Datasets
Models
Downloads: 1
Diff of
/TCARER_summaryReports.ipynb
[000000]
..
[b4a150]
Switch to unified view
| a | b/TCARER_summaryReports.ipynb | ||
|---|---|---|---|
| 1 | { |
||
| 2 | "cells": [ |
||
| 3 | { |
||
| 4 | "cell_type": "markdown", |
||
| 5 | "metadata": { |
||
| 6 | "deletable": true, |
||
| 7 | "editable": true |
||
| 8 | }, |
||
| 9 | "source": [ |
||
| 10 | "# Temporal-Comorbidity Adjusted Risk of Emergency Readmission (TCARER)\n", |
||
| 11 | "## <font style=\"font-weight:bold;color:gray\">Summary Reports</font>" |
||
| 12 | ] |
||
| 13 | }, |
||
| 14 | { |
||
| 15 | "cell_type": "markdown", |
||
| 16 | "metadata": { |
||
| 17 | "deletable": true, |
||
| 18 | "editable": true |
||
| 19 | }, |
||
| 20 | "source": [ |
||
| 21 | "## 1. Initialise" |
||
| 22 | ] |
||
| 23 | }, |
||
| 24 | { |
||
| 25 | "cell_type": "code", |
||
| 26 | "execution_count": 1, |
||
| 27 | "metadata": { |
||
| 28 | "collapsed": false, |
||
| 29 | "deletable": true, |
||
| 30 | "editable": true, |
||
| 31 | "scrolled": true |
||
| 32 | }, |
||
| 33 | "outputs": [], |
||
| 34 | "source": [ |
||
| 35 | "# reload modules\n", |
||
| 36 | "# Reload all modules (except those excluded by %aimport) every time before executing the Python code typed.\n", |
||
| 37 | "%load_ext autoreload \n", |
||
| 38 | "%autoreload 2" |
||
| 39 | ] |
||
| 40 | }, |
||
| 41 | { |
||
| 42 | "cell_type": "code", |
||
| 43 | "execution_count": 2, |
||
| 44 | "metadata": { |
||
| 45 | "collapsed": false, |
||
| 46 | "deletable": true, |
||
| 47 | "editable": true |
||
| 48 | }, |
||
| 49 | "outputs": [], |
||
| 50 | "source": [ |
||
| 51 | "# import libraries\n", |
||
| 52 | "import logging\n", |
||
| 53 | "import os\n", |
||
| 54 | "import sys\n", |
||
| 55 | "import gc\n", |
||
| 56 | "import pandas as pd\n", |
||
| 57 | "import numpy as np\n", |
||
| 58 | "import random\n", |
||
| 59 | "import statistics\n", |
||
| 60 | "from datetime import datetime\n", |
||
| 61 | "from collections import OrderedDict\n", |
||
| 62 | "from sklearn import preprocessing\n", |
||
| 63 | "from scipy.stats import stats\n", |
||
| 64 | "from IPython.display import display, HTML\n", |
||
| 65 | "from pprint import pprint\n", |
||
| 66 | "from pivottablejs import pivot_ui\n", |
||
| 67 | "from IPython.display import clear_output\n", |
||
| 68 | "import imblearn.over_sampling as oversampling\n", |
||
| 69 | "import matplotlib.pyplot as plt" |
||
| 70 | ] |
||
| 71 | }, |
||
| 72 | { |
||
| 73 | "cell_type": "code", |
||
| 74 | "execution_count": 4, |
||
| 75 | "metadata": { |
||
| 76 | "collapsed": false, |
||
| 77 | "deletable": true, |
||
| 78 | "editable": true |
||
| 79 | }, |
||
| 80 | "outputs": [], |
||
| 81 | "source": [ |
||
| 82 | "# import local classes\n", |
||
| 83 | "from Configs.CONSTANTS import CONSTANTS\n", |
||
| 84 | "from Configs.Logger import Logger\n", |
||
| 85 | "from Features.Variables import Variables\n", |
||
| 86 | "from ReadersWriters.ReadersWriters import ReadersWriters\n", |
||
| 87 | "from Stats.PreProcess import PreProcess\n", |
||
| 88 | "from Stats.FeatureSelection import FeatureSelection\n", |
||
| 89 | "from Stats.TrainingMethod import TrainingMethod\n", |
||
| 90 | "from Stats.Plots import Plots\n", |
||
| 91 | "from Stats.Stats import Stats" |
||
| 92 | ] |
||
| 93 | }, |
||
| 94 | { |
||
| 95 | "cell_type": "code", |
||
| 96 | "execution_count": 5, |
||
| 97 | "metadata": { |
||
| 98 | "collapsed": false, |
||
| 99 | "deletable": true, |
||
| 100 | "editable": true, |
||
| 101 | "scrolled": true |
||
| 102 | }, |
||
| 103 | "outputs": [ |
||
| 104 | { |
||
| 105 | "name": "stdout", |
||
| 106 | "output_type": "stream", |
||
| 107 | "text": [ |
||
| 108 | "\n", |
||
| 109 | "Make sure the correct Python interpreter is used!\n", |
||
| 110 | "3.5.3 (v3.5.3:1880cb95a742, Jan 16 2017, 16:02:32) [MSC v.1900 64 bit (AMD64)]\n", |
||
| 111 | "\n", |
||
| 112 | "Make sure sys.path of the Python interpreter is correct!\n", |
||
| 113 | "C:\\Users\\eagle\\Documents\\GitHub\\Analytics_UoW\\TCARER\n" |
||
| 114 | ] |
||
| 115 | } |
||
| 116 | ], |
||
| 117 | "source": [ |
||
| 118 | "# Check the interpreter\n", |
||
| 119 | "print(\"\\nMake sure the correct Python interpreter is used!\")\n", |
||
| 120 | "print(sys.version)\n", |
||
| 121 | "print(\"\\nMake sure sys.path of the Python interpreter is correct!\")\n", |
||
| 122 | "print(os.getcwd())" |
||
| 123 | ] |
||
| 124 | }, |
||
| 125 | { |
||
| 126 | "cell_type": "markdown", |
||
| 127 | "metadata": { |
||
| 128 | "deletable": true, |
||
| 129 | "editable": true |
||
| 130 | }, |
||
| 131 | "source": [ |
||
| 132 | "### 1.1. Initialise General Settings" |
||
| 133 | ] |
||
| 134 | }, |
||
| 135 | { |
||
| 136 | "cell_type": "code", |
||
| 137 | "execution_count": 6, |
||
| 138 | "metadata": { |
||
| 139 | "collapsed": false, |
||
| 140 | "deletable": true, |
||
| 141 | "editable": true |
||
| 142 | }, |
||
| 143 | "outputs": [ |
||
| 144 | { |
||
| 145 | "name": "stdout", |
||
| 146 | "output_type": "stream", |
||
| 147 | "text": [ |
||
| 148 | "Output path: C:\\Users\\eagle\\Documents\\GitHub\\tmp\\TCARER\\Basic_prototype\n" |
||
| 149 | ] |
||
| 150 | } |
||
| 151 | ], |
||
| 152 | "source": [ |
||
| 153 | "# init paths & directories\n", |
||
| 154 | "config_path = os.path.abspath(\"ConfigInputs/CONFIGURATIONS.ini\")\n", |
||
| 155 | "io_path = os.path.abspath(\"../../tmp/TCARER/Basic_prototype\")\n", |
||
| 156 | "schema = \"parr_sample_prototype\" \n", |
||
| 157 | "app_name = \"T-CARER\"\n", |
||
| 158 | "\n", |
||
| 159 | "print(\"Output path:\", io_path)" |
||
| 160 | ] |
||
| 161 | }, |
||
| 162 | { |
||
| 163 | "cell_type": "code", |
||
| 164 | "execution_count": 7, |
||
| 165 | "metadata": { |
||
| 166 | "collapsed": false, |
||
| 167 | "deletable": true, |
||
| 168 | "editable": true |
||
| 169 | }, |
||
| 170 | "outputs": [ |
||
| 171 | { |
||
| 172 | "name": "stderr", |
||
| 173 | "output_type": "stream", |
||
| 174 | "text": [ |
||
| 175 | "2017-10-29 13:03:26,935 - T-CARER - INFO - Creating 'C:\\Users\\eagle\\Documents\\GitHub\\tmp\\TCARER\\Basic_prototype\\T-CARER.log' File.\n" |
||
| 176 | ] |
||
| 177 | } |
||
| 178 | ], |
||
| 179 | "source": [ |
||
| 180 | "# init logs\n", |
||
| 181 | "if not os.path.exists(io_path):\n", |
||
| 182 | " os.makedirs(io_path, exist_ok=True)\n", |
||
| 183 | "\n", |
||
| 184 | "logger = Logger(path=io_path, app_name=app_name, ext=\"log\")\n", |
||
| 185 | "logger = logging.getLogger(app_name)" |
||
| 186 | ] |
||
| 187 | }, |
||
| 188 | { |
||
| 189 | "cell_type": "code", |
||
| 190 | "execution_count": 8, |
||
| 191 | "metadata": { |
||
| 192 | "collapsed": false, |
||
| 193 | "deletable": true, |
||
| 194 | "editable": true |
||
| 195 | }, |
||
| 196 | "outputs": [], |
||
| 197 | "source": [ |
||
| 198 | "# init constants \n", |
||
| 199 | "CONSTANTS.set(io_path, app_name)" |
||
| 200 | ] |
||
| 201 | }, |
||
| 202 | { |
||
| 203 | "cell_type": "code", |
||
| 204 | "execution_count": 9, |
||
| 205 | "metadata": { |
||
| 206 | "collapsed": false, |
||
| 207 | "deletable": true, |
||
| 208 | "editable": true |
||
| 209 | }, |
||
| 210 | "outputs": [], |
||
| 211 | "source": [ |
||
| 212 | "# initialise other classes\n", |
||
| 213 | "readers_writers = ReadersWriters()\n", |
||
| 214 | "plots = Plots()" |
||
| 215 | ] |
||
| 216 | }, |
||
| 217 | { |
||
| 218 | "cell_type": "code", |
||
| 219 | "execution_count": 10, |
||
| 220 | "metadata": { |
||
| 221 | "collapsed": true, |
||
| 222 | "deletable": true, |
||
| 223 | "editable": true |
||
| 224 | }, |
||
| 225 | "outputs": [], |
||
| 226 | "source": [ |
||
| 227 | "# other Constant variables\n", |
||
| 228 | "submodel_name = \"hesIp\"\n", |
||
| 229 | "submodel_input_name = \"tcarer_model_features_ip\"" |
||
| 230 | ] |
||
| 231 | }, |
||
| 232 | { |
||
| 233 | "cell_type": "code", |
||
| 234 | "execution_count": 11, |
||
| 235 | "metadata": { |
||
| 236 | "collapsed": true, |
||
| 237 | "deletable": true, |
||
| 238 | "editable": true |
||
| 239 | }, |
||
| 240 | "outputs": [], |
||
| 241 | "source": [ |
||
| 242 | "# set print settings\n", |
||
| 243 | "pd.set_option('display.width', 1600, 'display.max_colwidth', 800)" |
||
| 244 | ] |
||
| 245 | }, |
||
| 246 | { |
||
| 247 | "cell_type": "markdown", |
||
| 248 | "metadata": { |
||
| 249 | "deletable": true, |
||
| 250 | "editable": true |
||
| 251 | }, |
||
| 252 | "source": [ |
||
| 253 | " Common variables:\n", |
||
| 254 | "* Readmission\n", |
||
| 255 | " * 'label30', 'label365'\n", |
||
| 256 | "* Admissions Methods:\n", |
||
| 257 | " * 'admimeth\\_0t30d\\_prevalence\\_1\\_cnt', ...\n", |
||
| 258 | "* Prior Spells: \n", |
||
| 259 | " * 'prior\\_spells'\n", |
||
| 260 | "* Male:\n", |
||
| 261 | " * 'gender\\_1'\n", |
||
| 262 | "* LoS:\n", |
||
| 263 | " * 'trigger\\_los'\n", |
||
| 264 | "* Age:\n", |
||
| 265 | " * 'trigger\\_age'\n", |
||
| 266 | "* Charlson Score:\n", |
||
| 267 | " * 'trigger\\_charlsonFoster'\n", |
||
| 268 | "* predictions score\n", |
||
| 269 | " * score\n", |
||
| 270 | "* Most prevalent diagnoses groups (0-30-day, 0-730-day):\n", |
||
| 271 | " * 0-30-day: 'diagCCS\\_0t30d\\_prevalence\\_1\\_cnt', ...\n", |
||
| 272 | " * 0-730-day: 'diagCCS\\_0t30d\\_prevalence\\_1\\_cnt' + 'diagCCS\\_30t90d\\_prevalence\\_1\\_cnt' + \n", |
||
| 273 | " 'diagCCS\\_90t180d\\_prevalence\\_1\\_cnt' + 'diagCCS\\_180t365d\\_prevalence\\_1\\_cnt' + \n", |
||
| 274 | " 'diagCCS\\_365t730d\\_prevalence\\_1\\_cnt', ...\n", |
||
| 275 | "* Comorbidity diagnoses groups (0-730-day):\n", |
||
| 276 | " * 'prior\\_admiOther', 'prior\\_admiAcute', 'prior\\_spells', 'prior\\_asthma', 'prior\\_copd', 'prior\\_depression', 'prior\\_diabetes', 'prior\\_hypertension', 'prior\\_cancer', 'prior\\_chd', 'prior\\_chf'\n", |
||
| 277 | "* Charlson diagnoses groups (trigger):\n", |
||
| 278 | " * 'diagCci\\_01\\_myocardial\\_freq\\_\\_trigger',..." |
||
| 279 | ] |
||
| 280 | }, |
||
| 281 | { |
||
| 282 | "cell_type": "markdown", |
||
| 283 | "metadata": { |
||
| 284 | "deletable": true, |
||
| 285 | "editable": true |
||
| 286 | }, |
||
| 287 | "source": [ |
||
| 288 | "<br/><br/>" |
||
| 289 | ] |
||
| 290 | }, |
||
| 291 | { |
||
| 292 | "cell_type": "markdown", |
||
| 293 | "metadata": { |
||
| 294 | "deletable": true, |
||
| 295 | "editable": true |
||
| 296 | }, |
||
| 297 | "source": [ |
||
| 298 | "## 2. Load the Saved Model Outputs" |
||
| 299 | ] |
||
| 300 | }, |
||
| 301 | { |
||
| 302 | "cell_type": "markdown", |
||
| 303 | "metadata": { |
||
| 304 | "deletable": true, |
||
| 305 | "editable": true |
||
| 306 | }, |
||
| 307 | "source": [ |
||
| 308 | "<font style=\"font-weight:bold;color:red\">Note: Make sure the following files are located at the input path</font>\n", |
||
| 309 | "* Step\\_05\\_Features.bz2\n", |
||
| 310 | "* Step\\_07\\_Top\\_Features\\_...\n", |
||
| 311 | "* Step\\_07\\_Model\\_Train\\_model\\_rank\\_summaries\\_...\n", |
||
| 312 | "* Step\\_09\\_Model\\_..." |
||
| 313 | ] |
||
| 314 | }, |
||
| 315 | { |
||
| 316 | "cell_type": "markdown", |
||
| 317 | "metadata": { |
||
| 318 | "deletable": true, |
||
| 319 | "editable": true |
||
| 320 | }, |
||
| 321 | "source": [ |
||
| 322 | "<font style=\"font-weight:bold;color:red\">Note: Create features extra (Run only once)</font>" |
||
| 323 | ] |
||
| 324 | }, |
||
| 325 | { |
||
| 326 | "cell_type": "code", |
||
| 327 | "execution_count": null, |
||
| 328 | "metadata": { |
||
| 329 | "collapsed": true, |
||
| 330 | "deletable": true, |
||
| 331 | "editable": true |
||
| 332 | }, |
||
| 333 | "outputs": [], |
||
| 334 | "source": [ |
||
| 335 | "# settings\n", |
||
| 336 | "feature_table = 'tcarer_features'\n", |
||
| 337 | "featureExtra_table = 'tcarer_featuresExtra'" |
||
| 338 | ] |
||
| 339 | }, |
||
| 340 | { |
||
| 341 | "cell_type": "code", |
||
| 342 | "execution_count": null, |
||
| 343 | "metadata": { |
||
| 344 | "collapsed": false, |
||
| 345 | "deletable": true, |
||
| 346 | "editable": true, |
||
| 347 | "scrolled": true |
||
| 348 | }, |
||
| 349 | "outputs": [], |
||
| 350 | "source": [ |
||
| 351 | "result = readers_writers.load_mysql_procedure(\"tcarer_set_featuresExtra\", [feature_table, featureExtra_table], schema)" |
||
| 352 | ] |
||
| 353 | }, |
||
| 354 | { |
||
| 355 | "cell_type": "markdown", |
||
| 356 | "metadata": { |
||
| 357 | "deletable": true, |
||
| 358 | "editable": true |
||
| 359 | }, |
||
| 360 | "source": [ |
||
| 361 | "<br/><br/>" |
||
| 362 | ] |
||
| 363 | }, |
||
| 364 | { |
||
| 365 | "cell_type": "markdown", |
||
| 366 | "metadata": { |
||
| 367 | "deletable": true, |
||
| 368 | "editable": true |
||
| 369 | }, |
||
| 370 | "source": [ |
||
| 371 | "### 2.1. Initialise" |
||
| 372 | ] |
||
| 373 | }, |
||
| 374 | { |
||
| 375 | "cell_type": "code", |
||
| 376 | "execution_count": 16, |
||
| 377 | "metadata": { |
||
| 378 | "collapsed": true, |
||
| 379 | "deletable": true, |
||
| 380 | "editable": true |
||
| 381 | }, |
||
| 382 | "outputs": [], |
||
| 383 | "source": [ |
||
| 384 | "# select the target variable\n", |
||
| 385 | "target_feature = \"label365\" # \"label365\", \"label30\" \n", |
||
| 386 | "method_name = \"rfc\" # \"rfc\", \"gbrt\", \"randLogit\", \"wdnn\"\n", |
||
| 387 | "rank_models = [\"rfc\"] # [\"rfc\", \"gbrt\", \"randLogit\"]" |
||
| 388 | ] |
||
| 389 | }, |
||
| 390 | { |
||
| 391 | "cell_type": "markdown", |
||
| 392 | "metadata": { |
||
| 393 | "deletable": true, |
||
| 394 | "editable": true |
||
| 395 | }, |
||
| 396 | "source": [ |
||
| 397 | "<br/><br/>" |
||
| 398 | ] |
||
| 399 | }, |
||
| 400 | { |
||
| 401 | "cell_type": "markdown", |
||
| 402 | "metadata": { |
||
| 403 | "collapsed": true, |
||
| 404 | "deletable": true, |
||
| 405 | "editable": true |
||
| 406 | }, |
||
| 407 | "source": [ |
||
| 408 | "### 2.2. Load Features" |
||
| 409 | ] |
||
| 410 | }, |
||
| 411 | { |
||
| 412 | "cell_type": "markdown", |
||
| 413 | "metadata": { |
||
| 414 | "deletable": true, |
||
| 415 | "editable": true |
||
| 416 | }, |
||
| 417 | "source": [ |
||
| 418 | "Load pre-processed features" |
||
| 419 | ] |
||
| 420 | }, |
||
| 421 | { |
||
| 422 | "cell_type": "code", |
||
| 423 | "execution_count": 17, |
||
| 424 | "metadata": { |
||
| 425 | "collapsed": false, |
||
| 426 | "deletable": true, |
||
| 427 | "editable": true |
||
| 428 | }, |
||
| 429 | "outputs": [ |
||
| 430 | { |
||
| 431 | "name": "stdout", |
||
| 432 | "output_type": "stream", |
||
| 433 | "text": [ |
||
| 434 | "File size: 97692\n", |
||
| 435 | "Number of columns: 458\n", |
||
| 436 | "features: {train: 2500 , test: 2499 }\n" |
||
| 437 | ] |
||
| 438 | } |
||
| 439 | ], |
||
| 440 | "source": [ |
||
| 441 | "file_name = \"Step_07_Features\"\n", |
||
| 442 | "features = readers_writers.load_serialised_compressed(path=CONSTANTS.io_path, title=file_name)\n", |
||
| 443 | "\n", |
||
| 444 | "# print \n", |
||
| 445 | "print(\"File size: \", os.stat(os.path.join(CONSTANTS.io_path, file_name + \".bz2\")).st_size)\n", |
||
| 446 | "print(\"Number of columns: \", len(features[\"train_indep\"].columns)) \n", |
||
| 447 | "print(\"features: {train: \", len(features[\"train_indep\"]), \", test: \", len(features[\"test_indep\"]), \"}\")" |
||
| 448 | ] |
||
| 449 | }, |
||
| 450 | { |
||
| 451 | "cell_type": "markdown", |
||
| 452 | "metadata": { |
||
| 453 | "deletable": true, |
||
| 454 | "editable": true |
||
| 455 | }, |
||
| 456 | "source": [ |
||
| 457 | "### 2.3. Load Features Names" |
||
| 458 | ] |
||
| 459 | }, |
||
| 460 | { |
||
| 461 | "cell_type": "code", |
||
| 462 | "execution_count": 18, |
||
| 463 | "metadata": { |
||
| 464 | "collapsed": false, |
||
| 465 | "deletable": true, |
||
| 466 | "editable": true |
||
| 467 | }, |
||
| 468 | "outputs": [ |
||
| 469 | { |
||
| 470 | "data": { |
||
| 471 | "text/html": [ |
||
| 472 | "<div>\n", |
||
| 473 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 474 | " <thead>\n", |
||
| 475 | " <tr style=\"text-align: right;\">\n", |
||
| 476 | " <th></th>\n", |
||
| 477 | " <th>0</th>\n", |
||
| 478 | " </tr>\n", |
||
| 479 | " </thead>\n", |
||
| 480 | " <tbody>\n", |
||
| 481 | " <tr>\n", |
||
| 482 | " <th>0</th>\n", |
||
| 483 | " <td>epidur_0t30d_avg</td>\n", |
||
| 484 | " </tr>\n", |
||
| 485 | " <tr>\n", |
||
| 486 | " <th>1</th>\n", |
||
| 487 | " <td>epidur_365t730d_avg</td>\n", |
||
| 488 | " </tr>\n", |
||
| 489 | " <tr>\n", |
||
| 490 | " <th>2</th>\n", |
||
| 491 | " <td>preopdur_0t30d_avg</td>\n", |
||
| 492 | " </tr>\n", |
||
| 493 | " <tr>\n", |
||
| 494 | " <th>3</th>\n", |
||
| 495 | " <td>gapDays_0t30d_others_cnt</td>\n", |
||
| 496 | " </tr>\n", |
||
| 497 | " <tr>\n", |
||
| 498 | " <th>4</th>\n", |
||
| 499 | " <td>epidur_365t730d_others_cnt</td>\n", |
||
| 500 | " </tr>\n", |
||
| 501 | " <tr>\n", |
||
| 502 | " <th>5</th>\n", |
||
| 503 | " <td>preopdur_30t90d_others_cnt</td>\n", |
||
| 504 | " </tr>\n", |
||
| 505 | " <tr>\n", |
||
| 506 | " <th>6</th>\n", |
||
| 507 | " <td>epidur_0t30d_others_cnt</td>\n", |
||
| 508 | " </tr>\n", |
||
| 509 | " <tr>\n", |
||
| 510 | " <th>7</th>\n", |
||
| 511 | " <td>preopdur_0t30d_others_cnt</td>\n", |
