{"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":"2024-12-03T01:27:32.285342Z","iopub.execute_input":"2024-12-03T01:27:32.285685Z","iopub.status.idle":"2024-12-03T01:27:36.236232Z","shell.execute_reply.started":"2024-12-03T01:27:32.285645Z","shell.execute_reply":"2024-12-03T01:27:36.234964Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nfrom sklearn.impute import KNNImputer\nfrom sklearn.metrics import cohen_kappa_score\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.metrics import mean_squared_error\n\n# Load data\ndf = pd.read_csv(\"/kaggle/input/child-mind-institute-problematic-internet-use/train.csv\")\ndf = df.dropna(subset=['sii'])  # keeping labeled values only\ntest = pd.read_csv(\"/kaggle/input/child-mind-institute-problematic-internet-use/test.csv\")\n\n# Mapping season values to numeric\nseason_mapping = {\n    'Winter': -1,\n    'Spring': -0.5,\n    'Summer': 0.5,\n    'Fall': 1\n}\n\n# Replace categorical season values with numeric ones\ndf = df.replace(season_mapping)\ntest = test.replace(season_mapping)\n\n# Drop columns that are in df but not in test dataset\ntest_missing_columns = set(df.columns) - set(test.columns)\nfor col in test_missing_columns:\n    if col != 'sii':  # Retain the target column for training\n        df.drop(columns=col, inplace=True)\n\n# For later use: save ids and labels\ntrain_ids = df['id']\ntest_ids = test['id']\ntrain_labels = df['sii']\n\n# Drop 'id' and 'sii' from features for both train and test\ndf = df.drop(columns=['id', 'sii'])\ntest = test.drop(columns=['id'])\n\n# Remove columns that contain 'Season' from both train and test datasets\ndf = df.loc[:, ~df.columns.str.contains('Season')]\ntest = test.loc[:, ~test.columns.str.contains('Season')]\n\n# Impute missing values using KNNImputer\nimputer = KNNImputer(n_neighbors=4)  # Using 4 nearest neighbors\nimputed_data = imputer.fit_transform(df)\n\n# Convert imputed data back to DataFrame\ntrain = pd.DataFrame(imputed_data, columns=df.columns)\n\n# Optionally: Check the first few rows of imputed data\nprint(train.head())\n\n# Quadratic Weighted Kappa function for model evaluation\ndef quadratic_weighted_kappa(y_true, y_pred):\n    return cohen_kappa_score(y_true, y_pred, weights='quadratic')\n\n# Train-Test Split (for local validation)\nX_train, X_val, y_train, y_val = train_test_split(train, train_labels, test_size=0.2, random_state=42)\n\n# Example model: Random Forest Classifier\nmodel = RandomForestClassifier(n_estimators=100, random_state=42)\nmodel.fit(X_train, y_train)\n\n# Predict on validation set\ny_pred = model.predict(X_val)\n\n# Calculate the Quadratic Weighted Kappa\nqwk = quadratic_weighted_kappa(y_val, y_pred)\nprint(f\"Quadratic Weighted Kappa: {qwk}\")\n\n# Optionally: Check MSE as another evaluation metric\nmse = mean_squared_error(y_val, y_pred)\nprint(f\"Mean Squared Error: {mse}\")\n\n# Final model predictions on test dataset\ntest_imputed = imputer.transform(test)\ntest_predictions = model.predict(test_imputed)\n\n# Prepare final submission\nsubmission = pd.DataFrame({'id': test_ids, 'sii': test_predictions})\nsubmission.to_csv('submission.csv', index=False)\n\nprint(\"Submission saved as 'submission.csv'.\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-03T01:28:27.605214Z","iopub.execute_input":"2024-12-03T01:28:27.605876Z","iopub.status.idle":"2024-12-03T01:28:32.245856Z","shell.execute_reply.started":"2024-12-03T01:28:27.605817Z","shell.execute_reply":"2024-12-03T01:28:32.242389Z"}},"outputs":[],"execution_count":null}]}