{"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":"2024-10-13T16:49:16.274576Z","iopub.execute_input":"2024-10-13T16:49:16.275004Z","iopub.status.idle":"2024-10-13T16:49:17.438390Z","shell.execute_reply.started":"2024-10-13T16:49:16.274962Z","shell.execute_reply":"2024-10-13T16:49:17.437188Z"},"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":"2024-10-13T16:54:58.145691Z","iopub.execute_input":"2024-10-13T16:54:58.146143Z","iopub.status.idle":"2024-10-13T16:54:58.198901Z","shell.execute_reply.started":"2024-10-13T16:54:58.146100Z","shell.execute_reply":"2024-10-13T16:54:58.197773Z"},"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[['FGC-FGC_CU',\n                                 'FGC-FGC_CU_Zone',\n                                 'FGC-FGC_GSND',\n                                 'FGC-FGC_GSND_Zone',\n                                 'FGC-FGC_GSD',\n                                 'FGC-FGC_GSD_Zone',\n                                 'FGC-FGC_PU',\n                                 'FGC-FGC_PU_Zone',\n                                 'FGC-FGC_SRL',\n                                 'FGC-FGC_SRL_Zone',\n                                 'FGC-FGC_SRR',\n                                 'FGC-FGC_SRR_Zone',\n                                 'FGC-FGC_TL',\n                                 'FGC-FGC_TL_Zone',\n                                 'PreInt_EduHx-computerinternet_hoursday',\n                                 'sii']]\nselected_train","metadata":{"execution":{"iopub.status.busy":"2024-10-13T17:02:39.164569Z","iopub.execute_input":"2024-10-13T17:02:39.165031Z","iopub.status.idle":"2024-10-13T17:02:39.201363Z","shell.execute_reply.started":"2024-10-13T17:02:39.164984Z","shell.execute_reply":"2024-10-13T17:02:39.200133Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"selected_test = test_df.copy()\nselected_test = selected_test[['FGC-FGC_CU',\n                                 'FGC-FGC_CU_Zone',\n                                 'FGC-FGC_GSND',\n                                 'FGC-FGC_GSND_Zone',\n                                 'FGC-FGC_GSD',\n                                 'FGC-FGC_GSD_Zone',\n                                 'FGC-FGC_PU',\n                                 'FGC-FGC_PU_Zone',\n                                 'FGC-FGC_SRL',\n                                 'FGC-FGC_SRL_Zone',\n                                 'FGC-FGC_SRR',\n                                 'FGC-FGC_SRR_Zone',\n                                 'FGC-FGC_TL',\n                                 'FGC-FGC_TL_Zone',\n                                 'PreInt_EduHx-computerinternet_hoursday',]]\nselected_test","metadata":{"execution":{"iopub.status.busy":"2024-10-13T17:02:41.766696Z","iopub.execute_input":"2024-10-13T17:02:41.767159Z","iopub.status.idle":"2024-10-13T17:02:41.809450Z","shell.execute_reply.started":"2024-10-13T17:02:41.767119Z","shell.execute_reply":"2024-10-13T17:02:41.808215Z"},"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":"2024-10-13T17:02:47.203972Z","iopub.execute_input":"2024-10-13T17:02:47.205235Z","iopub.status.idle":"2024-10-13T17:02:47.246431Z","shell.execute_reply.started":"2024-10-13T17:02:47.205170Z","shell.execute_reply":"2024-10-13T17:02:47.245124Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"selected_test.fillna(0, inplace=True)\nselected_test","metadata":{"execution":{"iopub.status.busy":"2024-10-13T17:02:49.244606Z","iopub.execute_input":"2024-10-13T17:02:49.245052Z","iopub.status.idle":"2024-10-13T17:02:49.289376Z","shell.execute_reply.started":"2024-10-13T17:02:49.245009Z","shell.execute_reply":"2024-10-13T17:02:49.288027Z"},"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":"2024-10-13T17:02:57.777320Z","iopub.execute_input":"2024-10-13T17:02:57.777744Z","iopub.status.idle":"2024-10-13T17:02:57.865927Z","shell.execute_reply.started":"2024-10-13T17:02:57.777703Z","shell.execute_reply":"2024-10-13T17:02:57.864872Z"},"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":"2024-10-13T17:03:01.267131Z","iopub.execute_input":"2024-10-13T17:03:01.267575Z","iopub.status.idle":"2024-10-13T17:03:01.290490Z","shell.execute_reply.started":"2024-10-13T17:03:01.267530Z","shell.execute_reply":"2024-10-13T17:03:01.289043Z"},"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":"2024-10-13T17:03:04.702963Z","iopub.execute_input":"2024-10-13T17:03:04.703387Z","iopub.status.idle":"2024-10-13T17:03:04.717574Z","shell.execute_reply.started":"2024-10-13T17:03:04.703347Z","shell.execute_reply":"2024-10-13T17:03:04.716264Z"},"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":"2024-10-13T16:49:19.467476Z","iopub.execute_input":"2024-10-13T16:49:19.468433Z","iopub.status.idle":"2024-10-13T16:49:19.479195Z","shell.execute_reply.started":"2024-10-13T16:49:19.468378Z","shell.execute_reply":"2024-10-13T16:49:19.477855Z"},"trusted":true},"execution_count":null,"outputs":[]}]}