{"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)\nimport tensorflow as tf\nfrom sklearn.model_selection import train_test_split, GridSearchCV\nfrom sklearn.compose import ColumnTransformer\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.preprocessing import OneHotEncoder\nfrom sklearn.impute import SimpleImputer\nfrom sklearn.ensemble import GradientBoostingRegressor\nfrom sklearn.metrics import mean_squared_error\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":"2024-12-05T13:16:17.534655Z","iopub.execute_input":"2024-12-05T13:16:17.535149Z","iopub.status.idle":"2024-12-05T13:16:18.709244Z","shell.execute_reply.started":"2024-12-05T13:16:17.535108Z","shell.execute_reply":"2024-12-05T13:16:18.708085Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Corrected paths\ntrain_df = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/train.csv')\ntest_df = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/test.csv')\nsample_submission_path = '/kaggle/input/child-mind-institute-problematic-internet-use/sample_submission.csv'\ndata_dictionary_path = '/kaggle/input/child-mind-institute-problematic-internet-use/data_dictionary.csv'\n\n# Load datasets\ntry:\n    train_df = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/train.csv')\n    test_df = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/test.csv')\n\n    print(\"Datasets loaded successfully.\")\nexcept FileNotFoundError as e:\n    print(f\"File not found: {e}\")\n\n# Display basic information for each dataset\nprint(\"Train Data:\")\nprint(train_df.head())\n\nprint(\"\\nTest Data:\")\nprint(test_df.head())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-05T13:16:18.710880Z","iopub.execute_input":"2024-12-05T13:16:18.711234Z","iopub.status.idle":"2024-12-05T13:16:18.852911Z","shell.execute_reply.started":"2024-12-05T13:16:18.711190Z","shell.execute_reply":"2024-12-05T13:16:18.851558Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Menghapus baris dengan target 'sii' yang hilang\ntrain_df = train_df.dropna(subset=['sii'])\n\n# Memisahkan fitur dan target\nX = train_df.drop(columns=['id', 'sii'])\ny = train_df['sii']\n\n# Menangani kolom yang hilang di test set\nmissing_cols_in_test = set(X.columns) - set(test_df.columns)\nX = X.drop(columns=missing_cols_in_test)\n\n# Menentukan kolom numerik dan kategorikal\nnumeric_cols = X.select_dtypes(include=['int64', 'float64']).columns\ncategorical_cols = X.select_dtypes(include=['object']).columns\n\n# Preprocessing untuk kolom numerik\nnumeric_transformer = Pipeline(steps=[\n    ('imputer', SimpleImputer(strategy='median'))\n])\n\n# Preprocessing untuk kolom kategorikal\ncategorical_transformer = Pipeline(steps=[\n    ('imputer', SimpleImputer(strategy='most_frequent')),\n    ('onehot', OneHotEncoder(handle_unknown='ignore'))\n])\n\n# Membuat transformer untuk menggabungkan keduanya\npreprocessor = ColumnTransformer(\n    transformers=[\n        ('num', numeric_transformer, numeric_cols),\n        ('cat', categorical_transformer, categorical_cols)\n    ]\n)\n\n# Preprocessing data latih\nX_processed = preprocessor.fit_transform(X)\n\n# Membagi data menjadi train dan validation set\nX_train, X_val, y_train, y_val = train_test_split(X_processed, y, test_size=0.2, random_state=42)\n\n# Model GradientBoosting (untuk mencoba meningkatkan akurasi)\nmodel = GradientBoostingRegressor(random_state=42)\n\n# Mengatur parameter untuk GridSearchCV\nparam_grid = {\n    'n_estimators': [100, 200],\n    'learning_rate': [0.01, 0.1, 0.2],\n    'max_depth': [3, 4, 5],\n    'subsample': [0.8, 1.0]\n}\n\n# Mencari hyperparameter terbaik menggunakan GridSearchCV\ngrid_search = GridSearchCV(estimator=model, param_grid=param_grid, cv=5, n_jobs=-1, verbose=2, scoring='neg_mean_squared_error')\ngrid_search.fit(X_train, y_train)\n\n# Menampilkan hasil terbaik dari GridSearchCV\nprint(f\"Best Hyperparameters: {grid_search.best_params_}\")\n\n# Menggunakan model terbaik dari GridSearchCV untuk prediksi\nbest_model = grid_search.best_estimator_\n\n# Memprediksi hasil validasi\ny_pred = best_model.predict(X_val)\n\n# Menghitung Mean Squared Error\nmse = mean_squared_error(y_val, y_pred)\nprint(f'Mean Squared Error: {mse}')\n\n# Memproses data uji\nX_test = test_df.drop(columns=['id'])\nX_test = X_test.reindex(columns=X.columns, fill_value=np.nan)\nX_test_processed = preprocessor.transform(X_test)\n\n# Memprediksi hasil untuk data uji\ntest_predictions = best_model.predict(X_test_processed)\n\n# Menyimpan hasil prediksi ke dalam kolom 'sii'\ntest_df['sii'] = test_predictions.round().astype(int)\n\n# Menyimpan file submission\nsubmission = test_df[['id', 'sii']]\nsubmission.to_csv('submission.csv', index=False)\nprint(\"Submission file saved as submission.csv\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-05T13:16:18.855122Z","iopub.execute_input":"2024-12-05T13:16:18.855502Z","iopub.status.idle":"2024-12-05T13:19:12.736502Z","shell.execute_reply.started":"2024-12-05T13:16:18.855468Z","shell.execute_reply":"2024-12-05T13:19:12.735074Z"}},"outputs":[],"execution_count":null}]}