||
| 512 | " </tr>\n", |
||
| 513 | " <tr>\n", |
||
| 514 | " <th>8</th>\n", |
||
| 515 | " <td>epidur_30t90d_others_cnt</td>\n", |
||
| 516 | " </tr>\n", |
||
| 517 | " <tr>\n", |
||
| 518 | " <th>9</th>\n", |
||
| 519 | " <td>preopdur_90t180d_others_cnt</td>\n", |
||
| 520 | " </tr>\n", |
||
| 521 | " <tr>\n", |
||
| 522 | " <th>10</th>\n", |
||
| 523 | " <td>epidur_180t365d_avg</td>\n", |
||
| 524 | " </tr>\n", |
||
| 525 | " <tr>\n", |
||
| 526 | " <th>11</th>\n", |
||
| 527 | " <td>preopdur_30t90d_avg</td>\n", |
||
| 528 | " </tr>\n", |
||
| 529 | " <tr>\n", |
||
| 530 | " <th>12</th>\n", |
||
| 531 | " <td>preopdur_90t180d_avg</td>\n", |
||
| 532 | " </tr>\n", |
||
| 533 | " <tr>\n", |
||
| 534 | " <th>13</th>\n", |
||
| 535 | " <td>gapDays_365t730d_avg</td>\n", |
||
| 536 | " </tr>\n", |
||
| 537 | " <tr>\n", |
||
| 538 | " <th>14</th>\n", |
||
| 539 | " <td>operOPCSL1_0t30d_prevalence_1_cnt</td>\n", |
||
| 540 | " </tr>\n", |
||
| 541 | " <tr>\n", |
||
| 542 | " <th>15</th>\n", |
||
| 543 | " <td>operOPCSL1_0t30d_others_cnt</td>\n", |
||
| 544 | " </tr>\n", |
||
| 545 | " <tr>\n", |
||
| 546 | " <th>16</th>\n", |
||
| 547 | " <td>posopdur_30t90d_others_cnt</td>\n", |
||
| 548 | " </tr>\n", |
||
| 549 | " <tr>\n", |
||
| 550 | " <th>17</th>\n", |
||
| 551 | " <td>epidur_180t365d_others_cnt</td>\n", |
||
| 552 | " </tr>\n", |
||
| 553 | " <tr>\n", |
||
| 554 | " <th>18</th>\n", |
||
| 555 | " <td>posopdur_0t30d_avg</td>\n", |
||
| 556 | " </tr>\n", |
||
| 557 | " <tr>\n", |
||
| 558 | " <th>19</th>\n", |
||
| 559 | " <td>preopdur_180t365d_others_cnt</td>\n", |
||
| 560 | " </tr>\n", |
||
| 561 | " <tr>\n", |
||
| 562 | " <th>20</th>\n", |
||
| 563 | " <td>operOPCSL1_0t30d_prevalence_3_cnt</td>\n", |
||
| 564 | " </tr>\n", |
||
| 565 | " <tr>\n", |
||
| 566 | " <th>21</th>\n", |
||
| 567 | " <td>operOPCSL1_0t30d_prevalence_4_cnt</td>\n", |
||
| 568 | " </tr>\n", |
||
| 569 | " <tr>\n", |
||
| 570 | " <th>22</th>\n", |
||
| 571 | " <td>posopdur_365t730d_avg</td>\n", |
||
| 572 | " </tr>\n", |
||
| 573 | " <tr>\n", |
||
| 574 | " <th>23</th>\n", |
||
| 575 | " <td>operOPCSL1_0t30d_prevalence_2_cnt</td>\n", |
||
| 576 | " </tr>\n", |
||
| 577 | " <tr>\n", |
||
| 578 | " <th>24</th>\n", |
||
| 579 | " <td>epidur_30t90d_avg</td>\n", |
||
| 580 | " </tr>\n", |
||
| 581 | " <tr>\n", |
||
| 582 | " <th>25</th>\n", |
||
| 583 | " <td>posopdur_30t90d_avg</td>\n", |
||
| 584 | " </tr>\n", |
||
| 585 | " <tr>\n", |
||
| 586 | " <th>26</th>\n", |
||
| 587 | " <td>operOPCSL1_0t30d_prevalence_5_cnt</td>\n", |
||
| 588 | " </tr>\n", |
||
| 589 | " <tr>\n", |
||
| 590 | " <th>27</th>\n", |
||
| 591 | " <td>preopdur_180t365d_avg</td>\n", |
||
| 592 | " </tr>\n", |
||
| 593 | " <tr>\n", |
||
| 594 | " <th>28</th>\n", |
||
| 595 | " <td>preopdur_365t730d_others_cnt</td>\n", |
||
| 596 | " </tr>\n", |
||
| 597 | " <tr>\n", |
||
| 598 | " <th>29</th>\n", |
||
| 599 | " <td>preopdur_365t730d_avg</td>\n", |
||
| 600 | " </tr>\n", |
||
| 601 | " <tr>\n", |
||
| 602 | " <th>...</th>\n", |
||
| 603 | " <td>...</td>\n", |
||
| 604 | " </tr>\n", |
||
| 605 | " <tr>\n", |
||
| 606 | " <th>370</th>\n", |
||
| 607 | " <td>operOPCSL1_180t365d_prevalence_30_cnt</td>\n", |
||
| 608 | " </tr>\n", |
||
| 609 | " <tr>\n", |
||
| 610 | " <th>371</th>\n", |
||
| 611 | " <td>diagCCS_0t30d_prevalence_25_cnt</td>\n", |
||
| 612 | " </tr>\n", |
||
| 613 | " <tr>\n", |
||
| 614 | " <th>372</th>\n", |
||
| 615 | " <td>diagCCS_30t90d_prevalence_1_cnt</td>\n", |
||
| 616 | " </tr>\n", |
||
| 617 | " <tr>\n", |
||
| 618 | " <th>373</th>\n", |
||
| 619 | " <td>diagCCS_0t30d_prevalence_23_cnt</td>\n", |
||
| 620 | " </tr>\n", |
||
| 621 | " <tr>\n", |
||
| 622 | " <th>374</th>\n", |
||
| 623 | " <td>diagCCS_90t180d_prevalence_5_cnt</td>\n", |
||
| 624 | " </tr>\n", |
||
| 625 | " <tr>\n", |
||
| 626 | " <th>375</th>\n", |
||
| 627 | " <td>diagCCS_90t180d_prevalence_4_cnt</td>\n", |
||
| 628 | " </tr>\n", |
||
| 629 | " <tr>\n", |
||
| 630 | " <th>376</th>\n", |
||
| 631 | " <td>diagCCS_0t30d_prevalence_19_cnt</td>\n", |
||
| 632 | " </tr>\n", |
||
| 633 | " <tr>\n", |
||
| 634 | " <th>377</th>\n", |
||
| 635 | " <td>operOPCSL1_365t730d_prevalence_4_cnt</td>\n", |
||
| 636 | " </tr>\n", |
||
| 637 | " <tr>\n", |
||
| 638 | " <th>378</th>\n", |
||
| 639 | " <td>diagCCS_90t180d_prevalence_2_cnt</td>\n", |
||
| 640 | " </tr>\n", |
||
| 641 | " <tr>\n", |
||
| 642 | " <th>379</th>\n", |
||
| 643 | " <td>diagCCS_90t180d_prevalence_3_cnt</td>\n", |
||
| 644 | " </tr>\n", |
||
| 645 | " <tr>\n", |
||
| 646 | " <th>380</th>\n", |
||
| 647 | " <td>diagCCS_0t30d_prevalence_21_cnt</td>\n", |
||
| 648 | " </tr>\n", |
||
| 649 | " <tr>\n", |
||
| 650 | " <th>381</th>\n", |
||
| 651 | " <td>diagCCS_30t90d_prevalence_3_cnt</td>\n", |
||
| 652 | " </tr>\n", |
||
| 653 | " <tr>\n", |
||
| 654 | " <th>382</th>\n", |
||
| 655 | " <td>diagCCS_30t90d_prevalence_4_cnt</td>\n", |
||
| 656 | " </tr>\n", |
||
| 657 | " <tr>\n", |
||
| 658 | " <th>383</th>\n", |
||
| 659 | " <td>diagCCS_30t90d_prevalence_2_cnt</td>\n", |
||
| 660 | " </tr>\n", |
||
| 661 | " <tr>\n", |
||
| 662 | " <th>384</th>\n", |
||
| 663 | " <td>operOPCSL1_365t730d_prevalence_5_cnt</td>\n", |
||
| 664 | " </tr>\n", |
||
| 665 | " <tr>\n", |
||
| 666 | " <th>385</th>\n", |
||
| 667 | " <td>diagCCS_30t90d_prevalence_5_cnt</td>\n", |
||
| 668 | " </tr>\n", |
||
| 669 | " <tr>\n", |
||
| 670 | " <th>386</th>\n", |
||
| 671 | " <td>diagCCS_0t30d_prevalence_20_cnt</td>\n", |
||
| 672 | " </tr>\n", |
||
| 673 | " <tr>\n", |
||
| 674 | " <th>387</th>\n", |
||
| 675 | " <td>diagCCS_30t90d_prevalence_6_cnt</td>\n", |
||
| 676 | " </tr>\n", |
||
| 677 | " <tr>\n", |
||
| 678 | " <th>388</th>\n", |
||
| 679 | " <td>diagCCS_30t90d_prevalence_7_cnt</td>\n", |
||
| 680 | " </tr>\n", |
||
| 681 | " <tr>\n", |
||
| 682 | " <th>389</th>\n", |
||
| 683 | " <td>diagCCS_30t90d_prevalence_8_cnt</td>\n", |
||
| 684 | " </tr>\n", |
||
| 685 | " <tr>\n", |
||
| 686 | " <th>390</th>\n", |
||
| 687 | " <td>operOPCSL1_365t730d_prevalence_6_cnt</td>\n", |
||
| 688 | " </tr>\n", |
||
| 689 | " <tr>\n", |
||
| 690 | " <th>391</th>\n", |
||
| 691 | " <td>diagCCS_90t180d_prevalence_1_cnt</td>\n", |
||
| 692 | " </tr>\n", |
||
| 693 | " <tr>\n", |
||
| 694 | " <th>392</th>\n", |
||
| 695 | " <td>diagCCS_90t180d_others_cnt</td>\n", |
||
| 696 | " </tr>\n", |
||
| 697 | " <tr>\n", |
||
| 698 | " <th>393</th>\n", |
||
| 699 | " <td>operOPCSL1_365t730d_prevalence_7_cnt</td>\n", |
||
| 700 | " </tr>\n", |
||
| 701 | " <tr>\n", |
||
| 702 | " <th>394</th>\n", |
||
| 703 | " <td>diagCCS_0t30d_prevalence_17_cnt</td>\n", |
||
| 704 | " </tr>\n", |
||
| 705 | " <tr>\n", |
||
| 706 | " <th>395</th>\n", |
||
| 707 | " <td>diagCCS_0t30d_prevalence_18_cnt</td>\n", |
||
| 708 | " </tr>\n", |
||
| 709 | " <tr>\n", |
||
| 710 | " <th>396</th>\n", |
||
| 711 | " <td>diagCCS_0t30d_prevalence_16_cnt</td>\n", |
||
| 712 | " </tr>\n", |
||
| 713 | " <tr>\n", |
||
| 714 | " <th>397</th>\n", |
||
| 715 | " <td>operOPCSL1_365t730d_prevalence_8_cnt</td>\n", |
||
| 716 | " </tr>\n", |
||
| 717 | " <tr>\n", |
||
| 718 | " <th>398</th>\n", |
||
| 719 | " <td>diagCCS_30t90d_prevalence_30_cnt</td>\n", |
||
| 720 | " </tr>\n", |
||
| 721 | " <tr>\n", |
||
| 722 | " <th>399</th>\n", |
||
| 723 | " <td>diagCCS_30t90d_prevalence_29_cnt</td>\n", |
||
| 724 | " </tr>\n", |
||
| 725 | " </tbody>\n", |
||
| 726 | "</table>\n", |
||
| 727 | "<p>400 rows × 1 columns</p>\n", |
||
| 728 | "</div>" |
||
| 729 | ], |
||
| 730 | "text/plain": [ |
||
| 731 | " 0\n", |
||
| 732 | "0 epidur_0t30d_avg\n", |
||
| 733 | "1 epidur_365t730d_avg\n", |
||
| 734 | "2 preopdur_0t30d_avg\n", |
||
| 735 | "3 gapDays_0t30d_others_cnt\n", |
||
| 736 | "4 epidur_365t730d_others_cnt\n", |
||
| 737 | "5 preopdur_30t90d_others_cnt\n", |
||
| 738 | "6 epidur_0t30d_others_cnt\n", |
||
| 739 | "7 preopdur_0t30d_others_cnt\n", |
||
| 740 | "8 epidur_30t90d_others_cnt\n", |
||
| 741 | "9 preopdur_90t180d_others_cnt\n", |
||
| 742 | "10 epidur_180t365d_avg\n", |
||
| 743 | "11 preopdur_30t90d_avg\n", |
||
| 744 | "12 preopdur_90t180d_avg\n", |
||
| 745 | "13 gapDays_365t730d_avg\n", |
||
| 746 | "14 operOPCSL1_0t30d_prevalence_1_cnt\n", |
||
| 747 | "15 operOPCSL1_0t30d_others_cnt\n", |
||
| 748 | "16 posopdur_30t90d_others_cnt\n", |
||
| 749 | "17 epidur_180t365d_others_cnt\n", |
||
| 750 | "18 posopdur_0t30d_avg\n", |
||
| 751 | "19 preopdur_180t365d_others_cnt\n", |
||
| 752 | "20 operOPCSL1_0t30d_prevalence_3_cnt\n", |
||
| 753 | "21 operOPCSL1_0t30d_prevalence_4_cnt\n", |
||
| 754 | "22 posopdur_365t730d_avg\n", |
||
| 755 | "23 operOPCSL1_0t30d_prevalence_2_cnt\n", |
||
| 756 | "24 epidur_30t90d_avg\n", |
||
| 757 | "25 posopdur_30t90d_avg\n", |
||
| 758 | "26 operOPCSL1_0t30d_prevalence_5_cnt\n", |
||
| 759 | "27 preopdur_180t365d_avg\n", |
||
| 760 | "28 preopdur_365t730d_others_cnt\n", |
||
| 761 | "29 preopdur_365t730d_avg\n", |
||
| 762 | ".. ...\n", |
||
| 763 | "370 operOPCSL1_180t365d_prevalence_30_cnt\n", |
||
| 764 | "371 diagCCS_0t30d_prevalence_25_cnt\n", |
||
| 765 | "372 diagCCS_30t90d_prevalence_1_cnt\n", |
||
| 766 | "373 diagCCS_0t30d_prevalence_23_cnt\n", |
||
| 767 | "374 diagCCS_90t180d_prevalence_5_cnt\n", |
||
| 768 | "375 diagCCS_90t180d_prevalence_4_cnt\n", |
||
| 769 | "376 diagCCS_0t30d_prevalence_19_cnt\n", |
||
| 770 | "377 operOPCSL1_365t730d_prevalence_4_cnt\n", |
||
| 771 | "378 diagCCS_90t180d_prevalence_2_cnt\n", |
||
| 772 | "379 diagCCS_90t180d_prevalence_3_cnt\n", |
||
| 773 | "380 diagCCS_0t30d_prevalence_21_cnt\n", |
||
| 774 | "381 diagCCS_30t90d_prevalence_3_cnt\n", |
||
| 775 | "382 diagCCS_30t90d_prevalence_4_cnt\n", |
||
| 776 | "383 diagCCS_30t90d_prevalence_2_cnt\n", |
||
| 777 | "384 operOPCSL1_365t730d_prevalence_5_cnt\n", |
||
| 778 | "385 diagCCS_30t90d_prevalence_5_cnt\n", |
||
| 779 | "386 diagCCS_0t30d_prevalence_20_cnt\n", |
||
| 780 | "387 diagCCS_30t90d_prevalence_6_cnt\n", |
||
| 781 | "388 diagCCS_30t90d_prevalence_7_cnt\n", |
||
| 782 | "389 diagCCS_30t90d_prevalence_8_cnt\n", |
||
| 783 | "390 operOPCSL1_365t730d_prevalence_6_cnt\n", |
||
| 784 | "391 diagCCS_90t180d_prevalence_1_cnt\n", |
||
| 785 | "392 diagCCS_90t180d_others_cnt\n", |
||
| 786 | "393 operOPCSL1_365t730d_prevalence_7_cnt\n", |
||
| 787 | "394 diagCCS_0t30d_prevalence_17_cnt\n", |
||
| 788 | "395 diagCCS_0t30d_prevalence_18_cnt\n", |
||
| 789 | "396 diagCCS_0t30d_prevalence_16_cnt\n", |
||
| 790 | "397 operOPCSL1_365t730d_prevalence_8_cnt\n", |
||
| 791 | "398 diagCCS_30t90d_prevalence_30_cnt\n", |
||
| 792 | "399 diagCCS_30t90d_prevalence_29_cnt\n", |
||
| 793 | "\n", |
||
| 794 | "[400 rows x 1 columns]" |
||
| 795 | ] |
||
| 796 | }, |
||
| 797 | "metadata": {}, |
||
| 798 | "output_type": "display_data" |
||
| 799 | } |
||
| 800 | ], |
||
| 801 | "source": [ |
||
| 802 | "file_name = \"Step_07_Top_Features_rfc_adhoc\" \n", |
||
| 803 | "\n", |
||
| 804 | "features_names_selected = readers_writers.load_csv(path=CONSTANTS.io_path, title=file_name, dataframing=False)[0]\n", |
||
| 805 | "features_names_selected = [f.replace(\"\\n\", \"\") for f in features_names_selected]\n", |
||
| 806 | "display(pd.DataFrame(features_names_selected))" |
||
| 807 | ] |
||
| 808 | }, |
||
| 809 | { |
||
| 810 | "cell_type": "markdown", |
||
| 811 | "metadata": { |
||
| 812 | "deletable": true, |
||
| 813 | "editable": true |
||
| 814 | }, |
||
| 815 | "source": [ |
||
| 816 | "### 2.4. Load the fitted model" |
||
| 817 | ] |
||
| 818 | }, |
||
| 819 | { |
||
| 820 | "cell_type": "markdown", |
||
| 821 | "metadata": { |
||
| 822 | "deletable": true, |
||
| 823 | "editable": true |
||
| 824 | }, |
||
| 825 | "source": [ |
||
| 826 | "#### <font style=\"font-weight:bold;color:blue\">2.4.1. Basic Models</font>" |
||
| 827 | ] |
||
| 828 | }, |
||
| 829 | { |
||
| 830 | "cell_type": "markdown", |
||
| 831 | "metadata": { |
||
| 832 | "deletable": true, |
||
| 833 | "editable": true |
||
| 834 | }, |
||
| 835 | "source": [ |
||
| 836 | "Initialise" |
||
| 837 | ] |
||
| 838 | }, |
||
| 839 | { |
||
| 840 | "cell_type": "code", |
||
| 841 | "execution_count": 19, |
||
| 842 | "metadata": { |
||
| 843 | "collapsed": false, |
||
| 844 | "deletable": true, |
||
| 845 | "editable": true |
||
| 846 | }, |
||
| 847 | "outputs": [ |
||
| 848 | { |
||
| 849 | "name": "stderr", |
||
| 850 | "output_type": "stream", |
||
| 851 | "text": [ |
||
| 852 | "2017-10-29 13:04:19,778 - T-CARER - INFO - Running Random Forest Classifier\n" |
||
| 853 | ] |
||
| 854 | } |
||
| 855 | ], |
||
| 856 | "source": [ |
||
| 857 | "training_method = TrainingMethod(method_name)\n", |
||
| 858 | "\n", |
||
| 859 | "# file name\n", |
||
| 860 | "file_name = \"Step_09_Model_\" + method_name + \"_\" + target_feature" |
||
| 861 | ] |
||
| 862 | }, |
||
| 863 | { |
||
| 864 | "cell_type": "markdown", |
||
| 865 | "metadata": { |
||
| 866 | "deletable": true, |
||
| 867 | "editable": true |
||
| 868 | }, |
||
| 869 | "source": [ |
||
| 870 | "Load the model" |
||
| 871 | ] |
||
| 872 | }, |
||
| 873 | { |
||
| 874 | "cell_type": "code", |
||
| 875 | "execution_count": 20, |
||
| 876 | "metadata": { |
||
| 877 | "collapsed": false, |
||
| 878 | "deletable": true, |
||
| 879 | "editable": true |
||
| 880 | }, |
||
| 881 | "outputs": [ |
||
| 882 | { |
||
| 883 | "name": "stderr", |
||
| 884 | "output_type": "stream", |
||
| 885 | "text": [ |
||
| 886 | "2017-10-29 13:04:19,866 - T-CARER - INFO - Running Random Forest Classifier\n" |
||
| 887 | ] |
||
| 888 | } |
||
| 889 | ], |
||
| 890 | "source": [ |
||
| 891 | "training_method.load(path=CONSTANTS.io_path, title=file_name)" |
||
| 892 | ] |
||
| 893 | }, |
||
| 894 | { |
||
| 895 | "cell_type": "markdown", |
||
| 896 | "metadata": { |
||
| 897 | "deletable": true, |
||
| 898 | "editable": true |
||
| 899 | }, |
||
| 900 | "source": [ |
||
| 901 | "#### <font style=\"font-weight:bold;color:blue\">2.4.2. TensorFlow Models</font>" |
||
| 902 | ] |
||
| 903 | }, |
||
| 904 | { |
||
| 905 | "cell_type": "code", |
||
| 906 | "execution_count": 21, |
||
| 907 | "metadata": { |
||
| 908 | "collapsed": false, |
||
| 909 | "deletable": true, |
||
| 910 | "editable": true |
||
| 911 | }, |
||
| 912 | "outputs": [], |
||
| 913 | "source": [ |
||
| 914 | "class TrainingMethodTensorflow: \n", |
||
| 915 | " def __init__(self, summaries, features_names, num_features, cut_off, train_size, test_size):\n", |
||
| 916 | " self.model_predict = {\"train\": {'score': [], 'model_labels': []}, \n", |
||
| 917 | " \"test\": {'score': [], 'model_labels': []}}\n", |
||
| 918 | " self.__stats = Stats()\n", |
||
| 919 | " # summaries[\"fit\"][\"get_variable_names\"]\n", |
||
| 920 | " # summaries[\"fit\"][\"get_variable_value\"]\n", |
||
| 921 | " # summaries[\"fit\"][\"get_params\"]\n", |
||
| 922 | " # summaries[\"fit\"][\"export\"]\n", |
||
| 923 | " # summaries[\"fit\"][\"get_variable_names()\"]\n", |
||
| 924 | " # summaries[\"fit\"][\"params\"]\n", |
||
| 925 | " # summaries[\"fit\"][\"dnn_bias_\"]\n", |
||
| 926 | " # summaries[\"fit\"][\"dnn_weights_\"] \n", |
||
| 927 | " # summaries[\"train\"][\"results\"]\n", |
||
| 928 | " # summaries[\"test\"][\"results\"]\n", |
||
| 929 | " \n", |
||
| 930 | " self.model_predict[\"train\"]['pred'] = np.asarray([1 if i[1] >= 0.5 else 0 for i in summaries[\"train\"][\"predict_proba\"]][0:train_size])\n", |
||
| 931 | " self.model_predict[\"test\"]['pred'] = np.asarray([1 if i[1] >= 0.5 else 0 for i in summaries[\"test\"][\"predict_proba\"]][0:test_size])\n", |
||
| 932 | " \n", |
||
| 933 | " self.model_predict[\"train\"]['score'] = np.asarray([i[1] for i in summaries[\"train\"][\"predict_proba\"]][0:train_size])\n", |
||
| 934 | " self.model_predict[\"test\"]['score'] = np.asarray([i[1] for i in summaries[\"test\"][\"predict_proba\"]][0:test_size])\n", |
||
| 935 | " \n", |
||
| 936 | " self.model_predict[\"train\"]['score_0'] = np.asarray([i[0] for i in summaries[\"train\"][\"predict_proba\"]][0:train_size])\n", |
||
| 937 | " self.model_predict[\"test\"]['score_0'] = np.asarray([i[0] for i in summaries[\"test\"][\"predict_proba\"]][0:test_size])\n", |
||
| 938 | " \n", |
||
| 939 | " def train_summaries(self):\n", |
||
| 940 | " return {\"feature_importances_\": self.__weights}\n", |
||
| 941 | " \n", |
||
| 942 | " def predict_summaries(self, feature_target, sample_name):\n", |
||
| 943 | " return self.__stats.predict_summaries(self.model_predict[sample_name], feature_target)" |
||
| 944 | ] |
||
| 945 | }, |
||
| 946 | { |
||
| 947 | "cell_type": "code", |
||
| 948 | "execution_count": 22, |
||
| 949 | "metadata": { |
||
| 950 | "collapsed": false, |
||
| 951 | "deletable": true, |
||
| 952 | "editable": true |
||
| 953 | }, |
||
| 954 | "outputs": [ |
||
| 955 | { |
||
| 956 | "name": "stderr", |
||
| 957 | "output_type": "stream", |
||
| 958 | "text": [ |
||
| 959 | "2017-10-29 13:04:20,044 - T-CARER - ERROR - ReadersWriters._PickleSerialised - Can not open the file: \n", |
||
| 960 | "C:\\Users\\eagle\\Documents\\GitHub\\tmp\\TCARER\\Basic_prototype\\model_tensorflow_summaries_label365.bz2\n", |
||
| 961 | "\n" |
||
| 962 | ] |
||
