{"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":"2024-12-05T13:52:25.400670Z","iopub.execute_input":"2024-12-05T13:52:25.401216Z","iopub.status.idle":"2024-12-05T13:52:30.874522Z","shell.execute_reply.started":"2024-12-05T13:52:25.401162Z","shell.execute_reply":"2024-12-05T13:52:30.873290Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import classification_report, confusion_matrix, roc_curve, auc\nfrom sklearn.impute import SimpleImputer\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.compose import ColumnTransformer\nfrom sklearn.pipeline import Pipeline\nfrom xgboost import XGBClassifier\n\n# Membaca Dataset\ntrain_ds = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/train.csv', index_col='id')\ntest_ds = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/test.csv', index_col='id')\n\n# Pilihan Fitur\nselection = ['Physical-Height', 'Basic_Demos-Age', 'PreInt_EduHx-computerinternet_hoursday', 'Physical-Weight',\n             'FGC-FGC_CU', 'BIA-BIA_BMI', 'SDS-SDS_Total_T', 'FGC-FGC_PU', 'BIA-BIA_Frame_num', \n             'Physical-Systolic_BP', 'FGC-FGC_TL', 'BIA-BIA_FFMI', 'FGC-FGC_SRR_Zone', 'FGC-FGC_SRL_Zone']\n\n# Dataset untuk pelatihan\ntrain_ds_usable = train_ds[train_ds['sii'].notnull()]\nX = train_ds_usable[selection]\ny = train_ds_usable['sii']\n\n# Pembagian Data\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)\n\n# Pipeline untuk pemrosesan data\npreprocessor = ColumnTransformer(\n    transformers=[\n        ('num', Pipeline(steps=[('imputer', SimpleImputer(strategy='mean')), ('scaler', StandardScaler())]), \n         X.select_dtypes(include='float64').columns.tolist()),\n        ('cat', Pipeline(steps=[('imputer', SimpleImputer(strategy='most_frequent'))]), \n         X.select_dtypes(include='object').columns.tolist())\n    ]\n)\n\n# Pipeline untuk model XGBoost\nmodel_pipeline = Pipeline(steps=[\n    ('preprocessor', preprocessor),\n    ('classifier', XGBClassifier(use_label_encoder=False, eval_metric='mlogloss'))\n])\n\n# Melatih model\nmodel_pipeline.fit(X_train, y_train)\n\n# Prediksi dan Evaluasi\ny_pred = model_pipeline.predict(X_test)\nprint(classification_report(y_test, y_pred))\n\n# Confusion Matrix\nsns.heatmap(confusion_matrix(y_test, y_pred), annot=True, fmt='d', cmap='Blues')\nplt.title(\"Confusion Matrix\")\nplt.xlabel(\"Predicted\")\nplt.ylabel(\"True\")\nplt.show()\n\n# ROC Curve\ny_probs = model_pipeline.predict_proba(X_test)[:, 1]  # Ambil probabilitas kelas positif\nfpr, tpr, thresholds = roc_curve(y_test, y_probs, pos_label=3)\nroc_auc = auc(fpr, tpr)\n\nplt.plot(fpr, tpr, color='blue', label='ROC curve (area = %.2f)' % roc_auc)\nplt.plot([0, 1], [0, 1], color='red', linestyle='--')\nplt.xlabel('False Positive Rate')\nplt.ylabel('True Positive Rate')\nplt.title('Receiver Operating Characteristic')\nplt.legend(loc=\"lower right\")\nplt.show()\n\n# Persiapan untuk submission\ntest = test_ds[selection]\ny_test_pred = model_pipeline.predict(test)\n\n# Membuat file submission\nsubmission = pd.DataFrame({'id': test_ds.index, 'sii': y_test_pred})\nsubmission.to_csv('submission.csv', index=False)\nprint(\"Submission file created: submission.csv\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-05T13:52:56.103548Z","iopub.execute_input":"2024-12-05T13:52:56.103961Z","iopub.status.idle":"2024-12-05T13:52:59.023006Z","shell.execute_reply.started":"2024-12-05T13:52:56.103927Z","shell.execute_reply":"2024-12-05T13:52:59.020757Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}