{"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# 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\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":"2024-12-05T14:21:54.007135Z","iopub.execute_input":"2024-12-05T14:21:54.008455Z","iopub.status.idle":"2024-12-05T14:21:55.722239Z","shell.execute_reply.started":"2024-12-05T14:21:54.008409Z","shell.execute_reply":"2024-12-05T14:21:55.720998Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nfrom sklearn.decomposition import PCA\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.neural_network import MLPRegressor\nfrom sklearn.metrics import mean_squared_error, r2_score","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-05T14:22:15.447110Z","iopub.execute_input":"2024-12-05T14:22:15.448113Z","iopub.status.idle":"2024-12-05T14:22:15.453778Z","shell.execute_reply.started":"2024-12-05T14:22:15.448068Z","shell.execute_reply":"2024-12-05T14:22:15.452542Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Fungsi untuk melakukan encoding pada kolom string\ndef encode_string_columns(df):\n    # Melakukan pengecekan setiap kolom dalam DataFrame\n    for column in df.columns:\n        # Jika tipe data kolom adalah string (object)\n        if df[column].dtype == object:\n            # Mengubah kategori string menjadi angka menggunakan factorize\n            codes, _ = pd.factorize(df[column])\n            # Mengganti kolom dengan nilai yang terencode\n            df[column] = codes\n    return df\n\n# Membaca dataset train dan test\ndf = pd.read_csv(\"/kaggle/input/child-mind-institute-problematic-internet-use/train.csv\")\ndf_test = pd.read_csv(\"/kaggle/input/child-mind-institute-problematic-internet-use/test.csv\")\n\n# Menyimpan kolom 'id' dari df_test untuk digunakan nanti\nid = df_test['id']\n\n# Menghapus kolom 'id' dan 'sii' dari df (train data)\ndf = df.drop(columns=['id', 'sii'])\n\n# Menghapus kolom 'id' dari df_test (test data)\ndf_test = df_test.drop(columns=['id'])\n\n# Melakukan encoding pada kolom string di df (train data)\ndf = encode_string_columns(df)\n\n# Mengisi missing values (NaN) dengan 0 pada df (train data)\ndf.fillna(0, inplace=True)\n\n# Melakukan encoding pada kolom string di df_test (test data)\ndf_test = encode_string_columns(df_test)\n\n# Mengisi missing values (NaN) dengan 0 pada df_test (test data)\ndf_test.fillna(0, inplace=True)\n\n# Menemukan kolom yang ada pada kedua dataset (df dan df_test) secara bersama-sama\ncommon_columns = df.columns.intersection(df_test.columns)\n\n# Menampilkan nama-nama kolom yang ada pada kedua dataset\nprint(common_columns)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-05T14:22:19.899855Z","iopub.execute_input":"2024-12-05T14:22:19.900261Z","iopub.status.idle":"2024-12-05T14:22:19.987786Z","shell.execute_reply.started":"2024-12-05T14:22:19.900224Z","shell.execute_reply":"2024-12-05T14:22:19.986518Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Menyiapkan fitur dan target\nX = df[common_columns]  # Fitur diambil dari kolom yang umum antara df dan df_test\ny = df.drop(columns=common_columns)  # Target adalah sisa kolom yang tidak ada di common_columns\n\n# Membagi data menjadi set pelatihan dan validasi\nX_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)\n\n# Menstandarisasi fitur\nscaler = StandardScaler()\nX_train = scaler.fit_transform(X_train)  # Fit dan transform data pelatihan\nX_val = scaler.transform(X_val)  # Transform data validasi\nX_test = scaler.transform(df_test)  # Transform data uji (df_test)\n\n# Mendefinisikan model neural network untuk regresi\nmodel = MLPRegressor(hidden_layer_sizes=(10, 5), max_iter=1000, random_state=42)\n\n# Melatih model dengan data pelatihan\nmodel.fit(X_train, y_train)\n\n# Memprediksi pada set validasi\ny_pred = model.predict(X_val)\n\n# Mengevaluasi model menggunakan