| 963 | }, |
||
| 964 | { |
||
| 965 | "name": "stdout", |
||
| 966 | "output_type": "stream", |
||
| 967 | "text": [ |
||
| 968 | "[Errno 2] No such file or directory: 'C:\\\\Users\\\\eagle\\\\Documents\\\\GitHub\\\\tmp\\\\TCARER\\\\Basic_prototype\\\\model_tensorflow_summaries_label365.bz2'\n" |
||
| 969 | ] |
||
| 970 | }, |
||
| 971 | { |
||
| 972 | "ename": "SystemExit", |
||
| 973 | "evalue": "", |
||
| 974 | "output_type": "error", |
||
| 975 | "traceback": [ |
||
| 976 | "An exception has occurred, use %tb to see the full traceback.\n", |
||
| 977 | "\u001b[0;31mSystemExit\u001b[0m\n" |
||
| 978 | ] |
||
| 979 | }, |
||
| 980 | { |
||
| 981 | "name": "stderr", |
||
| 982 | "output_type": "stream", |
||
| 983 | "text": [ |
||
| 984 | "c:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\IPython\\core\\interactiveshell.py:2889: UserWarning: To exit: use 'exit', 'quit', or Ctrl-D.\n", |
||
| 985 | " warn(\"To exit: use 'exit', 'quit', or Ctrl-D.\", stacklevel=1)\n" |
||
| 986 | ] |
||
| 987 | } |
||
| 988 | ], |
||
| 989 | "source": [ |
||
| 990 | "file_name = \"model_tensorflow_summaries_\" + target_feature\n", |
||
| 991 | "summaries = readers_writers.load_serialised_compressed(path=CONSTANTS.io_path, title=file_name)" |
||
| 992 | ] |
||
| 993 | }, |
||
| 994 | { |
||
| 995 | "cell_type": "code", |
||
| 996 | "execution_count": null, |
||
| 997 | "metadata": { |
||
| 998 | "collapsed": false, |
||
| 999 | "deletable": true, |
||
| 1000 | "editable": true |
||
| 1001 | }, |
||
| 1002 | "outputs": [], |
||
| 1003 | "source": [ |
||
| 1004 | "num_features = 300\n", |
||
| 1005 | "cut_off = 0.5\n", |
||
| 1006 | "\n", |
||
| 1007 | "training_method = TrainingMethodTensorflow(summaries, features_names_selected, num_features, cut_off,\n", |
||
| 1008 | " len(features[\"train_indep\"].index), len(features[\"test_indep\"].index))" |
||
| 1009 | ] |
||
| 1010 | }, |
||
| 1011 | { |
||
| 1012 | "cell_type": "markdown", |
||
| 1013 | "metadata": { |
||
| 1014 | "deletable": true, |
||
| 1015 | "editable": true |
||
| 1016 | }, |
||
| 1017 | "source": [ |
||
| 1018 | "<br/><br/>" |
||
| 1019 | ] |
||
| 1020 | }, |
||
| 1021 | { |
||
| 1022 | "cell_type": "markdown", |
||
| 1023 | "metadata": { |
||
| 1024 | "deletable": true, |
||
| 1025 | "editable": true |
||
| 1026 | }, |
||
| 1027 | "source": [ |
||
| 1028 | "Performance" |
||
| 1029 | ] |
||
| 1030 | }, |
||
| 1031 | { |
||
| 1032 | "cell_type": "code", |
||
| 1033 | "execution_count": 23, |
||
| 1034 | "metadata": { |
||
| 1035 | "collapsed": false, |
||
| 1036 | "deletable": true, |
||
| 1037 | "editable": true |
||
| 1038 | }, |
||
| 1039 | "outputs": [ |
||
| 1040 | { |
||
| 1041 | "name": "stdout", |
||
| 1042 | "output_type": "stream", |
||
| 1043 | "text": [ |
||
| 1044 | "accuracy_score 0.6592\n", |
||
| 1045 | "average_precision_score 0.47970482114\n", |
||
| 1046 | "brier_score_loss 0.218148003816\n", |
||
| 1047 | "classification_report precision recall f1-score support\n", |
||
| 1048 | "\n", |
||
| 1049 | " 0 0.88 0.63 0.74 1885\n", |
||
| 1050 | " 1 0.40 0.74 0.52 615\n", |
||
| 1051 | "\n", |
||
| 1052 | "avg / total 0.76 0.66 0.68 2500\n", |
||
| 1053 | "\n", |
||
| 1054 | "confusion_matrix [[1194 691]\n", |
||
| 1055 | " [ 161 454]]\n", |
||
| 1056 | "f1_score 0.515909090909\n", |
||
| 1057 | "fbeta_score 0.436958614052\n", |
||
| 1058 | "hamming_loss 0.3408\n", |
||
| 1059 | "jaccard_similarity_score 0.6592\n", |
||
| 1060 | "log_loss 11.7710360041\n", |
||
| 1061 | "matthews_corrcoef 0.32124418171\n", |
||
| 1062 | "precision_recall_fscore_support (array([ 0.88118081, 0.39650655]), array([ 0.63342175, 0.73821138]), array([ 0.73703704, 0.51590909]), array([1885, 615], dtype=int64))\n", |
||
| 1063 | "precision_score 0.396506550218\n", |
||
| 1064 | "recall_score 0.738211382114\n", |
||
| 1065 | "roc_auc_score 0.742965646633\n", |
||
| 1066 | "zero_one_loss 0.3408\n", |
||
| 1067 | "\n", |
||
| 1068 | "\n", |
||
| 1069 | "accuracy_score 0.654661864746\n", |
||
| 1070 | "average_precision_score 0.423030738094\n", |
||
| 1071 | "brier_score_loss 0.22022287805\n", |
||
| 1072 | "classification_report precision recall f1-score support\n", |
||
| 1073 | "\n", |
||
| 1074 | " 0 0.90 0.63 0.74 1959\n", |
||
| 1075 | " 1 0.36 0.75 0.48 540\n", |
||
| 1076 | "\n", |
||
| 1077 | "avg / total 0.78 0.65 0.69 2499\n", |
||
| 1078 | "\n", |
||
| 1079 | "confusion_matrix [[1230 729]\n", |
||
| 1080 | " [ 134 406]]\n", |
||
| 1081 | "f1_score 0.484776119403\n", |
||
| 1082 | "fbeta_score 0.399606299213\n", |
||
| 1083 | "hamming_loss 0.345338135254\n", |
||
| 1084 | "jaccard_similarity_score 0.654661864746\n", |
||
| 1085 | "log_loss 11.9277898901\n", |
||
| 1086 | "matthews_corrcoef 0.313889024973\n", |
||
| 1087 | "precision_recall_fscore_support (array([ 0.90175953, 0.35770925]), array([ 0.62787136, 0.75185185]), array([ 0.74029491, 0.48477612]), array([1959, 540], dtype=int64))\n", |
||
| 1088 | "precision_score 0.357709251101\n", |
||
| 1089 | "recall_score 0.751851851852\n", |
||
| 1090 | "roc_auc_score 0.73645898323\n", |
||
| 1091 | "zero_one_loss 0.345338135254\n" |
||
| 1092 | ] |
||
| 1093 | } |
||
| 1094 | ], |
||
| 1095 | "source": [ |
||
| 1096 | "# train\n", |
||
| 1097 | "o_summaries = training_method.predict_summaries(features[\"train_target\"][target_feature], \"train\")\n", |
||
| 1098 | "for k in o_summaries.keys():\n", |
||
| 1099 | " print(k, o_summaries[k])\n", |
||
| 1100 | " \n", |
||
| 1101 | "print(\"\\n\")\n", |
||
| 1102 | "# test\n", |
||
| 1103 | "o_summaries = training_method.predict_summaries(features[\"test_target\"][target_feature], \"test\")\n", |
||
| 1104 | "for k in o_summaries.keys():\n", |
||
| 1105 | " print(k, o_summaries[k])" |
||
| 1106 | ] |
||
| 1107 | }, |
||
| 1108 | { |
||
| 1109 | "cell_type": "markdown", |
||
| 1110 | "metadata": { |
||
| 1111 | "deletable": true, |
||
| 1112 | "editable": true |
||
| 1113 | }, |
||
| 1114 | "source": [ |
||
| 1115 | "<br/><br/>" |
||
| 1116 | ] |
||
| 1117 | }, |
||
| 1118 | { |
||
| 1119 | "cell_type": "markdown", |
||
| 1120 | "metadata": { |
||
| 1121 | "deletable": true, |
||
| 1122 | "editable": true |
||
| 1123 | }, |
||
| 1124 | "source": [ |
||
| 1125 | "### 2.5. Load the Extra Features for Benchmarking" |
||
| 1126 | ] |
||
| 1127 | }, |
||
| 1128 | { |
||
| 1129 | "cell_type": "markdown", |
||
| 1130 | "metadata": { |
||
| 1131 | "deletable": true, |
||
| 1132 | "editable": true |
||
| 1133 | }, |
||
| 1134 | "source": [ |
||
| 1135 | "Read the extra features" |
||
| 1136 | ] |
||
| 1137 | }, |
||
| 1138 | { |
||
| 1139 | "cell_type": "code", |
||
| 1140 | "execution_count": 24, |
||
| 1141 | "metadata": { |
||
| 1142 | "collapsed": false, |
||
| 1143 | "deletable": true, |
||
| 1144 | "editable": true |
||
| 1145 | }, |
||
| 1146 | "outputs": [], |
||
| 1147 | "source": [ |
||
| 1148 | "table = 'tcarer_featuresExtra'\n", |
||
| 1149 | "features_extra_dtypes = {'patientID': 'U32', 'trigger_charlsonFoster': 'i4', 'trigger_los': 'i4', 'trigger_age': 'i4', 'prior_admiOther': 'i4', 'prior_admiAcute': 'i4', \n", |
||
| 1150 | " 'prior_spells': 'i4', 'prior_asthma': 'i4', 'prior_copd': 'i4', 'prior_depression': 'i4', 'prior_diabetes': 'i4', 'prior_hypertension': 'i4', 'prior_cancer': 'i4', 'prior_chd': 'i4', 'prior_chf': 'i4', \n", |
||
| 1151 | " 'diagCci_01_myocardial_freq': 'i4', 'diagCci_02_chf_freq': 'i4', 'diagCci_03_pvd_freq': 'i4', 'diagCci_04_cerebrovascular_freq': 'i4', 'diagCci_05_dementia_freq': 'i4', 'diagCci_06_cpd_freq': 'i4', 'diagCci_07_rheumatic_freq': 'i4', 'diagCci_08_ulcer_freq': 'i4', 'diagCci_09_liverMild_freq': 'i4', 'diagCci_10_diabetesNotChronic_freq': 'i4', 'diagCci_11_diabetesChronic_freq': 'i4', 'diagCci_12_hemiplegia_freq': 'i4', 'diagCci_13_renal_freq': 'i4', 'diagCci_14_malignancy_freq': 'i4', 'diagCci_15_liverSevere_freq': 'i4', 'diagCci_16_tumorSec_freq': 'i4', 'diagCci_17_aids_freq': 'i4', 'diagCci_18_depression_freq': 'i4', 'diagCci_19_cardiac_freq': 'i4', 'diagCci_20_valvular_freq': 'i4', 'diagCci_21_pulmonary_freq': 'i4', 'diagCci_22_vascular_freq': 'i4', 'diagCci_23_hypertensionNotComplicated_freq': 'i4', 'diagCci_24_hypertensionComplicated_freq': 'i4', 'diagCci_25_paralysis_freq': 'i4', 'diagCci_26_neuroOther_freq': 'i4', 'diagCci_27_pulmonaryChronic_freq': 'i4', 'diagCci_28_diabetesNotComplicated_freq': 'i4', 'diagCci_29_diabetesComplicated_freq': 'i4', 'diagCci_30_hypothyroidism_freq': 'i4', 'diagCci_31_renal_freq': 'i4', 'diagCci_32_liver_freq': 'i4', 'diagCci_33_ulcerNotBleeding_freq': 'i4', 'diagCci_34_psychoses_freq': 'i4', 'diagCci_35_lymphoma_freq': 'i4', 'diagCci_36_cancerSec_freq': 'i4', 'diagCci_37_tumorNotSec_freq': 'i4', 'diagCci_38_rheumatoid_freq': 'i4', 'diagCci_39_coagulopathy_freq': 'i4', 'diagCci_40_obesity_freq': 'i4', 'diagCci_41_weightLoss_freq': 'i4', 'diagCci_42_fluidDisorder_freq': 'i4', 'diagCci_43_bloodLoss_freq': 'i4', 'diagCci_44_anemia_freq': 'i4', 'diagCci_45_alcohol_freq': 'i4', 'diagCci_46_drug_freq': 'i4'}\n", |
||
| 1152 | "features_extra_name = features_extra_dtypes.keys()" |
||
| 1153 | ] |
||
| 1154 | }, |
||
| 1155 | { |
||
| 1156 | "cell_type": "code", |
||
| 1157 | "execution_count": 25, |
||
| 1158 | "metadata": { |
||
| 1159 | "collapsed": false, |
||
| 1160 | "deletable": true, |
||
| 1161 | "editable": true |
||
| 1162 | }, |
||
| 1163 | "outputs": [ |
||
| 1164 | { |
||
| 1165 | "ename": "ProgrammingError", |
||
| 1166 | "evalue": "(_mysql_exceptions.ProgrammingError) (1146, \"Table 'parr_sample_prototype.tcarer_featuresextra' doesn't exist\") [SQL: 'SELECT * FROM tcarer_featuresExtra']", |
||
| 1167 | "output_type": "error", |
||
| 1168 | "traceback": [ |
||
| 1169 | "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", |
||
| 1170 | "\u001b[0;31mProgrammingError\u001b[0m Traceback (most recent call last)", |
||
| 1171 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\sqlalchemy\\engine\\base.py\u001b[0m in \u001b[0;36m_execute_context\u001b[0;34m(self, dialect, constructor, statement, parameters, *args)\u001b[0m\n\u001b[1;32m 1181\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1182\u001b[0;31m context)\n\u001b[0m\u001b[1;32m 1183\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mBaseException\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1172 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\sqlalchemy\\engine\\default.py\u001b[0m in \u001b[0;36mdo_execute\u001b[0;34m(self, cursor, statement, parameters, context)\u001b[0m\n\u001b[1;32m 469\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mdo_execute\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcursor\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mstatement\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcontext\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 470\u001b[0;31m \u001b[0mcursor\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mexecute\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mstatement\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 471\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1173 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\MySQLdb\\cursors.py\u001b[0m in \u001b[0;36mexecute\u001b[0;34m(self, query, args)\u001b[0m\n\u001b[1;32m 249\u001b[0m \u001b[0mexc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0msys\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mexc_info\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;36m2\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 250\u001b[0;31m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0merrorhandler\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mexc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 251\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_executed\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mquery\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1174 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\MySQLdb\\connections.py\u001b[0m in \u001b[0;36mdefaulterrorhandler\u001b[0;34m(***failed resolving arguments***)\u001b[0m\n\u001b[1;32m 41\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0merrorvalue\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mBaseException\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m---> 42\u001b[0;31m \u001b[1;32mraise\u001b[0m \u001b[0merrorvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 43\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0merrorclass\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1175 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\MySQLdb\\cursors.py\u001b[0m in \u001b[0;36mexecute\u001b[0;34m(self, query, args)\u001b[0m\n\u001b[1;32m 246\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 247\u001b[0;31m \u001b[0mres\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_query\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mquery\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 248\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mException\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1176 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\MySQLdb\\cursors.py\u001b[0m in \u001b[0;36m_query\u001b[0;34m(self, q)\u001b[0m\n\u001b[1;32m 410\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_query\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mq\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 411\u001b[0;31m \u001b[0mrowcount\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_do_query\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mq\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 412\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_post_get_result\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1177 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\MySQLdb\\cursors.py\u001b[0m in \u001b[0;36m_do_query\u001b[0;34m(self, q)\u001b[0m\n\u001b[1;32m 373\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_last_executed\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mq\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 374\u001b[0;31m \u001b[0mdb\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mquery\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mq\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 375\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_do_get_result\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1178 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\MySQLdb\\connections.py\u001b[0m in \u001b[0;36mquery\u001b[0;34m(self, query)\u001b[0m\n\u001b[1;32m 269\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 270\u001b[0;31m \u001b[0m_mysql\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mconnection\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mquery\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mquery\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 271\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1179 | "\u001b[0;31mProgrammingError\u001b[0m: (1146, \"Table 'parr_sample_prototype.tcarer_featuresextra' doesn't exist\")", |
||
| 1180 | "\nThe above exception was the direct cause of the following exception:\n", |
||
| 1181 | "\u001b[0;31mProgrammingError\u001b[0m Traceback (most recent call last)", |
||
