{"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"},{"sourceId":200372733,"sourceType":"kernelVersion"}],"dockerImageVersionId":30786,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# 0. Import libraries.","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport warnings\nwarnings.filterwarnings('ignore')","metadata":{"execution":{"iopub.status.busy":"2024-10-14T00:47:09.802966Z","iopub.execute_input":"2024-10-14T00:47:09.803476Z","iopub.status.idle":"2024-10-14T00:47:11.117805Z","shell.execute_reply.started":"2024-10-14T00:47:09.803430Z","shell.execute_reply":"2024-10-14T00:47:11.116534Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 1. Import data.","metadata":{}},{"cell_type":"code","source":"train_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')","metadata":{"execution":{"iopub.status.busy":"2024-10-14T00:47:11.120010Z","iopub.execute_input":"2024-10-14T00:47:11.120542Z","iopub.status.idle":"2024-10-14T00:47:11.212719Z","shell.execute_reply.started":"2024-10-14T00:47:11.120499Z","shell.execute_reply":"2024-10-14T00:47:11.211618Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 2. Feature selection.","metadata":{}},{"cell_type":"code","source":"selected_train = train_df.copy()\nselected_train = selected_train[['BIA-BIA_Activity_Level_num',\n                                 'BIA-BIA_BMC',\n                                 'BIA-BIA_BMI',\n                                 'BIA-BIA_BMR',\n                                 'BIA-BIA_DEE',\n                                 'BIA-BIA_ECW',\n                                 'BIA-BIA_FFM',\n                                 'BIA-BIA_FFMI',\n                                 'BIA-BIA_FMI',\n                                 'BIA-BIA_Fat',\n                                 'BIA-BIA_Frame_num',\n                                 'BIA-BIA_ICW',\n                                 'BIA-BIA_LDM',\n                                 'BIA-BIA_LST',\n                                 'BIA-BIA_SMM',\n                                 'BIA-BIA_TBW',\n                                 'sii']]\nselected_train","metadata":{"execution":{"iopub.status.busy":"2024-10-14T00:52:56.894042Z","iopub.execute_input":"2024-10-14T00:52:56.894578Z","iopub.status.idle":"2024-10-14T00:52:56.935120Z","shell.execute_reply.started":"2024-10-14T00:52:56.894531Z","shell.execute_reply":"2024-10-14T00:52:56.933746Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"selected_test = test_df.copy()\nselected_test = selected_test[['BIA-BIA_Activity_Level_num',\n                                 'BIA-BIA_BMC',\n                                 'BIA-BIA_BMI',\n                                 'BIA-BIA_BMR',\n                                 'BIA-BIA_DEE',\n                                 'BIA-BIA_ECW',\n                                 'BIA-BIA_FFM',\n                                 'BIA-BIA_FFMI',\n                                 'BIA-BIA_FMI',\n                                 'BIA-BIA_Fat',\n                                 'BIA-BIA_Frame_num',\n                                 'BIA-BIA_ICW',\n                                 'BIA-BIA_LDM',\n                                 'BIA-BIA_LST',\n                                 'BIA-BIA_SMM',\n                                 'BIA-BIA_TBW']]\nselected_test","metadata":{"execution":{"iopub.status.busy":"2024-10-14T00:53:32.791748Z","iopub.execute_input":"2024-10-14T00:53:32.792217Z","iopub.status.idle":"2024-10-14T00:53:32.837313Z","shell.execute_reply.started":"2024-10-14T00:53:32.792165Z","shell.execute_reply":"2024-10-14T00:53:32.836193Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 3. Data preprocessing.","metadata":{}},{"cell_type":"code","source":"selected_train.fillna(0, inplace=True)\nselected_train['sii'] = selected_train.pop('sii')\nselected_train","metadata":{"execution":{"iopub.status.busy":"2024-10-14T00:54:34.800137Z","iopub.execute_input":"2024-10-14T00:54:34.800662Z","iopub.status.idle":"2024-10-14T00:54:34.849464Z","shell.execute_reply.started":"2024-10-14T00:54:34.800619Z","shell.execute_reply":"2024-10-14T00:54:34.847079Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"selected_test.fillna(0, inplace=True)\nselected_test","metadata":{"execution":{"iopub.status.busy":"2024-10-14T00:54:37.693020Z","iopub.execute_input":"2024-10-14T00:54:37.693475Z","iopub.status.idle":"2024-10-14T00:54:37.739586Z","shell.execute_reply.started":"2024-10-14T00:54:37.693434Z","shell.execute_reply":"2024-10-14T00:54:37.738373Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 4. Model training.","metadata":{}},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import MinMaxScaler\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.metrics import accuracy_score, classification_report\n\nX = selected_train.drop(columns=['sii'])  \ny = selected_train['sii']  \n\nscaler = MinMaxScaler()\nX = scaler.fit_transform(X)\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)\n\nmodel = LogisticRegression(random_state=42)\n\nmodel.fit(X_train, y_train)\n\ny_pred = model.predict(X_test)","metadata":{"execution":{"iopub.status.busy":"2024-10-14T00:54:44.301918Z","iopub.execute_input":"2024-10-14T00:54:44.302355Z","iopub.status.idle":"2024-10-14T00:54:44.399791Z","shell.execute_reply.started":"2024-10-14T00:54:44.302300Z","shell.execute_reply":"2024-10-14T00:54:44.398737Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 5. Evaluation.","metadata":{}},{"cell_type":"code","source":"accuracy = accuracy_score(y_test, y_pred)\nreport = classification_report(y_test, y_pred)\n\nprint(f\"Accuracy: {accuracy}\")\nprint(\"Report:\")\nprint(report)","metadata":{"execution":{"iopub.status.busy":"2024-10-14T00:54:46.302368Z","iopub.execute_input":"2024-10-14T00:54:46.302804Z","iopub.status.idle":"2024-10-14T00:54:46.324499Z","shell.execute_reply.started":"2024-10-14T00:54:46.302765Z","shell.execute_reply":"2024-10-14T00:54:46.323193Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 6. Model output.","metadata":{}},{"cell_type":"code","source":"predictions = model.predict(selected_test).astype(int)\n\npredictions_df = pd.DataFrame({\n    'id': test_df['id'],  \n    'sii': predictions  \n})\n\npredictions_df","metadata":{"execution":{"iopub.status.busy":"2024-10-14T00:54:48.982425Z","iopub.execute_input":"2024-10-14T00:54:48.983845Z","iopub.status.idle":"2024-10-14T00:54:49.000495Z","shell.execute_reply.started":"2024-10-14T00:54:48.983777Z","shell.execute_reply":"2024-10-14T00:54:48.999081Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions_df.to_csv('/kaggle/working/submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2024-10-14T00:55:01.807045Z","iopub.execute_input":"2024-10-14T00:55:01.807530Z","iopub.status.idle":"2024-10-14T00:55:01.814873Z","shell.execute_reply.started":"2024-10-14T00:55:01.807486Z","shell.execute_reply":"2024-10-14T00:55:01.813506Z"},"trusted":true},"execution_count":null,"outputs":[]}]}