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

jupyter notebook missed some imports

Browse Source
This commit is contained in:
Tim
2025-08-13 13:56:30 +02:00
parent 9c3dd33c0b
commit 4b35d4ca21
1 changed files with 224 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

296
notebook.ipynb
View File

@@ -16,12 +16,43 @@
},
{
"cell_type": "code",
"execution_count": null,
"id": "3116b75f",
"metadata": {
"jupyter": {
"is_executing": true
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" appid name release_date required_age price dlc_count \\\n",
"0 730 Counter-Strike 2 2012-08-21 0 0.0 1 \n",
"\n",
" detailed_description \\\n",
"0 For over two decades, Counter-Strike has offer... \n",
"\n",
" about_the_game \\\n",
"0 For over two decades, Counter-Strike has offer... \n",
"\n",
" short_description reviews ... \\\n",
"0 For over two decades, Counter-Strike has offer... NaN ... \n",
"\n",
" average_playtime_2weeks median_playtime_forever median_playtime_2weeks \\\n",
"0 879 5174 350 \n",
"\n",
" discount peak_ccu tags \\\n",
"0 0 1212356 {'FPS': 90857, 'Shooter': 65397, 'Multiplayer'... \n",
"\n",
" pct_pos_total num_reviews_total pct_pos_recent num_reviews_recent \n",
"0 86 8632939 82 96473 \n",
"\n",
"[1 rows x 47 columns]\n"
]
}
],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
@@ -30,10 +61,8 @@
"set_config(transform_output=\"pandas\")\n",
"\n",
"dataset = pd.read_csv(\"./games_march2025_cleaned_2k.csv\",sep=\",\")\n",
"print(dataset.head())"
],
"outputs": [],
"execution_count": null
"print(dataset.head(1))"
]
},
{
"cell_type": "markdown",
@@ -60,35 +89,58 @@
]
},
{
"metadata": {},
"cell_type": "code",
"execution_count": null,
"id": "d159117377f3633c",
"metadata": {},
"outputs": [],
"source": [
"#dataset.drop(['appid', 'name', 'release_date', 'reviews', 'header_image', 'website', 'support_url', 'support_email', 'metacritic_url', 'notes', 'developers', 'publishers', 'screenshots', 'movies', 'estimated_owners'], axis=1, inplace=True)\n",
"#print(dataset.head())"
],
"id": "d159117377f3633c",
"outputs": [],
"execution_count": null
]
},
{
"metadata": {},
"cell_type": "markdown",
"id": "e1b28ddd69f1e9a6",
"metadata": {},
"source": [
"## Hold onto necessary information\n",
"Our model should turn a textual description of a game into its genre. For that we need all the textual information a game has, as well as the genres of the game.\n",
"We use a ColumnTransformer to drop all unnecessary lines, merge all descriptions of a game into one big description and hold onto the genres\n",
"\n",
"It is important to use ``verbose_feature_names_out=False`` so the feature names don't get changed"
],
"id": "e1b28ddd69f1e9a6"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "986fbb31a7ae0d8b",
"metadata": {
"jupyter": {
"is_executing": true
}
},
"cell_type": "code",
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" desc \\\n",
"0 For over two decades, Counter-Strike has offer... \n",
"1 LAND, LOOT, SURVIVE! Play PUBG: BATTLEGROUNDS ... \n",
"2 The most-played game on Steam. Every day, mill... \n",
"3 When a young street hustler, a retired bank ro... \n",
"4 Edition Comparison Ultimate Edition The Tom Cl... \n",
"\n",
" genres \n",
"0 ['Action', 'Free To Play'] \n",
"1 ['Action', 'Adventure', 'Massively Multiplayer... \n",
"2 ['Action', 'Strategy', 'Free To Play'] \n",
"3 ['Action', 'Adventure'] \n",
"4 ['Action'] \n"
]
}
],
"source": [
"from sklearn.compose import ColumnTransformer\n",
"from sklearn.preprocessing import FunctionTransformer\n",
@@ -104,24 +156,24 @@
")\n",
"dataset = column_transformer.fit_transform(dataset)\n",
"print(dataset.head())"
],
"id": "986fbb31a7ae0d8b",
"outputs": [],
"execution_count": null
]
},
{
"metadata": {},
"cell_type": "markdown",
"id": "f9b89c0645811564",
"metadata": {},
"source": [
"### Adding missing Information\n",
"Some Games might not have any descriptions. For these we Input an Empty String\n",
"**TODO: check if dropna and fillna numeric_only is needed, as we dont have any numbers**"
],
"id": "f9b89c0645811564"
]
},
{
"metadata": {},
"cell_type": "code",
"execution_count": null,
"id": "44239f6b7fd23cde",
"metadata": {},
"outputs": [],
"source": [
"# missing numeric values => mean\n",
"dataset.fillna(dataset.mean(numeric_only=True), inplace=True)\n",
@@ -129,49 +181,82 @@
"dataset.fillna('', inplace=True)\n",
"# drop all lines with missing values\n",
"dataset.dropna(inplace=True)"
],
"id": "44239f6b7fd23cde",
"outputs": [],
"execution_count": null
]
},
{
"metadata": {},
"cell_type": "markdown",
"id": "ca5b59b9fa8160a0",
"metadata": {},
"source": [
"## Transform Genres\n",
"The genre information currently is a string holding a python array of genres. While this is machine-readable, we need One-Hot-Encoding for our model to work.\n",
"\n",
"#### Serializing the String-Array\n",
"The \"ast\" library can interpret python strings as python code, and as such will be used for serializing the genres."
