Sample is_male name probability estimates, conditioned by name, name/year, name/state, and name/year/state

is_male_name.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:93ee95c96f30075d52fc69273cdd5b032909e7e1f4a284aaaeae74d821041049"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Imports\n",
      "import requests\n",
      "import glob\n",
      "import pandas"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Read data\n",
      "name_data = pandas.read_csv('names/all-states', header=None)\n",
      "name_data.columns = ['state', 'sex', 'year', 'name', 'count']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 9
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Map sex to is_male\n",
      "name_data['is_male'] = (name_data['sex'] == 'M')\n",
      "name_data['male_count'] = name_data['is_male'] * name_data['count']\n",
      "\n",
      "# Map name to LC\n",
      "name_data['name'] = name_data['name'].apply(str.lower).apply(str.strip)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 44
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "name_data.head()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>state</th>\n",
        "      <th>sex</th>\n",
        "      <th>year</th>\n",
        "      <th>name</th>\n",
        "      <th>count</th>\n",
        "      <th>is_male</th>\n",
        "      <th>male_count</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> AK</td>\n",
        "      <td> F</td>\n",
        "      <td> 1910</td>\n",
        "      <td>     mary</td>\n",
        "      <td> 14</td>\n",
        "      <td> False</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> AK</td>\n",
        "      <td> F</td>\n",
        "      <td> 1910</td>\n",
        "      <td>    annie</td>\n",
        "      <td> 12</td>\n",
        "      <td> False</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> AK</td>\n",
        "      <td> F</td>\n",
        "      <td> 1910</td>\n",
        "      <td>     anna</td>\n",
        "      <td> 10</td>\n",
        "      <td> False</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> AK</td>\n",
        "      <td> F</td>\n",
        "      <td> 1910</td>\n",
        "      <td> margaret</td>\n",
        "      <td>  8</td>\n",
        "      <td> False</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> AK</td>\n",
        "      <td> F</td>\n",
        "      <td> 1910</td>\n",
        "      <td>    helen</td>\n",
        "      <td>  7</td>\n",
        "      <td> False</td>\n",
        "      <td> 0</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>5 rows \u00d7 7 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 45,
       "text": [
        "  state sex  year      name  count is_male  male_count\n",
        "0    AK   F  1910      mary     14   False           0\n",
        "1    AK   F  1910     annie     12   False           0\n",
        "2    AK   F  1910      anna     10   False           0\n",
        "3    AK   F  1910  margaret      8   False           0\n",
        "4    AK   F  1910     helen      7   False           0\n",
        "\n",
        "[5 rows x 7 columns]"
       ]
      }
     ],
     "prompt_number": 45
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Get probability male by name\n",
      "prob_male = name_data.groupby('name')['male_count'].sum() / name_data.groupby('name')['count'].sum()\n",
      "prob_male_year = name_data.groupby(['name', 'year'])['male_count'].sum() / name_data.groupby(['name', 'year'])['count'].sum()\n",
      "prob_male_state = name_data.groupby(['name', 'state'])['male_count'].sum() / name_data.groupby(['name', 'state'])['count'].sum()\n",
      "prob_male_year_state = name_data.groupby(['name', 'year', 'state'])['male_count'].sum() / name_data.groupby(['name', 'year', 'state'])['count'].sum()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "prob_male['michael']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 57,
       "text": [
        "0.99599974867530949"
       ]
      }
     ],
     "prompt_number": 57
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "prob_male_state[('michael', 'CA')]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 58,
       "text": [
        "0.99425400243755246"
       ]
      }
     ],
     "prompt_number": 58
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "prob_male_year[('michael', 2000)]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 59,
       "text": [
        "0.99825441850316388"
       ]
      }
     ],
     "prompt_number": 59
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "prob_male_year[('michael', 1960)]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 65,
       "text": [
        "0.99675659039524611"
       ]
      }
     ],
     "prompt_number": 65
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "prob_male_year[('chris', 1970)]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 71,
       "text": [
        "0.91570959803117313"
       ]
      }
     ],
     "prompt_number": 71
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "prob_male_year[('amy', 2000)]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 73,
       "text": [
        "0.0"
       ]
      }
     ],
     "prompt_number": 73
    }
   ],
   "metadata": {}
  }
 ]
}