cell": false, |
||
| 1410 | "toc_position": { |
||
| 1411 | "height": "calc(100% - 180px)", |
||
| 1412 | "left": "10px", |
||
| 1413 | "top": "150px", |
||
| 1414 | "width": "165px" |
||
| 1415 | }, |
||
| 1416 | "toc_section_display": true, |
||
| 1417 | "toc_window_display": false |
||
| 1418 | } |
||
| 1419 | }, |
||
| 1420 | "nbformat": 4, |
||
| 1421 | "nbformat_minor": 2 |
||
| 1422 | } |