| 1182 | "\u001b[0;32m<ipython-input-25-086a730ff34b>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[1;31m# Read features from the MySQL\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0mfeatures_extra\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdict\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0mfeatures_extra\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'train'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mreaders_writers\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mload_mysql_table\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mschema\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtable\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdataframing\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 4\u001b[0m \u001b[0mfeatures_extra\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'train'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mastype\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdtype\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mfeatures_extra_dtypes\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0mfeatures_extra\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'test'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mfeatures_extra\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'train'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1183 | "\u001b[0;32mC:\\Users\\eagle\\Documents\\GitHub\\Analytics_UoW\\TCARER\\ReadersWriters\\ReadersWriters.py\u001b[0m in \u001b[0;36mload_mysql_table\u001b[0;34m(db_schema, db_table, dataframing)\u001b[0m\n\u001b[1;32m 323\u001b[0m \"\"\"\n\u001b[1;32m 324\u001b[0m \u001b[0mquery\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;34m\"SELECT * FROM \"\u001b[0m \u001b[1;33m+\u001b[0m \u001b[0mdb_table\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 325\u001b[0;31m \u001b[1;32mreturn\u001b[0m \u001b[0mReadersWriters\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mload_mysql_query\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mquery\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdb_schema\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdataframing\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 326\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 327\u001b[0m \u001b[1;33m@\u001b[0m\u001b[0mstaticmethod\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1184 | "\u001b[0;32mC:\\Users\\eagle\\Documents\\GitHub\\Analytics_UoW\\TCARER\\ReadersWriters\\ReadersWriters.py\u001b[0m in \u001b[0;36mload_mysql_query\u001b[0;34m(query, db_schema, dataframing, batch, float_round_vars, float_round)\u001b[0m\n\u001b[1;32m 345\u001b[0m \u001b[0mengine\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdb\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mopen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 346\u001b[0m \u001b[0mdbc\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mMysqlCommand\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mengine\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdb\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdb_session_vars\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 347\u001b[0;31m \u001b[0moutput\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdbc\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mquery\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdataframing\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mbatch\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfloat_round_vars\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfloat_round\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 348\u001b[0m \u001b[0mdb\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 349\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0moutput\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1185 | "\u001b[0;32mC:\\Users\\eagle\\Documents\\GitHub\\Analytics_UoW\\TCARER\\ReadersWriters\\_MysqlCommand.py\u001b[0m in \u001b[0;36mread\u001b[0;34m(self, query, dataframing, batch, float_round_vars, float_round)\u001b[0m\n\u001b[1;32m 71\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__logger\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdebug\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Reading from MySQL database.\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 72\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mdataframing\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m---> 73\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__read_df\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mquery\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mbatch\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfloat_round_vars\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfloat_round\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 74\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 75\u001b[0m \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__read_arr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mquery\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1186 | "\u001b[0;32mC:\\Users\\eagle\\Documents\\GitHub\\Analytics_UoW\\TCARER\\ReadersWriters\\_MysqlCommand.py\u001b[0m in \u001b[0;36m__read_df\u001b[0;34m(self, query, batch, float_round_vars, float_round)\u001b[0m\n\u001b[1;32m 104\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 105\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mbatch\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 106\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpds\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread_sql\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msql\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mquery\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcon\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mconn\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcoerce_float\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mchunksize\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mbatch\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 107\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 108\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mdf\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mpds\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread_sql\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msql\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mquery\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcon\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mconn\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcoerce_float\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mchunksize\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mbatch\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1187 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\pandas\\io\\sql.py\u001b[0m in \u001b[0;36mread_sql\u001b[0;34m(sql, con, index_col, coerce_float, params, parse_dates, columns, chunksize)\u001b[0m\n\u001b[1;32m 413\u001b[0m \u001b[0msql\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex_col\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mindex_col\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mparams\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 414\u001b[0m \u001b[0mcoerce_float\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mcoerce_float\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparse_dates\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mparse_dates\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 415\u001b[0;31m chunksize=chunksize)\n\u001b[0m\u001b[1;32m 416\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 417\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1188 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\pandas\\io\\sql.py\u001b[0m in \u001b[0;36mread_query\u001b[0;34m(self, sql, index_col, coerce_float, parse_dates, params, chunksize)\u001b[0m\n\u001b[1;32m 1082\u001b[0m \u001b[0margs\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_convert_params\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msql\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 1083\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1084\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mexecute\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1085\u001b[0m \u001b[0mcolumns\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mresult\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkeys\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 1086\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1189 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\pandas\\io\\sql.py\u001b[0m in \u001b[0;36mexecute\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 973\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mexecute\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 974\u001b[0m \u001b[1;34m\"\"\"Simple passthrough to SQLAlchemy connectable\"\"\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 975\u001b[0;31m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mconnectable\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mexecute\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 976\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 977\u001b[0m def read_table(self, table_name, index_col=None, coerce_float=True,\n", |
||
| 1190 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\sqlalchemy\\engine\\base.py\u001b[0m in \u001b[0;36mexecute\u001b[0;34m(self, object, *multiparams, **params)\u001b[0m\n\u001b[1;32m 937\u001b[0m \"\"\"\n\u001b[1;32m 938\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobject\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mutil\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mstring_types\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 939\u001b[0;31m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_execute_text\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobject\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmultiparams\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 940\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 941\u001b[0m \u001b[0mmeth\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mobject\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_execute_on_connection\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1191 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\sqlalchemy\\engine\\base.py\u001b[0m in \u001b[0;36m_execute_text\u001b[0;34m(self, statement, multiparams, params)\u001b[0m\n\u001b[1;32m 1095\u001b[0m \u001b[0mstatement\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 1096\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1097\u001b[0;31m \u001b[0mstatement\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1098\u001b[0m )\n\u001b[1;32m 1099\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_has_events\u001b[0m \u001b[1;32mor\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mengine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_has_events\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1192 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\sqlalchemy\\engine\\base.py\u001b[0m in \u001b[0;36m_execute_context\u001b[0;34m(self, dialect, constructor, statement, parameters, *args)\u001b[0m\n\u001b[1;32m 1187\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 1188\u001b[0m \u001b[0mcursor\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1189\u001b[0;31m context)\n\u001b[0m\u001b[1;32m 1190\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 1191\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_has_events\u001b[0m \u001b[1;32mor\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mengine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_has_events\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1193 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\sqlalchemy\\engine\\base.py\u001b[0m in \u001b[0;36m_handle_dbapi_exception\u001b[0;34m(self, e, statement, parameters, cursor, context)\u001b[0m\n\u001b[1;32m 1391\u001b[0m util.raise_from_cause(\n\u001b[1;32m 1392\u001b[0m \u001b[0msqlalchemy_exception\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1393\u001b[0;31m \u001b[0mexc_info\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1394\u001b[0m )\n\u001b[1;32m 1395\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1194 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\sqlalchemy\\util\\compat.py\u001b[0m in \u001b[0;36mraise_from_cause\u001b[0;34m(exception, exc_info)\u001b[0m\n\u001b[1;32m 201\u001b[0m \u001b[0mexc_type\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mexc_value\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mexc_tb\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mexc_info\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 202\u001b[0m \u001b[0mcause\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mexc_value\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mexc_value\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mexception\u001b[0m \u001b[1;32melse\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 203\u001b[0;31m \u001b[0mreraise\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtype\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mexception\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mexception\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtb\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mexc_tb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcause\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mcause\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 204\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 205\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mpy3k\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1195 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\sqlalchemy\\util\\compat.py\u001b[0m in \u001b[0;36mreraise\u001b[0;34m(tp, value, tb, cause)\u001b[0m\n\u001b[1;32m 184\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__cause__\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcause\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 185\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__traceback__\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mtb\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 186\u001b[0;31m \u001b[1;32mraise\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mwith_traceback\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtb\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 187\u001b[0m \u001b[1;32mraise\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 188\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1196 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\sqlalchemy\\engine\\base.py\u001b[0m in \u001b[0;36m_execute_context\u001b[0;34m(self, dialect, constructor, statement, parameters, *args)\u001b[0m\n\u001b[1;32m 1180\u001b[0m \u001b[0mstatement\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 1181\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1182\u001b[0;31m context)\n\u001b[0m\u001b[1;32m 1183\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mBaseException\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 1184\u001b[0m self._handle_dbapi_exception(\n", |
||
| 1197 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\sqlalchemy\\engine\\default.py\u001b[0m in \u001b[0;36mdo_execute\u001b[0;34m(self, cursor, statement, parameters, context)\u001b[0m\n\u001b[1;32m 468\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 469\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mdo_execute\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcursor\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mstatement\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcontext\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 470\u001b[0;31m \u001b[0mcursor\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mexecute\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mstatement\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparameters\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 471\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 472\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mdo_execute_no_params\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcursor\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mstatement\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcontext\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1198 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\MySQLdb\\cursors.py\u001b[0m in \u001b[0;36mexecute\u001b[0;34m(self, query, args)\u001b[0m\n\u001b[1;32m 248\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mException\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 249\u001b[0m \u001b[0mexc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0msys\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mexc_info\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;36m2\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 250\u001b[0;31m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0merrorhandler\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mexc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 251\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_executed\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mquery\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 252\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_defer_warnings\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1199 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\MySQLdb\\connections.py\u001b[0m in \u001b[0;36mdefaulterrorhandler\u001b[0;34m(***failed resolving arguments***)\u001b[0m\n\u001b[1;32m 40\u001b[0m \u001b[1;32mdel\u001b[0m \u001b[0mconnection\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 41\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0merrorvalue\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mBaseException\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m---> 42\u001b[0;31m \u001b[1;32mraise\u001b[0m \u001b[0merrorvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 43\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0merrorclass\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 44\u001b[0m \u001b[1;32mraise\u001b[0m \u001b[0merrorclass\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0merrorvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1200 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\MySQLdb\\cursors.py\u001b[0m in \u001b[0;36mexecute\u001b[0;34m(self, query, args)\u001b[0m\n\u001b[1;32m 245\u001b[0m \u001b[0mres\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 246\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 247\u001b[0;31m \u001b[0mres\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_query\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mquery\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 