{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a3a7634f",
   "metadata": {},
   "source": [
    "# Machine Learning project in SoSe 2025 at HTW Saar\n",
    "### Contributors\n",
    "    - Maximilian Kany\n",
    "    - Florian Speicher\n",
    "    - Tim Wall\n",
    "\n",
    "#### Dataset\n",
    "For our project we use a steam DataSet from kaggle. You can find it under the following url: [Kaggle.com](https://www.kaggle.com/datasets/trolukovich/steam-games-complete-dataset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3116b75f",
   "metadata": {},
   "outputs": [
    {
     "ename": "ParserError",
     "evalue": "Error tokenizing data. C error: Expected 1 fields in line 2, saw 473\n",
     "output_type": "error",
     "traceback": [
      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
      "\u001b[31mParserError\u001b[39m                               Traceback (most recent call last)",
      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[3]\u001b[39m\u001b[32m, line 4\u001b[39m\n\u001b[32m      2\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mpandas\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mas\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mpd\u001b[39;00m\n\u001b[32m      3\u001b[39m \u001b[38;5;66;03m# load data\u001b[39;00m\n\u001b[32m----> \u001b[39m\u001b[32m4\u001b[39m cars = \u001b[43mpd\u001b[49m\u001b[43m.\u001b[49m\u001b[43mread_csv\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43m./steam_games.csv\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43msep\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43m\\\u001b[39;49m\u001b[33;43ms+\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43mheader\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[32m      5\u001b[39m \u001b[38;5;28mprint\u001b[39m(cars.head())\n",
      "\u001b[36mFile \u001b[39m\u001b[32mc:\\Users\\FlorianSpeicher\\anaconda3\\Lib\\site-packages\\pandas\\io\\parsers\\readers.py:1026\u001b[39m, in \u001b[36mread_csv\u001b[39m\u001b[34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)\u001b[39m\n\u001b[32m   1013\u001b[39m kwds_defaults = _refine_defaults_read(\n\u001b[32m   1014\u001b[39m     dialect,\n\u001b[32m   1015\u001b[39m     delimiter,\n\u001b[32m   (...)\u001b[39m\u001b[32m   1022\u001b[39m     dtype_backend=dtype_backend,\n\u001b[32m   1023\u001b[39m )\n\u001b[32m   1024\u001b[39m kwds.update(kwds_defaults)\n\u001b[32m-> \u001b[39m\u001b[32m1026\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_read\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n",
      "\u001b[36mFile \u001b[39m\u001b[32mc:\\Users\\FlorianSpeicher\\anaconda3\\Lib\\site-packages\\pandas\\io\\parsers\\readers.py:626\u001b[39m, in \u001b[36m_read\u001b[39m\u001b[34m(filepath_or_buffer, kwds)\u001b[39m\n\u001b[32m    623\u001b[39m     \u001b[38;5;28;01mreturn\u001b[39;00m parser\n\u001b[32m    625\u001b[39m \u001b[38;5;28;01mwith\u001b[39;00m parser:\n\u001b[32m--> \u001b[39m\u001b[32m626\u001b[39m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mparser\u001b[49m\u001b[43m.\u001b[49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43mnrows\u001b[49m\u001b[43m)\u001b[49m\n",
      "\u001b[36mFile \u001b[39m\u001b[32mc:\\Users\\FlorianSpeicher\\anaconda3\\Lib\\site-packages\\pandas\\io\\parsers\\readers.py:1923\u001b[39m, in \u001b[36mTextFileReader.read\u001b[39m\u001b[34m(self, nrows)\u001b[39m\n\u001b[32m   1916\u001b[39m nrows = validate_integer(\u001b[33m\"\u001b[39m\u001b[33mnrows\u001b[39m\u001b[33m\"\u001b[39m, nrows)\n\u001b[32m   1917\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m   1918\u001b[39m     \u001b[38;5;66;03m# error: \"ParserBase\" has no attribute \"read\"\u001b[39;00m\n\u001b[32m   1919\u001b[39m     (\n\u001b[32m   1920\u001b[39m         index,\n\u001b[32m   1921\u001b[39m         columns,\n\u001b[32m   1922\u001b[39m         col_dict,\n\u001b[32m-> \u001b[39m\u001b[32m1923\u001b[39m     ) = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_engine\u001b[49m\u001b[43m.\u001b[49m\u001b[43mread\u001b[49m\u001b[43m(\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# type: ignore[attr-defined]\u001b[39;49;00m\n\u001b[32m   1924\u001b[39m \u001b[43m        \u001b[49m\u001b[43mnrows\u001b[49m\n\u001b[32m   1925\u001b[39m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m   1926\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m:\n\u001b[32m   1927\u001b[39m     \u001b[38;5;28mself\u001b[39m.close()\n",
      "\u001b[36mFile \u001b[39m\u001b[32mc:\\Users\\FlorianSpeicher\\anaconda3\\Lib\\site-packages\\pandas\\io\\parsers\\c_parser_wrapper.py:234\u001b[39m, in \u001b[36mCParserWrapper.read\u001b[39m\u001b[34m(self, nrows)\u001b[39m\n\u001b[32m    232\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m    233\u001b[39m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m.low_memory:\n\u001b[32m--> \u001b[39m\u001b[32m234\u001b[39m         chunks = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_reader\u001b[49m\u001b[43m.\u001b[49m\u001b[43mread_low_memory\u001b[49m\u001b[43m(\u001b[49m\u001b[43mnrows\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    235\u001b[39m         \u001b[38;5;66;03m# destructive to chunks\u001b[39;00m\n\u001b[32m    236\u001b[39m         data = _concatenate_chunks(chunks)\n",
      "\u001b[36mFile \u001b[39m\u001b[32mparsers.pyx:838\u001b[39m, in \u001b[36mpandas._libs.parsers.TextReader.read_low_memory\u001b[39m\u001b[34m()\u001b[39m\n",
      "\u001b[36mFile \u001b[39m\u001b[32mparsers.pyx:905\u001b[39m, in \u001b[36mpandas._libs.parsers.TextReader._read_rows\u001b[39m\u001b[34m()\u001b[39m\n",
      "\u001b[36mFile \u001b[39m\u001b[32mparsers.pyx:874\u001b[39m, in \u001b[36mpandas._libs.parsers.TextReader._tokenize_rows\u001b[39m\u001b[34m()\u001b[39m\n",
      "\u001b[36mFile \u001b[39m\u001b[32mparsers.pyx:891\u001b[39m, in \u001b[36mpandas._libs.parsers.TextReader._check_tokenize_status\u001b[39m\u001b[34m()\u001b[39m\n",
      "\u001b[36mFile \u001b[39m\u001b[32mparsers.pyx:2061\u001b[39m, in \u001b[36mpandas._libs.parsers.raise_parser_error\u001b[39m\u001b[34m()\u001b[39m\n",
      "\u001b[31mParserError\u001b[39m: Error tokenizing data. C error: Expected 1 fields in line 2, saw 473\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "# load data\n",
    "cars = pd.read_csv(\"./steam_games.csv\",sep=\",\",header=None)\n",
    "print(cars.head())\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.13.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}