{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "from __future__ import print_function, division\n",
    "\n",
    "import nsfg3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import pandas\n",
    "import numpy as np\n",
    "\n",
    "def ReadFemResp1995():\n",
    "    \"\"\"Reads respondent data from NSFG Cycle 5.\n",
    "\n",
    "    returns: DataFrame\n",
    "    \"\"\"\n",
    "    dat_file = '1995FemRespData.dat.gz'\n",
    "    names = ['cmintvw', 'timesmar', 'cmmarrhx', 'cmbirth', 'finalwgt']\n",
    "    colspecs = [(12360-1, 12363),\n",
    "                (4637-1, 4638),\n",
    "                (11759-1, 11762),\n",
    "                (14-1, 16),\n",
    "                (12350-1, 12359)]\n",
    "    df = pandas.read_fwf(dat_file, \n",
    "                         compression='gzip', \n",
    "                         colspecs=colspecs, \n",
    "                         names=names)\n",
    "\n",
    "    df.timesmar.replace([98, 99], np.nan, inplace=True)\n",
    "    df['evrmarry'] = (df.timesmar > 0)\n",
    "\n",
    "    nsfg3.CleanData(df)\n",
    "    return df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "df = ReadFemResp1995()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "4006"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum(~df.evrmarry)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3918"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(df[(df.cmbirth >= 604) & (df.cmbirth <= 720)])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "192"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(df[(df.cmmarrhx >= 780) & (df.cmmarrhx <= 840)])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1141     514\n",
       "1142    2448\n",
       "1143    2466\n",
       "1144    1692\n",
       "1145    1381\n",
       "1146    1076\n",
       "1147     722\n",
       "1148     172\n",
       "1149      81\n",
       "1150     295\n",
       "Name: cmintvw, dtype: int64"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.cmintvw.value_counts().sort_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "349.8761      1\n",
       "356.8193      1\n",
       "433.7413      1\n",
       "434.1431      1\n",
       "441.2415      1\n",
       "463.0787      1\n",
       "464.5584      1\n",
       "468.2044      1\n",
       "472.6256      1\n",
       "482.7008      1\n",
       "495.1924      1\n",
       "498.6220      1\n",
       "507.9773      1\n",
       "511.4543      1\n",
       "519.3578      1\n",
       "523.6670      1\n",
       "525.7335      1\n",
       "555.8899      1\n",
       "561.4898      1\n",
       "561.6297      1\n",
       "564.7645      1\n",
       "567.7595      1\n",
       "589.4533      1\n",
       "590.1313      1\n",
       "590.1364      1\n",
       "617.0250      1\n",
       "634.0294      1\n",
       "634.8276      1\n",
       "637.1154      1\n",
       "640.9224      1\n",
       "             ..\n",
       "18588.5661    1\n",
       "18702.0666    1\n",
       "18890.5291    1\n",
       "19985.1776    1\n",
       "20077.5177    1\n",
       "20161.3343    1\n",
       "20457.1239    1\n",
       "20628.0956    1\n",
       "20731.0408    1\n",
       "20864.2010    1\n",
       "20916.7939    1\n",
       "21558.0296    1\n",
       "21886.1411    1\n",
       "22304.0038    1\n",
       "22568.3367    1\n",
       "22718.1978    1\n",
       "22812.9377    1\n",
       "23231.5175    1\n",
       "23497.7818    1\n",
       "23693.3226    1\n",
       "23758.9147    1\n",
       "24146.9122    1\n",
       "24653.6224    1\n",
       "24916.6825    1\n",
       "25049.8728    1\n",
       "25568.3298    1\n",
       "25840.3059    1\n",
       "26067.4314    1\n",
       "26562.8055    1\n",
       "33549.8227    1\n",
       "Name: finalwgt, dtype: int64"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.finalwgt.value_counts().sort_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1    5559\n",
       "2    1077\n",
       "3     174\n",
       "4      26\n",
       "5       5\n",
       "Name: timesmar, dtype: int64"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.timesmar.value_counts().sort_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "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": "3.5.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}