248\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mException\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 249\u001b[0m \u001b[0mexc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0msys\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mexc_info\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;36m2\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1201 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\MySQLdb\\cursors.py\u001b[0m in \u001b[0;36m_query\u001b[0;34m(self, q)\u001b[0m\n\u001b[1;32m 409\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 410\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_query\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mq\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 411\u001b[0;31m \u001b[0mrowcount\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_do_query\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mq\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 412\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_post_get_result\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 413\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mrowcount\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1202 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\MySQLdb\\cursors.py\u001b[0m in \u001b[0;36m_do_query\u001b[0;34m(self, q)\u001b[0m\n\u001b[1;32m 372\u001b[0m \u001b[0mdb\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_get_db\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 373\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_last_executed\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mq\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 374\u001b[0;31m \u001b[0mdb\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mquery\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mq\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 375\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_do_get_result\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 376\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrowcount\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1203 | "\u001b[0;32mc:\\users\\eagle\\appdata\\local\\programs\\python\\python35\\lib\\site-packages\\MySQLdb\\connections.py\u001b[0m in \u001b[0;36mquery\u001b[0;34m(self, query)\u001b[0m\n\u001b[1;32m 268\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread_query_result\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 269\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m--> 270\u001b[0;31m \u001b[0m_mysql\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mconnection\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mquery\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mquery\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 271\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m 272\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m__enter__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", |
||
| 1204 | "\u001b[0;31mProgrammingError\u001b[0m: (_mysql_exceptions.ProgrammingError) (1146, \"Table 'parr_sample_prototype.tcarer_featuresextra' doesn't exist\") [SQL: 'SELECT * FROM tcarer_featuresExtra']" |
||
| 1205 | ] |
||
| 1206 | } |
||
| 1207 | ], |
||
| 1208 | "source": [ |
||
| 1209 | "# Read features from the MySQL\n", |
||
| 1210 | "features_extra = dict()\n", |
||
| 1211 | "features_extra['train'] = readers_writers.load_mysql_table(schema, table, dataframing=True)\n", |
||
| 1212 | "features_extra['train'].astype(dtype=features_extra_dtypes)\n", |
||
| 1213 | "features_extra['test'] = features_extra['train']\n", |
||
| 1214 | "\n", |
||
| 1215 | "print(\"Number of columns: \", len(features_extra['train'].columns), \"; Total records: \", len(features_extra['train'].index))" |
||
| 1216 | ] |
||
| 1217 | }, |
||
| 1218 | { |
||
| 1219 | "cell_type": "markdown", |
||
| 1220 | "metadata": { |
||
| 1221 | "deletable": true, |
||
| 1222 | "editable": true |
||
| 1223 | }, |
||
| 1224 | "source": [ |
||
| 1225 | "Replace NaN appears in the Charlson-Index feature " |
||
| 1226 | ] |
||
| 1227 | }, |
||
| 1228 | { |
||
| 1229 | "cell_type": "code", |
||
| 1230 | "execution_count": null, |
||
| 1231 | "metadata": { |
||
| 1232 | "collapsed": true, |
||
| 1233 | "deletable": true, |
||
| 1234 | "editable": true |
||
| 1235 | }, |
||
| 1236 | "outputs": [], |
||
| 1237 | "source": [ |
||
| 1238 | "features_extra['train'].loc[:, \"trigger_charlsonFoster\"] = np.nan_to_num(features_extra['train'][\"trigger_charlsonFoster\"])\n", |
||
| 1239 | "features_extra['test'].loc[:, \"trigger_charlsonFoster\"] = np.nan_to_num(features_extra['test'][\"trigger_charlsonFoster\"])" |
||
| 1240 | ] |
||
| 1241 | }, |
||
| 1242 | { |
||
| 1243 | "cell_type": "markdown", |
||
| 1244 | "metadata": { |
||
| 1245 | "deletable": true, |
||
| 1246 | "editable": true |
||
| 1247 | }, |
||
| 1248 | "source": [ |
||
| 1249 | "Combine (join by PatientID)" |
||
| 1250 | ] |
||
| 1251 | }, |
||
| 1252 | { |
||
| 1253 | "cell_type": "code", |
||
| 1254 | "execution_count": null, |
||
| 1255 | "metadata": { |
||
| 1256 | "collapsed": false, |
||
| 1257 | "deletable": true, |
||
| 1258 | "editable": true |
||
| 1259 | }, |
||
| 1260 | "outputs": [], |
||
| 1261 | "source": [ |
||
| 1262 | "features_extra['train'] = features_extra['train'].merge(\n", |
||
| 1263 | " pd.concat([features['train_id'], features['train_target'], \n", |
||
| 1264 | " pd.DataFrame({'score': training_method.model_predict[\"train\"]['score']}), features['train_indep']], axis=1), \n", |
||
| 1265 | " how=\"inner\", on=\"patientID\")\n", |
||
| 1266 | "features_extra['test'] = features_extra['test'].merge(\n", |
||
| 1267 | " pd.concat([features['test_id'], features['test_target'], \n", |
||
| 1268 | " pd.DataFrame({'score': training_method.model_predict[\"test\"]['score']}), features['test_indep']], axis=1), \n", |
||
| 1269 | " how=\"inner\", on=\"patientID\")" |
||
| 1270 | ] |
||
| 1271 | }, |
||
| 1272 | { |
||
| 1273 | "cell_type": "markdown", |
||
| 1274 | "metadata": { |
||
| 1275 | "deletable": true, |
||
| 1276 | "editable": true |
||
| 1277 | }, |
||
| 1278 | "source": [ |
||
| 1279 | "<font style=\"font-weight:bold;color:red\">Clean-up</font>" |
||
| 1280 | ] |
||
| 1281 | }, |
||
| 1282 | { |
||
| 1283 | "cell_type": "code", |
||
| 1284 | "execution_count": null, |
||
| 1285 | "metadata": { |
||
| 1286 | "collapsed": false, |
||
| 1287 | "deletable": true, |
||
| 1288 | "editable": true, |
||
| 1289 | "scrolled": true |
||
| 1290 | }, |
||
| 1291 | "outputs": [], |
||
| 1292 | "source": [ |
||
| 1293 | "features = None\n", |
||
| 1294 | "gc.collect()" |
||
| 1295 | ] |
||
| 1296 | }, |
||
| 1297 | { |
||
| 1298 | "cell_type": "markdown", |
||
| 1299 | "metadata": { |
||
| 1300 | "deletable": true, |
||
| 1301 | "editable": true |
||
| 1302 | }, |
||
| 1303 | "source": [ |
||
| 1304 | "<br/><br/>" |
||
| 1305 | ] |
||
| 1306 | }, |
||
| 1307 | { |
||
| 1308 | "cell_type": "markdown", |
||
| 1309 | "metadata": { |
||
| 1310 | "deletable": true, |
||
| 1311 | "editable": true |
||
| 1312 | }, |
||
| 1313 | "source": [ |
||
| 1314 | "## 3. Charlson Index Model" |
||
| 1315 | ] |
||
| 1316 | }, |
||
| 1317 | { |
||
| 1318 | "cell_type": "markdown", |
||
| 1319 | "metadata": { |
||
| 1320 | "deletable": true, |
||
| 1321 | "editable": true |
||
| 1322 | }, |
||
| 1323 | "source": [ |
||
| 1324 | "### 3.1. Algorithm" |
||
| 1325 | ] |
||
| 1326 | }, |
||
| 1327 | { |
||
| 1328 | "cell_type": "markdown", |
||
| 1329 | "metadata": { |
||
| 1330 | "deletable": true, |
||
| 1331 | "editable": true |
||
| 1332 | }, |
||
| 1333 | "source": [ |
||
| 1334 | "<font style=\"font-weight:bold;color:brown\">Algorithm 1</font>: Random Forest" |
||
| 1335 | ] |
||
| 1336 | }, |
||
| 1337 | { |
||
| 1338 | "cell_type": "code", |
||
| 1339 | "execution_count": null, |
||
| 1340 | "metadata": { |
||
| 1341 | "collapsed": false, |
||
| 1342 | "deletable": true, |
||
| 1343 | "editable": true |
||
| 1344 | }, |
||
| 1345 | "outputs": [], |
||
| 1346 | "source": [ |
||
| 1347 | "charlson_method_name = \"rfc\"\n", |
||
| 1348 | "kwargs = {\"n_estimators\": 20, \"criterion\": 'gini', \"max_depth\": None, \"min_samples_split\": 100,\n", |
||
| 1349 | " \"min_samples_leaf\": 50, \"min_weight_fraction_leaf\": 0.0, \"max_features\": 'auto',\n", |
||
| 1350 | " \"max_leaf_nodes\": None, \"bootstrap\": True, \"oob_score\": False, \"n_jobs\": -1, \"random_state\": None,\n", |
||
| 1351 | " \"verbose\": 0, \"warm_start\": False, \"class_weight\": \"balanced_subsample\"}" |
||
| 1352 | ] |
||
| 1353 | }, |
||
| 1354 | { |
||
| 1355 | "cell_type": "markdown", |
||
| 1356 | "metadata": { |
||
| 1357 | "deletable": true, |
||
| 1358 | "editable": true |
||
| 1359 | }, |
||
| 1360 | "source": [ |
||
| 1361 | "<font style=\"font-weight:bold;color:brown\">Algorithm 2</font>: Logistic Regression" |
||
| 1362 | ] |
||
| 1363 | }, |
||
| 1364 | { |
||
| 1365 | "cell_type": "code", |
||
| 1366 | "execution_count": null, |
||
| 1367 | "metadata": { |
||
| 1368 | "collapsed": false, |
||
| 1369 | "deletable": true, |
||
| 1370 | "editable": true |
||
| 1371 | }, |
||
| 1372 | "outputs": [], |
||
| 1373 | "source": [ |
||
| 1374 | "charlson_method_name = \"lr\"\n", |
||
| 1375 | "kwargs = {\"penalty\": 'l2', \"dual\": False, \"tol\": 0.0001, \"C\": 1, \"fit_intercept\": True, \"intercept_scaling\": 1,\n", |
||
| 1376 | " \"class_weight\": None, \"random_state\": None, \"solver\": 'liblinear', \"max_iter\": 100, \"multi_class\": 'ovr',\n", |
||
| 1377 | " \"verbose\": 0, \"warm_start\": False, \"n_jobs\": -1}" |
||
| 1378 | ] |
||
| 1379 | }, |
||
| 1380 | { |
||
| 1381 | "cell_type": "markdown", |
||
| 1382 | "metadata": { |
||
| 1383 | "deletable": true, |
||
| 1384 | "editable": true |
||
| 1385 | }, |
||
| 1386 | "source": [ |
||
| 1387 | "<br/><br/>" |
||
| 1388 | ] |
||
| 1389 | }, |
||
| 1390 | { |
||
| 1391 | "cell_type": "markdown", |
||
| 1392 | "metadata": { |
||
| 1393 | "deletable": true, |
||
| 1394 | "editable": true |
||
| 1395 | }, |
||
| 1396 | "source": [ |
||
| 1397 | "### 3.2. Initialise" |
||
| 1398 | ] |
||
| 1399 | }, |
||
| 1400 | { |
||
| 1401 | "cell_type": "code", |
||
| 1402 | "execution_count": null, |
||
| 1403 | "metadata": { |
||
| 1404 | "collapsed": false, |
||
| 1405 | "deletable": true, |
||
| 1406 | "editable": true |
||
| 1407 | }, |
||
| 1408 | "outputs": [], |
||
| 1409 | "source": [ |
||
| 1410 | "# set features\n", |
||
| 1411 | "charlson_features_names = ['trigger_charlsonFoster']" |
||
| 1412 | ] |
||
| 1413 | }, |
||
| 1414 | { |
||
| 1415 | "cell_type": "code", |
||
| 1416 | "execution_count": null, |
||
| 1417 | "metadata": { |
||
| 1418 | "collapsed": false, |
||
| 1419 | "deletable": true, |
||
| 1420 | "editable": true |
||
| 1421 | }, |
||
| 1422 | "outputs": [], |
||
| 1423 | "source": [ |
||
| 1424 | "# select the target variable\n", |
||
| 1425 | "charlson_target_feature = \"label30\" # \"label30\", \"label365\" \n", |
||
| 1426 | "\n", |
||
| 1427 | "# file name\n", |
||
| 1428 | "file_name = \"report_Model_Charlson_\" + charlson_method_name + \"_\" + charlson_target_feature\n", |
||
| 1429 | "\n", |
||
| 1430 | "# initialise\n", |
||
| 1431 | "charlson_training_method = TrainingMethod(charlson_method_name)" |
||
| 1432 | ] |
||
| 1433 | }, |
||
| 1434 | { |
||
| 1435 | "cell_type": "markdown", |
||
| 1436 | "metadata": { |
||
| 1437 | "deletable": true, |
||
| 1438 | "editable": true |
||
| 1439 | }, |
||
| 1440 | "source": [ |
||
| 1441 | "### 3.3. Fit" |
||
| 1442 | ] |
||
| 1443 | }, |
||
| 1444 | { |
||
| 1445 | "cell_type": "markdown", |
||
| 1446 | "metadata": { |
||
| 1447 | "deletable": true, |
||
| 1448 | "editable": true |
||
| 1449 | }, |
||
| 1450 | "source": [ |
||
| 1451 | "Fit Model" |
||
| 1452 | ] |
||
| 1453 | }, |
||
| 1454 | { |
||
| 1455 | "cell_type": "code", |
||
| 1456 | "execution_count": null, |
||
| 1457 | "metadata": { |
||
| 1458 | "collapsed": false, |
||
| 1459 | "deletable": true, |
||
| 1460 | "editable": true |
||
| 1461 | }, |
||
| 1462 | "outputs": [], |
||
| 1463 | "source": [ |
||
| 1464 | "o_summaries = dict()\n", |
||
| 1465 | "# Fit\n", |
||
| 1466 | "model = charlson_training_method.train(features_extra[\"train\"][charlson_features_names], features_extra[\"train\"][target_feature], **kwargs)\n", |
||
| 1467 | "charlson_training_method.save_model(path=CONSTANTS.io_path, title=file_name)" |
||
| 1468 | ] |
||
| 1469 | }, |
||
| 1470 | { |
||
| 1471 | "cell_type": "code", |
||
| 1472 | "execution_count": null, |
||
| 1473 | "metadata": { |
||
| 1474 | "collapsed": true, |
||
| 1475 | "deletable": true, |
||
| 1476 | "editable": true |
||
| 1477 | }, |
||
| 1478 | "outputs": [], |
||
| 1479 | "source": [ |
||
| 1480 | "# load model\n", |
||
| 1481 | "# charlson_training_method.load(path=CONSTANTS.io_path, title=file_name)" |
||
| 1482 | ] |
||
| 1483 | }, |
||
| 1484 | { |
||
| 1485 | "cell_type": "code", |
||
| 1486 | "execution_count": null, |
||
| 1487 | "metadata": { |
||
| 1488 | "collapsed": false, |
||
| 1489 | "deletable": true, |
||
| 1490 | "editable": true |
||
| 1491 | }, |
||
| 1492 | "outputs": [], |
||
| 1493 | "source": [ |
||
| 1494 | "# short summary\n", |
||
| 1495 | "o_summaries = charlson_training_method.train_summaries()" |
||
| 1496 | ] |
||
| 1497 | }, |
||
| 1498 | { |
||
| 1499 | "cell_type": "markdown", |
||
| 1500 | "metadata": { |
||
| 1501 | "deletable": true, |
||
| 1502 | "editable": true |
||
| 1503 | }, |
||
| 1504 | "source": [ |
||
| 1505 | "Fit Performance" |
||
| 1506 | ] |
||
| 1507 | }, |
||
| 1508 | { |
||
| 1509 | "cell_type": "code", |
||
| 1510 | "execution_count": null, |
||
| 1511 | "metadata": { |
||
| 1512 | "collapsed": false, |
||
| 1513 | "deletable": true, |
||
| 1514 | "editable": true |
||
| 1515 | }, |
||
| 1516 | "outputs": [], |
||
| 1517 | "source": [ |
||
| 1518 | "o_summaries = dict()\n", |
||
| 1519 | "model = charlson_training_method.predict(features_extra[\"train\"][charlson_features_names], \"train\")" |
||
| 1520 | ] |
||
| 1521 | }, |
||
| 1522 | { |
||
| 1523 | "cell_type": "code", |
||
| 1524 | "execution_count": null, |
||
| 1525 | "metadata": { |
||
| 1526 | "collapsed": false, |
||
| 1527 | "deletable": true, |
||
| 1528 | "editable": true |
||
| 1529 | }, |
||
| 1530 | "outputs": [], |
||
| 1531 | "source": [ |
||
| 1532 | "# short summary\n", |
||
| 1533 | "o_summaries = charlson_training_method.predict_summaries(pd.Series(features_extra[\"train\"][target_feature]), \"train\")\n", |
||
| 1534 | "print(\"ROC AUC:\", o_summaries['roc_auc_score_1'], \"\\n\", o_summaries['classification_report'])\n", |
||
| 1535 | "for k in o_summaries.keys():\n", |
||
| 1536 | " print(k, o_summaries[k])" |
||
| 1537 | ] |
||
| 1538 | }, |
||
| 1539 | { |
||
| 1540 | "cell_type": "markdown", |
||
| 1541 | "metadata": { |
||
| 1542 | "deletable": true, |
||
| 1543 | "editable": true |
||
| 1544 | }, |
||
| 1545 | "source": [ |
||
| 1546 | "### 3.4. Predict" |
||
| 1547 | ] |
||
| 1548 | }, |
||
| 1549 | { |
||
| 1550 | "cell_type": "code", |
||
| 1551 | "execution_count": null, |
||
| 1552 | "metadata": { |
||
| 1553 | "collapsed": false, |
||
| 1554 | "deletable": true, |
||
| 1555 | "editable": true |
||
| 1556 | }, |
||
| 1557 | "outputs": [], |
||
| 1558 | "source": [ |
||
| 1559 | "o_summaries = dict()\n", |
||
| 1560 | "model = charlson_training_method.predict(features_extra[\"test\"][charlson_features_names], \"test\")" |
||
| 1561 | ] |
||
| 1562 | }, |
||
| 1563 | { |
||
| 1564 | "cell_type": "code", |
||
| 1565 | "execution_count": null, |
||
| 1566 | "metadata": { |
||
| 1567 | "collapsed": false, |
||
| 1568 | "deletable": true, |
||
| 1569 | "editable": true |
||
| 1570 | }, |
||
| 1571 | "outputs": [], |
||
| 1572 | "source": [ |
||
| 1573 | "# short summary\n", |
||
| 1574 | "o_summaries = charlson_training_method.predict_summaries(pd.Series(features_extra[\"test\"][target_feature]), \"test\")\n", |
||
| 1575 | "print(\"ROC AUC:\", o_summaries['roc_auc_score_1'], \"\\n\", o_summaries['classification_report'])\n", |
||
| 1576 | "for k in o_summaries.keys():\n", |
||
| 1577 | " print(k, o_summaries[k])" |
||
| 1578 | ] |
||
| 1579 | }, |
||
| 1580 | { |
||
| 1581 | "cell_type": "markdown", |
||
| 1582 | "metadata": { |
||
| 1583 | "deletable": true, |
||
| 1584 | "editable": true |
||
| 1585 | }, |
||
| 1586 | "source": [ |
||
| 1587 | "### 3.5. Cross-Validate" |
||
| 1588 | ] |
||
| 1589 | }, |
||
| 1590 | { |
||
| 1591 | "cell_type": "code", |
||
| 1592 | "execution_count": null, |
||
| 1593 | "metadata": { |
||
| 1594 | "collapsed": false, |
||
| 1595 | "deletable": true, |
||
| 1596 | "editable": true |
||
| 1597 | }, |
||
| 1598 | "outputs": [], |
||
| 1599 | "source": [ |
||
| 1600 | "o_summaries = dict()\n", |
||
| 1601 | "score = charlson_training_method.cross_validate(features_extra[\"test\"][charlson_features_names], features_extra[\"test\"][target_feature], \n", |
||
| 1602 | " scoring=\"neg_mean_squared_error\", cv=10)" |
||
| 1603 | ] |
||
| 1604 | }, |
||
| 1605 | { |
||
