coahuila_distritos_locales.csv

pdf-distritos.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import PyPDF2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load PDF"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "pdfFileObj = open('D05.pdf', 'rb')\n",
    "pdfReader = PyPDF2.PdfFileReader(pdfFileObj)\n",
    "text = \"\"\n",
    "for page in range(pdfReader.numPages):\n",
    "    pageObj = pdfReader.getPage(page)\n",
    "    text = text + pageObj.extractText()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load Distritos, by capturing Distrito title"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "metadata": {},
   "outputs": [],
   "source": [
    "distritos_split = text.split(\"\\nDistrito \")\n",
    "district_data = []\n",
    "# We jump first element that has no sections.\n",
    "for i in range(1,len(distritos_split)):\n",
    "    section_ranges = extract_ranges(distritos_split[i].replace(\"\\n\",\"\"))\n",
    "    district = distritos_split[i][1:3]\n",
    "    district_data.append([district, section_ranges])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Extract Ranges\n",
    "- We find the ranges from document with the phrase that defines it\n",
    "- Then we compare to the number present. Individual numbers is the difference between the numbers in ranges and other found"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "metadata": {},
   "outputs": [],
   "source": [
    "def extract_ranges(text):\n",
    "    ranges = re.findall('[0-9][0-9][0-9][0-9] a la [0-9][0-9][0-9][0-9]', text)\n",
    "    single_numbers = re.findall('[0-9][0-9][0-9][0-9]', text)\n",
    "    sections = []\n",
    "    individual_sections_in_ranges = []\n",
    "    for datum in ranges:\n",
    "        selected_sections = datum.split(\" a la \")\n",
    "        sections.append(selected_sections)\n",
    "        individual_sections_in_ranges.append(selected_sections[0])\n",
    "        individual_sections_in_ranges.append(selected_sections[1])\n",
    "    sections = sections + [[section, section] for section in single_numbers if section not in individual_sections_in_ranges]\n",
    "    return sections"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### We validate that we capture all sections"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 137,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def sum_sections(array_sections):\n",
    "    sum_data = 0\n",
    "    for section_range in array_sections:\n",
    "        sum_data = sum_data + int(section_range[1]) - int(section_range[0]) + 1\n",
    "    return sum_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 138,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "sum_district = 0\n",
    "for section in district_data:\n",
    "    sum_district = sum_district + sum_sections(section[1]) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## We know from the map, that coahuila does have 1688. Sections"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 139,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1688"
      ]
     },
     "execution_count": 139,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum_district"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 140,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 144,
   "metadata": {},
   "outputs": [],
   "source": [
    "pd.DataFrame(district_data, columns = [\"distrito\", \"rangos\"]).to_csv(\"coahuila_distritos_locales.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['0003', '0008', '0040', '0041', '1682', '1710', '0240', '0249', '0444', '0449', '1506', '1513']\n",
      "['0003', '0008', '0010', '0037', '0040', '0041', '1682', '1710', '0240', '0249', '0444', '0449', '1506', '1513', '1515', '1518', '1520']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[['0003', '0008'],\n",
       " ['0040', '0041'],\n",
       " ['1682', '1710'],\n",
       " ['0240', '0249'],\n",
       " ['0444', '0449'],\n",
       " ['1506', '1513'],\n",
       " ['0010', '0010'],\n",
       " ['0037', '0037'],\n",
       " ['1515', '1515'],\n",
       " ['1518', '1518'],\n",
       " ['1520', '1520']]"
      ]
     },
     "execution_count": 103,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "extract_ranges(distritos_split[1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import re"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [],
   "source": [
    "m = re.findall('[0-9][0-9][0-9][0-9]', crude_data[1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['0233',\n",
       " '0237',\n",
       " '0238',\n",
       " '0239',\n",
       " '0508',\n",
       " '0523',\n",
       " '0525',\n",
       " '0577',\n",
       " '0610',\n",
       " '0612',\n",
       " '0644',\n",
       " '1548',\n",
       " '1567']"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Non Kanon"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 145,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "17\n"
     ]
    }
   ],
   "source": [
    "print(len(text.split(\"\\nDistrito \")))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 146,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "distritos_split = text.split(\"\\nDistrito \")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 147,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['\\n ', '01', '02', '03', '04', '05', '06', '07', '08', '09', '10', '11', '12', '13', '14', '15', '16']\n"
     ]
    }
   ],
   "source": [
    "print([distrito[1:3] for distrito in distritos_split])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}