01-explore-patient-table.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# eICU Collaborative Research Database\n",
    "\n",
    "# Notebook 1: Exploring the `patient` table\n",
    "\n",
    "The aim of this notebook is to introduce the `patient` table, a key table in the eICU Collaborative Research Database. \n",
    "\n",
    "The `patient` table contains patient demographics and admission and discharge details for hospital and ICU stays. For more detail, see: http:https://eicu-crd.mit.edu/eicutables/patient/\n",
    "\n",
    "Before starting, you will need to copy the eicu demo database file ('eicu_demo.sqlite3') to the `data` directory.\n",
    "\n",
    "Documentation on the eICU Collaborative Research Database can be found at: http:https://eicu-crd.mit.edu/. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1. Getting set up"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Import libraries\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import sqlite3\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Plot settings\n",
    "%matplotlib inline\n",
    "plt.style.use('ggplot')\n",
    "fontsize = 20 # size for x and y ticks\n",
    "plt.rcParams['legend.fontsize'] = fontsize\n",
    "plt.rcParams.update({'font.size': fontsize})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Connect to the database\n",
    "fn = os.path.join('data','eicu_demo.sqlite3')\n",
    "con = sqlite3.connect(fn)\n",
    "cur = con.cursor()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "hello world\n"
     ]
    }
   ],
   "source": [
    "print('hello world')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2. Display list of tables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "query = \\\n",
    "\"\"\"\n",
    "SELECT type, name\n",
    "FROM sqlite_master \n",
    "WHERE type='table'\n",
    "ORDER BY name;\n",
    "\"\"\"\n",
    "\n",
    "list_of_tables = pd.read_sql_query(query,con)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>type</th>\n",
       "      <th>name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>table</td>\n",
       "      <td>admissiondrug</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>table</td>\n",
       "      <td>admissiondx</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>table</td>\n",
       "      <td>apacheapsvar</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>table</td>\n",
       "      <td>apachepatientresult</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>table</td>\n",
       "      <td>apachepredvar</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>table</td>\n",
       "      <td>careplancareprovider</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>table</td>\n",
       "      <td>careplaneol</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>table</td>\n",
       "      <td>careplangeneral</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>table</td>\n",
       "      <td>careplangoal</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>table</td>\n",
       "      <td>careplaninfectiousdisease</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>table</td>\n",
       "      <td>diagnosis</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>table</td>\n",
       "      <td>infusiondrug</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>table</td>\n",
       "      <td>lab</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>table</td>\n",
       "      <td>medication</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>table</td>\n",
       "      <td>pasthistory</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>table</td>\n",
       "      <td>patient</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>table</td>\n",
       "      <td>treatment</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>table</td>\n",
       "      <td>vitalaperiodic</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>table</td>\n",
       "      <td>vitalperiodic</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     type                       name\n",
       "0   table              admissiondrug\n",
       "1   table                admissiondx\n",
       "2   table               apacheapsvar\n",
       "3   table        apachepatientresult\n",
       "4   table              apachepredvar\n",
       "5   table       careplancareprovider\n",
       "6   table                careplaneol\n",
       "7   table            careplangeneral\n",
       "8   table               careplangoal\n",
       "9   table  careplaninfectiousdisease\n",
       "10  table                  diagnosis\n",
       "11  table               infusiondrug\n",
       "12  table                        lab\n",
       "13  table                 medication\n",
       "14  table                pasthistory\n",
       "15  table                    patient\n",
       "16  table                  treatment\n",
       "17  table             vitalaperiodic\n",
       "18  table              vitalperiodic"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list_of_tables"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3. Reviewing the patient table"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "SELECT *\n",
      "FROM patient;\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# query to load data from the patient table\n",
    "query = \\\n",
    "\"\"\"\n",
    "SELECT *\n",
    "FROM patient;\n",
    "\"\"\"\n",
    "\n",
    "print(query)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# run the query and assign the output to a variable\n",
    "patient_tab = pd.read_sql_query(query,con)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>patientunitstayid</th>\n",
       "      <th>patienthealthsystemstayid</th>\n",
       "      <th>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>ethnicity</th>\n",
       "      <th>hospitalid</th>\n",
       "      <th>wardid</th>\n",
       "      <th>apacheadmissiondx</th>\n",
       "      <th>admissionheight</th>\n",
       "      <th>hospitaladmityear</th>\n",
       "      <th>...</th>\n",
       "      <th>unitstaytype</th>\n",
       "      <th>admissionweight</th>\n",
       "      <th>dischargeweight</th>\n",
       "      <th>unitdischargeyear</th>\n",
       "      <th>unitdischargetime24</th>\n",
       "      <th>unitdischargetime</th>\n",
       "      <th>unitdischargeoffset</th>\n",
       "      <th>unitdischargelocation</th>\n",
       "      <th>unitdischargestatus</th>\n",
       "      <th>uniquepid</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>165840</td>\n",
       "      <td>148008</td>\n",
       "      <td>Male</td>\n",
       "      <td>81</td>\n",
       "      <td>Caucasian</td>\n",
       "      <td>61</td>\n",
       "      <td>120</td>\n",
       "      <td>Arrest, respiratory (without cardiac arrest)</td>\n",
       "      <td>167.0</td>\n",
       "      <td>2015</td>\n",
       "      <td>...</td>\n",
       "      <td>admit</td>\n",
       "      <td>92.4</td>\n",