| 1606 | "cell_type": "code", |
||
| 1607 | "execution_count": null, |
||
| 1608 | "metadata": { |
||
| 1609 | "collapsed": false, |
||
| 1610 | "deletable": true, |
||
| 1611 | "editable": true |
||
| 1612 | }, |
||
| 1613 | "outputs": [], |
||
| 1614 | "source": [ |
||
| 1615 | "# short summary\n", |
||
| 1616 | "o_summaries = charlson_training_method.cross_validate_summaries()\n", |
||
| 1617 | "print(\"Scores: \", o_summaries)" |
||
| 1618 | ] |
||
| 1619 | }, |
||
| 1620 | { |
||
| 1621 | "cell_type": "markdown", |
||
| 1622 | "metadata": { |
||
| 1623 | "deletable": true, |
||
| 1624 | "editable": true |
||
| 1625 | }, |
||
| 1626 | "source": [ |
||
| 1627 | "### 3.6. Save" |
||
| 1628 | ] |
||
| 1629 | }, |
||
| 1630 | { |
||
| 1631 | "cell_type": "code", |
||
| 1632 | "execution_count": null, |
||
| 1633 | "metadata": { |
||
| 1634 | "collapsed": false, |
||
| 1635 | "deletable": true, |
||
| 1636 | "editable": true, |
||
| 1637 | "scrolled": true |
||
| 1638 | }, |
||
| 1639 | "outputs": [], |
||
| 1640 | "source": [ |
||
| 1641 | "charlson_training_method.save_model(path=CONSTANTS.io_path, title=file_name)" |
||
| 1642 | ] |
||
| 1643 | }, |
||
| 1644 | { |
||
| 1645 | "cell_type": "markdown", |
||
| 1646 | "metadata": { |
||
| 1647 | "deletable": true, |
||
| 1648 | "editable": true |
||
| 1649 | }, |
||
| 1650 | "source": [ |
||
| 1651 | "<br/><br/>" |
||
| 1652 | ] |
||
| 1653 | }, |
||
| 1654 | { |
||
| 1655 | "cell_type": "markdown", |
||
| 1656 | "metadata": { |
||
| 1657 | "deletable": true, |
||
| 1658 | "editable": true |
||
| 1659 | }, |
||
| 1660 | "source": [ |
||
| 1661 | "## 4. Features Statistics" |
||
| 1662 | ] |
||
| 1663 | }, |
||
| 1664 | { |
||
| 1665 | "cell_type": "markdown", |
||
| 1666 | "metadata": { |
||
| 1667 | "collapsed": true, |
||
| 1668 | "deletable": true, |
||
| 1669 | "editable": true |
||
| 1670 | }, |
||
| 1671 | "source": [ |
||
| 1672 | "### 4.1. Features Rank" |
||
| 1673 | ] |
||
| 1674 | }, |
||
| 1675 | { |
||
| 1676 | "cell_type": "markdown", |
||
| 1677 | "metadata": { |
||
| 1678 | "collapsed": false, |
||
| 1679 | "deletable": true, |
||
| 1680 | "editable": true |
||
| 1681 | }, |
||
| 1682 | "source": [ |
||
| 1683 | "<i>It is produced during modelling</i>" |
||
| 1684 | ] |
||
| 1685 | }, |
||
| 1686 | { |
||
| 1687 | "cell_type": "markdown", |
||
| 1688 | "metadata": { |
||
| 1689 | "deletable": true, |
||
| 1690 | "editable": true |
||
| 1691 | }, |
||
| 1692 | "source": [ |
||
| 1693 | "### 4.2. Descriptive Statistics" |
||
| 1694 | ] |
||
| 1695 | }, |
||
| 1696 | { |
||
| 1697 | "cell_type": "markdown", |
||
| 1698 | "metadata": { |
||
| 1699 | "collapsed": false, |
||
| 1700 | "deletable": true, |
||
| 1701 | "editable": true |
||
| 1702 | }, |
||
| 1703 | "source": [ |
||
| 1704 | "<i>It is produced during modelling</i>" |
||
| 1705 | ] |
||
| 1706 | }, |
||
| 1707 | { |
||
| 1708 | "cell_type": "markdown", |
||
| 1709 | "metadata": { |
||
| 1710 | "deletable": true, |
||
| 1711 | "editable": true |
||
| 1712 | }, |
||
| 1713 | "source": [ |
||
| 1714 | "### 4.3. Features Weigths" |
||
| 1715 | ] |
||
| 1716 | }, |
||
| 1717 | { |
||
| 1718 | "cell_type": "code", |
||
| 1719 | "execution_count": null, |
||
| 1720 | "metadata": { |
||
| 1721 | "collapsed": false, |
||
| 1722 | "deletable": true, |
||
| 1723 | "editable": true |
||
| 1724 | }, |
||
| 1725 | "outputs": [], |
||
| 1726 | "source": [ |
||
| 1727 | "def features_importance_rank(fitting_method, ranking_file_name=None, rank_models=[\"rfc\", \"gbrt\", \"randLogit\"]):\n", |
||
| 1728 | " # Fitting weight\n", |
||
| 1729 | " o_summaries = pd.DataFrame({\"Name\": fitting_method.model_labels,\n", |
||
| 1730 | " \"Fitting Weight\": fitting_method.train_summaries()[\"feature_importances_\"]},\n", |
||
| 1731 | " index = fitting_method.model_labels)\n", |
||
| 1732 | " o_summaries = o_summaries.sort_values(\"Fitting Weight\", ascending=False)\n", |
||
| 1733 | " o_summaries = o_summaries.reset_index(drop=True)\n", |
||
| 1734 | " \n", |
||
| 1735 | " # Ranking scores\n", |
||
| 1736 | " if ranking_file_name is not None:\n", |
||
| 1737 | " for rank_model in rank_models:\n", |
||
| 1738 | " o_summaries_ranks = readers_writers.load_serialised_compressed(\n", |
||
| 1739 | " path=CONSTANTS.io_path, title=ranking_file_name + rank_model)\n", |
||
| 1740 | " for trial in range(len(o_summaries_ranks)):\n", |
||
| 1741 | " o_summaries_rank = pd.DataFrame(o_summaries_ranks[trial])\n", |
||
| 1742 | " o_summaries_rank.columns = [\"Name\", \"Importance - \" + rank_model + \" - Trial_\" + str(trial),\n", |
||
| 1743 | " \"Order - \" + rank_model + \" - Trial_\" + str(trial)]\n", |
||
| 1744 | " o_summaries = o_summaries.merge(o_summaries_rank, how=\"outer\", on=\"Name\")\n", |
||
| 1745 | " \n", |
||
| 1746 | " return o_summaries" |
||
| 1747 | ] |
||
| 1748 | }, |
||
| 1749 | { |
||
| 1750 | "cell_type": "code", |
||
| 1751 | "execution_count": null, |
||
| 1752 | "metadata": { |
||
| 1753 | "collapsed": false, |
||
| 1754 | "deletable": true, |
||
| 1755 | "editable": true |
||
| 1756 | }, |
||
| 1757 | "outputs": [], |
||
| 1758 | "source": [ |
||
| 1759 | "file_name = \"Step_07_Model_Train_model_rank_summaries_\"\n", |
||
| 1760 | "\n", |
||
| 1761 | "o_summaries = features_importance_rank(fitting_method=training_method, ranking_file_name=file_name, rank_models=rank_models)\n", |
||
| 1762 | "\n", |
||
| 1763 | "file_name = \"report_weights_ranks\"\n", |
||
| 1764 | "readers_writers.save_csv(path=CONSTANTS.io_path, title=file_name, data=o_summaries, append=False, extension=\"csv\", header=o_summaries.columns)\n", |
||
| 1765 | "\n", |
||
| 1766 | "display(o_summaries.head())" |
||
| 1767 | ] |
||
| 1768 | }, |
||
| 1769 | { |
||
| 1770 | "cell_type": "markdown", |
||
| 1771 | "metadata": { |
||
| 1772 | "deletable": true, |
||
| 1773 | "editable": true |
||
| 1774 | }, |
||
| 1775 | "source": [ |
||
| 1776 | "<br/><br/>" |
||
| 1777 | ] |
||
| 1778 | }, |
||
| 1779 | { |
||
| 1780 | "cell_type": "markdown", |
||
| 1781 | "metadata": { |
||
| 1782 | "deletable": true, |
||
| 1783 | "editable": true |
||
| 1784 | }, |
||
| 1785 | "source": [ |
||
| 1786 | "## 5. Model Performance" |
||
| 1787 | ] |
||
| 1788 | }, |
||
| 1789 | { |
||
| 1790 | "cell_type": "markdown", |
||
| 1791 | "metadata": { |
||
| 1792 | "deletable": true, |
||
| 1793 | "editable": true |
||
| 1794 | }, |
||
| 1795 | "source": [ |
||
| 1796 | "### 5.1. Performance Indicators" |
||
| 1797 | ] |
||
| 1798 | }, |
||
| 1799 | { |
||
| 1800 | "cell_type": "code", |
||
| 1801 | "execution_count": null, |
||
| 1802 | "metadata": { |
||
| 1803 | "collapsed": true, |
||
| 1804 | "deletable": true, |
||
| 1805 | "editable": true |
||
| 1806 | }, |
||
| 1807 | "outputs": [], |
||
| 1808 | "source": [ |
||
| 1809 | "measures = [\"accuracy_score\", \"precision_score\", \"recall_score\",\n", |
||
| 1810 | " \"roc_auc_score_1\", \"f1_score\", \"fbeta_score\", \"average_precision_score\", \n", |
||
| 1811 | " \"log_loss\", \"zero_one_loss\", \"hamming_loss\", \"jaccard_similarity_score\", \"matthews_corrcoef\"]" |
||
| 1812 | ] |
||
| 1813 | }, |
||
| 1814 | { |
||
| 1815 | "cell_type": "code", |
||
| 1816 | "execution_count": null, |
||
| 1817 | "metadata": { |
||
| 1818 | "collapsed": false, |
||
| 1819 | "deletable": true, |
||
| 1820 | "editable": true |
||
| 1821 | }, |
||
| 1822 | "outputs": [], |
||
| 1823 | "source": [ |
||
| 1824 | "# train\n", |
||
| 1825 | "o_summaries = training_method.predict_summaries(features_extra[\"train\"][target_feature], \"train\")\n", |
||
| 1826 | "o_summaries = np.array([(m, o_summaries[m]) for m in measures])\n", |
||
| 1827 | "report_performance = pd.DataFrame({\"Measure\": o_summaries[:, 0], \n", |
||
| 1828 | " \"Sample Train\": o_summaries[:, 1], \n", |
||
| 1829 | " \"Sample Test\": [None] * len(measures)})\n", |
||
| 1830 | "\n", |
||
| 1831 | "# test\n", |
||
| 1832 | "o_summaries = training_method.predict_summaries(features_extra[\"test\"][target_feature], \"test\")\n", |
||
| 1833 | "o_summaries = np.array([(m, o_summaries[m]) for m in measures])\n", |
||
| 1834 | "report_performance[\"Sample Test\"] = o_summaries[:, 1]" |
||
| 1835 | ] |
||
| 1836 | }, |
||
| 1837 | { |
||
| 1838 | "cell_type": "code", |
||
| 1839 | "execution_count": null, |
||
| 1840 | "metadata": { |
||
| 1841 | "collapsed": false, |
||
| 1842 | "deletable": true, |
||
| 1843 | "editable": true, |
||
| 1844 | "scrolled": true |
||
| 1845 | }, |
||
| 1846 | "outputs": [], |
||
| 1847 | "source": [ |
||
| 1848 | "# print\n", |
||
| 1849 | "file_name = \"report_performance_\" + method_name + \"_\" + target_feature\n", |
||
| 1850 | "display(report_performance)\n", |
||
| 1851 | "readers_writers.save_csv(path=CONSTANTS.io_path, title=file_name, data=report_performance, append=False)" |
||
| 1852 | ] |
||
| 1853 | }, |
||
| 1854 | { |
||
| 1855 | "cell_type": "markdown", |
||
| 1856 | "metadata": { |
||
| 1857 | "deletable": true, |
||
| 1858 | "editable": true |
||
| 1859 | }, |
||
| 1860 | "source": [ |
||
| 1861 | "### 5.2. Population Statistics" |
||
| 1862 | ] |
||
| 1863 | }, |
||
| 1864 | { |
||
| 1865 | "cell_type": "code", |
||
| 1866 | "execution_count": null, |
||
| 1867 | "metadata": { |
||
| 1868 | "collapsed": false, |
||
| 1869 | "deletable": true, |
||
| 1870 | "editable": true |
||
| 1871 | }, |
||
| 1872 | "outputs": [], |
||
| 1873 | "source": [ |
||
| 1874 | "def population_statistics(df, diagnoses, cutpoints=[0.50, 0.60, 0.70, 0.80, 0.90]):\n", |
||
| 1875 | " o_summaries = pd.DataFrame(columns=['Name'], index=diagnoses)\n", |
||
| 1876 | " o_summaries['Name'] = diagnoses\n", |
||
| 1877 | " \n", |
||
| 1878 | " for diagnose in diagnoses:\n", |
||
| 1879 | " o_summaries.loc[diagnose, 'Total'] = len(df.index)\n", |
||
| 1880 | " if diagnose not in df:\n", |
||
| 1881 | " continue\n", |
||
| 1882 | " \n", |
||
| 1883 | " o_summaries.loc[diagnose, 'Total - diagnose'] = len(df.loc[(df[diagnose] > 0)].index)\n", |
||
| 1884 | " o_summaries.loc[diagnose, 'Total - diagnose - label_1'] = len(df.loc[(df[diagnose] > 0) & (df[target_feature] > 0)].index)\n", |
||
| 1885 | " o_summaries.loc[diagnose, 'Emergency Readmission Rate - cnt 1'] = len(df.loc[(df[diagnose] > 0) & (df['admimeth_0t30d_prevalence_1_cnt'] > 0) & (df[target_feature] > 0)].index)\n", |
||
| 1886 | " o_summaries.loc[diagnose, 'Emergency Readmission Rate - cnt 2'] = len(df.loc[(df[diagnose] > 0) & (df['admimeth_0t30d_prevalence_2_cnt'] > 0) & (df[target_feature] > 0)].index)\n", |
||
| 1887 | " o_summaries.loc[diagnose, 'Emergency Readmission Rate - cnt 3'] = len(df.loc[(df[diagnose] > 0) & (df['admimeth_0t30d_prevalence_3_cnt'] > 0) & (df[target_feature] > 0)].index)\n", |
||
| 1888 | " o_summaries.loc[diagnose, 'Prior Spells'] = len(df.loc[(df[diagnose] > 0) & (df['prior_spells'] > 0) & (df[target_feature] > 0)].index)\n", |
||
| 1889 | " o_summaries.loc[diagnose, 'Male - perc'] = len(df.loc[(df[diagnose] > 0) & (df['gender_1'] > 0) & (df[target_feature] > 0)].index)\n", |
||
| 1890 | " age = df.loc[(df[diagnose] > 0) & (df[target_feature] > 0)]['trigger_age'].describe(percentiles=[.25, .5, .75])\n", |
||
| 1891 | " o_summaries.loc[diagnose, 'Age - IQR_min'] = age['min']\n", |
||
| 1892 | " o_summaries.loc[diagnose, 'Age - IQR_25'] = age['25%']\n", |
||
| 1893 | " o_summaries.loc[diagnose, 'Age - IQR_50'] = age['50%']\n", |
||
| 1894 | " o_summaries.loc[diagnose, 'Age - IQR_75'] = age['75%']\n", |
||
| 1895 | " o_summaries.loc[diagnose, 'Age - IQR_max'] = age['max']\n", |
||
| 1896 | " los = df.loc[(df[diagnose] > 0) & (df[target_feature] > 0)]['trigger_los'].describe(percentiles=[.25, .5, .75])\n", |
||
| 1897 | " o_summaries.loc[diagnose, 'LoS - IQR_min'] = los['min']\n", |
||
| 1898 | " o_summaries.loc[diagnose, 'LoS - IQR_25'] = los['25%']\n", |
||
| 1899 | " o_summaries.loc[diagnose, 'LoS - IQR_50'] = los['50%']\n", |
||
| 1900 | " o_summaries.loc[diagnose, 'LoS - IQR_75'] = los['75%']\n", |
||
| 1901 | " o_summaries.loc[diagnose, 'LoS - IQR_max'] = los['max']\n", |
||
| 1902 | " for cutpoint in cutpoints:\n", |
||
| 1903 | " o_summaries.loc[diagnose, 'score - ' + str(cutpoint)] = len(df.loc[(df[diagnose] > 0) & (df['score'] > cutpoint)].index)\n", |
||
| 1904 | " o_summaries.loc[diagnose, 'TP - ' + str(cutpoint)] = len(df.loc[(df[diagnose] > 0) & (df[target_feature] > 0) & (df['score'] > cutpoint)].index)\n", |
||
| 1905 | " o_summaries.loc[diagnose, 'FP - ' + str(cutpoint)] = len(df.loc[(df[diagnose] > 0) & (df[target_feature] == 0) & (df['score'] > cutpoint)].index)\n", |
||
| 1906 | " o_summaries.loc[diagnose, 'FN - ' + str(cutpoint)] = len(df.loc[(df[diagnose] > 0) & (df[target_feature] > 0) & (df['score'] <= cutpoint)].index)\n", |
||
| 1907 | " o_summaries.loc[diagnose, 'TN - ' + str(cutpoint)] = len(df.loc[(df[diagnose] > 0) & (df[target_feature] == 0) & (df['score'] <= cutpoint)].index)\n", |
||
| 1908 | " \n", |
||
| 1909 | " \n", |
||
| 1910 | " o_summaries.loc[diagnose, 'Charlson - 0'] = len(df.loc[(df[diagnose] > 0) & (df[\"trigger_charlsonFoster\"] == 0)].index)\n", |
||
| 1911 | " o_summaries.loc[diagnose, 'Charlson - 0 - label_1'] = len(df.loc[(df[diagnose] > 0) & (df[\"trigger_charlsonFoster\"] == 0) & (df[target_feature] > 0)].index)\n", |
||
| 1912 | " o_summaries.loc[diagnose, 'Charlson - 1'] = len(df.loc[(df[diagnose] > 0) & (df[\"trigger_charlsonFoster\"] == 1)].index)\n", |
||
| 1913 | " o_summaries.loc[diagnose, 'Charlson - 1 - label_1'] = len(df.loc[(df[diagnose] > 0) & (df[\"trigger_charlsonFoster\"] == 1) & (df[target_feature] > 0)].index)\n", |
||
| 1914 | " o_summaries.loc[diagnose, 'Charlson - 2'] = len(df.loc[(df[diagnose] > 0) & (df[\"trigger_charlsonFoster\"] == 2)].index)\n", |
||
| 1915 | " o_summaries.loc[diagnose, 'Charlson - 2 - label_1'] = len(df.loc[(df[diagnose] > 0) & (df[\"trigger_charlsonFoster\"] == 2) & (df[target_feature] > 0)].index)\n", |
||
| 1916 | " o_summaries.loc[diagnose, 'Charlson - 3'] = len(df.loc[(df[diagnose] > 0) & (df[\"trigger_charlsonFoster\"] == 3)].index)\n", |
||
| 1917 | " o_summaries.loc[diagnose, 'Charlson - 3 - label_1'] = len(df.loc[(df[diagnose] > 0) & (df[\"trigger_charlsonFoster\"] == 3) & (df[target_feature] > 0)].index)\n", |
||
| 1918 | " o_summaries.loc[diagnose, 'Charlson - 4+'] = len(df.loc[(df[diagnose] > 0) & (df[\"trigger_charlsonFoster\"] >= 4)].index)\n", |
||
| 1919 | " o_summaries.loc[diagnose, 'Charlson - 4+ - label_1'] = len(df.loc[(df[diagnose] > 0) & (df[\"trigger_charlsonFoster\"] >= 4) & (df[target_feature] > 0)].index)\n", |
||
| 1920 | " \n", |
||
| 1921 | " for cutpoint in cutpoints:\n", |
||
| 1922 | " o_summaries.loc[diagnose, 'Charlson - 0 - label_1 - TP - ' + str(cutpoint)] = \\\n", |
||
| 1923 | " len(df.loc[(df[diagnose] > 0) & (df[\"trigger_charlsonFoster\"] == 0) & (df[target_feature] > 0) & (df['score'] > cutpoint)].index)\n", |
||
| 1924 | " \n", |
||
| 1925 | " return o_summaries" |
||
| 1926 | ] |
||
| 1927 | }, |
||
| 1928 | { |
||
| 1929 | "cell_type": "markdown", |
||
| 1930 | "metadata": { |
||
| 1931 | "deletable": true, |
||
| 1932 | "editable": true |
||
| 1933 | }, |
||
| 1934 | "source": [ |
||
| 1935 | "#### 5.2.1. Most Prevalent Diagnoses Groups\n", |
||
| 1936 | "Most prevalent diagnoses groups (30-day, 1-year readmission): \n", |
||
| 1937 | "* Total, Admissions, Emergency Readmission Rate, Prior Spells, Male (%), Age (IQR), LoS (IQR), TP, FP, FN, TN" |
||
| 1938 | ] |
||
| 1939 | }, |
||
| 1940 | { |
||
| 1941 | "cell_type": "code", |
||
| 1942 | "execution_count": null, |
||
| 1943 | "metadata": { |
||
| 1944 | "collapsed": true, |
||
| 1945 | "deletable": true, |
||
| 1946 | "editable": true |
||
| 1947 | }, |
||
| 1948 | "outputs": [], |
||
| 1949 | "source": [ |
||
| 1950 | "diagnoses = ['diagCCS_0t30d_others_cnt', 'diagCCS_0t30d_prevalence_1_cnt', 'diagCCS_0t30d_prevalence_2_cnt', 'diagCCS_0t30d_prevalence_3_cnt', 'diagCCS_0t30d_prevalence_4_cnt', 'diagCCS_0t30d_prevalence_5_cnt', 'diagCCS_0t30d_prevalence_6_cnt', 'diagCCS_0t30d_prevalence_7_cnt', 'diagCCS_0t30d_prevalence_8_cnt', 'diagCCS_0t30d_prevalence_9_cnt', 'diagCCS_0t30d_prevalence_10_cnt', 'diagCCS_0t30d_prevalence_11_cnt', 'diagCCS_0t30d_prevalence_12_cnt', 'diagCCS_0t30d_prevalence_13_cnt', 'diagCCS_0t30d_prevalence_14_cnt', 'diagCCS_0t30d_prevalence_15_cnt', 'diagCCS_0t30d_prevalence_16_cnt', 'diagCCS_0t30d_prevalence_17_cnt', 'diagCCS_0t30d_prevalence_18_cnt', 'diagCCS_0t30d_prevalence_19_cnt', 'diagCCS_0t30d_prevalence_20_cnt', 'diagCCS_0t30d_prevalence_21_cnt', 'diagCCS_0t30d_prevalence_22_cnt', 'diagCCS_0t30d_prevalence_23_cnt', 'diagCCS_0t30d_prevalence_24_cnt', 'diagCCS_0t30d_prevalence_25_cnt', 'diagCCS_0t30d_prevalence_26_cnt', 'diagCCS_0t30d_prevalence_27_cnt', 'diagCCS_0t30d_prevalence_28_cnt', 'diagCCS_0t30d_prevalence_29_cnt', 'diagCCS_0t30d_prevalence_30_cnt'\n", |
||