],
"id": "ca5b59b9fa8160a0"
]
},
{
"metadata": {},
"cell_type": "code",
"execution_count": null,
"id": "ebc5a24e9bc87fdd",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0 [Action, Free To Play]\n",
"1 [Action, Adventure, Massively Multiplayer, Fre...\n",
"2 [Action, Strategy, Free To Play]\n",
"3 [Action, Adventure]\n",
"4 [Action]\n",
"Name: genres, dtype: object\n"
]
}
],
"source": [
"import ast\n",
"\n",
"dataset['genres'] = dataset['genres'].map(lambda s: ast.literal_eval(s))\n",
"print(dataset['genres'])"
],
"id": "ebc5a24e9bc87fdd",
"outputs": [],
"execution_count": null
"print(dataset['genres'].head())"
]
},
{
"metadata": {},
"cell_type": "markdown",
"id": "f90756f9ad9211f4",
"metadata": {},
"source": [
"#### One-Hot-Encoding an Python-Array\n",
"The sklearn ``OneHotEncoder()`` is only able to work with an 1D Array of different classes, such as ``['Politics', 'Sport', 'Culture']``. Every datapoint can only have one concurrent classification.\n",
"Steam allows an app/bundle to have multiple genres. As such, our dataset has an 2D Array of different classes, which sklearn's ``MultiLabelBinarizer()`` does support."
],
"id": "f90756f9ad9211f4"
]
},
{
"metadata": {},
"cell_type": "code",
"execution_count": null,
"id": "d2c3527a5fc876bf",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Action Adventure Casual Early Access Free To Play Gore Indie \\\n",
"0 1 0 0 0 1 0 0 \n",
"1 1 1 0 0 1 0 0 \n",
"2 1 0 0 0 1 0 0 \n",
"3 1 1 0 0 0 0 0 \n",
"4 1 0 0 0 0 0 0 \n",
"\n",
" Massively Multiplayer RPG Racing Simulation Sports Strategy Violent \n",
"0 0 0 0 0 0 0 0 \n",
"1 1 0 0 0 0 0 0 \n",
"2 0 0 0 0 0 1 0 \n",
"3 0 0 0 0 0 0 0 \n",
"4 0 0 0 0 0 0 0 \n"
]
}
],
"source": [
"from sklearn.preprocessing import MultiLabelBinarizer\n",
"\n",
@@ -179,16 +264,15 @@
"genres_encoded = mlb_genres.fit_transform(dataset.pop('genres'))\n",
"genres_df = pd.DataFrame(genres_encoded, columns=mlb_genres.classes_)\n",
"print(genres_df.head())"
],
"id": "d2c3527a5fc876bf",
"outputs": [],
"execution_count": null
]
},
{
"metadata": {},
"cell_type": "markdown",
"source": "With this, our target matrix is completed.",
"id": "671c01f9f4ae66d9"
"id": "671c01f9f4ae66d9",
"metadata": {},
"source": [
"With this, our target matrix is completed."