       "      <td>92.4</td>\n",
       "      <td>2015</td>\n",
       "      <td>23:48:00</td>\n",
       "      <td>midnight</td>\n",
       "      <td>75</td>\n",
       "      <td>Step-Down Unit (SDU)</td>\n",
       "      <td>Alive</td>\n",
       "      <td>002-12363</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>165841</td>\n",
       "      <td>148008</td>\n",
       "      <td>Male</td>\n",
       "      <td>81</td>\n",
       "      <td>Caucasian</td>\n",
       "      <td>61</td>\n",
       "      <td>120</td>\n",
       "      <td></td>\n",
       "      <td>167.0</td>\n",
       "      <td>2015</td>\n",
       "      <td>...</td>\n",
       "      <td>stepdown/other</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2015</td>\n",
       "      <td>03:15:00</td>\n",
       "      <td>morning</td>\n",
       "      <td>207</td>\n",
       "      <td>Death</td>\n",
       "      <td>Expired</td>\n",
       "      <td>002-12363</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>193119</td>\n",
       "      <td>169237</td>\n",
       "      <td>Male</td>\n",
       "      <td>84</td>\n",
       "      <td>Caucasian</td>\n",
       "      <td>69</td>\n",
       "      <td>98</td>\n",
       "      <td>Rhythm disturbance (atrial, supraventricular)</td>\n",
       "      <td>157.5</td>\n",
       "      <td>2015</td>\n",
       "      <td>...</td>\n",
       "      <td>admit</td>\n",
       "      <td>54.3</td>\n",
       "      <td>54.3</td>\n",
       "      <td>2015</td>\n",
       "      <td>02:23:00</td>\n",
       "      <td>morning</td>\n",
       "      <td>2176</td>\n",
       "      <td>Step-Down Unit (SDU)</td>\n",
       "      <td>Alive</td>\n",
       "      <td>002-13750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>193120</td>\n",
       "      <td>169237</td>\n",
       "      <td>Male</td>\n",
       "      <td>84</td>\n",
       "      <td>Caucasian</td>\n",
       "      <td>69</td>\n",
       "      <td>98</td>\n",
       "      <td></td>\n",
       "      <td>157.5</td>\n",
       "      <td>2015</td>\n",
       "      <td>...</td>\n",
       "      <td>stepdown/other</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2015</td>\n",
       "      <td>03:42:00</td>\n",
       "      <td>morning</td>\n",
       "      <td>79</td>\n",
       "      <td>Floor</td>\n",
       "      <td>Alive</td>\n",
       "      <td>002-13750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>147894</td>\n",
       "      <td>134127</td>\n",
       "      <td>Male</td>\n",
       "      <td>79</td>\n",
       "      <td>Caucasian</td>\n",
       "      <td>60</td>\n",
       "      <td>83</td>\n",
       "      <td></td>\n",
       "      <td>160.0</td>\n",
       "      <td>2015</td>\n",
       "      <td>...</td>\n",
       "      <td>admit</td>\n",
       "      <td>NaN</td>\n",
       "      <td>88.1</td>\n",
       "      <td>2015</td>\n",
       "      <td>00:10:00</td>\n",
       "      <td>midnight</td>\n",
       "      <td>4</td>\n",
       "      <td>Step-Down Unit (SDU)</td>\n",
       "      <td>Alive</td>\n",
       "      <td>002-14007</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 36 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   patientunitstayid  patienthealthsystemstayid gender age  ethnicity  \\\n",
       "0             165840                     148008   Male  81  Caucasian   \n",
       "1             165841                     148008   Male  81  Caucasian   \n",
       "2             193119                     169237   Male  84  Caucasian   \n",
       "3             193120                     169237   Male  84  Caucasian   \n",
       "4             147894                     134127   Male  79  Caucasian   \n",
       "\n",
       "   hospitalid  wardid                              apacheadmissiondx  \\\n",
       "0          61     120   Arrest, respiratory (without cardiac arrest)   \n",
       "1          61     120                                                  \n",
       "2          69      98  Rhythm disturbance (atrial, supraventricular)   \n",
       "3          69      98                                                  \n",
       "4          60      83                                                  \n",
       "\n",
       "   admissionheight  hospitaladmityear    ...        unitstaytype  \\\n",
       "0            167.0               2015    ...               admit   \n",
       "1            167.0               2015    ...      stepdown/other   \n",
       "2            157.5               2015    ...               admit   \n",
       "3            157.5               2015    ...      stepdown/other   \n",
       "4            160.0               2015    ...               admit   \n",
       "\n",
       "  admissionweight  dischargeweight unitdischargeyear  unitdischargetime24  \\\n",
       "0            92.4             92.4              2015             23:48:00   \n",
       "1             NaN              NaN              2015             03:15:00   \n",
       "2            54.3             54.3              2015             02:23:00   \n",
       "3             NaN              NaN              2015             03:42:00   \n",
       "4             NaN             88.1              2015             00:10:00   \n",
       "\n",
       "  unitdischargetime unitdischargeoffset  unitdischargelocation  \\\n",
       "0          midnight                  75   Step-Down Unit (SDU)   \n",
       "1           morning                 207                  Death   \n",
       "2           morning                2176   Step-Down Unit (SDU)   \n",
       "3           morning                  79                  Floor   \n",
       "4          midnight                   4   Step-Down Unit (SDU)   \n",
       "\n",
       "  unitdischargestatus  uniquepid  \n",
       "0               Alive  002-12363  \n",
       "1             Expired  002-12363  \n",
       "2               Alive  002-13750  \n",
       "3               Alive  002-13750  \n",
       "4               Alive  002-14007  \n",
       "\n",
       "[5 rows x 36 columns]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# display the first few rows of the dataframe\n",
    "patient_tab.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index([u'patientunitstayid', u'patienthealthsystemstayid', u'gender', u'age',\n",
       "       u'ethnicity', u'hospitalid', u'wardid', u'apacheadmissiondx',\n",
       "       u'admissionheight', u'hospitaladmityear', u'hospitaladmittime24',\n",
       "       u'hospitaladmittime', u'hospitaladmitoffset', u'hospitaladmitsource',\n",
       "       u'hospitaldischargeyear', u'hospitaldischargetime24',\n",
       "       u'hospitaldischargetime', u'hospitaldischargeoffset',\n",
       "       u'hospitaldischargelocation', u'hospitaldischargestatus', u'unittype',\n",
       "       u'unitadmityear', u'unitadmittime24', u'unitadmittime',\n",
       "       u'unitadmitsource', u'unitvisitnumber', u'unitstaytype',\n",