Mean Squared Error dan R2 Score\nmse = mean_squared_error(y_val, y_pred)\nr2 = r2_score(y_val, y_pred)\nprint(f'Mean Squared Error: {mse:.2f}')\nprint(f'R2 Score: {r2:.2f}')\n\n# Memprediksi pada set uji (test set)\ny_test_predict = model.predict(X_test)\ny_test_predict_df = pd.DataFrame(y_test_predict, columns=y.columns)\n\n# Menggabungkan nilai prediksi dengan DataFrame test asli\ndf_test_with_predictions = pd.concat([df_test.reset_index(drop=True), y_test_predict_df], axis=1)\n\n# Menyusun ulang kolom agar sesuai dengan urutan kolom di DataFrame latih (train)\ndf_test_with_predictions = df_test_with_predictions[df.columns]\n\n# Menampilkan beberapa baris pertama dari DataFrame hasil prediksi\nprint(df_test_with_predictions.head())\n\n# Membaca ulang file CSV untuk dataset latih\ndf = pd.read_csv(\"/kaggle/input/child-mind-institute-problematic-internet-use/train.csv\")\ndf_test = df_test_with_predictions  # Menggunakan DataFrame test dengan prediksi yang sudah digabungkan\n\n# Memastikan bahwa df dan df_test adalah DataFrame\ndf = pd.DataFrame(df)\ndf_test = pd.DataFrame(df_test)\n\n# Menampilkan bentuk (shape) dari dataset latih dan uji\nprint(df.shape)\n\n# Menampilkan nama-nama kolom\ncol = df.columns\n\n# Menampilkan ID yang disalin sebelumnya\nprint(id)\n\n# Menghapus kolom 'id' dan 'sii' dari dataset latih\ndf = df.drop(columns=[\"id\", 'sii'])\n\n# Mencari kolom bertipe string pada dataset latih\nstring_columns = df.select_dtypes(include='object').columns\n\n# Menampilkan isi dari dataset latih dan dataset uji\nprint(df)\nprint(df_test)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-05T14:22:23.917033Z","iopub.execute_input":"2024-12-05T14:22:23.917440Z","iopub.status.idle":"2024-12-05T14:22:33.934522Z","shell.execute_reply.started":"2024-12-05T14:22:23.917406Z","shell.execute_reply":"2024-12-05T14:22:33.933128Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Mengenkode kolom string dalam DataFrame\nencoded_df = encode_string_columns(df)\nencoded_df_test = encode_string_columns(df_test)\n\n# Mengisi nilai kosong dengan 0 di DataFrame hasil encoding\nencoded_df.fillna(0, inplace=True)\nencoded_df_test.fillna(0, inplace=True)\n\n# Menampilkan dimensi DataFrame yang telah dienkode\nprint(encoded_df.shape)\nprint(encoded_df_test.shape)\n\n# Fungsi untuk menentukan jumlah komponen optimal berdasarkan threshold variansi yang dijelaskan\ndef choose_optimal_components(explained_variance_ratio, threshold=0.95):\n    # Menghitung variansi kumulatif\n    cumulative_variance = explained_variance_ratio.cumsum()  \n    # Menentukan jumlah komponen yang mencakup variansi lebih dari threshold\n    optimal_components = (cumulative_variance >= threshold).argmax() + 1  \n    return optimal_components, cumulative_variance\n\n# Fungsi untuk melakukan PCA (Principal Component Analysis)\ndef perform_pca(data, data_test, threshold=0.95):\n    # Memisahkan fitur (tanpa kolom terakhir yang dianggap sebagai target)\n    features = data.iloc[:, :-1]\n    features_test = data_test.iloc[:, :-1]\n\n    # Standarisasi fitur\n    scaler = StandardScaler()\n    standardized_data = scaler.fit_transform(features)  # Standarisasi data pelatihan\n    standardized_data_test = scaler.transform(features_test)  # Standarisasi data uji\n\n    # Melakukan PCA tanpa menentukan jumlah komponen terlebih dahulu\n    pca = PCA()\n    pca.fit(standardized_data)\n\n    # Menentukan jumlah komponen optimal berdasarkan threshold\n    optimal_components, cumulative_variance = choose_optimal_components(pca.explained_variance_ratio_, threshold)\n\n    # Melakukan PCA dengan jumlah komponen optimal\n    pca = PCA(n_components=optimal_components)\n    principal_components = pca.fit_transform(standardized_data)\n\n    # Membuat DataFrame untuk menyimpan komponen utama\n    columns = [f\"PC{i+1}\" for i in range(optimal_components)]\n    pca_df = pd.DataFrame(data=principal_components, columns=columns)\n\n    # Mengaplikasikan PCA pada data uji\n    principal_components_test = pca.transform(standardized_data_test)\n    columns_test = [f\"PC{i+1}\" for i in range(optimal_components)]\n    pca_test_df = pd.DataFrame(data=principal_components_test, columns=columns_test)\n\n    return pca_df, optimal_components, cumulative_variance, pca_test_df\n\n# Menentukan data yang akan dianalisis\ndata = encoded_df\ndata_test = encoded_df_test\n\n# Menjalankan PCA dengan threshold untuk variansi yang dijelaskan\nthreshold = 0.95  # Tingkat variansi yang diinginkan\npca_result, optimal_components, cumulative_variance, pca_test_df = perform_pca(data, data_test, threshold)\n\n# Menampilkan hasil PCA\nprint(pca_result)\n\n# Mengisi nilai kosong dengan 0 pada hasil PCA\npca_result.fillna(0, inplace=True)\nprint(pca_result)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-05T14:22:41.341973Z","iopub.execute_input":"2024-12-05T14:22:41.342431Z","iopub.status.idle":"2024-12-05T14:22:41.627171Z","shell.execute_reply.started":"2024-12-05T14:22:41.342390Z","shell.execute_reply":"2024-12-05T14:22:41.624567Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nfrom sklearn.neural_network import MLPClassifier\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.metrics import accuracy_score, mean_squared_error, r2_score\n\n# Menggunakan hasil PCA sebagai fitur\nX = pca_result\nX.fillna(method='ffill', inplace=True)  # Mengisi nilai kosong dengan metode forward fill\ndf_test = pca_test_df\ndf_test.fillna(method='ffill', inplace=True)  # Mengisi nilai kosong dengan metode forward fill\n\n# Membaca data target dari file\ny = pd.read_csv(\"/kaggle/input/child-mind-institute-problematic-internet-use/train.csv\")\ny = y['sii']  # Mengambil kolom target 'sii'\ny.fillna(0, inplace=True)  # Mengisi nilai kosong dengan 0\n\n# Menampilkan fitur dan target untuk verifikasi\nprint(X)\nprint(y)\n\n# Membagi data menjadi data latih dan validasi\nX_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)\nX_test = df_test  # Data uji dari PCA test result\n\n# Standarisasi fitur\nscaler = StandardScaler()\nX_train = scaler.fit_transform(X_train)  # Fit dan transform data latih\nX_val = scaler.transform(X_val)  # Transform data validasi\nX_test = scaler.transform(X_test)  # Transform data uji\n\n# Mendefinisikan model neural network untuk klasifikasi\nmodel = MLPClassifier(hidden_layer_sizes=(10, 5), max_iter=1000, random_state=42)\n\n# Melatih model\nmodel.fit(X_train, y_train)\n\n# Memprediksi data validasi\ny_pred = model.predict(X_val)\n\n# Menghitung metrik evaluasi\nmse = mean_squared_error(y_val, y_pred)\nr2 = r2_score(y_val, y_pred)\naccuracy = accuracy_score(y_val, y_pred)\n\n# Menampilkan hasil evaluasi\nprint(f'Validation Accuracy: {accuracy:.2f}')\nprint(f'Mean Squared Error: {mse:.2f}')\nprint(f'R2 Score: {r2:.2f}')\n\n# Memprediksi data uji\ny_test_predict = model.predict(X_test)\n\n# Menampilkan hasil prediksi\nprint(y_test_predict)\n\n# Membuat DataFrame hasil prediksi\ny_test_predict = pd.DataFrame(y_test_predict.astype(int), columns=[\"sii\"])\n\n# Menggabungkan ID dan prediksi untuk membuat file submission\nsubmission = pd.concat([id, y_test_predict], axis=1)\n\n# Menampilkan beberapa baris pertama dari submission\nprint(submission.head())\n\n# Menyimpan hasil ke file CSV\nsubmission.to_csv(\"/kaggle/working/submission.csv\", index=False)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-05T14:23:47.556380Z","iopub.execute_input":"2024-12-05T14:23:47.556778Z","iopub.status.idle":"2024-12-05T14:23:50.739533Z","shell.execute_reply.started":"2024-12-05T14:23:47.556743Z","shell.execute_reply":"2024-12-05T14:23:50.737799Z"}},"outputs":[],"execution_count":null}]}