fonnesbeck/Najwa Visit.ipynb

## Najwa Visit.ipynb
{
  "cells": [
    {
      "metadata": {
        "trusted": true,
        "collapsed": true
      },
      "cell_type": "code",
      "source": "%matplotlib inline\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom datetime import datetime\nimport seaborn as sb",
      "execution_count": 1,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false
      },
      "cell_type": "code",
      "source": "hospitalized = pd.read_csv('data/hospitalized.csv', index_col=0)",
      "execution_count": 76,
      "outputs": [
        {
          "output_type": "stream",
          "text": "/Users/fonnescj/anaconda3/envs/dev/lib/python3.5/site-packages/IPython/core/interactiveshell.py:2717: DtypeWarning: Columns (140,142,144,146,148,181,206,212,213,262,281,282,283,297,298) have mixed types. Specify dtype option on import or set low_memory=False.\n  interactivity=interactivity, compiler=compiler, result=result)\n",
          "name": "stderr"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false
      },
      "cell_type": "code",
      "source": "hospitalized.shape",
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": "(3168, 408)"
          },
          "metadata": {},
          "execution_count": 3
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "## Virus-negative individuals"
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false
      },
      "cell_type": "code",
      "source": "hospitalized['pcr_growth'] = (hospitalized[hospitalized.columns[hospitalized.columns.str.startswith('pcr_result')]]\n                                     .sum(1)==0).replace({False:'Growth', True:'No Growth'})",
      "execution_count": 39,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false
      },
      "cell_type": "code",
      "source": "by_growth = hospitalized.groupby('pcr_growth')",
      "execution_count": 45,
      "outputs": []
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "Plot of age by PCR growth status"
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false
      },
      "cell_type": "code",
      "source": "hospitalized.hist('age_months', by='pcr_growth', sharex=True)",
      "execution_count": 42,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": "array([<matplotlib.axes._subplots.AxesSubplot object at 0x110f0e0f0>,\n       <matplotlib.axes._subplots.AxesSubplot object at 0x1136cc390>], dtype=object)"
          },
          "metadata": {},
          "execution_count": 42
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": "<matplotlib.figure.Figure at 0x111f14080>",
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAsMAAAHcCAYAAAAz5KeRAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nf35VIkAcQm7pAAAAAElFTkSuQmCC\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "Plot of length of stay by PCR growth"
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false
      },
      "cell_type": "code",
      "source": "hospitalized.hist('length_of_stay', by='pcr_growth', sharex=True)",
      "execution_count": 43,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": "array([<matplotlib.axes._subplots.AxesSubplot object at 0x111fc70f0>,\n       <matplotlib.axes._subplots.AxesSubplot object at 0x113c6b080>], dtype=object)"
          },
          "metadata": {},
          "execution_count": 43
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": "<matplotlib.figure.Figure at 0x1109ee0f0>",
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAsMAAAHcCAYAAAAz5KeRAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "Higher sepsis and blood culture rates for no growth individuals"
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false
      },
      "cell_type": "code",
      "source": "by_growth[['adm_pneumo', 'adm_bronchopneumo', 'adm_sepsis', 'adm_bronchiolitis', 'blood_culture']].mean()",
      "execution_count": 46,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": "            adm_pneumo  adm_bronchopneumo  adm_sepsis  adm_bronchiolitis  \\\npcr_growth                                                                 \nGrowth        0.135994           0.343278    0.235568           0.194886   \nNo Growth     0.073254           0.228279    0.497445           0.074957   \n\n            blood_culture  \npcr_growth                 \nGrowth           0.423922  \nNo Growth        0.576068  ",
