First agate ipython experiment

exonerations.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import csv\n",
    "\n",
    "import agate\n",
    "\n",
    "text_type = agate.TextType()\n",
    "number_type = agate.NumberType()\n",
    "boolean_type = agate.BooleanType()\n",
    "\n",
    "columns = (\n",
    "    ('last_name', text_type),\n",
    "    ('first_name', text_type),\n",
    "    ('age', number_type),\n",
    "    ('race', text_type),\n",
    "    ('state', text_type),\n",
    "    ('tags', text_type),\n",
    "    ('crime', text_type),\n",
    "    ('sentence', text_type),\n",
    "    ('convicted', number_type),\n",
    "    ('exonerated', number_type),\n",
    "    ('dna', boolean_type),\n",
    "    ('dna_essential', text_type),\n",
    "    ('mistaken_witness', boolean_type),\n",
    "    ('false_confession', boolean_type),\n",
    "    ('perjury', boolean_type),\n",
    "    ('false_evidence', boolean_type),\n",
    "    ('official_misconduct', boolean_type),\n",
    "    ('inadequate_defense', boolean_type),\n",
    ")\n",
    "\n",
    "with open('examples/realdata/exonerations-20150828.csv') as f:\n",
    "    # Create a csv reader\n",
    "    reader = csv.reader(f)\n",
    "\n",
    "    # Skip header\n",
    "    next(f)\n",
    "\n",
    "    # Create the table\n",
    "    exonerations = agate.Table(reader, columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false,
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "False confessions: 211\n"
     ]
    }
   ],
   "source": [
    "num_false_confessions = exonerations.columns['false_confession'].aggregate(agate.Count(True))\n",
    "\n",
    "print('False confessions: %i' % num_false_confessions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Median age at time of arrest: 26\n"
     ]
    }
   ],
   "source": [
    "with_age = exonerations.where(lambda row: row['age'] is not None)\n",
    "\n",
    "median_age = with_age.columns['age'].aggregate(agate.Median())\n",
    "\n",
    "print('Median age at time of arrest: %i' % median_age)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "|------------+------------+-----+-----------+-------+---------+---------+------|\n",
      "|  last_name | first_name | age | race      | state | tags    | crime   | ...  |\n",
      "|------------+------------+-----+-----------+-------+---------+---------+------|\n",
      "|  Murray    | Lacresha   | 11  | Black     | TX    | CV, F   | Murder  | ...  |\n",
      "|  Adams     | Johnathan  | 12  | Caucasian | GA    | CV, P   | Murder  | ...  |\n",
      "|  Harris    | Anthony    | 12  | Black     | OH    | CV      | Murder  | ...  |\n",
      "|  Edmonds   | Tyler      | 13  | Caucasian | MS    |         | Murder  | ...  |\n",
      "|  Handley   | Zachary    | 13  | Caucasian | PA    | A, CV   | Arson   | ...  |\n",
      "|  Jimenez   | Thaddeus   | 13  | Hispanic  | IL    |         | Murder  | ...  |\n",
      "|  Pacek     | Jerry      | 13  | Caucasian | PA    |         | Murder  | ...  |\n",
      "|  Barr      | Jonathan   | 14  | Black     | IL    | CDC, CV | Murder  | ...  |\n",
      "|  Brim      | Dominique  | 14  | Black     | MI    | F       | Assault | ...  |\n",
      "|  Brown     | Timothy    | 14  | Black     | FL    |         | Murder  | ...  |\n",
      "|------------+------------+-----+-----------+-------+---------+---------+------|\n"
     ]
    }
   ],
   "source": [
    "sorted_by_age = exonerations.order_by('age')\n",
    "youngest_ten = sorted_by_age.limit(10)\n",
    "\n",
    "print(youngest_ten.format(max_columns=7))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "|--------+-------+-------------------------|\n",
      "|  group | count | median_years_in_prison  |\n",
      "|--------+-------+-------------------------|\n",
      "|  DC    | 15    | 27                      |\n",
      "|  NE    | 9     | 20                      |\n",
      "|  ID    | 2     | 19                      |\n",
      "|  VT    | 1     | 18                      |\n",
      "|  LA    | 45    | 16                      |\n",
      "|  ...   | ...   | ...                     |\n",
      "|--------+-------+-------------------------|\n"
     ]
    }
   ],
   "source": [
    "with_years_in_prison = exonerations.compute([\n",
    "    ('years_in_prison', agate.Change('convicted', 'exonerated'))\n",
    "])\n",
    "\n",
    "state_totals = with_years_in_prison.group_by('state')\n",
    "\n",
    "medians = state_totals.aggregate([\n",
    "    ('years_in_prison', agate.Median(), 'median_years_in_prison')\n",
    "])\n",
    "\n",
    "sorted_medians = medians.order_by('median_years_in_prison', reverse=True)\n",
    "\n",
    "print(sorted_medians.format(max_rows=5))"
   ]
  }
 ],
 "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": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}