]
},
{
"cell_type": "markdown",
@@ -201,8 +285,32 @@
},
{
"cell_type": "code",
"execution_count": null,
"id": "4e8b407c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" 00 000 000km 000th 00am 00f 00i 00p 00v 01 ... 이터널 이터널리턴 \\\n",
"0 0.0 0.0 0.0 0.00000 0.0 0.0 0.0 0.0 0.0 0.0 ... 0.0 0.0 \n",
"1 0.0 0.0 0.0 0.00000 0.0 0.0 0.0 0.0 0.0 0.0 ... 0.0 0.0 \n",
"2 0.0 0.0 0.0 0.14649 0.0 0.0 0.0 0.0 0.0 0.0 ... 0.0 0.0 \n",
"3 0.0 0.0 0.0 0.00000 0.0 0.0 0.0 0.0 0.0 0.0 ... 0.0 0.0 \n",
"4 0.0 0.0 0.0 0.00000 0.0 0.0 0.0 0.0 0.0 0.0 ... 0.0 0.0 \n",
"\n",
" 이현준 정대찬 중입니다 철권 토탈워 페르소나 한국어 한글을 \n",
"0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 \n",
"1 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 \n",
"2 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 \n",
"3 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 \n",
"4 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 \n",
"\n",
"[5 rows x 29351 columns]\n"
]
}
],
"source": [
"from sklearn.feature_extraction.text import TfidfVectorizer\n",
"\n",
@@ -210,52 +318,60 @@
"tfidf_matrix = vectorizer.fit_transform(dataset['desc']) # matrix, not pandas df\n",
"tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())\n",
"print(tfidf_df.head())"
],
"outputs": [],
"execution_count": null
]
},
{
"cell_type": "markdown",
"id": "ad84e777",
"metadata": {},
"source": "With this our feature matrix is completed"
"source": [
"With this our feature matrix is completed"
]
},
{
"metadata": {},
"cell_type": "code",
"outputs": [],
"execution_count": null,
"id": "86d9da42f4df8e49",
"metadata": {},
"outputs": [],
"source": [
"X = tfidf_df\n",
"y = genres_df"
],
"id": "86d9da42f4df8e49"
]
},
{
"metadata": {},
"cell_type": "markdown",
"id": "aeb782668f311cd8",
"metadata": {},
"source": [
"## The Model\n",
"\n",
"#### Removing unpredicatble Datapoints\n",
"Some Datapoints don't have a genre assigned (all feature values in y are 0). The model we use can't handle such cases, thus they have to be removed.\n",
"We filter after all values that we can use with a mask, and apply that mask to our matrices."
],
"id": "aeb782668f311cd8"
]
},
{
"metadata": {},
"cell_type": "code",
"outputs": [],
"execution_count": null,
"id": "4919bf1b37d171a7",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"13\n"
]
}
],
"source": [
"mask = y.sum(axis=1).map(lambda x: x > 0)\n",
"print((mask == False).sum()) # count of unpredictable datapoints\n",
"\n",
"X_clean = X[mask]\n",
"y_clean = y[mask]"
],
"id": "4919bf1b37d171a7"
]
},
{
"cell_type": "markdown",
@@ -269,19 +385,19 @@
},
{
"cell_type": "code",
"execution_count": null,
"id": "cfbf3787",
"metadata": {
"jupyter": {
"is_executing": true
}
},
"outputs": [],
"source": [
"from sklearn.model_selection import train_test_split\n",
"\n",
"X_train, X_test, y_train, y_test = train_test_split(X_clean, y_clean, random_state=0)"
],
"outputs": [],
"execution_count": null
]
},
{
"cell_type": "markdown",
@@ -295,19 +411,22 @@
]
},
{
"metadata": {},
"cell_type": "code",
"outputs": [],
"execution_count": null,
"id": "8c1d72c4532bd509",
"metadata": {},
"outputs": [],
"source": [
"# n_jobs=1 since there seems to be some multithreading join issue in sklearn (or my pc is too bad)\n",
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.multioutput import MultiOutputClassifier\n",
"\n",
"# n_jobs=1 since there seems to be some multithreading join issue in sklearn (or my pc is to bad)\n",
"multi_target_clf = MultiOutputClassifier(LogisticRegression(max_iter=1337, random_state=0), n_jobs=1)\n",
"\n",
"multi_target_clf.fit(X_train, y_train)\n",
"\n",
"y_pred = multi_target_clf.predict(X_test)"
],
"id": "8c1d72c4532bd509"
]
},
{
"cell_type": "markdown",
@@ -319,12 +438,45 @@
]
},
{
"metadata": {},
"cell_type": "code",
"outputs": [],
"execution_count": null,
"source": "print(classification_report(y_test, y_pred, zero_division=0.0))",
"id": "e2ebea6945193e07"
"id": "e2ebea6945193e07",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" precision recall f1-score support\n",
"\n",
" 0 0.78 0.91 0.84 300\n",
" 1 0.78 0.62 0.69 216\n",
" 2 1.00 0.03 0.07 86\n",
" 3 0.00 0.00 0.00 46\n",
" 4 1.00 0.04 0.07 83\n",
" 5 0.00 0.00 0.00 0\n",
" 6 0.79 0.81 0.80 245\n",
" 7 0.00 0.00 0.00 42\n",
" 8 0.90 0.34 0.49 127\n",
" 9 0.00 0.00 0.00 12\n",
" 10 0.89 0.25 0.39 127\n",
" 11 0.00 0.00 0.00 14\n",
" 12 0.88 0.14 0.24 106\n",
" 13 0.00 0.00 0.00 0\n",
"\n",
" micro avg 0.79 0.50 0.61 1404\n",
" macro avg 0.50 0.22 0.26 1404\n",
"weighted avg 0.77 0.50 0.53 1404\n",
" samples avg 0.77 0.56 0.60 1404\n",
"\n"
]
}
],
"source": [
"from sklearn.metrics import classification_report\n",
"\n",
"print(classification_report(y_test, y_pred, zero_division=0.0))"
]
},
{
"cell_type": "markdown",