            "text/html": "<div>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>adm_pneumo</th>\n      <th>adm_bronchopneumo</th>\n      <th>adm_sepsis</th>\n      <th>adm_bronchiolitis</th>\n      <th>blood_culture</th>\n    </tr>\n    <tr>\n      <th>pcr_growth</th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>Growth</th>\n      <td>0.135994</td>\n      <td>0.343278</td>\n      <td>0.235568</td>\n      <td>0.194886</td>\n      <td>0.423922</td>\n    </tr>\n    <tr>\n      <th>No Growth</th>\n      <td>0.073254</td>\n      <td>0.228279</td>\n      <td>0.497445</td>\n      <td>0.074957</td>\n      <td>0.576068</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
          },
          "metadata": {},
          "execution_count": 46
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "Bacteria positives"
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false,
        "scrolled": true
      },
      "cell_type": "code",
      "source": "by_growth[['blood_acintobacter',\n 'blood_alcaligenese',\n 'blood_candida',\n 'blood_ecoli',\n 'blood_klebsiella',\n 'blood_pneumo',\n 'blood_mening',\n 'blood_staph',\n 'blood_strep',\n 'blood_other_gram_neg']].mean().round(3)",
      "execution_count": 49,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": "            blood_acintobacter  blood_alcaligenese  blood_candida  \\\npcr_growth                                                          \nGrowth                   0.375               0.167          0.143   \nNo Growth                0.000               0.000          0.000   \n\n            blood_ecoli  blood_klebsiella  blood_pneumo  blood_mening  \\\npcr_growth                                                              \nGrowth            0.000             0.167         0.014         0.027   \nNo Growth         0.286             0.429         0.048         0.000   \n\n            blood_staph  blood_strep  blood_other_gram_neg  \npcr_growth                                                  \nGrowth            0.123        0.571                 0.167  \nNo Growth         0.143        0.300                 0.000  ",
            "text/html": "<div>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>blood_acintobacter</th>\n      <th>blood_alcaligenese</th>\n      <th>blood_candida</th>\n      <th>blood_ecoli</th>\n      <th>blood_klebsiella</th>\n      <th>blood_pneumo</th>\n      <th>blood_mening</th>\n      <th>blood_staph</th>\n      <th>blood_strep</th>\n      <th>blood_other_gram_neg</th>\n    </tr>\n    <tr>\n      <th>pcr_growth</th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>Growth</th>\n      <td>0.375</td>\n      <td>0.167</td>\n      <td>0.143</td>\n      <td>0.000</td>\n      <td>0.167</td>\n      <td>0.014</td>\n      <td>0.027</td>\n      <td>0.123</td>\n      <td>0.571</td>\n      <td>0.167</td>\n    </tr>\n    <tr>\n      <th>No Growth</th>\n      <td>0.000</td>\n      <td>0.000</td>\n      <td>0.000</td>\n      <td>0.286</td>\n      <td>0.429</td>\n      <td>0.048</td>\n      <td>0.000</td>\n      <td>0.143</td>\n      <td>0.300</td>\n      <td>0.000</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
          },
          "metadata": {},
          "execution_count": 49
        }
      ]
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": true
      },
      "cell_type": "code",
      "source": "by_sepsis = hospitalized.groupby('adm_sepsis')",
      "execution_count": 68,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false
      },
      "cell_type": "code",
      "source": "pcr_lookup = {'pcr_result___1': 'RSV',\n'pcr_result___2': 'HMPV',\n'pcr_result___3': 'flu A',\n'pcr_result___4': 'flu B',\n'pcr_result___5': 'rhino',\n'pcr_result___6': 'PIV1',\n'pcr_result___7': 'PIV2',\n'pcr_result___8': 'PIV3',\n'pcr_result___13': 'H1N1',\n'pcr_result___14': 'H3N2',\n'pcr_result___15': 'Swine',\n'pcr_result___16': 'Swine H1',\n'pcr_result___17': 'flu C',\n'pcr_result___18': 'Adeno'}\n\nhospitalized['RSV'] = hospitalized.pcr_result___1.astype(int)\nhospitalized['HMPV'] = hospitalized.pcr_result___2.astype(int)\nhospitalized['Rhino'] = hospitalized.pcr_result___5.astype(int)\nhospitalized['Influenza'] = (hospitalized.pcr_result___3 | hospitalized.pcr_result___4).astype(int)\nhospitalized['Adeno'] = hospitalized.pcr_result___18.astype(int)\nhospitalized['PIV'] = (hospitalized.pcr_result___6 | hospitalized.pcr_result___7 | hospitalized.pcr_result___8).astype(int)\nhospitalized['No virus'] = (hospitalized[list(pcr_lookup.keys())].sum(1) == 0).astype(int)\n",
