{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import random\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "num_records = 100\n",
    "first_names = [\"Alan\", \"Miguel\", \"Lakshmi\", \"Chen\", \"Oluwaseun\", \"Dmitri\", \"Nadia\", \"John\", \"Jane\", \"Alice\", \"Terrance\", \"Elena\"]\n",
    "last_names = [\"Patel\", \"Rodriguez\", \"Kim\", \"Okafor\", \"Nasser\", \"Ivanov\", \"Smith\", \"Brown\", \"Johnson\", \"Lee\", \"Malcolm\", \"Chatterjee\"]\n",
    "# new last names\n",
    "judge_last_names = [\"James\", \"Skaarsgard\", \"Oleg\", \"Morgan\", \"Brown\", \"Connor\"]\n",
    "case_types = [\"Criminal\", \"Civil\", \"Family\", \"Criminal\", \"Civil\", \"Family\"]\n",
    "cities = ['new York', 'LOS angeles', 'chicago', 'houston', 'BOSTON']\n",
    "weather_types = ['sunny', 'cloudy', 'rainy', 'snowy']\n",
    "get_random_date = lambda: f'2023-0{random.randint(1,9)}-{random.randint(10,28)}'\n",
    "get_random_case_number = lambda: f'{random.choice([\"CR\", \"CASE\"])}-{random.randint(1000,9999)}'\n",
    "get_random_fee = lambda: random.choice([100, 150, 200, 250])\n",
    "\n",
    "get_random_int = lambda: random.randint(1000, 9999)\n",
    "\n",
    "# Define column names with standard casing\n",
    "case_date_col = 'case_date'\n",
    "lastname_col = 'lastname'\n",
    "firstname_col = 'firstname'\n",
    "case_type_col = 'case_type'\n",
    "case_id_col = 'case_id'\n",
    "court_fee_col = 'court_fee'\n",
    "jurisdiction_col = 'jurisdiction'\n",
    "case_id_prefix = 'CR'\n",
    "\n",
    "# Use inconsistent casing for values\n",
    "legal_entries_a_data = {\n",
    "    case_date_col: [get_random_date() for _ in range(num_records)],\n",
    "    lastname_col: [random.choice(last_names) for _ in range(num_records)],\n",
    "    firstname_col: [random.choice(first_names) for _ in range(num_records)],\n",
    "    case_type_col: [random.choice(case_types) for _ in range(num_records)],\n",
    "    case_id_col: [f'{case_id_prefix}-{get_random_int()}' for _ in range(num_records)],\n",
    "    court_fee_col: [get_random_fee() for _ in range(num_records)],\n",
    "    jurisdiction_col: [random.choice(cities) for _ in range(num_records)],\n",
    "    'judge_last_name': [random.choice(judge_last_names) for _ in range(num_records)]\n",
    "}\n",
    "\n",
    "legal_entries_a = pd.DataFrame(legal_entries_a_data)\n",
    "\n",
    "# Apply the transform_row function for legal_entries_A to create legal_entries_B\n",
    "def transform_row(row):\n",
    "    return pd.Series({\n",
    "        'Date_of_Case' : row[case_date_col].replace(\"-\", \"/\"),\n",
    "        'Fee' : float(row[court_fee_col]),\n",
    "        'FullName' : f\"{row[firstname_col]} {row[lastname_col]}\".title(),\n",
    "        'CaseNumber' : f'{row[case_id_col].replace(case_id_prefix, \"case-\")}',\n",
    "        'CaseKind' : row[case_type_col].capitalize(),\n",
    "        'Date_of_Case' : row[case_date_col].replace(\"-\", \"/\"),\n",
    "        'Location' : row[jurisdiction_col].replace(\" \", \"\")[:random.randint(4,5)].upper(),\n",
    "        'Weather': random.choice(weather_types)\n",
    "    })\n",
    "\n",
    "def transform_to_template(row):\n",
    "    return pd.Series({\n",
    "        'CaseDate': row[case_date_col],\n",
    "        'FullName': f\"{row[firstname_col]} {row[lastname_col]}\",\n",
    "        'CaseType': \"Family\" if \"Fam\" in row[case_type_col] else \"Civil\" if 'Civ' in row[case_type_col] else row[case_type_col].capitalize(),\n",
    "        'CaseID': f'{row[case_id_col].replace(case_id_prefix, \"CASE\")}',\n",
    "        'Fee': row[court_fee_col],\n",
    "        'Jurisdiction': row[jurisdiction_col].title()\n",
    "    })\n",
    "\n",
    "legal_entries_b = legal_entries_a.apply(transform_row, axis=1)\n",
    "legal_template = legal_entries_a.apply(transform_to_template, axis=1)\n",
    "\n",
    "data_dir_path = os.path.join(os.getcwd(), \"data\")\n",
    "legal_entries_a.to_csv(os.path.join(data_dir_path, \"legal_entries_a.csv\"), index=False)\n",
    "legal_entries_b.to_csv(os.path.join(data_dir_path, \"legal_entries_b.csv\"), index=False)\n",
    "legal_template.to_csv(os.path.join(data_dir_path, \"legal_template.csv\"), index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "venv",
   "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": "3.9.6"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}