{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":81933,"databundleVersionId":9643020,"sourceType":"competition"}],"dockerImageVersionId":30804,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2024-12-05T08:38:10.025827Z","iopub.execute_input":"2024-12-05T08:38:10.026322Z","iopub.status.idle":"2024-12-05T08:38:15.038885Z","shell.execute_reply.started":"2024-12-05T08:38:10.026283Z","shell.execute_reply":"2024-12-05T08:38:15.037426Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nfrom sklearn.decomposition import PCA\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.model_selection import train_test_split, RandomizedSearchCV\nfrom sklearn.neural_network import MLPClassifier\nfrom sklearn.metrics import accuracy_score, mean_squared_error, classification_report, confusion_matrix, ConfusionMatrixDisplay\nfrom imblearn.over_sampling import SMOTE\nimport matplotlib.pyplot as plt\n\n# Fungsi untuk meng-encode kolom string\ndef encode_string_columns(df):\n    for column in df.columns:\n        if df[column].dtype == object:\n            codes, _ = pd.factorize(df[column])\n            df[column] = codes\n    return df\n\n# Fungsi untuk visualisasi PCA cumulative variance\ndef perform_pca_with_visualization(X, X_test, variance_threshold=0.95):\n    scaler = StandardScaler()\n    X_scaled = scaler.fit_transform(X)\n    X_test_scaled = scaler.transform(X_test)\n\n    pca = PCA()\n    pca.fit(X_scaled)\n    cumulative_variance = pca.explained_variance_ratio_.cumsum()\n\n    # Plot cumulative variance\n    plt.figure(figsize=(8, 5))\n    plt.plot(cumulative_variance, marker='o', linestyle='--')\n    plt.title('Cumulative Explained Variance')\n    plt.xlabel('Number of Components')\n    plt.ylabel('Explained Variance')\n    plt.grid(True)\n    plt.show()\n\n    # Tentukan jumlah komponen optimal\n    n_components = (cumulative_variance >= variance_threshold).argmax() + 1\n\n    # Transformasi dengan PCA\n    pca = PCA(n_components=n_components)\n    X_pca = pca.fit_transform(X_scaled)\n    X_test_pca = pca.transform(X_test_scaled)\n\n    return X_pca, X_test_pca, n_components, scaler\n\n# Fungsi evaluasi model\ndef evaluate_model(y_true, y_pred):\n    cm = confusion_matrix(y_true, y_pred)\n    disp = ConfusionMatrixDisplay(confusion_matrix=cm)\n    disp.plot(cmap='viridis', xticks_rotation='vertical')\n    plt.show()\n    print(\"Classification Report:\\n\", classification_report(y_true, y_pred))\n\n# Load data\ntrain_path = \"/kaggle/input/child-mind-institute-problematic-internet-use/train.csv\"\ntest_path = \"/kaggle/input/child-mind-institute-problematic-internet-use/test.csv\"\n\ndf = pd.read_csv(train_path)\ndf_test = pd.read_csv(test_path)\n\n# Simpan ID untuk pengujian\nid_test = df_test['id']\n\n# Drop kolom 'id' dan target 'sii' dari data pelatihan\ndf = df.drop(columns=['id', 'sii'])\ndf_test = df_test.drop(columns=['id'])\n\n# Encode kolom string\ndf = encode_string_columns(df)\ndf_test = encode_string_columns(df_test)\n\n# Isi nilai kosong dengan median\ndf.fillna(df.median(), inplace=True)\ndf_test.fillna(df_test.median(), inplace=True)\n\n# Pastikan kolom pada data pelatihan dan pengujian sama\ncommon_columns = df.columns.intersection(df_test.columns)\nX = df[common_columns]\ndf_test = df_test[common_columns]\n\n# Load target (y)\ny = pd.read_csv(train_path)['sii']\ny.fillna(y.median(), inplace=True)\n\n# Penanganan data tidak seimbang menggunakan SMOTE\nsmote = SMOTE(random_state=42)\nX, y = smote.fit_resample(X, y)\n\n# Lakukan PCA dengan visualisasi\nX_pca, X_test_pca, n_components, scaler = perform_pca_with_visualization(X, df_test)\nprint(f\"Optimal number of PCA components: {n_components}\")\n\n# Split data\nX_train, X_val, y_train, y_val = train_test_split(X_pca, y, test_size=0.2, random_state=42)\n\n# Model Neural Network\nmodel = MLPClassifier(random_state=42, max_iter=500, early_stopping=True, validation_fraction=0.2)\n\n# Hyperparameter grid\nparam_distributions = {\n    'hidden_layer_sizes': [(128, 64), (256, 128, 64), (512, 256, 128)],\n    'activation': ['relu', 'tanh'],\n    'alpha': [0.0001, 0.001, 0.005],\n    'solver': ['adam'],\n    'learning_rate': ['constant', 'adaptive'],\n    'learning_rate_init': [0.001, 0.0005]\n}\n\n# Randomized Search\nrandom_search = RandomizedSearchCV(estimator=model, param_distributions=param_distributions, \n                                   scoring='accuracy', n_iter=10, cv=5, n_jobs=-1, random_state=42)\nrandom_search.fit(X_train, y_train)\n\n# Best model\nbest_model = random_search.best_estimator_\nprint(\"Best parameters:\", random_search.best_params_)\n\n# Evaluasi pada data validasi\ny_val_pred = best_model.predict(X_val)\naccuracy = accuracy_score(y_val, y_val_pred)\nmse = mean_squared_error(y_val, y_val_pred)\n\nprint(f\"Validation Accuracy: {accuracy:.2f}\")\nprint(f\"Mean Squared Error: {mse:.2f}\")\n\n# Evaluasi tambahan dengan confusion matrix\nevaluate_model(y_val, y_val_pred)\n\n# Prediksi pada data uji\ny_test_pred = best_model.predict(X_test_pca)\n\n# Prepare submission\nsubmission = pd.DataFrame({\n    \"id\": id_test,\n    \"sii\": y_test_pred.astype(int)\n})\nprint(submission.head())\n\n# Save ke CSV\nsubmission.to_csv(\"/kaggle/working/submission.csv\", index=False)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-07T06:34:55.224613Z","iopub.execute_input":"2024-12-07T06:34:55.225076Z","iopub.status.idle":"2024-12-07T06:38:16.112374Z","shell.execute_reply.started":"2024-12-07T06:34:55.225014Z","shell.execute_reply":"2024-12-07T06:38:16.110166Z"}},"outputs":[],"execution_count":null}]}