       "       u'admissionweight', u'dischargeweight', u'unitdischargeyear',\n",
       "       u'unitdischargetime24', u'unitdischargetime', u'unitdischargeoffset',\n",
       "       u'unitdischargelocation', u'unitdischargestatus', u'uniquepid'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# list all of the columns in the table\n",
    "patient_tab.columns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Questions\n",
    "\n",
    "- What does `patientunitstayid` represent? (hint, see: http:https://eicu-crd.mit.edu/eicutables/patient/)\n",
    "- What does `patienthealthsystemstayid` represent?\n",
    "- What does `uniquepid` represent?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>uniquepid</th>\n",
       "      <th>patientunitstayid</th>\n",
       "      <th>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>unitdischargestatus</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>002-12363</td>\n",
       "      <td>165840</td>\n",
       "      <td>Male</td>\n",
       "      <td>81</td>\n",
       "      <td>Alive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>002-12363</td>\n",
       "      <td>165841</td>\n",
       "      <td>Male</td>\n",
       "      <td>81</td>\n",
       "      <td>Expired</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>002-13750</td>\n",
       "      <td>193119</td>\n",
       "      <td>Male</td>\n",
       "      <td>84</td>\n",
       "      <td>Alive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>002-13750</td>\n",
       "      <td>193120</td>\n",
       "      <td>Male</td>\n",
       "      <td>84</td>\n",
       "      <td>Alive</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>002-14007</td>\n",
       "      <td>147894</td>\n",
       "      <td>Male</td>\n",
       "      <td>79</td>\n",
       "      <td>Alive</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   uniquepid  patientunitstayid gender age unitdischargestatus\n",
       "0  002-12363             165840   Male  81               Alive\n",
       "1  002-12363             165841   Male  81             Expired\n",
       "2  002-13750             193119   Male  84               Alive\n",
       "3  002-13750             193120   Male  84               Alive\n",
       "4  002-14007             147894   Male  79               Alive"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# select a limited number of columns to view\n",
    "columns = ['uniquepid', 'patientunitstayid','gender','age','unitdischargestatus']\n",
    "patient_tab[columns].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([u'14', u'18', u'19', u'21', u'22', u'24', u'26', u'27', u'28',\n",
       "       u'30', u'31', u'32', u'33', u'34', u'35', u'36', u'37', u'38',\n",
       "       u'39', u'40', u'41', u'42', u'43', u'44', u'45', u'46', u'47',\n",
       "       u'48', u'49', u'50', u'51', u'52', u'53', u'54', u'55', u'56',\n",
       "       u'57', u'58', u'59', u'60', u'61', u'62', u'63', u'64', u'65',\n",
       "       u'66', u'67', u'68', u'69', u'70', u'71', u'72', u'73', u'74',\n",
       "       u'75', u'76', u'77', u'78', u'79', u'80', u'81', u'82', u'83',\n",
       "       u'84', u'85', u'86', u'87', u'88', u'89', u'> 89'], dtype=object)"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# what are the unique values for age?\n",
    "age_col = 'age'\n",
    "patient_tab[age_col].sort_values().unique()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Questions\n",
    "\n",
    "- Try plotting a histogram of ages using the commands in the cell below. Why does the plot fail?\n",
    "\n",
    "```python\n",
    "# try plotting a histogram of ages\n",
    "figsize = (18,8)\n",
    "patient_tab[age_col].plot(kind='hist',\n",
    "                          figsize=figsize, \n",
    "                          fontsize=fontsize,\n",
    "                          bins=15)\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "ename": "TypeError",
     "evalue": "Empty 'DataFrame': no numeric data to plot",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-18-071ea2989a3d>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      3\u001b[0m                           \u001b[0mfigsize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mfigsize\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m                           \u001b[0mfontsize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mfontsize\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m                           bins=15)\n\u001b[0m",
      "\u001b[0;32m/usr/local/lib/python2.7/site-packages/pandas/plotting/_core.pyc\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, kind, ax, figsize, use_index, title, grid, legend, style, logx, logy, loglog, xticks, yticks, xlim, ylim, rot, fontsize, colormap, table, yerr, xerr, label, secondary_y, **kwds)\u001b[0m\n\u001b[1;32m   2444\u001b[0m                            \u001b[0mcolormap\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcolormap\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtable\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtable\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0myerr\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0myerr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2445\u001b[0m                            \u001b[0mxerr\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mxerr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlabel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mlabel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msecondary_y\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msecondary_y\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2446\u001b[0;31m                            **kwds)\n\u001b[0m\u001b[1;32m   2447\u001b[0m     \u001b[0m__call__\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__doc__\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mplot_series\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__doc__\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2448\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python2.7/site-packages/pandas/plotting/_core.pyc\u001b[0m in \u001b[0;36mplot_series\u001b[0;34m(data, kind, ax, figsize, use_index, title, grid, legend, style, logx, logy, loglog, xticks, yticks, xlim, ylim, rot, fontsize, colormap, table, yerr, xerr, label, secondary_y, **kwds)\u001b[0m\n\u001b[1;32m   1886\u001b[0m                  \u001b[0myerr\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0myerr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mxerr\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mxerr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1887\u001b[0m                  \u001b[0mlabel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mlabel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msecondary_y\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msecondary_y\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1888\u001b[0;31m                  **kwds)\n\u001b[0m\u001b[1;32m   1889\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1890\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python2.7/site-packages/pandas/plotting/_core.pyc\u001b[0m in \u001b[0;36m_plot\u001b[0;34m(data, x, y, subplots, ax, kind, **kwds)\u001b[0m\n\u001b[1;32m   1680\u001b[0m         \u001b[0mplot_obj\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mklass\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msubplots\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msubplots\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0max\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0max\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkind\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mkind\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1681\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1682\u001b[0;31m     \u001b[0mplot_obj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgenerate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1683\u001b[0m     \u001b[0mplot_obj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdraw\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1684\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0mplot_obj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresult\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python2.7/site-packages/pandas/plotting/_core.pyc\u001b[0m in \u001b[0;36mgenerate\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    234\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mgenerate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    235\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_args_adjust\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 236\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_compute_plot_data\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    237\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_setup_subplots\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    238\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_make_plot\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/usr/local/lib/python2.7/site-packages/pandas/plotting/_core.pyc\u001b[0m in \u001b[0;36m_compute_plot_data\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    343\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mis_empty\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    344\u001b[0m             raise TypeError('Empty {0!r}: no numeric data to '\n\u001b[0;32m--> 345\u001b[0;31m                             'plot'.format(numeric_data.__class__.__name__))\n\u001b[0m\u001b[1;32m    346\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    347\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnumeric_data\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mTypeError\u001b[0m: Empty 'DataFrame': no numeric data to plot"
     ]
    }
   ],
   "source": [
    "figsize = (18,8)\n",
    "patient_tab[age_col].plot(kind='hist',\n",
    "                          figsize=figsize, \n",
    "                          fontsize=fontsize,\n",
    "                          bins=15)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 14.,  18.,  19.,  21.,  22.,  24.,  26.,  27.,  28.,  30.,  31.,\n",
       "        32.,  33.,  34.,  35.,  36.,  37.,  38.,  39.,  40.,  41.,  42.,\n",
       "        43.,  44.,  45.,  46.,  47.,  48.,  49.,  50.,  51.,  52.,  53.,\n",
       "        54.,  55.,  56.,  57.,  58.,  59.,  60.,  61.,  62.,  63.,  64.,\n",
       "        65.,  66.,  67.,  68.,  69.,  70.,  71.,  72.,  73.,  74.,  75.,\n",
       "        76.,  77.,  78.,  79.,  80.,  81.,  82.,  83.,  84.,  85.,  86.,\n",
       "        87.,  88.,  89.,  nan])"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# create a column containing numerical ages\n",
    "# If ‘coerce’, then invalid parsing will be set as NaN\n",
    "agenum_col = 'age_num'\n",
    "patient_tab[agenum_col] = pd.to_numeric(patient_tab[age_col], errors='coerce')\n",
    "patient_tab[agenum_col].sort_values().unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x109bec410>"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABFMAAAHxCAYAAAChyPPTAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nEREREREREVmAkylERERERERERBb4H/1jZVbaKm9cAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x1094cd210>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# try plotting a histogram of ages\n",
    "figsize = (18,8)\n",
    "patient_tab[agenum_col].plot(kind='hist',\n",
    "                             figsize=figsize, \n",
    "                             fontsize=fontsize,\n",
    "                             bins=15)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Questions\n",
    "\n",
    "- Use the `mean()` method to find the mean age (hint: `patient_tab[agenum_col].mean()`). What is the mean? Why might we expect this to be lower than the true mean?\n",
    "- In the same way that you use `.mean()`, you can use `.describe()`. Use the `describe()` method to explore the `admissionweight` of patients in kg. What issue do you see? What are some methods that you could use to deal with this issue?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    1419.000000\n",
       "mean       82.221226\n",
       "std        28.649613\n",
       "min         0.000000\n",
       "25%        63.500000\n",
       "50%        77.100000\n",
       "75%        93.550000\n",
       "max       252.900000\n",
       "Name: admissionweight, dtype: float64"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "patient_tab['admissionweight'].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "# set threshold based on 99th quantile\n",
    "adweight_col = 'admissionweight'\n",
    "quant = patient_tab[adweight_col].quantile(0.99)\n",
    "patient_tab[patient_tab[adweight_col] > quant] = None\n",
    "low_quant = patient_tab[adweight_col].quantile(0.01)\n",
    "patient_tab[patient_tab[adweight_col] < low_quant] = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    1377.000000\n",
       "mean       80.345839\n",
       "std        23.311258\n",
       "min        39.000000\n",
       "25%        63.500000\n",
       "50%        77.100000\n",
       "75%        92.400000\n",
       "max       164.400000\n",
       "Name: admissionweight, dtype: float64"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# describe the admission weights\n",
    "patient_tab[adweight_col].describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Questions\n",
    "\n",
    "- What is the average change in weight between `admissionweight` and `dischargeweight`?\n",
    "- Plot a distribution of the weight change"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# set threshold based on 99th quantile\n",
    "disweight_col = 'dischargeweight'\n",
    "quant = patient_tab[disweight_col].quantile(0.99)\n",
