{"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":"2024-12-05T13:39:01.649351Z","iopub.execute_input":"2024-12-05T13:39:01.650169Z","iopub.status.idle":"2024-12-05T13:39:03.132418Z","shell.execute_reply.started":"2024-12-05T13:39:01.650103Z","shell.execute_reply":"2024-12-05T13:39:03.131255Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\n\ndf = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/sample_submission.csv')\n\ndf.head()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-05T13:39:03.134925Z","iopub.execute_input":"2024-12-05T13:39:03.135425Z","iopub.status.idle":"2024-12-05T13:39:03.149542Z","shell.execute_reply.started":"2024-12-05T13:39:03.135371Z","shell.execute_reply":"2024-12-05T13:39:03.148377Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\n\ndf = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/data_dictionary.csv')\n\ndf.head()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-05T13:39:03.150883Z","iopub.execute_input":"2024-12-05T13:39:03.151212Z","iopub.status.idle":"2024-12-05T13:39:03.167996Z","shell.execute_reply.started":"2024-12-05T13:39:03.151166Z","shell.execute_reply":"2024-12-05T13:39:03.166882Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\n\ndf = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/train.csv')\n\ndf.head()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-05T13:39:03.170663Z","iopub.execute_input":"2024-12-05T13:39:03.171025Z","iopub.status.idle":"2024-12-05T13:39:03.246463Z","shell.execute_reply.started":"2024-12-05T13:39:03.170989Z","shell.execute_reply":"2024-12-05T13:39:03.245374Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\n\ndf = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/test.csv')\n\ndf.head()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-05T13:39:03.248024Z","iopub.execute_input":"2024-12-05T13:39:03.248353Z","iopub.status.idle":"2024-12-05T13:39:03.280338Z","shell.execute_reply.started":"2024-12-05T13:39:03.248319Z","shell.execute_reply":"2024-12-05T13:39:03.279051Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\n\ndf = pd.read_parquet('/kaggle/input/child-mind-institute-problematic-internet-use/series_test.parquet/id=00115b9f/part-0.parquet')\n\ndf.head()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-05T13:39:03.282354Z","iopub.execute_input":"2024-12-05T13:39:03.282848Z","iopub.status.idle":"2024-12-05T13:39:03.308863Z","shell.execute_reply.started":"2024-12-05T13:39:03.282810Z","shell.execute_reply":"2024-12-05T13:39:03.307699Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\n\ndf = pd.read_parquet('/kaggle/input/child-mind-institute-problematic-internet-use/series_test.parquet/id=001f3379/part-0.parquet')\n\ndf.head()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-05T13:39:03.310117Z","iopub.execute_input":"2024-12-05T13:39:03.310574Z","iopub.status.idle":"2024-12-05T13:39:03.361774Z","shell.execute_reply.started":"2024-12-05T13:39:03.310522Z","shell.execute_reply":"2024-12-05T13:39:03.360696Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\n\ndf = pd.read_parquet('/kaggle/input/child-mind-institute-problematic-internet-use/series_train.parquet/id=0745c390/part-0.parquet')\n\ndf.head()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-05T13:39:03.363340Z","iopub.execute_input":"2024-12-05T13:39:03.363831Z","iopub.status.idle":"2024-12-05T13:39:03.389486Z","shell.execute_reply.started":"2024-12-05T13:39:03.363781Z","shell.execute_reply":"2024-12-05T13:39:03.388379Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\n\ndf = pd.read_parquet('/kaggle/input/child-mind-institute-problematic-internet-use/series_train.parquet/id=eaab7a96/part-0.parquet')\n\ndf.head()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-05T13:39:03.390873Z","iopub.execute_input":"2024-12-05T13:39:03.391207Z","iopub.status.idle":"2024-12-05T13:39:03.438316Z","shell.execute_reply.started":"2024-12-05T13:39:03.391175Z","shell.execute_reply":"2024-12-05T13:39:03.437206Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.impute import SimpleImputer\nfrom sklearn.preprocessing import StandardScaler\n\n# Step 1: Load train and test data\ntrain_data = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/train.csv')\ntest_data = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/test.csv')\n\n# Step 2: Handle missing target (y_train)\n# Fill missing 'sii' with the mode and ensure target is integer\ntrain_data['sii'] = train_data['sii'].fillna(train_data['sii'].mode()[0]).astype(int)\nprint(f\"Target values (sii): {train_data['sii'].unique()}\")\n\n# Step 3: Select features\nfeatures = ['Basic_Demos-Age', 'Basic_Demos-Sex', 'Physical-BMI', \n            'Physical-Height', 'Physical-Weight', 'PreInt_EduHx-computerinternet_hoursday']\n\n# Ensure features exist in both datasets\navailable_features = [feature for feature in features if feature in test_data.columns]\n\nX_train = train_data[available_features]\ny_train = train_data['sii']\nX_test = test_data[available_features]\n\n# Step 4: Handle missing values in features\nimputer = SimpleImputer(strategy='mean')\nX_train = imputer.fit_transform(X_train)\nX_test = imputer.transform(X_test)\n\n# Step 5: Scale the features\nscaler = StandardScaler()\nX_train = scaler.fit_transform(X_train)\nX_test = scaler.transform(X_test)\n\n# Step 6: Train the Random Forest Model\nmodel = RandomForestClassifier(n_estimators=100, random_state=42)\nmodel.fit(X_train, y_train)\n\n# Step 7: Make Predictions on Test Data\npredictions = model.predict(X_test)\n\n# Step 8: Prepare Submission File\nsubmission = pd.DataFrame({\n    'id': test_data['id'],\n    'sii': predictions.astype(int)  # Ensure predictions are integers\n})\n\n# Save the submission file\nsubmission.to_csv('/kaggle/working/submission.csv', index=False)\n\n# Display preview of the submission file\nprint(submission.head())\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-05T13:39:03.442034Z","iopub.execute_input":"2024-12-05T13:39:03.442394Z","iopub.status.idle":"2024-12-05T13:39:03.448196Z","shell.execute_reply.started":"2024-12-05T13:39:03.442359Z","shell.execute_reply":"2024-12-05T13:39:03.447119Z"}},"outputs":[],"execution_count":null}]}