{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "import re"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "states = ['Alabama', 'Alaska', 'Arizona', 'Arkansas', 'California', 'Colorado', 'Connecticut', 'Delaware', 'Florida', 'Georgia', \n",
    "        'Hawaii', 'Idaho', 'Illinois', 'Indiana', 'Iowa', 'Kansas', 'Kentucky', 'Louisiana', 'Maine', 'Maryland', \n",
    "        'Massachusetts', 'Michigan', 'Minnesota', 'Mississippi', 'Missouri', 'Montana', 'Nebraska', 'Nevada', 'New Hampshire', 'New Jersey', \n",
    "        'New Mexico', 'New York', 'North Carolina', 'North Dakota', 'Ohio', 'Oklahoma', 'Oregon', 'Pennsylvania', 'Rhode Island', 'South Carolina', \n",
    "        'South Dakota', 'Tennessee', 'Texas', 'Utah', 'Vermont', 'Virginia', 'Washington', 'West Virginia', 'Wisconsin', 'Wyoming']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "def count_strings(input, str_):\n",
    "    pattern = re.compile(str_)\n",
    "    return len(pattern.findall(input, re.IGNORECASE))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [],
   "source": [
    "def predict_state(text):\n",
    "    # Predict state of jurisdiction\n",
    "    state_dict = {}\n",
    "    for state in states:\n",
    "        state_dict[state.replace(\" \", \"_\")] = count_strings(text, state)\n",
    "\n",
    "    return max(state_dict, key=state_dict.get)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('dev-0/in.tsv', 'r', encoding='utf8') as f:\n",
    "    dev0_x = f.readlines()\n",
    "\n",
    "with open('dev-0/out.tsv', 'wt') as f:\n",
    "    for x in dev0_x:\n",
    "        f.write(\"jurisdiction=\"+str(predict_state(x))+'\\n')\n",
    "\n",
    "f.close()\n",
    "\n",
    "\n",
    "with open('train/in.tsv', 'r', encoding='utf8') as f:\n",
    "    train_x = f.readlines()\n",
    "\n",
    "with open('train/out.tsv', 'wt') as f:\n",
    "    for x in train_x:\n",
    "        f.write(\"jurisdiction=\"+str(predict_state(x))+'\\n')\n",
    "\n",
    "f.close()\n",
    "\n",
    "\n",
    "with open('test-A/in.tsv', 'r', encoding='utf8') as f:\n",
    "    testA_x = f.readlines()\n",
    "\n",
    "with open('test-A/out.tsv', 'wt') as f:\n",
    "    for x in testA_x:\n",
    "        f.write(\"jurisdiction=\"+str(predict_state(x))+'\\n')\n",
    "\n",
    "f.close()"
   ]
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "df93b008b708122b991044997d8941ca5d5845b048d54848454a010a3b0bd41a"
  },
  "kernelspec": {
   "display_name": "Python 3.8.13 ('eks')",
   "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": "3.8.13"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}