    "patient_tab[patient_tab[disweight_col] > quant] = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    828.000000\n",
       "mean      82.543357\n",
       "std       23.889156\n",
       "min        1.000000\n",
       "25%       65.875000\n",
       "50%       78.755000\n",
       "75%       96.925000\n",
       "max      151.800000\n",
       "Name: dischargeweight, dtype: float64"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# describe the discharge weights\n",
    "patient_tab[disweight_col].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "patient_tab['weight_change'] = patient_tab[adweight_col] - patient_tab[disweight_col]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x109c410d0>"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABFkAAAHxCAYAAAC26mMaAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzs3X1wluWdL/BvSAwhJIhAU6RgobWoxNaXqgWsCCoI06Od\nbpXabbU7do/Oru5Yd3pGOq1H6cu0zu54tmd62uPZ7jpazxG1hbYUl/qKWgRlUWoBN+oiRQVLEJHw\nIhDI+cMhLU1QeHIDSZ7P5x/D/Vxvt7884nznvq67oq2trS0AAAAAdEmfI70AAAAAgN5AyAIAAABQ\nACELAAAAQAGELAAAAAAFELIAAAAAFEDIAgAAAFAAIQsAAABAAaqO9ALezV133ZWXX345a9euTUtL\nS6qrq/O+970vZ555ZqZOnZq6uroOfZqamjJ79uy8+OKL2bVrV4YOHZpJkyZl6tSp6dOn80xp6dKl\nmTt3blavXp09e/ZkxIgRmTJlSs4999xDfYsAAABAL1HR1tbWdqQXsT9/+Zd/mQ996EMZPnx4BgwY\nkB07duTFF1/Mf/7nf2bQoEH5zne+k0GDBrW3X7JkSW699dZUV1dn3Lhxqaury9KlS7N27dqMHTs2\n119/fYc55s+fn9tvvz319fUZP358qqqqsnjx4rzxxhu56KKL8sUvfvFw3jIAAADQQ3XrkKW1tTVV\nVR0ftpk1a1bmzJmTKVOm5Mtf/nKSZPv27fm7v/u7bN++Pd/+9rczatSo9jFmzpyZF154Idddd13G\njx/fPk5zc3O+8pWvpKamJrfcckuGDBmSJNm2bVtmzJiRP/zhD/n2t7+dj3zkI4fhbgEAAICerFuf\nydJZwJIk48aNS5K8/vrr7dcWLVqUlpaWnH322e0By94xPve5zyVJHnzwwX3GeeSRR9La2ppp06a1\nByxJUltbm8985jOd9gEAAADoTLcOWfbn3//935MkH/zgB9uvrVixIkly6qmndmg/ZsyYVFdXp6mp\nKa2trR36nHLKKR36nHbaaUmS5cuXH/C69o5H+VDz8qTu5UfNy5O6lx81L0/qXp7Uvfwcrpr3iJDl\nl7/8Ze67777ccccduemmm3Lvvfdm5MiR+fSnP93eZu3atUmSY489tkP/Pn36pKGhIbt378769esP\nqM/AgQPTt2/fvPHGG9m5c+cBrdMXtfyoeXlS9/Kj5uVJ3cuPmpcndS9P6l5+DlfNu/Xbhfb61a9+\nlbfeeqv9z6eeemquueaa1NfXt1/btm1bkne2+nRm7/WtW7ceVJ8dO3Zk27Ztqa6u7tpNAAAAAL1a\njwhZ/s//+T9Jks2bN6epqSn/9//+3/y3//bf8rWvfS0jR448qLEqKioOuO3eM4EPpg8AAABQnnpE\nyLLXgAEDcuaZZ2bUqFG57rrr8oMf/CD/+I//mOSPT6PsfTrlz3X21EptbW1aWlqybdu21NXVdeiz\nffv2JEm/fv06HXPFihX7PHI0ffr0Eu6KnkzNy5O6lx81L0/qXn7UvDype3lS9/Izffr03Hvvve1/\nbmxsTGNjY+Hz9KiQZa8hQ4Zk+PDhWb16dbZs2ZK6uroMGzYsq1atyrp16/Z5u1CS7NmzJ+vXr09l\nZWUaGhrarw8bNixNTU1Zt25dh9c0b9q0KTt27MjgwYP3u1Wos6LsPeeF8lBfX5+WlpYjvQwOM3Uv\nP2pentS9/Kh5eVL38qTu5WfYsGGHJVzrEQffdmbjxo1J3jnUNklOPvnkJMmyZcs6tF25cmV27tyZ\nE044YZ/XQr9bn2eeeWafNgAAAADvptuGLOvWret0609bW1vuvvvubN68OSeeeGL79p+xY8emvr4+\nCxcuzKpVq9rb79q1K7NmzUqSTJkyZZ+xJk6cmKqqqsyfPz/Nzc3t17ds2ZI5c+YkSSZPnlz4vQEA\nAAC9T7fdLvTss8/m//2//5cTTzwxDQ0Nqaury1tvvZWVK1dm/fr1OeaYY3LVVVe1t+/Xr1+uvvrq\n3Hrrrbn55pszfvz41NXVZenSpVm7dm3GjRuXcePG7TNHQ0NDLr/88tx+++2ZMWNGxo8fn6qqqixe\nvDgbN27MRRdd1GEbEQAAAEBnKtr2vkKnm3nllVfy4IMPpqmpKW+88Ua2bt2ampqaHHvssTn99NMz\nbdq09O/fv0O/F154IbNnz84LL7yQXbt2ZejQoZk0aVKmTZu237cEPfPMM5k7d25WrVqVtra2DB8+\nPFOnTs2ECRMOet3OZCkv9nKWJ3UvP2pentS9/Kh5eVL38qTu5WfYsGGHZZ5uG7L0VEKW8uI/zuVJ\n3cuPmpcndS8/al6e1L08qXv5OVwhS7c9kwUAAACgJxGyAAAAABRAyAIAAABQACELAAAAQAGELAAA\nAAAFELIAAAAAFEDIAgAAAFAAIQsAAABAAYQsAAAAAAUQsgAAAAAUQMgCAAAAUAAhCwAAAEABhCwA\nAAAABRCyAAAAABRAyAIAAABQACELAAAAQAGELAAAAAAFELIAAAAAFEDIAgAAAFAAIQsAAABAAYQs\nAAAAAAUQsgAAAAAUQMgCAAAAUAAhCwAAAEABhCwAAAAABRCyAAAAABRAyAIAAABQACELAAAAQAGE\nLAAAAAAFELIAAAAAFEDIAgAAAFAAIQsAAABAAYQsAAAAAAUQsgAAAAAUQMgCAAAAUAAhCwAAAEAB\nhCwAAAAABRCyAAAAABRAyAIAAABQACELAAAAQAGELAAAAAAFqDrSCwCA7qbyzQ3Jxub2P++orErl\n7taDG2TQ+7L7mCEFrwwAgO5MyAIAf25jc3Z+74YuDVE945ZEyAIAUFZsFwIAAAAogJAFAAAAoABC\nFgAAAIACCFkAAAAACiBkAQAAACiAkAUAAACgAEIWAAAAgAIIWQAAAAAKIGQBAAAAKICQBQAAAKAA\nQhYAAACAAghZAAAAAAogZAEAAAAogJAFAAAAoABCFgAAAIACCFkAAAAACiBkAQAAAChA1ZFewP5s\n2bIlTz31VJ599tmsWbMmGzduTFVVVY477rhMnDgxkyZNSkVFRXv75ubmXHvttfsdb/z48bnuuus6\n/WzBggV54IEH8uqrr6ZPnz4ZNWpULrroopx++umF3xcAAADQO3XbkGXRokX58Y9/nGOOOSaNjY0Z\nMmRI3nrrrTz11FO57bbbsmzZsvz93/99h34jR47MmWee2eH6iBEjOp3nzjvvzLx58zJ48OBccMEF\naW1tzcKFC3PLLbfkyiuvzIUXXlj4vQEAAAC9T7cNWYYNG5Ybbrihw9Mkn//85/O1r30tTz31VJ5+\n+umcddZZ+3z+wQ9+MJdccskBzfHCCy9k3rx5GTp0aL773e+mtrY2SXLxxRfnhhtuyE9+8pN8/OMf\nz5AhQ4q5KQAAAKDX6rZnsjQ2Nna6Xefoo4/O5MmTkyQrVqzo0hwPPPBAkuQv/uIv2gOWJBkyZEgu\nvPDC7Nq1K48++miX5gAAAADKQ7cNWd5NZWXlPv/8U2+++WYeeuihzJkzJw899FDWrFmz33H2hjSn\nnHJKh89OPfXUJMny5cuLWDIAAADQy3Xb7UL7s2fPnjz22GNJ/hiE/Knnnnsuzz333D7XxowZk2uu\nuWafbT87duzIxo0bU1NTk4EDB3YY59hjj02SrFu3rsjlAwAAAL1UjwtZ7rrrrrz66qs5/fTT87GP\nfaz9et++ffPZz342Z511VhoaGpIka9asyX333Zfly5fnW9/6Vv7hH/4h1dXVSZJt27YlyT7bhP7U\n3utbt249lLcDAAAA9BI9arvQ/fffn3nz5mX48OEdXtc8YMCATJ8+PSNHjkxtbW1qa2tz4okn5utf\n/3qOP/74vP7663n44YcPes4/fU00AAAAwP70mCdZ5s+fnzvuuCMjRozIjTfemP79+x9Qvz59+uT8\n88/PSy+9lOeffz7Tpk1L8scnVfY+0fLn3utJl+SdM13+9PDd6dOnp76+/oDWRe9QXV2t5mVI3Xu/\nHZVd/+uxsrIqtX5PejTf9fKj5uVJ3cuTupene++9t/3nxsbGNDY2Fj5HjwhZ5s2blzvvvDPHHXdc\nbrzxxgwYMOCg+u9tv2PHjvZrffv2zaBBg7Jx48Zs2rSpw7kse89i2Xs2S2c6K0pLS8tBrY2erb6+\nXs3LkLr3fpW7W7s8xu7drX5Pejjf9fKj5uVJ3cuTupef+vr6TJ8+/ZDP0+23C/385z/PnXfemVGj\nRuWmm2466IAlSV544YUkaT+rZa+9AcmyZcs69Hn22WeTJB/96EcPej4AAACg/HTrkOWnP/1p7r77\n7nz4wx/OjTfemLq6uv22ffnll9PW1tbh+vLlyzNv3rwkyTnnnLPPZ1OmTEmSzJkzZ58DbtevX59f\n//rXOeqoozJx4sQC7gQAAADo7brtdqEFCxbkvvvuS58+fXLCCSfk/vvv79Dmfe97X3sIcuedd2bd\nunUZPXp0Bg8enOSdtwstX748SXLZZZdl9OjR+/QfPXp0PvWpT2XevHn56le/mrFjx6a1tTVPPvlk\ntm7dmi9/+cv7vPYZAAAAYH+6bcjS3NycJNmzZ0+nAUuSjBkzpj1kmTBhQp5++umsWrUqv/3tb9Pa\n2pqBAwdm/PjxufDCC3PiiSd2OsYVV1yRkSNHZv78+Xn44YdTUVGRD33oQ7n44otz2mmnHZJ7AwAA\nAHqfbhuyXHrppbn00ksPuP2kSZMyadKkkuaaMGFCJkyYUFJfAAAAgKSbn8kCAAAA0FMIWQAAAAAK\nIGQBAAAAKICQBQAAAKAAQhYAAACAAghZAAAAAAogZAEAAAAogJAFAAAAoABCFgAAAIACCFkAAAAA\nCiBkAQAAACiAkAUAAACgAEIWAAAAgAIIWQAAAAAKIGQBAAAAKICQBQAAAKAAQhYAAACAAghZAAAA\nAAogZAEAAAAogJAFAAAAoABCFgAAAIACCFkAAAAACiBkAQAAACiAkAUAAACgAEIWAAAAgAIIWQAA\nAAAKIGQBAAAAKICQBQAAAKAAQhYAAACAAghZAAAAAAogZAEAAAAogJAFAAAAoABCFgAAAIACCFkA\nAAAACiBkAQAAACiAkAUAAACgAEIWAAAAgAIIWQAAAAAKIGQBAAAAKICQBQAAAKAAQhYAAACAAghZ\nAAAAAAogZAEAAAAogJAFAAAAoABCFgAAAIACCFkAAAAACiBkAQAAACiAkAUAAACgAEIWAAAAgAII\nWQAAAAAKIGQBAAAAKICQBQAAAKAAQhYAAACAAghZAAAAAAogZAEAAAAogJAFAAAAoABCFgAAAIAC\nCFkAAAAACiBkAQAAAChA1ZFewP5s2bIlTz31VJ599tmsWbMmGzduTFVVVY477rhMnDgxkyZNSkVF\nRYd+TU1NmT17dl588cXs2rUrQ4cOzaRJkzJ16tT06dN5prR06dLMnTs3q1evzp49ezJixIhMmTIl\n55577qG+TQAAAKCX6LYhy6JFi/LjH/84xxxzTBobGzNkyJC89dZbeeqpp3Lbbbdl2bJl+fu///t9\n+ixZsiS33nprqqurM27cuNTV1WXp0qW544470tTUlOuvv77DPPPnz8/tt9+e+vr6TJgwIVVVVVm8\neHF++MMf5pVXXskXv/jFw3XLAAAAQA/WbUOWYcOG5YYbbsjpp5++z/XPf/7z+drXvpannnoqTz/9\ndM4666wkyfbt23PbbbelT58+ufnmmzNq1KgkyWWXXZaZM2dm8eLFefLJJzN+/Pj2sZqbm/OTn/wk\ndXV1+d73vpchQ4YkSS655JLMmDEjc+fOzSc+8Yl85CMfOUx3DQAAAPRU3fZMlsbGxg4BS5IcffTR\nmTx5cpJkxYoV7dcXLVqUlpaWnH322e0BS5JUVVXlc5/7XJLkwQcf3GesRx55JK2trZk2bVp7wJIk\ntbW1+cxnPtNpHwAAAIDOdNuQ5d1UVlbu88/kj4HLqaee2qH9mDFjUl1dnaamprS2tnboc8opp3To\nc9pppyVJli9fXtzCAQAAgF6rx4Use/bsyWOPPZZk30Bl7dq1SZJjjz22Q58+ffqkoaEhu3fvzvr1\n6w+oz8CBA9O3b9+88cYb2blzZ6H3AAAAAPQ+PS5kueuuu/Lqq6/m9NNPz8c+9rH269u2bUvyzlaf\nzuy9vnXr1oPus7cdAAAAwP70qJDl/vvvz7x58zJ8+PBce+21JY3R2Wuf96etre2g+wAAAADlqdu+\nXejPzZ8/P3fccUdGjBiRG2+8Mf3799/n8/d66qSzp1Zqa2vT0tKSbdu2pa6urkOf7du3J0n69evX\n6ZgrVqzY5/Dd6dOnp76+/iDuip6uurpazcuQuvd+Oyq7/tdjZWVVav2e9Gi+6+VHzcuTupcndS9P\n9957b/vPjY2NaWxsLHyOHhGyzJs3L3feeWeOO+643HjjjRkwYECHNsOGDcuqVauybt26fd4ulLxz\njsv69etTWVmZhoaGffo0NTVl3bp1HV7TvGnTpuzYsSODBw9OdXV1p+vqrCgtLS2l3iY9UH19vZqX\nIXXv/Sp3t753o/ewe3er35Mezne9/Kh5eVL38qTu5ae+vj7Tp08/5PN0++1CP//5z3PnnXdm1KhR\nuemmmzoNWJLk5JNPTpIsW7asw2crV67Mzp07c8IJJ6SqquqA+jzzzDP7tAEAAAB4N906ZPnpT3+a\nu+++Ox/+8Idz4403drqlZ6+xY8emvr4+CxcuzKpVq9qv79q1K7NmzUqSTJkyZZ8+EydOTFVVVebP\nn5/m5ub261u2bMmcOXOSJJMnTy7ylgAAAIBeqttuF1qwYEHuu+++9OnTJyeccELuv//+Dm3e9773\nZeLEiUneOTfl6quvzq233pqbb74548ePT11dXZYuXZq1a9dm3LhxGTdu3D79Gxoacvnll+f222/P\njBkzMn78+FRVVWXx4sXZuHFjLrroog7biAAAAAA6021Dlr1PluzZs6fTgCVJxowZ0x6yJMmZZ56Z\nmTNnZvbs2Xn66aeza9euDB06NF/60pcybdq0TseYOnVqGhoaMnfu3Dz++ONpa2vL8OHD8/nPfz4T\nJkwo/L4AAACA3qmibe97iinE2rVrj/QSOIwcmFWe1L33q/zP57Pzezd0aYzqGbdk94dPKmhFHAm+\n6+VHzcuTupcndS8/w4YNOyzzdOszWQAAAAB6CiELAAAAQAGELAAAAAAFELIAAAAAFEDIAgAAAFAA\nIQsAAABAAYQsAAAAAAUQsgAAAAAUQMgCAAAAUICSQ5YVK1YUuQ4AAACAHq2q1I7f/OY38/73vz8T\nJ07Mueeem8GDBxe5LgAAAIAepeSQ5aijjsof/vCH3HPPPbnvvvvy0Y9+NOedd17OOOOMVFWVPCwA\nAABAj1RyGvLP//zP+c1vfpMFCxbkpZdeym9/+9v89re/TV1dXc4555xMnDgxI0eOLHCpAAAAAN1X\nySFLv379Mnny5EyePDmvvfZaHnnkkTzxxBN566238m//9m/5t3/7t4waNSrnnXdezj777PTv37/I\ndQMAAAB0KxVtbW1tRQ22Z8+ePPPMM3nkkUeybNmy7N69O8k7W4vOOuusTJw4MR/72MeKmq5bWrt2\n7ZFeAodRfX19WlpajvQyOMzUvfer/M/ns/N7N3RpjOoZt2T3h08qaEUcCb7r5UfNy5O6lyd1Lz/D\nhg07LPMUenhKnz59csYZZ+SMM87I5s2b8/jjj+fhhx/O2rVrs3DhwixcuDBDhgzJ+eefnwsuuCAD\nBgwocnoAAACAI6bkVzi/l40bN6a5uTmbN2/e5/qGDRtyzz335Jprrsns2bMP1fQAAAAAh1WhT7Js\n2bIlTzzxRBYsWJDVq1e3Xz/uuOMyadKkfOITn8jvfve7PPjgg3nppZdyzz33pKqqKhdffHGRywAA\nAAA47LocsrS1tWXZsmV59NFHs3Tp0rS2tiZJampqMm7cuFxwwQU5/vjj29tPnDgxEydOzIMPPpgf\n//jHeeihh4QsAAAAQI9Xcsiydu3aLFiwII8//njefPPN9uvHH398zj///IwfPz41NTX77T958uTM\nmjUrzc3NpS4BAAAAoNsoOWS5/vrr23+uq6vLOeeck/PPPz8jRow44DFqamqyZcuWUpcAAAAA0G10\nabtQY2NjzjvvvIwdOzZVVQc/1MyZM9u3FwEAAAD0ZCWHLP/zf/7PvP/97+/S5EOGDOlSfwAAAIDu\nouRXOHc1YAEAAADoTUp+kmXjxo1ZsGBBjjnmmEyaNOld2z7yyCPZtGlTzjvvvAwcOLDUKQEAAAC6\nrZKfZFmwYEHuueeetLS0vGfbDRs25J577sljjz1W6nQAAAAA3VrJIcvSpUuTJGPHjn3PthMnTkyS\n/Pu//3up0wEAAAB0ayWHLM3Nzenbt28aGhres21DQ0P69u2b9evXlzodAAAAQLdWcsiydevWg3pt\nc1VVVbZs2VLqdAAAAADdWskhS319fbZu3ZrNmze/Z9vNmzdn69at6d+/f6nTAQAAAHRrJYcsxx9/\nfJLkoYcees+2Dz744D59AAAAAHqbkkOW888/P0ly3333ZcGCBftt9+ijj+anP/1pkuS8884rdToA\nAACAbu3AD1X5M6eddlrGjRuXRYsW5Uc/+lHmzZuX0047LUOGDEnyzsG4zz77bF555ZUkySc+8Ymc\nccYZxawaAAAAoJspOWRJkmuvvTa1tbV5+OGHs2bNmqxZs6bTduedd16uvPLKrkwFAAAA0K11KWSp\nqqrKVVddlalTp+axxx7Liy++mLfeeittbW0ZOHBgPvKRj+Tcc8/NcccdV9R6AQAAALqlLoUsex13\n3HG5/PLLixgKAAAAoEcq+eBbAAAAAP5IyAIAAABQgC5vF1q7dm2efvrprFmzJlu3bs3u3bv327ai\noiJf//rXuzolAAAAQLfTpZDlrrvuyq9+9au0tbUVtR4AAACAHqnkkOWBBx7I3LlzkyTDhw/Pxz/+\n8QwaNCjV1dWFLQ4AAACgpyg5ZHnooYeSJBdeeGGuvPLKwhYEAAAA0BOVfPDtunXrkiSXXXZZYYsB\nAAAA6KlKfpKluro6VVVVqa2tLXI9AAAAAD1SyU+yHH/88dm+fXs2b95c5HoAAAAAeqSSQ5ZPf/rT\nSZKf//znhS0GAAAAoKcqOWQZM2ZMrrrqqvz617/Ov/zLv2TDhg1FrgsAAACgRyn5TJbrrrsuSVJZ\nWZkHHnggDzzwQI4++uj069fvXft9//vfL3VKAAAAgG6r5JDl9ddf73DtrbfeyltvvdWlBQEAAAD0\nRCWHLN/4xjeKXAcAAABAj1ZyyPLRj360yHUAAAAA9GglH3wLAAAAwB+V/CTLn9qzZ09Wr16dDRs2\nZOfOnfnkJz9ZxLAAAAAAPUaXQ5a5c+fmF7/4RVpaWtqv/WnIsnXr1tx0001pbW3NTTfdlGOOOaar\nUwIAAAB0O13aLvSDH/wgd911V1paWjJkyJBUVlZ2aNO/f/+MHj0669aty8KFC7syHQAAAEC3VXLI\n8uSTT+aJJ57IwIED881vfjP/63/9r9TV1XXa9pxzzkmS/O53vyt1OgAAAIBureSQ5ZFHHkmSfOlL\nX8oJJ5zwrm0//OEPp6KiImvWrCl1OgAAAIBureSQ5eWXX05FRUXOPPPM92xbXV2d2trabN68udTp\nAAAAALq1kkOWt99+O/369ctRRx11QO13796dPn28MRoAAADonUp+u9CAAQOycePGvP3226mpqXnX\ntq+//nrefvvtDB069KDmWLx4cVauXJnf//73Wb16dd5+++2cc845ufbaazu0bW5u7vT6XuPHj891\n113X6WcLFizIAw88kFdffTV9+vTJqFGjctFFF+X0008/qPUCAAAA5avkkGX06NFZvHhxFi9enIkT\nJ75r21/+8pdJksbGxoOaY/bs2fn973+fmpqaDB48OK+99tp79hk5cmSnW5hGjBjRafs777wz8+bN\ny+DBg3PBBRektbU1CxcuzC233JIrr7wyF1544UGtGQAAAChPJYcsF154YRYvXpxZs2bl+OOPz/Dh\nwzu0aW1tzezZs/Pwww+noqIiU6dOPag5/uqv/iqDBg3K0KFDs3LlysycOfM9+3zwgx/MJZdcckDj\nv/DCC5k3b16GDh2a7373u6mtrU2SXHzxxbnhhhvyk5/8JB//+MczZMiQg1o3AAAAUH5KDlnGjBmT\nT33qU5k3b16+9rWv5ZRTTsnbb7+dJLnrrruyYcOGrFixov2w20suuSTHHXfcQc9xKD3wwANJkr/4\ni79oD1iSZMiQIbnwwgvzs5/9LI8++mguvfTSQ7oOAAAAoOfr0km0V1xxRb74xS8mSZYsWZIdO3Yk\nSebOnZtFixZl8+bNqa6uzhVXXHHAT5d01ZtvvpmHHnooc+bMyUMPPfSur41esWJFkuSUU07p8Nmp\np56aJFm+fPmhWSgAAADQq5T8JMteF110USZNmpTFixenqakpmzZtyp49e3L00Udn9OjRGT9+fAYM\nGFDEWg/Ic889l+eee26fa2PGjMk111yzz7afHTt2ZOPGjampqcnAgQM7jHPssccmSdatW3doFwwA\nAAD0Cl0OWZKkrq4uF1xwQS644IIihitJ375989nPfjZnnXVWGhoakiRr1qzJfffdl+XLl+db3/pW\n/uEf/iHV1dVJkm3btiXJPtuE/tTe61u3bj0MqwcAAAB6ui5tF+pOBgwYkOnTp2fkyJGpra1NbW1t\nTjzxxHz961/P8ccfn9dffz0PP/zwQY9bUVFxCFYLAAAA9Da9JmTZnz59+uT8889Pkjz//PPt1/c+\nqbL3iZY/915PugAAAAD8qZK3C337298+6D4VFRX5+te/XuqUJdt7Jszeg3mTd7YXDRo0KBs3bsym\nTZs6nMuy9yyWvWezdGbFihXth+cmyfTp01NfX1/k0unmqqur1bwMqXvvt6Oy67tpKyurUuv3pEfz\nXS8/al6e1L08qXt5uvfee9t/bmxsTGNjY+FzlPx/kb/73e+KXMch9cILLyRJ+1ktezU2NuaJJ57I\nsmXLMnHixH0+e/bZZ5MkH/3oR/c7bmdFaWlpKWDF9BT19fVqXobUvfer3N3a5TF27271e9LD+a6X\nHzUvT+otkKNKAAAgAElEQVRentS9/NTX12f69OmHfJ6SQ5arr776XT/ftm1bXnrppSxZsiQ1NTX5\n7Gc/m5qamlKne08vv/xyRo4c2eEMleXLl2fevHlJknPOOWefz6ZMmZInnngic+bMyZlnnpn+/fsn\nSdavX59f//rXOeqoozqELwAAAACdKTlkOe+88w6o3dq1a/Od73wnTzzxRL75zW8e1BxLlizJkiVL\nkiSbNm1KkjQ1NeWHP/xhkneSqMsvvzxJcuedd2bdunUZPXp0Bg8enOSdtwstX748SXLZZZdl9OjR\n+4w/evTofOpTn8q8efPy1a9+NWPHjk1ra2uefPLJbN26NV/+8pf3ee0zAAAAwP4U8grndzNs2LD8\n1//6X/Pd7343P//5z3PppZcecN/Vq1fnscce2+fa+vXrs379+iTvbP/ZG7JMmDAhTz/9dFatWpXf\n/va3aW1tzcCBAzN+/PhceOGFOfHEEzud44orrsjIkSMzf/78PPzww6moqMiHPvShXHzxxTnttNNK\nvGsAAACg3BzykCVJPvaxj+Woo47KwoULDypkufTSSw+4/aRJkzJp0qSS1jdhwoRMmDChpL4AAAAA\nyWF6hXNFRUUqKiqyYcOGwzEdAAAAwGF3WEKWF198MTt37ky/fv0Ox3QAAAAAh90h3S7U1taWpUuX\n5vbbb0/y7q9DBgAAAOjJSg5Zrrvuunf9fOfOndm0aVP27NmTJKmrqzss76QGAAAAOBJKDllef/31\nA2pXWVmZj3/84/nCF76QoUOHljodAAAAQLdWcsjyjW98410/r6ysTG1tbT7wgQ/kqKOOKnUaAAAA\ngB6h5JDF+SoAAAAAf3RY3i4EAAAA0NsJWQAAAAAKUPJ2odtuu62QBVRUVOSqq64qZCwAAACAI6Xk\nkOWRRx4pbBFCFgAAAKCnKzlk+cxnPpPdu3fnoYceyrZt2zJo0KCcdNJJGTRoUNra2vLmm2/mP/7j\nP/LGG2+ktrY2F1xwQSorK4tcOwAAAEC3UXLIcskll+Rb3/pWWltb87d/+7eZMGFCKioqOrR7/PHH\n88///M958cUX841vfCNVVSVPCQAAANBtlXzw7S9+8Yv8x3/8R/76r/865557bqcBS5JMmDAhX/7y\nl/P888/nl7/8ZckLBQAAAOjOSg5ZfvOb36Sqqiqf/OQn37PtOeeck6qqqvzmN78pdToAAACAbq3k\nkKW5uTnV1dUHdM5KZWVlqqur09zcXOp0AAAAAN1aySFLTU1Ntm3blldfffU9277yyivZtm1bampq\nSp0OAAAAoFsrOWRpbGxMkvzoRz/Ktm3b9ttu27Zt+d//+3/v0wcAAACgtyn5VT/Tp0/P0qVL89JL\nL+W6667L5MmTM2bMmBxzzDFJkjfffDMrV67Mww8/nE2bNqW6ujrTp08vbOEAAAAA3UnJIcsHPvCB\nzJgxI//0T/+UzZs352c/+1l+9rOfddq2vr4+X/nKVzJs2LCSFwoAAADQnZUcsiTJySefnH/6p3/K\n/fffn6eeeiqvvfZa2trakiQVFRX5wAc+kLFjx2batGmpq6srZMEAAAAA3VGXQpYkqaury/Tp0zN9\n+vTs3LkzW7Zsab9eXV3d5QUCAAAA9ARdDln+VHV1dQYNGlTkkAAAAAA9QmEhS0tLS954443s2LEj\nJ5xwQlHDAgAAAPQIXQ5ZFi9enDlz5mT16tVJ3jmLZdasWe2fb926Nd///vfT1taWr3zlK+nfv39X\npwQAAADodvp0pfOsWbPyP/7H/8jq1atTWVmZioqK9oNv9+rfv3/69++f5557LosWLerSYgEAAAC6\nq5JDlueeey5z5sxJTU1N/u7v/i533nlnBgwY0GnbiRMnJkmWLVtW6nQAAAAA3VrJ24Xmz5+fJPnC\nF76QT37yk+/adu8ZLXu3FAEAAAD0NiU/yfLiiy8mSSZMmPCebWtqalJbW5tNmzaVOh0AAABAt1Zy\nyLJ169bU1tampqbmgNr/+VktAAAAAL1JySFLXV1dtm3blp07d75n240bN2b79u0ZOHBgqdMBAAAA\ndGslhywf/vCHkxzYYbYPPPBAkuTEE08sdToAAACAbq3kkOX8889Pktx9993vetbKo48+ml/84hdJ\nkgsuuKDU6QAAAAC6tZLfLnTGGWdk3LhxWbRoUW644YacffbZ7VuHHnjggTQ3N2fZsmVZs2ZNkndC\nGU+yAAAAAL1VySFLklx77bUZMGBAfv3rX2fevHnt1//lX/5ln3bTpk3LFVdc0ZWpAAAAALq1LoUs\nVVVVufLKKzN16tQsWLAgL7zwQt588820tbXl6KOPzujRozNx4sSMGDGiqPUCAAAAdEtdCln2GjZs\nWP7yL/+yiKEAAAAAeqSSQ5Zbb701FRUV+cIXvpCGhoYi1wQAAADQ45T8dqElS5Zk6dKlAhYAAACA\ndCFkGThwYI466qgi1wIAAADQY5UcsjQ2Nmbbtm157bXXilwPAAAAQI9Ucsjy6U9/OtXV1fnXf/3X\ntLa2FrkmAAAAgB6n5INv+/fvn6uuuio//vGP89WvfjVTp07N6NGjM2DAgPTps//sZtCgQaVOCQAA\nANBtlRyy/M3f/E37z+vWrcvtt9/+nn0qKioya9asUqcEAAAA6LZK3i5Uira2tsM5HQAAAMBhU/KT\nLHfffXeR6wAAAADo0UoOWd7t3BUAAACAcnPAScn999+fRx555FCuBQAAAKDHOuCQ5Y477sg999zT\n6Wc/+tGP8o//+I+FLQoAAACgpyl5u9CfevbZZ/PWW28VMRQAAABAj+RgFQAAAIACCFkAAAAAClDI\ndiEA6A4q39yQbGzu8jgVrbsKWA0AAOVGyAJA77GxOTu/d0OXh+l73U0FLAYAgHJjuxAAAABAAQ7q\nSZYtW7Zk5syZnV5P0ulnf6qioiL//b//94OZEgAAAKBHOKiQpbW1NStXrtzv5+/2GQAAAEBvdsAh\ny7nnnnso1wEAAADQox1wyPK3f/u3h3IdAAAAAD2ag28BAAAACtBtX+G8ePHirFy5Mr///e+zevXq\nvP322znnnHNy7bXX7rdPU1NTZs+enRdffDG7du3K0KFDM2nSpEydOjV9+nSeJy1dujRz587N6tWr\ns2fPnowYMSJTpkyxPQoAAAA4KN02ZJk9e3Z+//vfp6amJoMHD85rr732ru2XLFmSW2+9NdXV1Rk3\nblzq6uqydOnS3HHHHWlqasr111/foc/8+fNz++23p76+PhMmTEhVVVUWL16cH/7wh3nllVfyxS9+\n8VDdHgAAANDLdNuQ5a/+6q8yaNCgDB06NCtXrnzX10Nv3749t912W/r06ZObb745o0aNSpJcdtll\nmTlzZhYvXpwnn3wy48ePb+/T3Nycn/zkJ6mrq8v3vve9DBkyJElyySWXZMaMGZk7d24+8YlP5CMf\n+cihvVEAAACgV+i2Z7KMGTMmQ4cOPaC2ixYtSktLS84+++z2gCVJqqqq8rnPfS5J8uCDD+7T55FH\nHklra2umTZvWHrAkSW1tbT7zmc902gcAAABgf7ptyHIwVqxYkSQ59dRTO3w2ZsyYVFdXp6mpKa2t\nrR36nHLKKR36nHbaaUmS5cuXH4rlAgAAAL1QrwhZ1q5dmyQ59thjO3zWp0+fNDQ0ZPfu3Vm/fv0B\n9Rk4cGD69u2bN954Izt37jxEqwYAAAB6k14Rsmzbti3JO1t9OrP3+tatWw+6z952AAAAAO+mV4Qs\nB6qiouKA27a1tR10HwAAAKB8ddu3Cx2M93rqpLOnVmpra9PS0pJt27alrq6uQ5/t27cnSfr167ff\neVesWNF+tkuSTJ8+PfX19Qd/A/RY1dXVal6G1L372lFZzF9rRQTslZVVqfV70qP5rpcfNS9P6l6e\n1L083Xvvve0/NzY2prGxsfA5ekXIMmzYsKxatSrr1q3b5+1CSbJnz56sX78+lZWVaWho2KdPU1NT\n1q1b1+E1zZs2bcqOHTsyePDgVFdX73fezorS0tJSwB3RU9TX16t5GVL37qtyd+t7NzoAe59m7Ird\nu1v9nvRwvuvlR83Lk7qXJ3UvP/X19Zk+ffohn6dXbBc6+eSTkyTLli3r8NnKlSuzc+fOnHDCCamq\nqjqgPs8888w+bQAAAADeS68IWcaOHZv6+vosXLgwq1atar++a9euzJo1K0kyZcqUffpMnDgxVVVV\nmT9/fpqbm9uvb9myJXPmzEmSTJ48+TCsHgAAAOgNuu12oSVLlmTJkiVJ3tm+kyRNTU354Q9/mOSd\nR30uv/zyJO+cm3L11Vfn1ltvzc0335zx48enrq4uS5cuzdq1azNu3LiMGzdun/EbGhpy+eWX5/bb\nb8+MGTMyfvz4VFVVZfHixdm4cWMuuuiiDtuIAAAAAPan24Ysq1evzmOPPbbPtfXr12f9+vVJ/hiS\n7HXmmWdm5syZmT17dp5++uns2rUrQ4cOzZe+9KVMmzat0zmmTp2ahoaGzJ07N48//nja2toyfPjw\nfP7zn8+ECRMO3c0BAAAAvU63DVkuvfTSXHrppQfVZ/To0ZkxY8ZB9Tn99NNz+umnH1QfAAAAgD/X\nK85kAQAAADjShCwAAAAABRCyAAAAABRAyAIAAABQACELAAAAQAGELAAAAAAFELIAAAAAFEDIAgAA\nAFAAIQsAAABAAYQsAAAAAAUQsgAAAAAUQMgCAAAAUAAhCwAAAEABhCwAAAAABRCyAAAAABRAyAIA\nAABQACELAAAAQAGELAAAAAAFELIAAAAAFEDIAgAAAFAAIQsAAABAAYQsAAAAAAUQsgAAAAAUQMgC\nAAAAUAAhCwAAAEABhCwAAAAABRCyAAAAABSg6kgvAACSpPLNDcnG5i6NUdG6q6DVAADAwROyANA9\nbGzOzu/d0KUh+l53U0GLAQCAg2e7EAAAAEABhCwAAAAABRCyAAAAABRAyAIAAABQACELAAAAQAGE\nLAAAAAAFELIAAAAAFEDIAgAAAFAAIQsAAABAAYQsAAAAAAUQsgAAAAAUQMgCAAAAUAAhCwAAAEAB\nhCwAAAAABRCyAAAAABRAyAIAAABQACELAAAAQAGELAAAAAAFELIAAAAAFEDIAgAAAFAAIQsAAABA\nAYQsAAAAAAUQsgAAAAAUQMgCAAAAUICqI70AAHq+yjc3JBubuzRGReuuglYDAABHhpAFgK7b2Jyd\n37uhS0P0ve6mghYDAABHhu1CAAAAAAUQsgAAAAAUwHYhADgEKqqqUvmfz3dtkEHvy+5jhhSzIAAA\nDjkhCwAcCi2bs/P7M7s0RPWMWxIhCwBAj9HrQpZrrrkmGzZs6PSzgQMH5rbbbutwvampKbNnz86L\nL76YXbt2ZejQoZk0aVKmTp2aPn3sqAIAAADeW68LWZKktrY2n/rUpzpcr6mp6XBtyZIlufXWW1Nd\nXZ1x48alrq4uS5cuzR133JGmpqZcf/31h2PJAAAAQA/XK0OW/v3755JLLnnPdtu3b89tt92WPn36\n5Oabb86oUaOSJJdddllmzpyZxYsX58knn8z48eMP9ZIBAACAHq6s98IsWrQoLS0tOfvss9sDliSp\nqqrK5z73uSTJgw8+eKSWBwAAAPQgvfJJll27duWJJ57Ihg0b0rdv33zwgx/MSSed1OF8lRUrViRJ\nTj311A5jjBkzJtXV1Wlqakpra2uqqnrlvyoAAACgIL0yOdi0aVN+8IMf7HOtoaEhf/M3f5MxY8a0\nX1u7dm2S5Nhjj+0wRp8+fdLQ0JBXX30169evz7Bhww7togEAAIAerdeFLJMmTcpJJ52UESNGpKam\nJuvXr8/8+fPz4IMP5rvf/W6+853v5LjjjkuSbNu2Lck7B+V2Zu/1rVu3Hp7FAwAAAD1WrzuT5ZJL\nLkljY2MGDBiQ6urqDB8+PH/913+d//Jf/kt27tyZe++996DHrKioOAQrBQAAAHqTXvcky/5Mnjw5\nv/rVr/L888+3X9v7pMreJ1r+3Hs96bJixYr2c12SZPr06amvry9qyfQA1dXVal6G1L2jHZVd/+uk\niEC7qFC8u6ylsrIqtX7Xjhjf9fKj5uVJ3cuTupenP33oorGxMY2NjYXPUTYhy9FHH50k2bFjR/u1\nYcOGZdWqVVm3bt0+bxdKkj179mT9+vWprKxMQ0NDp2N2VpSWlpaCV053Vl9fr+ZlSN07qtzd2uUx\n2trausUYRY1TxBi7d7f6XTuCfNfLj5qXJ3UvT+pefurr6zN9+vRDPk+v2y60P01NTUmS97///e3X\nTj755CTJsmXLOrRfuXJldu7cmRNOOMGbhQAAAID31KtCltdee22fJ1X2am5uzr/+678mSc4555z2\n62PHjk19fX0WLlyYVatWtV/ftWtXZs2alSSZMmXKIV41AAAA0Bv0qkc0nnzyyfzqV7/KSSedlCFD\nhqRfv375wx/+kGeeeSa7du3K6aefnosuuqi9fb9+/XL11Vfn1ltvzc0335zx48enrq4uS5cuzdq1\nazNu3LiMGzfuCN4RAAAA0FP0qpClsbEx69aty8svv5ympqbs2LEj/fv3z0knnZQJEybs8xTLXmee\neWZmzpyZ2bNn5+mnn86uXbsydOjQfOlLX8q0adOOwF0AAAAAPVGvClnGjBmTMWPGHHS/0aNHZ8aM\nGYdgRQAAAEC56FVnsgAAAAAcKUIWAAAAgAIIWQAAAAAKIGQBAAAAKICQBQAAAKAAQhYAAACAAghZ\nAAAAAAogZAEAAAAoQNWRXgAAR07lmxuSjc1dHqeidVcBqwEAgJ5NyAJQzjY2Z+f3bujyMH2vu6mA\nxQAAQM9muxAAAABAAYQsAAAAAAUQsgAAAAAUQMgCAAAAUAAhCwAAAEABhCwAAAAABRCyAAAAABRA\nyAIAAABQACELAAAAQAGELAAAAAAFELIAAAAAFEDIAgAAAFAAIQsAAABAAaqO9AIAgM5VVFWl8j+f\n7/pAg96X3ccM6fo4AAC8KyELAHRXLZuz8/szuzxM9YxbEiELAMAhZ7sQAAAAQAGELAAAAAAFELIA\nAAAAFEDIAgAAAFAAIQsAAABAAYQsAAAAAAUQsgAAAAAUQMgCAAAAUAAhCwAAAEABhCwAAAAABag6\n0gsAKDeVb25INjZ3faBB78vuY4Z0fRwAAKAQQhaAw21jc3Z+74YuD1M945ZEyAL/v727D2rqyv8H\n/gZCQImKKAGyilLFB0Bs5UHRVpQOPlV3tqvGqtvdqQ9ltvVpnHb73R1Z67qz/XW3v7biWsfR6W6p\n60LLWDsKplYWZFeEQRRSQXnQRUWBwEblSWLS3O8ffpM1TUAhV8gl79cMM3jPyfUkH87JzSfnnkNE\nRETkMni7EBERERERERGRCDiThYhIojxkMnhdvezcOUxGkVpDRERERERMshARSVVbKx7s2eXUKXy2\n7hSpMURERERExNuFiIiIiIiIiIhEwCQLEREREREREZEImGQhIiIiIiIiIhIBkyxERERERERERCJg\nkoWIiIiIiIiISARMshARERERERERiYBJFiIiIiIiIiIiETDJQkREREREREQkAiZZiIiIiIiIiIhE\nwCQLEREREREREZEIZAPdACIiKfG60wJDXQ28vjf1+RweJqOILSIiIiIiIlfBJAsRUW/om3H//73j\n1Cl8tu4UqTFET8ZDJoPX1cvOncNvGISONucbExCI70eOdv48RERERC6ISRYiIqLBrq0VD/bscuoU\nPlt3On0OAJD/z/sAkyxEREQ0SHFNFiIiIiIiIiIiETDJQkREREREREQkAiZZiIiIiIiIiIhEwDVZ\niMhteN1pAfTNTp2DOwMREREREVF3mGQhIpcnRnIEeJggMXyww6lzcGcgIiIiIiLqDpMsROT69M14\n4OS2yQATJERERERE9HQxyUJERESSIsrstoBAfM+tpImIiEhkTLIA0Ov1yMjIQHl5Odrb2+Hv74+4\nuDisXLkSfn5+A908IknjOihEJDoRZrfJ/+d9gEkWIiIiEpnbJ1mampqwY8cOtLa2Ii4uDiqVClev\nXsXJkydRXl6O3bt3Q6FQDHQziaRLhA9DvM2HiIiIiIikwO2TLIcOHUJrayvWrVuHhQsXWo+np6cj\nOzsbGRkZ2LBhwwC2kGjgcBYKEVHPeOsSERERPcqtkyw6nQ5arRZKpdImwQIAarUap0+fRkFBAX7+\n859DLpcPUCuJBhBnoRCRyDxkMnhdvezcOVwpeTvIbl1i0oio78TaDZF9iEja3DrJcunSJQBAdHS0\nXZmvry8mT54MrVaL6upqREVF9XfziIiIBp+2VjzYs8upUzB5+xQNsqQRUb8SaTdE9iEiaXPrJMvt\n27cBACEhIQ7LQ0JCoNVq0dDQwCQLERHRIPIkM2oMXjJ4fW/q+TwizKoRY3aPK33zLcrzAUR5Tr2d\nWeAw5i702nKmERGR63PrJEtnZycAYOjQoQ7LLcc7Ojr6rU098W66BfPtG06dwyP0GZhGBYnUInqU\nK00RFastLjUln4hITCLMqAFEmlUjxuyeHf8fXq4y7ov02orybb4Yt72K9dr6DYPQ0ebcOUxGGD7Y\n4dQ5OEvCPYiyrp4If7MAXOva9pHn9CSJdIeYqKTHcOsky+MIggAA8PDwGOCW/B+TEcJdvVOn8Bgz\nXpy2kD1XmiIqUls4JZ+ISCJcKWk02Ij42vJWOeo3Iq2rN5gSpoA4z4mJSnocD8GSSXBDhw8fxvHj\nx/Hqq69i6dKlduWffvopvvnmG2zYsAHJycl25RUVFaioqLD+W61WP9X2EhEREREREVHffPHFF9bf\nIyMjERkZKfr/4Sn6GSVEpVIBABoaGhyWW453t2ZLZGQk1Gq19efRgJF7YMzdE+Pufhhz98S4ux/G\n3D0x7u6JcXc/X3zxhc3n96eRYAHcPMlieVG1Wq1dWVdXF6qqqiCXyzFp0qT+bhoRERERERERSYxb\nJ1mCgoIQHR0NnU4HjUZjU5aZmQmDwYDExETI5fIBaiERERERERERSYXXu+++++5AN2IgTZ48GYWF\nhSgqKkJdXR2uX7+Oo0ePorCwECqVClu2bOlVkkWpVD7F1pIrYszdE+Pufhhz98S4ux/G3D0x7u6J\ncXc//RFzt1741kKv1yMzMxNlZWVob2+Hv78/4uPjsWLFCvj5+Q1084iIiIiIiIhIAphkISIiIiIi\nIiISgVuvyUJEREREREREJBYmWYiIiIiIiIiIRCAb6AYMBmazGXl5eSgoKMCNGzdgNBoxcuRITJgw\nAa+88gqCg4PtHpOfn49Tp06hvr4enp6eCAsLw7JlyzBjxowBeAbkjP379yM/Px8AkJaWhqCgILs6\nZrMZJ0+eRH5+PhoaGiCXyxEeHo7ly5dzi3AJaGxsRFFREbRaLRoaGnDv3j34+fkhPDwcL730knU7\neEfY16VLr9cjIyMD5eXl1vW64uLisHLlSq7XJWHt7e0oLi7GxYsXcePGDej1eshkMoSGhmLevHmY\nP38+PDw87B5XVVWFo0ePoqamBkajEcHBwZg/fz4WLVoET09+ZyVFBQUF2LdvHwAgJSUFSUlJdnVK\nS0tx/Phx1NXVwWw2Y+zYsViwYAESExP7u7nkhO+++w4ajQY1NTXo6OiAQqFAaGgoXnrpJTz77LM2\nddnXpe/ChQvIycnBrVu30NbWhpEjRyIsLAxLly51eN3NmEtDUVERKisrcf36ddTV1aGrqwsvvPAC\nNm3a1O1j+hJbMcZ9t99dyFldXV147733oNFooFAoEBcXhylTpsDPzw/V1dWYOHEiQkJCbB6Tnp6O\nI0eOwNPTE3PnzsXYsWNx6dIl5OXlYfjw4Zg4ceIAPRvqrfPnz+PIkSPw9fWFyWTC4sWLoVAo7Op9\n9NFHyMnJgZ+fH+bOnYvAwECUlZUhNzcX48ePh0qlGoDW05M6dOgQTp48CR8fH0ybNg3Tpk2Dj48P\nLly4gPz8fAwbNsxhv2Vfl66mpib85je/QXV1NaZNm4aYmBgYjUYUFhaipKQEzz//fK92niPXcebM\nGRw8eBD379/HlClT8OyzzyIwMBCVlZUoKirCzZs3kZCQYPOYkpISvPfee7hz5w5mzZqFiIgI3Lp1\nC//6179w69Ytu/rk+lpaWvDHP/4RXl5eMJlMiI2NRVhYmE0djUaDffv2wWAw4Pnnn8fEiRNRW1uL\ngoICGAwGREdHD1DrqTcOHz6MQ4cOwWAwYMaMGYiOjsaoUaOg0+ng4eFhE0f2dek7fPgwPv30U9y/\nfx8xMTGIioqCt7c3SktLkZubi5CQEISGhlrrM+bSkZaWhtLSUrS3t2PUqFFoa2vDuHHjEB8f77B+\nX2Ir2rgvkFP27NkjqNVq4fTp0w7Lv//+e5t/V1VVCWq1WtiyZYvQ0dFhPd7c3CysW7dOWLt2rdDc\n3PxU20ziuHfvnrBx40bh448/Ft59911BrVYLjY2NdvX++c9/Cmq1Wvjtb38rGI1G6/GrV68Ka9as\nETZs2CDcv3+/P5tOvZSfny/8+9//tjteWVkprF69WlizZo1w584dmzL2dWn7/e9/L6jVakGj0dgc\n/+yzzwS1Wi0cPHhwgFpGzrp06ZJQWlpqd/zu3bvCL3/5S0GtVgvFxcXW452dncL69euFNWvWCNeu\nXbMeNxqNwo4dOwS1Wi2cPXu2X9pO4vnd734nbN68Wfj8888FtVot5Obm2pTrdDphzZo1wrp162zG\n6o6ODmHz5s2CWq0Wqqur+7vZ1EvffvutoFarhU8++UQwmUx25Y9ep7OvS9+dO3eEVatWCa+//rrQ\n2tpqU1ZRUSGo1Wph06ZN1mOMubRUVFQIDQ0N1t/VarWwd+9eh3X7Elsxx33Of3JCXV0dzp49izlz\n5uDFF190WOeH05BOnToFAPjpT3+KoUOHWo+PHj0aCxcuhNFoRF5e3tNrNInmwIED8PDwwPr163us\n9+233wIAVq1aBZnsv3foPfPMM0hISEBrayuKioqealvJOYmJiRg/frzd8alTpyIyMhImkwnV1dU2\nZZovJBYAAAxASURBVOzr0qXT6aDVaqFUKrFw4UKbMrVaDR8fHxQUFODBgwcD1EJyRmRkpMPb9UaM\nGIHk5GQAQEVFhfX4uXPn0NbWhjlz5tjMdJDJZFi1ahWA/47zJA05OTmoqKjAG2+8AR8fH4d1/vGP\nf1hnqI4ePdp6fOjQoXj55ZcBMO6uzmQyITMzE6NHj8brr78OLy8vuzqPXqezr0tfS0sLBEHAxIkT\nMWzYMJuyiIgI+Pr6orW11XqMMZeWiIgIh8twONKX2Io57jPJ4oSCggIAwOzZs9HZ2YmCggIcO3YM\np0+fRmNjo8PHWC7cpk+fbldmuSf00qVLT6nFJJb8/HycP38eGzdudHh7kIXlw7ePjw+mTJliV/7c\nc88BYMylzHLR9sOEKvu6dFni4mhKqK+vLyZPngyDwWCXWCPps/TnRz+MWfryD9dtAB5e8MnlclRV\nVcFkMvVPI8kp9fX1OHLkCJYsWeLwfdmipzGc793SoNVq0draipkzZ8LDwwMXLlzA119/jZycHIfj\nN/u69AUHB0Mmk6G2thZtbW02ZZWVlejq6rJ5b2fMB6++xFbMcZ8L3zrh2rVrAIDm5mZs3rwZ7e3t\nNuULFizAunXrrAvoGQwG6PV6+Pr6wt/f3+58lrVbGhoannLLyRnNzc3461//irlz5yI2NrbHuo2N\njTCbzQgKCnK4uBJjLm3Nzc347rvv4OPjg4iICOtx9nVpu337NgDYradlERISYl0EOSoqqj+bRk+R\n2WzGmTNnANhelPX09+Dp6QmlUon6+nrodDqur+XizGYz/vznPyMwMBCrV6/usW5Pcff394ePjw/+\n85//4MGDB1yfyUXV1tYCePjN9a9+9SvcvHnTpnzq1KnYvn07hg8fDoB9fTBQKBRYu3Yt0tPTsX37\ndsTFxUGhUKCxsRGlpaWYPn06Nm7caK3PmA9efYmtmOM+kyxOuHfvHoCHi1vGx8fjlVdeQUBAAGpq\nanDw4EGcOnUKI0aMwIoVKwAAnZ2dAGBz68CjLMc7Ojr6ofXUF4IgYN++fRgyZAhee+21x9Z/0phb\n6pF0mEwmpKWlwWQyYfXq1TYxZl+XNsbPPR0+fBj19fXWhTEt+PcweHz55Ze4fv06du/eDW9v7x7r\nPkncDQYDOjs7mWRxUZbbQo4fP44xY8Zg9+7dGDduHHQ6HT7//HOUl5fjo48+ws6dOwGwrw8WS5Ys\nQWBgIPbv34/c3Fzr8eDgYCQmJlqTagBjPpj1JbZijvtun2R588030dLS8sT1H90mymw2AwBUKhW2\nbdtmnbESFRWF7du345133sGJEyfw8ssvO7wPtDuOto4k8TgT8xMnTuDy5cv49a9/3W0H7A1BEJw+\nBz0ZZ+L+Q2azGWlpaaiursacOXOwdOnSPrWJfV2aLP2W8Rs8cnJykJ2djTFjxvS4FWRP+Pfg2mpr\na3Hs2DEsW7ZMlJ3dOA64Pst1upeXF9555x3rGgtjx47FW2+9ha1bt6KyshI1NTUIDw9/4vMy5q7t\n66+/RkZGBpYsWYKFCxfC398ft2/fxt/+9jekpaWhrq4Oa9eu7dU5GfPBqzex7c247/ZJluDg4F59\nAzFy5Ejr75a1OGJjY+1e7HHjxkGpVKKpqQm3bt1CaGjoY2ctPC57RuLobcwDAgIAPLz1JyMjA/Pn\nz3d4f58jj4v5/fv3berR09PXuP+QJcFSXFyM2bNnO/xAxr4ubey37kWj0eCzzz7D2LFjkZqaCj8/\nP5ty9mfpM5vN2Lt3L1QqFdRqtU1Zd192DB06FG1tbejs7HS49pplHBgyZIj4DSZRWPpyWFiYzSKW\nACCXyzF9+nTk5eWhtrYW4eHh7OuDQGVlJY4cOYKZM2fi1VdftR4fP3483n77bWzduhUnTpxAcnIy\nlEolYz6I9SW2Yo77bp9kSU1N7fNjQ0JCUFtba3dBZmE5btmBwsfHBwEBAdDr9bh7967dWg2W9Rm6\nWweAxNHXmN+8eRMmkwl5eXnd7gqzZcsWAMDbb7+N2NhYBAcHw9PTE01NTTCbzXbrsjDm/ceZvm5h\nNpvx8ccfo7i4GC+88ALefPNNh9ls9nVps9yb292aOYzf4JGdnY309HSEhoYiNTXVZhq5hUqlwrVr\n19DQ0GCzQwHwcEzQ6XTw8vKCUqnsr2ZTL3V1dVk3JOjuG+wDBw7gwIEDWLJkCX7xi19ApVKhqqoK\nDQ0NdrMc7t69C4PBgFGjRvFWIRdmGcu7+4Bs+RBluU5nX5e+0tJSALBZJ89CLpdjwoQJKCkpQV1d\nHZRKJWM+iPUltmKO+9xdyAmWe7Zv3LhhV2Yymaxv6IGBgdbjkZGRAICysjK7x1y8eBEAMG3aNNHb\nSs4LDAxEUlKSwx/Lh+iEhAQkJSVZYy6TyTBp0iQYDAZcuXLF7pyMuXSYTCZ88MEHKC4uRmJiIjZt\n2tTjdEH2demyxE6r1dqVdXV1oaqqCnK5HJMmTervppGIjh07hvT0dISFhWHnzp0OEywArIsbO+rL\nlZWVePDgASZPngyZzO2/t3JZMpms2/dvy8X3lClTkJSUZO3XPcX9woULNnXINVneY+vr6x2WWxbC\ntXzIYl+XPqPRCAA22zQ/yrLjkCWGjPng1ZfYijnuM8nihJkzZ2LkyJE4d+6cdQVzi6ysLHR2diIq\nKgojRoywHl+wYAEA4KuvvrJZaEen0+Gbb76Bt7c35s2b1y/tp94ZP348UlJSHP5Yvi1ZvXo1UlJS\nMG7cOOvjLDHPyMiwDv7Aw/vDz507hxEjRmDmzJn9+2SoV0wmE/70pz+htLQUL774It54443HPoZ9\nXbqCgoIQHR0NnU4HjUZjU5aZmQmDwYDExER+gy1hWVlZ+Pvf/44JEyYgNTXV4bRgi1mzZmHYsGE4\ne/asdVdB4OHFfEZGBoD/9ndyTXK5vNv375iYGABAYmIiUlJSkJCQAACYN28eZDIZNBoNmpubredq\nb2/HV199BQBITk7u/ydDT2z06NGIiYlBS0sLsrOzbcrKy8tRVlYGhUJhvQWcfV36pk6dCgDIzc2F\nXq+3Kbt48SKuXLli8yUJYz549SW2Yo77HgJX3nSKVqvF+++/DwCIj49HQEAAamtrceXKFfj7+2PX\nrl0IDg62eUx6ejqys7MREBCAWbNmwWQyobCwEO3t7Vi/fj07swTt2rULlZWVSEtLQ1BQkF35hx9+\niOLiYqhUKsTExKCtrQ3nzp2D0WjEW2+9Zb3II9f0ySef4MyZMxg+fDiSk5MdzmCJjIy0m57Kvi5d\nTU1NSE1Nxb179xAbG4sf/ehHqKmpQWVlJVQqFXbv3t3jB3NyXfn5+di/fz88PT2xaNEih7cSBAYG\n2iRBS0pK8OGHH8Lb2xuzZ8+GQqFAaWkpbt++jYSEBGzbtq0fnwGJ6csvv0RWVhZSUlKQlJRkU6bR\naPCXv/wFCoUCs2fPhkwmQ1FREfR6PZYtW4af/exnA9RqelJ6vR6pqaloaWlBVFQUwsLC0NTUhPPn\nz8PDwwPbtm1DfHy8tT77urQJgoA//OEP0Gq18PX1RXx8PPz9/VFfX2+difDaa69h0aJF1scw5tJR\nUlKCkpISAA9v3ykvL4dSqbQm14YNG2azFk9fYivWuM8kiwhu3LiBrKwsXL58GZ2dnfD398eMGTOw\nfPlyu7UYLAoKCqDRaFBfXw8PDw8888wz+PGPf4znnnuun1tPYti1axcuX76MPXv2OEyymM1maDQa\n5OXlobGxEd7e3pg0aRKWL1/eqxXtaWBYkmg9WblypXW79kexr0uXXq9HZmYmysrK0N7eDn9/f8TH\nx2PFihXdrsVFrs/yobonERER1m1dLaqrq3H06FFUV1fDaDQiODgY8+fPx+LFi7nzhIT1lGQBHk4R\nP378OK5duwZBEDBmzBgsWrQIc+fOHYDWUl+0tbUhKysL58+fx927dzFkyBBMnToVP/nJTzBhwgS7\n+uzr0ma55i4sLER9fT0MBgMUCgXCw8OxePFih7dqM+bS8Lj3b6VSib1799oc60tsxRj3mWQhIiIi\nIiIiIhIB12QhIiIiIiIiIhIBkyxERERERERERCJgkoWIiIiIiIiISARMshARERERERERiYBJFiIi\nIiIiIiIiETDJQkREREREREQkAiZZiIiIiIiIiIhEwCQLEREREREREZEImGQhIiIiIiIiIhIBkyxE\nRERERERERCL4X3noN5mvBFWmAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x109cf2f10>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# plot the weight changes\n",
    "figsize = (18,8)\n",
    "patient_tab['weight_change'].plot(kind='hist',\n",
    "                             figsize=figsize, \n",
    "                             fontsize=fontsize,\n",
    "                             bins=50)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}