{"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":30786,"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":"2024-12-06T08:02:31.360358Z","iopub.execute_input":"2024-12-06T08:02:31.360766Z","iopub.status.idle":"2024-12-06T08:02:35.396865Z","shell.execute_reply.started":"2024-12-06T08:02:31.360731Z","shell.execute_reply":"2024-12-06T08:02:35.395687Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.compose import ColumnTransformer\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.preprocessing import StandardScaler, OneHotEncoder\nfrom sklearn.impute import SimpleImputer\nfrom sklearn.metrics import mean_squared_error\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Dropout, Input, BatchNormalization\nfrom tensorflow.keras.callbacks import EarlyStopping\n\n# Load dataset tabular\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')\n\n# Menghapus baris dengan nilai NaN di kolom target 'sii'\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# Menyesuaikan kolom yang hilang di test dataset\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    ('scaler', StandardScaler())  # Menambahkan scaling\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# Menggabungkan preprocessing\npreprocessor = ColumnTransformer(\n    transformers=[\n        ('num', numeric_transformer, numeric_cols),\n        ('cat', categorical_transformer, categorical_cols)\n    ]\n)\n\n# Preprocessing pada dataset\nX_processed = preprocessor.fit_transform(X)\n\n# Membagi data ke dalam 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# Membuat model Neural Network\nmodel = Sequential([\n    Input(shape=(X_train.shape[1],)),  # Input layer\n    Dense(256, activation='relu'),  # Hidden layer 1\n    BatchNormalization(),  # Batch Normalization\n    Dropout(0.3),  # Regularisasi dropout\n    Dense(128, activation='relu'),  # Hidden layer 2\n    BatchNormalization(),\n    Dropout(0.3),\n    Dense(64, activation='relu'),  # Hidden layer 3\n    BatchNormalization(),\n    Dropout(0.2),\n    Dense(1, activation='linear')  # Output layer (regresi)\n])\n\n# Compile model\nmodel.compile(optimizer='adam', loss='mean_squared_error')\n\n# Early Stopping\nearly_stopping = EarlyStopping(monitor='val_loss', patience=10, restore_best_weights=True)\n\n# Train model\nhistory = model.fit(X_train, y_train, epochs=100, batch_size=32, \n                    validation_data=(X_val, y_val), \n                    callbacks=[early_stopping], verbose=1)\n\n# Prediksi pada data validasi\ny_pred = model.predict(X_val)\nmse = mean_squared_error(y_val, y_pred)\nprint(f'Mean Squared Error: {mse}')\n\n# Preprocessing pada data test\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# Prediksi pada data test\ntest_predictions = model.predict(X_test_processed)\ntest_df['sii'] = test_predictions.round().astype(int)\n\n# Membuat file submission\nsubmission = test_df[['id', 'sii']]\nsubmission.to_csv('submission.csv', index=False)\nprint(\"Submission file saved as submission.csv\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-06T08:11:34.392188Z","iopub.execute_input":"2024-12-06T08:11:34.392619Z","iopub.status.idle":"2024-12-06T08:12:03.526267Z","shell.execute_reply.started":"2024-12-06T08:11:34.392582Z","shell.execute_reply":"2024-12-06T08:12:03.525027Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}