{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":81933,"databundleVersionId":9643020,"sourceType":"competition"}],"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},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nfrom sklearn.model_selection import train_test_split, cross_val_score\nfrom sklearn.metrics import cohen_kappa_score\nfrom sklearn.preprocessing import StandardScaler\nfrom imblearn.combine import SMOTETomek\nfrom sklearn.linear_model import LogisticRegression\n\n# Load Dataset\ntrain = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/train.csv')\ntest = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/test.csv')\n\n# Feature Selection\nfeatures = ['Physical-BMI', 'Physical-Height', 'Physical-Weight', \n            'PreInt_EduHx-computerinternet_hoursday', \n            'PAQ_A-PAQ_A_Total', 'SDS-SDS_Total_Raw']\ntarget = 'sii'\n\n# Handle Missing Values\nfor col in features:\n    if col in train.columns:\n        train[col] = train[col].fillna(train[col].median())\n        if col in test.columns:\n            test[col] = test[col].fillna(test[col].median())\n\n# Fill missing target values\ntrain[target] = train[target].fillna(0).astype(int)\n\n# Feature Engineering: Adding Interaction Features\ntrain['BMI_Height'] = train['Physical-BMI'] * train['Physical-Height']\ntest['BMI_Height'] = test['Physical-BMI'] * test['Physical-Height']\n\n# Update feature list\nfeatures.append('BMI_Height')\n\n# Normalize Features\nscaler = StandardScaler()\nX = scaler.fit_transform(train[features])\ny = train[target].values\n\n# Balance Data using SMOTE + Tomek Links\nsmote_tomek = SMOTETomek(random_state=42)\nX_balanced, y_balanced = smote_tomek.fit_resample(X, y)\n\n# Split Data\nX_train, X_val, y_train, y_val = train_test_split(X_balanced, y_balanced, test_size=0.2, random_state=42)\n\n# Train Model: Logistic Regression\nmodel = LogisticRegression(random_state=42, max_iter=1000)\nmodel.fit(X_train, y_train)\n\n# Evaluate Model\ny_pred = model.predict(X_val)\nscore = cohen_kappa_score(y_val, y_pred, weights='quadratic')\nprint(\"Quadratic Weighted Kappa Score (Validation):\", score)\n\n# Cross-Validation for Stability\ncv_scores = cross_val_score(model, X_balanced, y_balanced, cv=5, scoring='accuracy')\nprint(\"Cross-Validated Accuracy:\", np.mean(cv_scores))\n\n# Predict on Test Data\nX_test = scaler.transform(test[features])\ntest['sii'] = model.predict(X_test)\n\n# Save Submission File\nsubmission = test[['id', 'sii']]\nsubmission.to_csv('submission.csv', index=False)\nprint(\"Submission file saved as 'submission.csv'\")\n","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}