| 1951 | " , 'diagCCS_30t90d_others_cnt', 'diagCCS_30t90d_prevalence_1_cnt', 'diagCCS_30t90d_prevalence_2_cnt', 'diagCCS_30t90d_prevalence_3_cnt', 'diagCCS_30t90d_prevalence_4_cnt', 'diagCCS_30t90d_prevalence_5_cnt', 'diagCCS_30t90d_prevalence_6_cnt', 'diagCCS_30t90d_prevalence_7_cnt', 'diagCCS_30t90d_prevalence_8_cnt', 'diagCCS_30t90d_prevalence_9_cnt', 'diagCCS_30t90d_prevalence_10_cnt', 'diagCCS_30t90d_prevalence_11_cnt', 'diagCCS_30t90d_prevalence_12_cnt', 'diagCCS_30t90d_prevalence_13_cnt', 'diagCCS_30t90d_prevalence_14_cnt', 'diagCCS_30t90d_prevalence_15_cnt', 'diagCCS_30t90d_prevalence_16_cnt', 'diagCCS_30t90d_prevalence_17_cnt', 'diagCCS_30t90d_prevalence_18_cnt', 'diagCCS_30t90d_prevalence_19_cnt', 'diagCCS_30t90d_prevalence_20_cnt', 'diagCCS_30t90d_prevalence_21_cnt', 'diagCCS_30t90d_prevalence_22_cnt', 'diagCCS_30t90d_prevalence_23_cnt', 'diagCCS_30t90d_prevalence_24_cnt', 'diagCCS_30t90d_prevalence_25_cnt', 'diagCCS_30t90d_prevalence_26_cnt', 'diagCCS_30t90d_prevalence_27_cnt', 'diagCCS_30t90d_prevalence_28_cnt', 'diagCCS_30t90d_prevalence_29_cnt', 'diagCCS_30t90d_prevalence_30_cnt'\n", |
||
| 1952 | " , 'diagCCS_90t180d_others_cnt', 'diagCCS_90t180d_prevalence_1_cnt', 'diagCCS_90t180d_prevalence_2_cnt', 'diagCCS_90t180d_prevalence_3_cnt', 'diagCCS_90t180d_prevalence_4_cnt', 'diagCCS_90t180d_prevalence_5_cnt', 'diagCCS_90t180d_prevalence_6_cnt', 'diagCCS_90t180d_prevalence_7_cnt', 'diagCCS_90t180d_prevalence_8_cnt', 'diagCCS_90t180d_prevalence_9_cnt', 'diagCCS_90t180d_prevalence_10_cnt', 'diagCCS_90t180d_prevalence_11_cnt', 'diagCCS_90t180d_prevalence_12_cnt', 'diagCCS_90t180d_prevalence_13_cnt', 'diagCCS_90t180d_prevalence_14_cnt', 'diagCCS_90t180d_prevalence_15_cnt', 'diagCCS_90t180d_prevalence_16_cnt', 'diagCCS_90t180d_prevalence_17_cnt', 'diagCCS_90t180d_prevalence_18_cnt', 'diagCCS_90t180d_prevalence_19_cnt', 'diagCCS_90t180d_prevalence_20_cnt', 'diagCCS_90t180d_prevalence_21_cnt', 'diagCCS_90t180d_prevalence_22_cnt', 'diagCCS_90t180d_prevalence_23_cnt', 'diagCCS_90t180d_prevalence_24_cnt', 'diagCCS_90t180d_prevalence_25_cnt', 'diagCCS_90t180d_prevalence_26_cnt', 'diagCCS_90t180d_prevalence_27_cnt', 'diagCCS_90t180d_prevalence_28_cnt', 'diagCCS_90t180d_prevalence_29_cnt', 'diagCCS_90t180d_prevalence_30_cnt'\n", |
||
| 1953 | " , 'diagCCS_180t365d_others_cnt', 'diagCCS_180t365d_prevalence_1_cnt', 'diagCCS_180t365d_prevalence_2_cnt', 'diagCCS_180t365d_prevalence_3_cnt', 'diagCCS_180t365d_prevalence_4_cnt', 'diagCCS_180t365d_prevalence_5_cnt', 'diagCCS_180t365d_prevalence_6_cnt', 'diagCCS_180t365d_prevalence_7_cnt', 'diagCCS_180t365d_prevalence_8_cnt', 'diagCCS_180t365d_prevalence_9_cnt', 'diagCCS_180t365d_prevalence_10_cnt', 'diagCCS_180t365d_prevalence_11_cnt', 'diagCCS_180t365d_prevalence_12_cnt', 'diagCCS_180t365d_prevalence_13_cnt', 'diagCCS_180t365d_prevalence_14_cnt', 'diagCCS_180t365d_prevalence_15_cnt', 'diagCCS_180t365d_prevalence_16_cnt', 'diagCCS_180t365d_prevalence_17_cnt', 'diagCCS_180t365d_prevalence_18_cnt', 'diagCCS_180t365d_prevalence_19_cnt', 'diagCCS_180t365d_prevalence_20_cnt', 'diagCCS_180t365d_prevalence_21_cnt', 'diagCCS_180t365d_prevalence_22_cnt', 'diagCCS_180t365d_prevalence_23_cnt', 'diagCCS_180t365d_prevalence_24_cnt', 'diagCCS_180t365d_prevalence_25_cnt', 'diagCCS_180t365d_prevalence_26_cnt', 'diagCCS_180t365d_prevalence_27_cnt', 'diagCCS_180t365d_prevalence_28_cnt', 'diagCCS_180t365d_prevalence_29_cnt', 'diagCCS_180t365d_prevalence_30_cnt'\n", |
||
| 1954 | " , 'diagCCS_365t730d_others_cnt', 'diagCCS_365t730d_prevalence_1_cnt', 'diagCCS_365t730d_prevalence_2_cnt', 'diagCCS_365t730d_prevalence_3_cnt', 'diagCCS_365t730d_prevalence_4_cnt', 'diagCCS_365t730d_prevalence_5_cnt', 'diagCCS_365t730d_prevalence_6_cnt', 'diagCCS_365t730d_prevalence_7_cnt', 'diagCCS_365t730d_prevalence_8_cnt', 'diagCCS_365t730d_prevalence_9_cnt', 'diagCCS_365t730d_prevalence_10_cnt', 'diagCCS_365t730d_prevalence_11_cnt', 'diagCCS_365t730d_prevalence_12_cnt', 'diagCCS_365t730d_prevalence_13_cnt', 'diagCCS_365t730d_prevalence_14_cnt', 'diagCCS_365t730d_prevalence_15_cnt', 'diagCCS_365t730d_prevalence_16_cnt', 'diagCCS_365t730d_prevalence_17_cnt', 'diagCCS_365t730d_prevalence_18_cnt', 'diagCCS_365t730d_prevalence_19_cnt', 'diagCCS_365t730d_prevalence_20_cnt', 'diagCCS_365t730d_prevalence_21_cnt', 'diagCCS_365t730d_prevalence_22_cnt', 'diagCCS_365t730d_prevalence_23_cnt', 'diagCCS_365t730d_prevalence_24_cnt', 'diagCCS_365t730d_prevalence_25_cnt', 'diagCCS_365t730d_prevalence_26_cnt', 'diagCCS_365t730d_prevalence_27_cnt', 'diagCCS_365t730d_prevalence_28_cnt', 'diagCCS_365t730d_prevalence_29_cnt', 'diagCCS_365t730d_prevalence_30_cnt']\n", |
||
| 1955 | "file_name = \"report_population_prevalent_diagnoses_\" + method_name + \"_\" + target_feature + \"_\"" |
||
| 1956 | ] |
||
| 1957 | }, |
||
| 1958 | { |
||
| 1959 | "cell_type": "code", |
||
| 1960 | "execution_count": null, |
||
| 1961 | "metadata": { |
||
| 1962 | "collapsed": false, |
||
| 1963 | "deletable": true, |
||
| 1964 | "editable": true |
||
| 1965 | }, |
||
| 1966 | "outputs": [], |
||
| 1967 | "source": [ |
||
| 1968 | "o_summaries = population_statistics(features_extra['train'], diagnoses)\n", |
||
| 1969 | "readers_writers.save_csv(path=CONSTANTS.io_path, title=file_name + \"train\", data=o_summaries, append=False, extension=\"csv\", header=o_summaries.columns)\n", |
||
| 1970 | "\n", |
||
| 1971 | "o_summaries = population_statistics(features_extra['test'], diagnoses)\n", |
||
| 1972 | "readers_writers.save_csv(path=CONSTANTS.io_path, title=file_name + \"test\", data=o_summaries, append=False, extension=\"csv\", header=o_summaries.columns)" |
||
| 1973 | ] |
||
| 1974 | }, |
||
| 1975 | { |
||
| 1976 | "cell_type": "markdown", |
||
| 1977 | "metadata": { |
||
| 1978 | "deletable": true, |
||
| 1979 | "editable": true |
||
| 1980 | }, |
||
| 1981 | "source": [ |
||
| 1982 | "#### 5.2.2. Major Comorbidity Groups\n", |
||
| 1983 | "Comorbidity diagnoses groups (30-day, 1-year readmission): \n", |
||
| 1984 | "* Total, Admissions, Emergency Readmission Rate, Prior Spells, Male (%), Age (IQR), LoS (IQR), TP, FP, FN, TN" |
||
| 1985 | ] |
||
| 1986 | }, |
||
| 1987 | { |
||
| 1988 | "cell_type": "code", |
||
| 1989 | "execution_count": null, |
||
| 1990 | "metadata": { |
||
| 1991 | "collapsed": false, |
||
| 1992 | "deletable": true, |
||
| 1993 | "editable": true |
||
| 1994 | }, |
||
| 1995 | "outputs": [], |
||
| 1996 | "source": [ |
||
| 1997 | "diagnoses = ['prior_admiOther', 'prior_admiAcute', 'prior_spells', 'prior_asthma', 'prior_copd', 'prior_depression', 'prior_diabetes', 'prior_hypertension', 'prior_cancer', 'prior_chd', 'prior_chf']\n", |
||
| 1998 | "file_name = \"report_population_comorbidity_diagnoses_\" + method_name + \"_\" + target_feature + \"_\"" |
||
| 1999 | ] |
||
| 2000 | }, |
||
| 2001 | { |
||
| 2002 | "cell_type": "code", |
||
| 2003 | "execution_count": null, |
||
| 2004 | "metadata": { |
||
| 2005 | "collapsed": false, |
||
| 2006 | "deletable": true, |
||
| 2007 | "editable": true |
||
| 2008 | }, |
||
| 2009 | "outputs": [], |
||
| 2010 | "source": [ |
||
| 2011 | "o_summaries = population_statistics(features_extra['train'], diagnoses)\n", |
||
| 2012 | "readers_writers.save_csv(path=CONSTANTS.io_path, title=file_name + \"train\", data=o_summaries, append=False, extension=\"csv\", header=o_summaries.columns)\n", |
||
| 2013 | "\n", |
||
| 2014 | "o_summaries = population_statistics(features_extra['test'], diagnoses)\n", |
||
| 2015 | "readers_writers.save_csv(path=CONSTANTS.io_path, title=file_name + \"test\", data=o_summaries, append=False, extension=\"csv\", header=o_summaries.columns)" |
||
| 2016 | ] |
||
| 2017 | }, |
||
| 2018 | { |
||
| 2019 | "cell_type": "markdown", |
||
| 2020 | "metadata": { |
||
| 2021 | "deletable": true, |
||
| 2022 | "editable": true |
||
| 2023 | }, |
||
| 2024 | "source": [ |
||
| 2025 | "#### 5.2.3. Charlson Comorbidity Groups\n", |
||
| 2026 | "Charlson diagnoses groups (30-day, 1-year readmission): \n", |
||
| 2027 | "* Total, Admissions, Emergency Readmission Rate, Prior Spells, Male (%), Age (IQR), LoS (IQR), TP, FP, FN, TN" |
||
| 2028 | ] |
||
| 2029 | }, |
||
| 2030 | { |
||
| 2031 | "cell_type": "code", |
||
| 2032 | "execution_count": null, |
||
| 2033 | "metadata": { |
||
| 2034 | "collapsed": true, |
||
| 2035 | "deletable": true, |
||
| 2036 | "editable": true |
||
| 2037 | }, |
||
| 2038 | "outputs": [], |
||
| 2039 | "source": [ |
||
| 2040 | "diagnoses = ['diagCci_01_myocardial_freq', 'diagCci_02_chf_freq', 'diagCci_03_pvd_freq', 'diagCci_04_cerebrovascular_freq', 'diagCci_05_dementia_freq', 'diagCci_06_cpd_freq', 'diagCci_07_rheumatic_freq', 'diagCci_08_ulcer_freq', 'diagCci_09_liverMild_freq', 'diagCci_10_diabetesNotChronic_freq', 'diagCci_11_diabetesChronic_freq', 'diagCci_12_hemiplegia_freq', 'diagCci_13_renal_freq', 'diagCci_14_malignancy_freq', 'diagCci_15_liverSevere_freq', 'diagCci_16_tumorSec_freq', 'diagCci_17_aids_freq', 'diagCci_18_depression_freq', 'diagCci_19_cardiac_freq', 'diagCci_20_valvular_freq', 'diagCci_21_pulmonary_freq', 'diagCci_22_vascular_freq', 'diagCci_23_hypertensionNotComplicated_freq', 'diagCci_24_hypertensionComplicated_freq', 'diagCci_25_paralysis_freq', 'diagCci_26_neuroOther_freq', 'diagCci_27_pulmonaryChronic_freq', 'diagCci_28_diabetesNotComplicated_freq', 'diagCci_29_diabetesComplicated_freq', 'diagCci_30_hypothyroidism_freq', 'diagCci_31_renal_freq', 'diagCci_32_liver_freq', 'diagCci_33_ulcerNotBleeding_freq', 'diagCci_34_psychoses_freq', 'diagCci_35_lymphoma_freq', 'diagCci_36_cancerSec_freq', 'diagCci_37_tumorNotSec_freq', 'diagCci_38_rheumatoid_freq', 'diagCci_39_coagulopathy_freq', 'diagCci_40_obesity_freq', 'diagCci_41_weightLoss_freq', 'diagCci_42_fluidDisorder_freq', 'diagCci_43_bloodLoss_freq', 'diagCci_44_anemia_freq', 'diagCci_45_alcohol_freq', 'diagCci_46_drug_freq']\n", |
||
| 2041 | "file_name = \"report_population_charlson_diagnoses_\" + method_name + \"_\" + target_feature + \"_\"" |
||
| 2042 | ] |
||
| 2043 | }, |
||
| 2044 | { |
||
| 2045 | "cell_type": "code", |
||
| 2046 | "execution_count": null, |
||
| 2047 | "metadata": { |
||
| 2048 | "collapsed": false, |
||
| 2049 | "deletable": true, |
||
| 2050 | "editable": true |
||
| 2051 | }, |
||
| 2052 | "outputs": [], |
||
| 2053 | "source": [ |
||
| 2054 | "o_summaries = population_statistics(features_extra['train'], diagnoses)\n", |
||
| 2055 | "readers_writers.save_csv(path=CONSTANTS.io_path, title=file_name + \"train\", data=o_summaries, append=False, extension=\"csv\", header=o_summaries.columns)\n", |
||
| 2056 | "\n", |
||
| 2057 | "o_summaries = population_statistics(features_extra['test'], diagnoses)\n", |
||
| 2058 | "readers_writers.save_csv(path=CONSTANTS.io_path, title=file_name + \"test\", data=o_summaries, append=False, extension=\"csv\", header=o_summaries.columns)" |
||
| 2059 | ] |
||
| 2060 | }, |
||
| 2061 | { |
||
| 2062 | "cell_type": "markdown", |
||
| 2063 | "metadata": { |
||
| 2064 | "deletable": true, |
||
| 2065 | "editable": true |
||
| 2066 | }, |
||
| 2067 | "source": [ |
||
| 2068 | "#### 5.2.4. Most Prevalent Operatons\n", |
||
| 2069 | "Most prevalent operations variables (30-day, 1-year readmission): \n", |
||
| 2070 | "* Total, Admissions, Emergency Readmission Rate, Prior Spells, Male (%), Age (IQR), LoS (IQR), TP, FP, FN, TN" |
||
| 2071 | ] |
||
| 2072 | }, |
||
| 2073 | { |
||
| 2074 | "cell_type": "code", |
||
| 2075 | "execution_count": null, |
||
| 2076 | "metadata": { |
||
| 2077 | "collapsed": true, |
||
| 2078 | "deletable": true, |
||
| 2079 | "editable": true |
||
| 2080 | }, |
||
| 2081 | "outputs": [], |
||
| 2082 | "source": [ |
||
| 2083 | "diagnoses = ['operOPCSL1_0t30d_others_cnt', 'operOPCSL1_0t30d_prevalence_1_cnt', 'operOPCSL1_0t30d_prevalence_2_cnt', 'operOPCSL1_0t30d_prevalence_3_cnt', 'operOPCSL1_0t30d_prevalence_4_cnt', 'operOPCSL1_0t30d_prevalence_5_cnt', 'operOPCSL1_0t30d_prevalence_6_cnt', 'operOPCSL1_0t30d_prevalence_7_cnt', 'operOPCSL1_0t30d_prevalence_8_cnt', 'operOPCSL1_0t30d_prevalence_9_cnt', 'operOPCSL1_0t30d_prevalence_10_cnt', 'operOPCSL1_0t30d_prevalence_11_cnt', 'operOPCSL1_0t30d_prevalence_12_cnt', 'operOPCSL1_0t30d_prevalence_13_cnt', 'operOPCSL1_0t30d_prevalence_14_cnt', 'operOPCSL1_0t30d_prevalence_15_cnt', 'operOPCSL1_0t30d_prevalence_16_cnt', 'operOPCSL1_0t30d_prevalence_17_cnt', 'operOPCSL1_0t30d_prevalence_18_cnt', 'operOPCSL1_0t30d_prevalence_19_cnt', 'operOPCSL1_0t30d_prevalence_20_cnt', 'operOPCSL1_0t30d_prevalence_21_cnt', 'operOPCSL1_0t30d_prevalence_22_cnt', 'operOPCSL1_0t30d_prevalence_23_cnt', 'operOPCSL1_0t30d_prevalence_24_cnt', 'operOPCSL1_0t30d_prevalence_25_cnt', 'operOPCSL1_0t30d_prevalence_26_cnt', 'operOPCSL1_0t30d_prevalence_27_cnt', 'operOPCSL1_0t30d_prevalence_28_cnt', 'operOPCSL1_0t30d_prevalence_29_cnt', 'operOPCSL1_0t30d_prevalence_30_cnt'\n", |
||
| 2084 | " , 'operOPCSL1_30t90d_others_cnt', 'operOPCSL1_30t90d_prevalence_1_cnt', 'operOPCSL1_30t90d_prevalence_2_cnt', 'operOPCSL1_30t90d_prevalence_3_cnt', 'operOPCSL1_30t90d_prevalence_4_cnt', 'operOPCSL1_30t90d_prevalence_5_cnt', 'operOPCSL1_30t90d_prevalence_6_cnt', 'operOPCSL1_30t90d_prevalence_7_cnt', 'operOPCSL1_30t90d_prevalence_8_cnt', 'operOPCSL1_30t90d_prevalence_9_cnt', 'operOPCSL1_30t90d_prevalence_10_cnt', 'operOPCSL1_30t90d_prevalence_11_cnt', 'operOPCSL1_30t90d_prevalence_12_cnt', 'operOPCSL1_30t90d_prevalence_13_cnt', 'operOPCSL1_30t90d_prevalence_14_cnt', 'operOPCSL1_30t90d_prevalence_15_cnt', 'operOPCSL1_30t90d_prevalence_16_cnt', 'operOPCSL1_30t90d_prevalence_17_cnt', 'operOPCSL1_30t90d_prevalence_18_cnt', 'operOPCSL1_30t90d_prevalence_19_cnt', 'operOPCSL1_30t90d_prevalence_20_cnt', 'operOPCSL1_30t90d_prevalence_21_cnt', 'operOPCSL1_30t90d_prevalence_22_cnt', 'operOPCSL1_30t90d_prevalence_23_cnt', 'operOPCSL1_30t90d_prevalence_24_cnt', 'operOPCSL1_30t90d_prevalence_25_cnt', 'operOPCSL1_30t90d_prevalence_26_cnt', 'operOPCSL1_30t90d_prevalence_27_cnt', 'operOPCSL1_30t90d_prevalence_28_cnt', 'operOPCSL1_30t90d_prevalence_29_cnt', 'operOPCSL1_30t90d_prevalence_30_cnt'\n", |
||
| 2085 | " , 'operOPCSL1_90t180d_others_cnt', 'operOPCSL1_90t180d_prevalence_1_cnt', 'operOPCSL1_90t180d_prevalence_2_cnt', 'operOPCSL1_90t180d_prevalence_3_cnt', 'operOPCSL1_90t180d_prevalence_4_cnt', 'operOPCSL1_90t180d_prevalence_5_cnt', 'operOPCSL1_90t180d_prevalence_6_cnt', 'operOPCSL1_90t180d_prevalence_7_cnt', 'operOPCSL1_90t180d_prevalence_8_cnt', 'operOPCSL1_90t180d_prevalence_9_cnt', 'operOPCSL1_90t180d_prevalence_10_cnt', 'operOPCSL1_90t180d_prevalence_11_cnt', 'operOPCSL1_90t180d_prevalence_12_cnt', 'operOPCSL1_90t180d_prevalence_13_cnt', 'operOPCSL1_90t180d_prevalence_14_cnt', 'operOPCSL1_90t180d_prevalence_15_cnt', 'operOPCSL1_90t180d_prevalence_16_cnt', 'operOPCSL1_90t180d_prevalence_17_cnt', 'operOPCSL1_90t180d_prevalence_18_cnt', 'operOPCSL1_90t180d_prevalence_19_cnt', 'operOPCSL1_90t180d_prevalence_20_cnt', 'operOPCSL1_90t180d_prevalence_21_cnt', 'operOPCSL1_90t180d_prevalence_22_cnt', 'operOPCSL1_90t180d_prevalence_23_cnt', 'operOPCSL1_90t180d_prevalence_24_cnt', 'operOPCSL1_90t180d_prevalence_25_cnt', 'operOPCSL1_90t180d_prevalence_26_cnt', 'operOPCSL1_90t180d_prevalence_27_cnt', 'operOPCSL1_90t180d_prevalence_28_cnt', 'operOPCSL1_90t180d_prevalence_29_cnt', 'operOPCSL1_90t180d_prevalence_30_cnt'\n", |
||
| 2086 | " , 'operOPCSL1_180t365d_others_cnt', 'operOPCSL1_180t365d_prevalence_1_cnt', 'operOPCSL1_180t365d_prevalence_2_cnt', 'operOPCSL1_180t365d_prevalence_3_cnt', 'operOPCSL1_180t365d_prevalence_4_cnt', 'operOPCSL1_180t365d_prevalence_5_cnt', 'operOPCSL1_180t365d_prevalence_6_cnt', 'operOPCSL1_180t365d_prevalence_7_cnt', 'operOPCSL1_180t365d_prevalence_8_cnt', 'operOPCSL1_180t365d_prevalence_9_cnt', 'operOPCSL1_180t365d_prevalence_10_cnt', 'operOPCSL1_180t365d_prevalence_11_cnt', 'operOPCSL1_180t365d_prevalence_12_cnt', 'operOPCSL1_180t365d_prevalence_13_cnt', 'operOPCSL1_180t365d_prevalence_14_cnt', 'operOPCSL1_180t365d_prevalence_15_cnt', 'operOPCSL1_180t365d_prevalence_16_cnt', 'operOPCSL1_180t365d_prevalence_17_cnt', 'operOPCSL1_180t365d_prevalence_18_cnt', 'operOPCSL1_180t365d_prevalence_19_cnt', 'operOPCSL1_180t365d_prevalence_20_cnt', 'operOPCSL1_180t365d_prevalence_21_cnt', 'operOPCSL1_180t365d_prevalence_22_cnt', 'operOPCSL1_180t365d_prevalence_23_cnt', 'operOPCSL1_180t365d_prevalence_24_cnt', 'operOPCSL1_180t365d_prevalence_25_cnt', 'operOPCSL1_180t365d_prevalence_26_cnt', 'operOPCSL1_180t365d_prevalence_27_cnt', 'operOPCSL1_180t365d_prevalence_28_cnt', 'operOPCSL1_180t365d_prevalence_29_cnt', 'operOPCSL1_180t365d_prevalence_30_cnt'\n", |
||
| 2087 | " , 'operOPCSL1_365t730d_others_cnt', 'operOPCSL1_365t730d_prevalence_1_cnt', 'operOPCSL1_365t730d_prevalence_2_cnt', 'operOPCSL1_365t730d_prevalence_3_cnt', 'operOPCSL1_365t730d_prevalence_4_cnt', 'operOPCSL1_365t730d_prevalence_5_cnt', 'operOPCSL1_365t730d_prevalence_6_cnt', 'operOPCSL1_365t730d_prevalence_7_cnt', 'operOPCSL1_365t730d_prevalence_8_cnt', 'operOPCSL1_365t730d_prevalence_9_cnt', 'operOPCSL1_365t730d_prevalence_10_cnt', 'operOPCSL1_365t730d_prevalence_11_cnt', 'operOPCSL1_365t730d_prevalence_12_cnt', 'operOPCSL1_365t730d_prevalence_13_cnt', 'operOPCSL1_365t730d_prevalence_14_cnt', 'operOPCSL1_365t730d_prevalence_15_cnt', 'operOPCSL1_365t730d_prevalence_16_cnt', 'operOPCSL1_365t730d_prevalence_17_cnt', 'operOPCSL1_365t730d_prevalence_18_cnt', 'operOPCSL1_365t730d_prevalence_19_cnt', 'operOPCSL1_365t730d_prevalence_20_cnt', 'operOPCSL1_365t730d_prevalence_21_cnt', 'operOPCSL1_365t730d_prevalence_22_cnt', 'operOPCSL1_365t730d_prevalence_23_cnt', 'operOPCSL1_365t730d_prevalence_24_cnt', 'operOPCSL1_365t730d_prevalence_25_cnt', 'operOPCSL1_365t730d_prevalence_26_cnt', 'operOPCSL1_365t730d_prevalence_27_cnt', 'operOPCSL1_365t730d_prevalence_28_cnt', 'operOPCSL1_365t730d_prevalence_29_cnt', 'operOPCSL1_365t730d_prevalence_30_cnt']\n", |
