{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import os"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load data from file into a pandas df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "File 'hr.csv' loaded successfully.                                                                                      \n",
      "Found 311 rows, 36 columns\n"
     ]
    }
   ],
   "source": [
    "DATADIR=\"data/\"\n",
    "FILENAME=None\n",
    "\n",
    "while FILENAME is None:\n",
    "    \n",
    "    file_candidate = input(\"Enter file name:\")\n",
    "    if file_candidate == \"\": break\n",
    "    \n",
    "    try:\n",
    "        print(f\"Assesing file '{file_candidate}'...\".ljust(120), end=\"\\r\")\n",
    "        file_path = DATADIR + file_candidate\n",
    "        extension = file_candidate.split(\".\")[-1] \n",
    "        match extension:\n",
    "            case \"csv\":\n",
    "                df = pd.read_csv(file_path)\n",
    "            case \"json\":\n",
    "                df = pd.read_json(file_path)\n",
    "            case \"xlsx\":\n",
    "                df = pd.read_excel(file_path)\n",
    "            case _:\n",
    "                print(f\"Error: Invalid extension '{extension}'\")\n",
    "                continue\n",
    "        print(f\"File '{file_candidate}' loaded successfully.\")\n",
    "        rows, columns = df.shape\n",
    "        print(f\"Found {rows} rows, {columns} columns\")\n",
    "        FILENAME = file_candidate\n",
    "    except FileNotFoundError:\n",
    "        print(f\"Error: '{file_candidate}' doesn't exist in {os.getcwd()}/{DATADIR}\")\n",
    "    except Exception as error:\n",
    "        print(f\"Error: Unable to read file '{file_candidate}' ({str(type(error))}: {error})\".ljust(120))"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Clean data to remove duplicates and rows with missing values."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "DROP_MISSING = True\n",
    "REMOVE_DUPLICATES = True\n",
    "\n",
    "df = df.dropna(how=\"any\" if DROP_MISSING else \"all\")\n",
    "if REMOVE_DUPLICATES: df = df.drop_duplicates()"
   ]
  }
 ],
 "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": "3.10.6"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}