{"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":"2024-10-13T07:55:39.591496Z","iopub.execute_input":"2024-10-13T07:55:39.591991Z","iopub.status.idle":"2024-10-13T07:55:40.864405Z","shell.execute_reply.started":"2024-10-13T07:55:39.591937Z","shell.execute_reply":"2024-10-13T07:55:40.863200Z"},"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":"2024-10-13T07:55:40.865934Z","iopub.execute_input":"2024-10-13T07:55:40.866614Z","iopub.status.idle":"2024-10-13T07:55:40.966555Z","shell.execute_reply.started":"2024-10-13T07:55:40.866559Z","shell.execute_reply":"2024-10-13T07:55:40.965370Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.columns","metadata":{"execution":{"iopub.status.busy":"2024-10-13T07:56:54.471043Z","iopub.execute_input":"2024-10-13T07:56:54.471481Z","iopub.status.idle":"2024-10-13T07:56:54.480977Z","shell.execute_reply.started":"2024-10-13T07:56:54.471441Z","shell.execute_reply":"2024-10-13T07:56:54.479609Z"},"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[['Physical-BMI','Physical-Height','Physical-Weight','Physical-Waist_Circumference','sii']]\nselected_train","metadata":{"execution":{"iopub.status.busy":"2024-10-13T08:00:21.202425Z","iopub.execute_input":"2024-10-13T08:00:21.203001Z","iopub.status.idle":"2024-10-13T08:00:21.230482Z","shell.execute_reply.started":"2024-10-13T08:00:21.202949Z","shell.execute_reply":"2024-10-13T08:00:21.229039Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"selected_test = test_df.copy()\nselected_test = selected_test[['Physical-BMI','Physical-Height','Physical-Weight','Physical-Waist_Circumference']]\nselected_test","metadata":{"execution":{"iopub.status.busy":"2024-10-13T08:01:28.628991Z","iopub.execute_input":"2024-10-13T08:01:28.629647Z","iopub.status.idle":"2024-10-13T08:01:28.651745Z","shell.execute_reply.started":"2024-10-13T08:01:28.629590Z","shell.execute_reply":"2024-10-13T08:01:28.650444Z"},"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":"2024-10-13T08:01:44.061442Z","iopub.execute_input":"2024-10-13T08:01:44.061912Z","iopub.status.idle":"2024-10-13T08:01:44.084721Z","shell.execute_reply.started":"2024-10-13T08:01:44.061865Z","shell.execute_reply":"2024-10-13T08:01:44.083383Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"selected_test.fillna(0, inplace=True)\nselected_test","metadata":{"execution":{"iopub.status.busy":"2024-10-13T08:01:51.198443Z","iopub.execute_input":"2024-10-13T08:01:51.198868Z","iopub.status.idle":"2024-10-13T08:01:51.219909Z","shell.execute_reply.started":"2024-10-13T08:01:51.198810Z","shell.execute_reply":"2024-10-13T08:01:51.218670Z"},"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":"2024-10-13T08:02:56.875975Z","iopub.execute_input":"2024-10-13T08:02:56.876467Z","iopub.status.idle":"2024-10-13T08:02:56.944155Z","shell.execute_reply.started":"2024-10-13T08:02:56.876423Z","shell.execute_reply":"2024-10-13T08:02:56.942803Z"},"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\"Precisión: {accuracy}\")\nprint(\"Reporte de clasificación:\")\nprint(report)","metadata":{"execution":{"iopub.status.busy":"2024-10-13T08:03:00.325972Z","iopub.execute_input":"2024-10-13T08:03:00.326399Z","iopub.status.idle":"2024-10-13T08:03:00.347850Z","shell.execute_reply.started":"2024-10-13T08:03:00.326360Z","shell.execute_reply":"2024-10-13T08:03:00.346593Z"},"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":"2024-10-13T08:03:04.187753Z","iopub.execute_input":"2024-10-13T08:03:04.188217Z","iopub.status.idle":"2024-10-13T08:03:04.203174Z","shell.execute_reply.started":"2024-10-13T08:03:04.188174Z","shell.execute_reply":"2024-10-13T08:03:04.201979Z"},"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":"2024-10-13T07:55:42.986105Z","iopub.execute_input":"2024-10-13T07:55:42.986510Z","iopub.status.idle":"2024-10-13T07:55:42.998243Z","shell.execute_reply.started":"2024-10-13T07:55:42.986469Z","shell.execute_reply":"2024-10-13T07:55:42.996765Z"},"trusted":true},"execution_count":null,"outputs":[]}]}