bhps_understanding_society_sex.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from matplotlib import pyplot as plt\n",
    "import collections\n",
    "import scipy.stats\n",
    "import numpy as np\n",
    "%matplotlib inline\n",
    "\n",
    "WEIGHTED = False"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "BHPS wave: b\n",
      "Contingency table\n",
      "[[ 8753  2934]\n",
      " [ 2279 11487]]\n",
      "Odds ratio: 15.037, p-value: 0.000000\n",
      "\n",
      "BHPS wave: d\n",
      "Contingency table\n",
      "[[ 8474  2820]\n",
      " [ 2080 11205]]\n",
      "Odds ratio: 16.188, p-value: 0.000000\n",
      "\n",
      "BHPS wave: f\n",
      "Contingency table\n",
      "[[ 8496  3200]\n",
      " [ 2260 11467]]\n",
      "Odds ratio: 13.471, p-value: 0.000000\n",
      "\n",
      "BHPS wave: h\n",
      "Contingency table\n",
      "[[ 9573  3441]\n",
      " [ 2415 13347]]\n",
      "Odds ratio: 15.376, p-value: 0.000000\n",
      "\n",
      "BHPS wave: j\n",
      "Contingency table\n",
      "[[13731  4632]\n",
      " [ 3309 19077]]\n",
      "Odds ratio: 17.090, p-value: 0.000000\n",
      "\n",
      "BHPS wave: l\n",
      "Contingency table\n",
      "[[14268  4831]\n",
      " [ 3502 19633]]\n",
      "Odds ratio: 16.558, p-value: 0.000000\n",
      "\n",
      "BHPS wave: n\n",
      "Contingency table\n",
      "[[13325  4521]\n",
      " [ 3316 18672]]\n",
      "Odds ratio: 16.596, p-value: 0.000000\n",
      "\n",
      "BHPS wave: p\n",
      "Contingency table\n",
      "[[12731  4291]\n",
      " [ 3122 17905]]\n",
      "Odds ratio: 17.016, p-value: 0.000000\n",
      "\n",
      "BHPS wave: r\n",
      "Contingency table\n",
      "[[11626  4044]\n",
      " [ 2948 16500]]\n",
      "Odds ratio: 16.091, p-value: 0.000000\n",
      "\n"
     ]
    }
   ],
   "source": [
    "codes = 'bdfhjlnpr'\n",
    "for code in codes:\n",
    "    nominations = collections.defaultdict(lambda: 0)\n",
    "    \n",
    "    bhps = pd.read_stata('../data/bhps/%sindresp.dta' % code, convert_categoricals=False)\n",
    "    for _, row in bhps.iterrows():\n",
    "        sex = row['%ssex' % code]\n",
    "        weight = row['%sxrwght' % code]\n",
    "        for i in range(1, 4):\n",
    "            nominations[(sex, row['%snetsx%d' % (code, i)])] += weight if WEIGHTED else 1\n",
    "            \n",
    "    # Construct the cross tabulation\n",
    "    table = [[nominations[(1, 1)], nominations[(1, 2)]],\n",
    "             [nominations[(2, 1)], nominations[(2, 2)]]]\n",
    "\n",
    "    print(\"BHPS wave:\", code)\n",
    "    print(\"Contingency table\")\n",
    "    print(np.round(table).astype(int))\n",
    "    print(\"Odds ratio: %.3f, p-value: %f\" % scipy.stats.fisher_exact(table))\n",
    "    print()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Understanding Society wave: c\n",
      "Contingency table\n",
      "[[36226  9144]\n",
      " [ 7773 51412]]\n",
      "Odds ratio: 26.204, p-value: 0.000000\n",
      "\n",
      "Understanding Society wave: f\n",
      "Contingency table\n",
      "[[34125  7847]\n",
      " [ 6211 47765]]\n",
      "Odds ratio: 33.444, p-value: 0.000000\n",
      "\n"
     ]
    }
   ],
   "source": [
    "codes = 'cf'\n",
    "for code in codes:\n",
    "    nominations = collections.defaultdict(lambda: 0)\n",
    "    \n",
    "    us = pd.read_stata('../data/understanding_society/%s_indresp.dta' % code, convert_categoricals=False)\n",
    "    for _, row in us.iterrows():\n",
    "        sex = row['%s_sex' % code]\n",
    "        weight = row['%s_indscub_xw' % code]\n",
    "        for i in range(1, 4):\n",
    "            nominations[(sex, row['%s_netsx_%d' % (code, i)])] += weight if WEIGHTED else 1\n",
    "            \n",
    "    # Construct the cross tabulation\n",
    "    table = [[nominations[(1, 1)], nominations[(1, 2)]],\n",
    "             [nominations[(2, 1)], nominations[(2, 2)]]]\n",
    "\n",
    "    print(\"Understanding Society wave:\", code)\n",
    "    print(\"Contingency table\")\n",
    "    print(np.round(table).astype(int))\n",
    "    print(\"Odds ratio: %.3f, p-value: %f\" % scipy.stats.fisher_exact(table))\n",
    "    print()"
   ]
  }
 ],
 "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": "3.6.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}