Uni/machine-learning
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Minor Changes

Browse Source
This commit is contained in:
FlorianSpeicher
2025-08-05 22:47:07 +02:00
parent 8172759f93
commit fd2e905094
1 changed files with 116 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

134
notebook.ipynb
View File

@@ -17,28 +17,126 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 4,
"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"
"name": "stdout",
"output_type": "stream",
"text": [
" 0 1 \\\n",
"0 url types \n",
"1 https://store.steampowered.com/app/379720/DOOM/ app \n",
"2 https://store.steampowered.com/app/578080/PLAY... app \n",
"3 https://store.steampowered.com/app/637090/BATT... app \n",
"4 https://store.steampowered.com/app/221100/DayZ/ app \n",
"\n",
" 2 \\\n",
"0 name \n",
"1 DOOM \n",
"2 PLAYERUNKNOWN'S BATTLEGROUNDS \n",
"3 BATTLETECH \n",
"4 DayZ \n",
"\n",
" 3 \\\n",
"0 desc_snippet \n",
"1 Now includes all three premium DLC packs (Unto... \n",
"2 PLAYERUNKNOWN'S BATTLEGROUNDS is a battle roya... \n",
"3 Take command of your own mercenary outfit of '... \n",
"4 The post-soviet country of Chernarus is struck... \n",
"\n",
" 4 \\\n",
"0 recent_reviews \n",
"1 Very Positive,(554),- 89% of the 554 user revi... \n",
"2 Mixed,(6,214),- 49% of the 6,214 user reviews ... \n",
"3 Mixed,(166),- 54% of the 166 user reviews in t... \n",
"4 Mixed,(932),- 57% of the 932 user reviews in t... \n",
"\n",
" 5 6 \\\n",
"0 all_reviews release_date \n",
"1 Very Positive,(42,550),- 92% of the 42,550 use... May 12, 2016 \n",
"2 Mixed,(836,608),- 49% of the 836,608 user revi... Dec 21, 2017 \n",
"3 Mostly Positive,(7,030),- 71% of the 7,030 use... Apr 24, 2018 \n",
"4 Mixed,(167,115),- 61% of the 167,115 user revi... Dec 13, 2018 \n",
"\n",
" 7 8 \\\n",
"0 developer publisher \n",
"1 id Software Bethesda Softworks,Bethesda Softworks \n",
"2 PUBG Corporation PUBG Corporation,PUBG Corporation \n",
"3 Harebrained Schemes Paradox Interactive,Paradox Interactive \n",
"4 Bohemia Interactive Bohemia Interactive,Bohemia Interactive \n",
"\n",
" 9 \\\n",
"0 popular_tags \n",
"1 FPS,Gore,Action,Demons,Shooter,First-Person,Gr... \n",
"2 Survival,Shooter,Multiplayer,Battle Royale,PvP... \n",
"3 Mechs,Strategy,Turn-Based,Turn-Based Tactics,S... \n",
"4 Survival,Zombies,Open World,Multiplayer,PvP,Ma... \n",
"\n",
" 10 \\\n",
"0 game_details \n",
"1 Single-player,Multi-player,Co-op,Steam Achieve... \n",
"2 Multi-player,Online Multi-Player,Stats \n",
"3 Single-player,Multi-player,Online Multi-Player... \n",
"4 Multi-player,Online Multi-Player,Steam Worksho... \n",
"\n",
" 11 12 \\\n",
"0 languages achievements \n",
"1 English,French,Italian,German,Spanish - Spain,... 54 \n",
"2 English,Korean,Simplified Chinese,French,Germa... 37 \n",
"3 English,French,German,Russian 128 \n",
"4 English,French,Italian,German,Spanish - Spain,... NaN \n",
"\n",
" 13 \\\n",
"0 genre \n",
"1 Action \n",
"2 Action,Adventure,Massively Multiplayer \n",
"3 Action,Adventure,Strategy \n",
"4 Action,Adventure,Massively Multiplayer \n",
"\n",
" 14 \\\n",
"0 game_description \n",
"1 About This Game Developed by id software, the... \n",
"2 About This Game PLAYERUNKNOWN'S BATTLEGROUND... \n",
"3 About This Game From original BATTLETECH/Mec... \n",
"4 About This Game The post-soviet country of Ch... \n",
"\n",
" 15 \\\n",
"0 mature_content \n",
"1 NaN \n",
"2 Mature Content Description The developers de... \n",
"3 NaN \n",
"4 NaN \n",
"\n",
" 16 \\\n",
"0 minimum_requirements \n",
"1 Minimum:,OS:,Windows 7/8.1/10 (64-bit versions... \n",
"2 Minimum:,Requires a 64-bit processor and opera... \n",
"3 Minimum:,Requires a 64-bit processor and opera... \n",
"4 Minimum:,OS:,Windows 7/8.1 64-bit,Processor:,I... \n",
"\n",
" 17 18 \\\n",
"0 recommended_requirements original_price \n",
"1 Recommended:,OS:,Windows 7/8.1/10 (64-bit vers... $19.99 \n",
"2 Recommended:,Requires a 64-bit processor and o... $29.99 \n",
"3 Recommended:,Requires a 64-bit processor and o... $39.99 \n",
"4 Recommended:,OS:,Windows 10 64-bit,Processor:,... $44.99 \n",
"\n",
" 19 \n",
"0 discount_price \n",
"1 $14.99 \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\FlorianSpeicher\\AppData\\Local\\Temp\\ipykernel_38708\\931669033.py:4: DtypeWarning: Columns (12) have mixed types. Specify dtype option on import or set low_memory=False.\n",
" cars = pd.read_csv(\"./steam_games.csv\",sep=\",\",header=None)\n"
]
}
],