||
| 2088 | "file_name = \"report_population_operations_\" + method_name + \"_\" + target_feature + \"_\"" |
||
| 2089 | ] |
||
| 2090 | }, |
||
| 2091 | { |
||
| 2092 | "cell_type": "code", |
||
| 2093 | "execution_count": null, |
||
| 2094 | "metadata": { |
||
| 2095 | "collapsed": true, |
||
| 2096 | "deletable": true, |
||
| 2097 | "editable": true |
||
| 2098 | }, |
||
| 2099 | "outputs": [], |
||
| 2100 | "source": [ |
||
| 2101 | "o_summaries = population_statistics(features_extra['train'], diagnoses)\n", |
||
| 2102 | "readers_writers.save_csv(path=CONSTANTS.io_path, title=file_name + \"train\", data=o_summaries, append=False, extension=\"csv\", header=o_summaries.columns)\n", |
||
| 2103 | "\n", |
||
| 2104 | "o_summaries = population_statistics(features_extra['test'], diagnoses)\n", |
||
| 2105 | "readers_writers.save_csv(path=CONSTANTS.io_path, title=file_name + \"test\", data=o_summaries, append=False, extension=\"csv\", header=o_summaries.columns)" |
||
| 2106 | ] |
||
| 2107 | }, |
||
| 2108 | { |
||
| 2109 | "cell_type": "markdown", |
||
| 2110 | "metadata": { |
||
| 2111 | "deletable": true, |
||
| 2112 | "editable": true |
||
| 2113 | }, |
||
| 2114 | "source": [ |
||
| 2115 | "#### 5.2.4. Most Prevalent Main Speciality\n", |
||
| 2116 | "Most prevalent operations variables (30-day, 1-year readmission): \n", |
||
| 2117 | "* Total, Admissions, Emergency Readmission Rate, Prior Spells, Male (%), Age (IQR), LoS (IQR), TP, FP, FN, TN" |
||
| 2118 | ] |
||
| 2119 | }, |
||
| 2120 | { |
||
| 2121 | "cell_type": "code", |
||
| 2122 | "execution_count": null, |
||
| 2123 | "metadata": { |
||
| 2124 | "collapsed": true, |
||
| 2125 | "deletable": true, |
||
| 2126 | "editable": true |
||
| 2127 | }, |
||
| 2128 | "outputs": [], |
||
| 2129 | "source": [ |
||
| 2130 | "diagnoses = ['mainspef_0t30d_others_cnt', 'mainspef_0t30d_prevalence_1_cnt', 'mainspef_0t30d_prevalence_2_cnt', 'mainspef_0t30d_prevalence_3_cnt', 'mainspef_0t30d_prevalence_4_cnt', 'mainspef_0t30d_prevalence_5_cnt', 'mainspef_0t30d_prevalence_6_cnt', 'mainspef_0t30d_prevalence_7_cnt', 'mainspef_0t30d_prevalence_8_cnt', 'mainspef_0t30d_prevalence_9_cnt', 'mainspef_0t30d_prevalence_10_cnt'\n", |
||
| 2131 | " , 'mainspef_30t90d_others_cnt', 'mainspef_30t90d_prevalence_1_cnt', 'mainspef_30t90d_prevalence_2_cnt', 'mainspef_30t90d_prevalence_3_cnt', 'mainspef_30t90d_prevalence_4_cnt', 'mainspef_30t90d_prevalence_5_cnt', 'mainspef_30t90d_prevalence_6_cnt', 'mainspef_30t90d_prevalence_7_cnt', 'mainspef_30t90d_prevalence_8_cnt', 'mainspef_30t90d_prevalence_9_cnt', 'mainspef_30t90d_prevalence_10_cnt'\n", |
||
| 2132 | " , 'mainspef_90t180d_others_cnt', 'mainspef_90t180d_prevalence_1_cnt', 'mainspef_90t180d_prevalence_2_cnt', 'mainspef_90t180d_prevalence_3_cnt', 'mainspef_90t180d_prevalence_4_cnt', 'mainspef_90t180d_prevalence_5_cnt', 'mainspef_90t180d_prevalence_6_cnt', 'mainspef_90t180d_prevalence_7_cnt', 'mainspef_90t180d_prevalence_8_cnt', 'mainspef_90t180d_prevalence_9_cnt', 'mainspef_90t180d_prevalence_10_cnt'\n", |
||
| 2133 | " , 'mainspef_180t365d_others_cnt', 'mainspef_180t365d_prevalence_1_cnt', 'mainspef_180t365d_prevalence_2_cnt', 'mainspef_180t365d_prevalence_3_cnt', 'mainspef_180t365d_prevalence_4_cnt', 'mainspef_180t365d_prevalence_5_cnt', 'mainspef_180t365d_prevalence_6_cnt', 'mainspef_180t365d_prevalence_7_cnt', 'mainspef_180t365d_prevalence_8_cnt', 'mainspef_180t365d_prevalence_9_cnt', 'mainspef_180t365d_prevalence_10_cnt'\n", |
||
| 2134 | " , 'mainspef_365t730d_others_cnt', 'mainspef_365t730d_prevalence_1_cnt', 'mainspef_365t730d_prevalence_2_cnt', 'mainspef_365t730d_prevalence_3_cnt', 'mainspef_365t730d_prevalence_4_cnt', 'mainspef_365t730d_prevalence_5_cnt', 'mainspef_365t730d_prevalence_6_cnt', 'mainspef_365t730d_prevalence_7_cnt', 'mainspef_365t730d_prevalence_8_cnt', 'mainspef_365t730d_prevalence_9_cnt', 'mainspef_365t730d_prevalence_10_cnt']\n", |
||
| 2135 | "file_name = \"report_population_operations_\" + method_name + \"_\" + target_feature + \"_\"" |
||
| 2136 | ] |
||
| 2137 | }, |
||
| 2138 | { |
||
| 2139 | "cell_type": "code", |
||
| 2140 | "execution_count": null, |
||
| 2141 | "metadata": { |
||
| 2142 | "collapsed": false, |
||
| 2143 | "deletable": true, |
||
| 2144 | "editable": true |
||
| 2145 | }, |
||
| 2146 | "outputs": [], |
||
| 2147 | "source": [ |
||
| 2148 | "o_summaries = population_statistics(features_extra['train'], diagnoses)\n", |
||
| 2149 | "readers_writers.save_csv(path=CONSTANTS.io_path, title=file_name + \"train\", data=o_summaries, append=False, extension=\"csv\", header=o_summaries.columns)\n", |
||
| 2150 | "\n", |
||
| 2151 | "o_summaries = population_statistics(features_extra['test'], diagnoses)\n", |
||
| 2152 | "readers_writers.save_csv(path=CONSTANTS.io_path, title=file_name + \"test\", data=o_summaries, append=False, extension=\"csv\", header=o_summaries.columns)" |
||
| 2153 | ] |
||
| 2154 | }, |
||
| 2155 | { |
||
| 2156 | "cell_type": "markdown", |
||
| 2157 | "metadata": { |
||
| 2158 | "deletable": true, |
||
| 2159 | "editable": true |
||
| 2160 | }, |
||
| 2161 | "source": [ |
||
| 2162 | "#### 5.2.5. Other Variables\n", |
||
| 2163 | "Other variables (30-day, 1-year readmission): \n", |
||
| 2164 | "* Total, Admissions, Emergency Readmission Rate, Prior Spells, Male (%), Age (IQR), LoS (IQR), TP, FP, FN, TN" |
||
| 2165 | ] |
||
| 2166 | }, |
||
| 2167 | { |
||
| 2168 | "cell_type": "code", |
||
| 2169 | "execution_count": null, |
||
| 2170 | "metadata": { |
||
| 2171 | "collapsed": true, |
||
| 2172 | "deletable": true, |
||
| 2173 | "editable": true |
||
| 2174 | }, |
||
| 2175 | "outputs": [], |
||
| 2176 | "source": [ |
||
| 2177 | "diagnoses = ['gapDays_0t30d_avg', 'gapDays_30t90d_avg', 'gapDays_90t180d_avg', 'gapDays_180t365d_avg', 'gapDays_365t730d_avg', \n", |
||
| 2178 | " 'epidur_0t30d_avg', 'epidur_30t90d_avg', 'epidur_90t180d_avg', 'epidur_180t365d_avg', 'epidur_365t730d_avg', \n", |
||
| 2179 | " 'preopdur_0t30d_avg', 'preopdur_30t90d_avg', 'preopdur_90t180d_avg', 'preopdur_180t365d_avg', 'preopdur_365t730d_avg', \n", |
||
| 2180 | " 'posopdur_0t30d_avg', 'posopdur_30t90d_avg', 'posopdur_90t180d_avg', 'posopdur_180t365d_avg', 'posopdur_365t730d_avg']\n", |
||
| 2181 | "file_name = \"report_population_other_variables_\" + method_name + \"_\" + target_feature + \"_\"" |
||
| 2182 | ] |
||
| 2183 | }, |
||
| 2184 | { |
||
| 2185 | "cell_type": "code", |
||
| 2186 | "execution_count": null, |
||
| 2187 | "metadata": { |
||
| 2188 | "collapsed": true, |
||
| 2189 | "deletable": true, |
||
| 2190 | "editable": true |
||
| 2191 | }, |
||
| 2192 | "outputs": [], |
||
| 2193 | "source": [ |
||
| 2194 | "o_summaries = population_statistics(features_extra['train'], diagnoses)\n", |
||
| 2195 | "readers_writers.save_csv(path=CONSTANTS.io_path, title=file_name + \"train\", data=o_summaries, append=False, extension=\"csv\", header=o_summaries.columns)\n", |
||
| 2196 | "\n", |
||
| 2197 | "o_summaries = population_statistics(features_extra['test'], diagnoses)\n", |
||
| 2198 | "readers_writers.save_csv(path=CONSTANTS.io_path, title=file_name + \"test\", data=o_summaries, append=False, extension=\"csv\", header=o_summaries.columns)" |
||
| 2199 | ] |
||
| 2200 | }, |
||
| 2201 | { |
||
| 2202 | "cell_type": "markdown", |
||
| 2203 | "metadata": { |
||
| 2204 | "deletable": true, |
||
| 2205 | "editable": true |
||
| 2206 | }, |
||
| 2207 | "source": [ |
||
| 2208 | "<br/><br/>" |
||
| 2209 | ] |
||
| 2210 | }, |
||
| 2211 | { |
||
| 2212 | "cell_type": "markdown", |
||
| 2213 | "metadata": { |
||
| 2214 | "deletable": true, |
||
| 2215 | "editable": true |
||
| 2216 | }, |
||
| 2217 | "source": [ |
||
| 2218 | "### 5.3. Plots" |
||
| 2219 | ] |
||
| 2220 | }, |
||
| 2221 | { |
||
| 2222 | "cell_type": "code", |
||
| 2223 | "execution_count": null, |
||
| 2224 | "metadata": { |
||
| 2225 | "collapsed": true, |
||
| 2226 | "deletable": true, |
||
| 2227 | "editable": true |
||
| 2228 | }, |
||
| 2229 | "outputs": [], |
||
| 2230 | "source": [ |
||
| 2231 | "file_name = \"report_population_\" + method_name + \"_\" + target_feature + \"_\"" |
||
| 2232 | ] |
||
| 2233 | }, |
||
| 2234 | { |
||
| 2235 | "cell_type": "markdown", |
||
| 2236 | "metadata": { |
||
| 2237 | "deletable": true, |
||
| 2238 | "editable": true |
||
| 2239 | }, |
||
| 2240 | "source": [ |
||
| 2241 | "#### 5.3.1. ROC" |
||
| 2242 | ] |
||
| 2243 | }, |
||
| 2244 | { |
||
| 2245 | "cell_type": "code", |
||
| 2246 | "execution_count": null, |
||
| 2247 | "metadata": { |
||
| 2248 | "collapsed": false, |
||
| 2249 | "deletable": true, |
||
| 2250 | "editable": true |
||
| 2251 | }, |
||
| 2252 | "outputs": [], |
||
| 2253 | "source": [ |
||
| 2254 | "fig, summaries = plots.roc(training_method.model_predict[\"test\"], features_extra[\"test\"][target_feature], \n", |
||
| 2255 | " title=\"ROC Curve\", lw=2)\n", |
||
| 2256 | "display(fig)" |
||
| 2257 | ] |
||
| 2258 | }, |
||
| 2259 | { |
||
| 2260 | "cell_type": "code", |
||
| 2261 | "execution_count": null, |
||
| 2262 | "metadata": { |
||
| 2263 | "collapsed": false, |
||
| 2264 | "deletable": true, |
||
| 2265 | "editable": true |
||
| 2266 | }, |
||
| 2267 | "outputs": [], |
||
| 2268 | "source": [ |
||
| 2269 | "# save\n", |
||
| 2270 | "plt.savefig(os.path.join(CONSTANTS.io_path, file_name + \"_roc\" + \".pdf\"), \n", |
||
| 2271 | " dpi=300, facecolor='w', edgecolor='w', orientation='portrait', papertype=None, format=\"pdf\",\n", |
||
| 2272 | " transparent=False, bbox_inches=None, pad_inches=0.1, frameon=None)" |
||
| 2273 | ] |
||
| 2274 | }, |
||
| 2275 | { |
||
| 2276 | "cell_type": "markdown", |
||
| 2277 | "metadata": { |
||
| 2278 | "deletable": true, |
||
| 2279 | "editable": true |
||
| 2280 | }, |
||
| 2281 | "source": [ |
||
| 2282 | "#### 5.3.2. Precision Recall" |
||
| 2283 | ] |
||
| 2284 | }, |
||
| 2285 | { |
||
| 2286 | "cell_type": "code", |
||
| 2287 | "execution_count": null, |
||
| 2288 | "metadata": { |
||
| 2289 | "collapsed": false, |
||
| 2290 | "deletable": true, |
||
| 2291 | "editable": true, |
||
| 2292 | "scrolled": true |
||
| 2293 | }, |
||
| 2294 | "outputs": [], |
||
| 2295 | "source": [ |
||
| 2296 | "fig, summaries = plots.precision_recall(training_method.model_predict[\"test\"], \n", |
||
| 2297 | " features_extra[\"test\"][target_feature], \n", |
||
| 2298 | " title=\"Precision-Recall Curve\", lw=2)\n", |
||
| 2299 | "display(fig)" |
||
| 2300 | ] |
||
| 2301 | }, |
||
| 2302 | { |
||
| 2303 | "cell_type": "code", |
||
| 2304 | "execution_count": null, |
||
| 2305 | "metadata": { |
||
| 2306 | "collapsed": true, |
||
| 2307 | "deletable": true, |
||
| 2308 | "editable": true |
||
| 2309 | }, |
||
| 2310 | "outputs": [], |
||
| 2311 | "source": [ |
||
| 2312 | "# save\n", |
||
| 2313 | "plt.savefig(os.path.join(CONSTANTS.io_path, file_name + \"_precision_recall\" + \".pdf\"), \n", |
||
| 2314 | " dpi=300, facecolor='w', edgecolor='w', orientation='portrait', papertype=None, format=\"pdf\",\n", |
||
| 2315 | " transparent=False, bbox_inches=None, pad_inches=0.1, frameon=None)" |
||
| 2316 | ] |
||
| 2317 | }, |
||
| 2318 | { |
||
| 2319 | "cell_type": "markdown", |
||
| 2320 | "metadata": { |
||
| 2321 | "deletable": true, |
||
| 2322 | "editable": true |
||
| 2323 | }, |
||
| 2324 | "source": [ |
||
| 2325 | "#### 5.3.3. Learning Curve" |
||
| 2326 | ] |
||
| 2327 | }, |
||
| 2328 | { |
||
| 2329 | "cell_type": "code", |
||
| 2330 | "execution_count": null, |
||
| 2331 | "metadata": { |
||
| 2332 | "collapsed": false, |
||
| 2333 | "deletable": true, |
||
| 2334 | "editable": true |
||
| 2335 | }, |
||
| 2336 | "outputs": [], |
||
| 2337 | "source": [ |
||
| 2338 | "fig, summaries = plots.learning_curve(training_method.model_train, \n", |
||
| 2339 | " features_extra[\"test\"][features_names_selected], \n", |
||
| 2340 | " features_extra[\"test\"][target_feature],\n", |
||
| 2341 | " title=\"Learning Curve\", ylim=None, cv=None, n_jobs=-1, train_sizes=np.linspace(.1, 1.0, 5))\n", |
||
| 2342 | "display(fig)" |
||
| 2343 | ] |
||
| 2344 | }, |
||
| 2345 | { |
||
| 2346 | "cell_type": "code", |
||
| 2347 | "execution_count": null, |
||
| 2348 | "metadata": { |
||
| 2349 | "collapsed": true, |
||
| 2350 | "deletable": true, |
||
| 2351 | "editable": true |
||
| 2352 | }, |
||
| 2353 | "outputs": [], |
||
| 2354 | "source": [ |
||
| 2355 | "# save\n", |
||
| 2356 | "plt.savefig(os.path.join(CONSTANTS.io_path, file_name + \"_learning_curve\" + \".pdf\"), \n", |
||
| 2357 | " dpi=300, facecolor='w', edgecolor='w', orientation='portrait', papertype=None, format=\"pdf\",\n", |
||
| 2358 | " transparent=False, bbox_inches=None, pad_inches=0.1, frameon=None)" |
||
| 2359 | ] |
||
| 2360 | }, |
||
| 2361 | { |
||
| 2362 | "cell_type": "markdown", |
||
| 2363 | "metadata": { |
||
| 2364 | "deletable": true, |
||
| 2365 | "editable": true |
||
| 2366 | }, |
||
| 2367 | "source": [ |
||
| 2368 | "#### 5.3.4. Validation Curve" |
||
| 2369 | ] |
||
| 2370 | }, |
||
| 2371 | { |
||
| 2372 | "cell_type": "markdown", |
||
| 2373 | "metadata": { |
||
| 2374 | "deletable": true, |
||
| 2375 | "editable": true |
||
| 2376 | }, |
||
| 2377 | "source": [ |
||
| 2378 | "Set the model's metadata" |
||
| 2379 | ] |
||
| 2380 | }, |
||
| 2381 | { |
||
| 2382 | "cell_type": "code", |
||
| 2383 | "execution_count": null, |
||
| 2384 | "metadata": { |
||
| 2385 | "collapsed": false, |
||
| 2386 | "deletable": true, |
||
| 2387 | "editable": true |
||
| 2388 | }, |
||
| 2389 | "outputs": [], |
||
| 2390 | "source": [ |
||
| 2391 | "# method metadata\n", |
||
| 2392 | "if method_name == \"lr\":\n", |
||
| 2393 | " param_name = \"clf__C\"\n", |
||
| 2394 | " param_range = [0.001, 0.01, 0.1, 1.0, 10.0, 100.0]\n", |
||
| 2395 | "elif method_name == \"rfc\":\n", |
||
| 2396 | " param_name = \"max_features\"\n", |
||
| 2397 | " param_range = range(1, 4, 1) # range(1, 20, 1)\n", |
||
| 2398 | "elif method_name == \"nn\":\n", |
||
| 2399 | " param_name = \"alpha\"\n", |
||
| 2400 | " param_range = range(1e4, 1e6, 9e4)" |
||
| 2401 | ] |
||
| 2402 | }, |
||
| 2403 | { |
||
| 2404 | "cell_type": "code", |
||
| 2405 | "execution_count": null, |
||
| 2406 | "metadata": { |
||
| 2407 | "collapsed": false, |
||
| 2408 | "deletable": true, |
||
| 2409 | "editable": true |
||
| 2410 | }, |
||
| 2411 | "outputs": [], |
||
| 2412 | "source": [ |
||
| 2413 | "fig, summaries = plots.validation_curve(training_method.model_train, \n", |
||
| 2414 | " features_extra[\"test\"][features_names_selected], \n", |
||
| 2415 | " features_extra[\"test\"][target_feature],\n", |
||
| 2416 | " param_name, param_range, \n", |
||
| 2417 | " title=\"Learning Curve\", ylim=None, cv=None, lw=2, n_jobs=-1)\n", |
||
| 2418 | "display(fig)" |
||
| 2419 | ] |
||
| 2420 | }, |
||
| 2421 | { |
||
| 2422 | "cell_type": "code", |
||
| 2423 | "execution_count": null, |
||
| 2424 | "metadata": { |
||
| 2425 | "collapsed": true, |
||
| 2426 | "deletable": true, |
||
| 2427 | "editable": true |
||
| 2428 | }, |
||
| 2429 | "outputs": [], |
||
| 2430 | "source": [ |
||
| 2431 | "# save\n", |
||
| 2432 | "plt.savefig(os.path.join(CONSTANTS.io_path, file_name + \"_validation_curve\" + \".pdf\"), \n", |
||
| 2433 | " dpi=300, facecolor='w', edgecolor='w', orientation='portrait', papertype=None, format=\"pdf\",\n", |
||
| 2434 | " transparent=False, bbox_inches=None, pad_inches=0.1, frameon=None)" |
||
| 2435 | ] |
||
| 2436 | }, |
||
| 2437 | { |
||
| 2438 | "cell_type": "markdown", |
||
| 2439 | "metadata": { |
||
| 2440 | "deletable": true, |
||
| 2441 | "editable": true |
||
| 2442 | }, |
||
| 2443 | "source": [ |
||
| 2444 | "<br/><br/>" |
||
| 2445 | ] |
||
| 2446 | }, |
||
| 2447 | { |
||
| 2448 | "cell_type": "markdown", |
||
| 2449 | "metadata": { |
||
| 2450 | "collapsed": true, |
||
| 2451 | "deletable": true, |
||
| 2452 | "editable": true |
||
| 2453 | }, |
||
| 2454 | "source": [ |
||
| 2455 | "Fin!" |
||
| 2456 | ] |
||
| 2457 | } |
||
| 2458 | ], |
||
| 2459 | "metadata": { |
||
| 2460 | "kernelspec": { |
||
| 2461 | "display_name": "Python 3", |
||
| 2462 | "language": "python", |
||
| 2463 | "name": "python3" |
||
| 2464 | }, |
||
| 2465 | "language_info": { |
||
| 2466 | "codemirror_mode": { |
||
| 2467 | "name": "ipython", |
||
| 2468 | "version": 3 |
||
| 2469 | }, |
||
| 2470 | "file_extension": ".py", |
||
| 2471 | "mimetype": "text/x-python", |
||
| 2472 | "name": "python", |
||
| 2473 | "nbconvert_exporter": "python", |
||
| 2474 | "pygments_lexer": "ipython3", |
||
| 2475 | "version": "3.5.3" |
||
| 2476 | } |
||
| 2477 | }, |
||
| 2478 | "nbformat": 4, |
||
| 2479 | "nbformat_minor": 2 |
||
| 2480 | } |