      "execution_count": 74,
      "outputs": []
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "Risk factors by sepsis status"
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false
      },
      "cell_type": "code",
      "source": "by_sepsis[['age_months', 'icu', 'length_of_stay', 'oxygen', 'no_growth', 'death',\n          'RSV', 'Adeno', 'PIV', 'Influenza', 'Rhino']].describe()",
      "execution_count": 75,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": "                   age_months          icu  length_of_stay       oxygen  \\\nadm_sepsis                                                                \n0          count  2268.000000  2242.000000     2245.000000  2243.000000   \n           mean      6.932981     0.063336        4.912695     0.362015   \n           std       5.636301     0.243621        3.839174     0.480690   \n           min       0.000000     0.000000        0.000000     0.000000   \n           25%       2.000000     0.000000        2.000000     0.000000   \n           50%       5.000000     0.000000        4.000000     0.000000   \n           75%      10.000000     0.000000        6.000000     1.000000   \n           max      23.000000     1.000000       47.000000     1.000000   \n1          count   900.000000   894.000000      894.000000   894.000000   \n           mean      1.078889     0.116331        7.295302     0.224832   \n           std       1.317039     0.320801        4.054506     0.417705   \n           min       0.000000     0.000000        0.000000     0.000000   \n           25%       0.000000     0.000000        5.000000     0.000000   \n           50%       1.000000     0.000000        7.000000     0.000000   \n           75%       2.000000     0.000000        9.000000     0.000000   \n           max      14.000000     1.000000       42.000000     1.000000   \n\n                          RSV        Adeno          PIV    Influenza  \\\nadm_sepsis                                                             \n0          count  2268.000000  2268.000000  2268.000000  2268.000000   \n           mean      0.507055     0.164021     0.055996     0.031746   \n           std       0.500060     0.370376     0.229966     0.175362   \n           min       0.000000     0.000000     0.000000     0.000000   \n           25%       0.000000     0.000000     0.000000     0.000000   \n           50%       1.000000     0.000000     0.000000     0.000000   \n           75%       1.000000     0.000000     0.000000     0.000000   \n           max       1.000000     1.000000     1.000000     1.000000   \n1          count   900.000000   900.000000   900.000000   900.000000   \n           mean      0.274444     0.114444     0.053333     0.031111   \n           std       0.446482     0.318527     0.224822     0.173715   \n           min       0.000000     0.000000     0.000000     0.000000   \n           25%       0.000000     0.000000     0.000000     0.000000   \n           50%       0.000000     0.000000     0.000000     0.000000   \n           75%       1.000000     0.000000     0.000000     0.000000   \n           max       1.000000     1.000000     1.000000     1.000000   \n\n                        Rhino  \nadm_sepsis                     \n0          count  2268.000000  \n           mean      0.383598  \n           std       0.486369  \n           min       0.000000  \n           25%       0.000000  \n           50%       0.000000  \n           75%       1.000000  \n           max       1.000000  \n1          count   900.000000  \n           mean      0.408889  \n           std       0.491902  \n           min       0.000000  \n           25%       0.000000  \n           50%       0.000000  \n           75%       1.000000  \n           max       1.000000  ",
            "text/html": "<div>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th></th>\n      <th>age_months</th>\n      <th>icu</th>\n      <th>length_of_stay</th>\n      <th>oxygen</th>\n      <th>RSV</th>\n      <th>Adeno</th>\n      <th>PIV</th>\n      <th>Influenza</th>\n      <th>Rhino</th>\n    </tr>\n    <tr>\n      <th>adm_sepsis</th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th rowspan=\"8\" valign=\"top\">0</th>\n      <th>count</th>\n      <td>2268.000000</td>\n      <td>2242.000000</td>\n      <td>2245.000000</td>\n      <td>2243.000000</td>\n      <td>2268.000000</td>\n      <td>2268.000000</td>\n      <td>2268.000000</td>\n      <td>2268.000000</td>\n      <td>2268.000000</td>\n    </tr>\n    <tr>\n      <th>mean</th>\n      <td>6.932981</td>\n      <td>0.063336</td>\n      <td>4.912695</td>\n      <td>0.362015</td>\n      <td>0.507055</td>\n      <td>0.164021</td>\n      <td>0.055996</td>\n      <td>0.031746</td>\n      <td>0.383598</td>\n    </tr>\n    <tr>\n      <th>std</th>\n      <td>5.636301</td>\n      <td>0.243621</td>\n      <td>3.839174</td>\n      <td>0.480690</td>\n      <td>0.500060</td>\n      <td>0.370376</td>\n      <td>0.229966</td>\n      <td>0.175362</td>\n      <td>0.486369</td>\n    </tr>\n    <tr>\n      <th>min</th>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n    </tr>\n    <tr>\n      <th>25%</th>\n      <td>2.000000</td>\n      <td>0.000000</td>\n      <td>2.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n    </tr>\n    <tr>\n      <th>50%</th>\n      <td>5.000000</td>\n      <td>0.000000</td>\n      <td>4.000000</td>\n      <td>0.000000</td>\n      <td>1.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n    </tr>\n    <tr>\n      <th>75%</th>\n      <td>10.000000</td>\n      <td>0.000000</td>\n      <td>6.000000</td>\n      <td>1.000000</td>\n      <td>1.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>1.000000</td>\n    </tr>\n    <tr>\n      <th>max</th>\n      <td>23.000000</td>\n      <td>1.000000</td>\n      <td>47.000000</td>\n      <td>1.000000</td>\n      <td>1.000000</td>\n      <td>1.000000</td>\n      <td>1.000000</td>\n      <td>1.000000</td>\n      <td>1.000000</td>\n    </tr>\n    <tr>\n      <th rowspan=\"8\" valign=\"top\">1</th>\n      <th>count</th>\n      <td>900.000000</td>\n      <td>894.000000</td>\n      <td>894.000000</td>\n      <td>894.000000</td>\n      <td>900.000000</td>\n      <td>900.000000</td>\n      <td>900.000000</td>\n      <td>900.000000</td>\n      <td>900.000000</td>\n    </tr>\n    <tr>\n      <th>mean</th>\n      <td>1.078889</td>\n      <td>0.116331</td>\n      <td>7.295302</td>\n      <td>0.224832</td>\n      <td>0.274444</td>\n      <td>0.114444</td>\n      <td>0.053333</td>\n      <td>0.031111</td>\n      <td>0.408889</td>\n    </tr>\n    <tr>\n      <th>std</th>\n      <td>1.317039</td>\n      <td>0.320801</td>\n      <td>4.054506</td>\n      <td>0.417705</td>\n      <td>0.446482</td>\n      <td>0.318527</td>\n      <td>0.224822</td>\n      <td>0.173715</td>\n      <td>0.491902</td>\n    </tr>\n    <tr>\n      <th>min</th>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n    </tr>\n    <tr>\n      <th>25%</th>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>5.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n    </tr>\n    <tr>\n      <th>50%</th>\n      <td>1.000000</td>\n      <td>0.000000</td>\n      <td>7.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n    </tr>\n    <tr>\n      <th>75%</th>\n      <td>2.000000</td>\n      <td>0.000000</td>\n      <td>9.000000</td>\n      <td>0.000000</td>\n      <td>1.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>0.000000</td>\n      <td>1.000000</td>\n    </tr>\n    <tr>\n      <th>max</th>\n      <td>14.000000</td>\n      <td>1.000000</td>\n      <td>42.000000</td>\n      <td>1.000000</td>\n      <td>1.000000</td>\n      <td>1.000000</td>\n      <td>1.000000</td>\n      <td>1.000000</td>\n      <td>1.000000</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
          },
          "metadata": {},
          "execution_count": 75
        }
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3",
      "language": "python"
    },
    "latex_envs": {
      "eqNumInitial": 0,
      "eqLabelWithNumbers": true,
      "current_citInitial": 1,
      "cite_by": "apalike",
      "bibliofile": "biblio.bib"
    },
    "language_info": {
      "pygments_lexer": "ipython3",
      "name": "python",
      "codemirror_mode": {
        "version": 3,
        "name": "ipython"
      },
      "nbconvert_exporter": "python",
      "version": "3.5.2",
      "mimetype": "text/x-python",
      "file_extension": ".py"
    },
    "gist": {
      "id": "",
      "data": {
        "description": "Najwa Analyses",
        "public": true
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 1
}