first commit

nlp-pucrs · Nov 6, 2017 · 85c0984 · 85c0984
1 parent fbfcba8
commit 85c0984
Show file tree

Hide file tree

Showing 16 changed files with 5,231 additions and 0 deletions.
diff --git a/.gitignore b/.gitignore
@@ -0,0 +1,2 @@
+/.ipynb_checkpoints
+/__pycache__
diff --git a/1_dataset_stats.ipynb b/1_dataset_stats.ipynb
@@ -0,0 +1,240 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "collapsed": false,
+    "deletable": true,
+    "editable": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['medication', 'frequency', 'dose', 'target'], dtype='object')"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "prescription = pd.read_csv('data/prescriptions_sample.csv.gz', compression='gzip')\n",
+    "prescription.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "collapsed": false,
+    "deletable": true,
+    "editable": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "150113"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(prescription)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "collapsed": false,
+    "deletable": true,
+    "editable": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr>\n",
+       "      <th></th>\n",
+       "      <th>target</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th></th>\n",
+       "      <th>count</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>medication</th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ALOPURINOL</th>\n",
+       "      <td>4729</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>AMPICILINA</th>\n",
+       "      <td>7226</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ANLODIPINO</th>\n",
+       "      <td>10392</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>BISACODIL</th>\n",
+       "      <td>9483</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>CETOPROFENO</th>\n",
+       "      <td>10907</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>CLORETO</th>\n",
+       "      <td>5593</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>DIAZEPAM</th>\n",
+       "      <td>9030</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>DICLOFENACO</th>\n",
+       "      <td>5559</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>DOXAZOSINA</th>\n",
+       "      <td>6280</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ENALAPRIL</th>\n",
+       "      <td>9585</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ENOXAPARINA</th>\n",
+       "      <td>7666</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>HIDRALAZINA</th>\n",
+       "      <td>6056</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>LOPERAMIDA</th>\n",
+       "      <td>4957</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>MORFINA</th>\n",
+       "      <td>5362</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>PARACETAMOL</th>\n",
+       "      <td>10811</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>POLIMIXINA</th>\n",
+       "      <td>7257</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RISPERIDONA</th>\n",
+       "      <td>5431</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SULFAMETOXAZOL</th>\n",
+       "      <td>7086</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>TENOFOVIR</th>\n",
+       "      <td>4518</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>VARFARINA</th>\n",
+       "      <td>6419</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>VITAMINAS</th>\n",
+       "      <td>5766</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "               target\n",
+       "                count\n",
+       "medication           \n",
+       "ALOPURINOL       4729\n",
+       "AMPICILINA       7226\n",
+       "ANLODIPINO      10392\n",
+       "BISACODIL        9483\n",
+       "CETOPROFENO     10907\n",
+       "CLORETO          5593\n",
+       "DIAZEPAM         9030\n",
+       "DICLOFENACO      5559\n",
+       "DOXAZOSINA       6280\n",
+       "ENALAPRIL        9585\n",
+       "ENOXAPARINA      7666\n",
+       "HIDRALAZINA      6056\n",
+       "LOPERAMIDA       4957\n",
+       "MORFINA          5362\n",
+       "PARACETAMOL     10811\n",
+       "POLIMIXINA       7257\n",
+       "RISPERIDONA      5431\n",
+       "SULFAMETOXAZOL   7086\n",
+       "TENOFOVIR        4518\n",
+       "VARFARINA        6419\n",
+       "VITAMINAS        5766"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prescription[['medication','target']].groupby(['medication']).agg(['count'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true,
+    "deletable": true,
+    "editable": true
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.5.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}