{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.12.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[],"dockerImageVersionId":28755,"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\n\n# Use the kagglehub client library to attach Kaggle resources like competitions, datasets, and models to your session\n# Learn more about kagglehub: https://github.com/Kaggle/kagglehub/blob/main/README.md\n\nimport kagglehub\n# kagglehub.dataset_download('<owner>/<dataset-slug>')","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nfrom sklearn.model_selection import StratifiedKFold\nfrom sklearn.preprocessing import OneHotEncoder\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.metrics import roc_auc_score\n\n# 1. Load Datasets\ntrain = pd.read_csv('/kaggle/input/competitions/cat-in-the-dat-ii/train.csv')\ntest = pd.read_csv('/kaggle/input/competitions/cat-in-the-dat-ii/test.csv')\n\n# Separate target and IDs\ny_train = train['target'].values\ntest_ids = test['id'].values\n\ntrain_features = train.drop(columns=['id', 'target'])\ntest_features = test.drop(columns=['id'])\n\n# 2. Preprocess Missing Values\n# Treating missing values (NaN) as a distinct categorical state\nfeatures = list(train_features.columns)\nfor col in features:\n    train_features[col] = train_features[col].astype(str).fillna('missing')\n    test_features[col] = test_features[col].astype(str).fillna('missing')\n\n# 3. One-Hot Encoding\n# Encode all features into a sparse matrix\nohe = OneHotEncoder(handle_unknown='ignore', sparse_output=True)\nX_train = ohe.fit_transform(train_features)\nX_test = ohe.transform(test_features)\n\n# 4. Out-of-Fold Cross-Validation with Logistic Regression\nn_splits = 5\nskf = StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=42)\n\noof_preds = np.zeros(len(train))\ntest_preds = np.zeros(len(test))\n\nprint(f\"Starting {n_splits}-Fold Cross-Validation...\")\n\nfor fold, (train_idx, val_idx) in enumerate(skf.split(X_train, y_train)):\n    X_tr, y_tr = X_train[train_idx], y_train[train_idx]\n    X_va, y_va = X_train[val_idx], y_train[val_idx]\n    \n    # Logistic Regression with C tuning for regularized sparse features\n    model = LogisticRegression(C=0.10, max_iter=1000, solver='lbfgs')\n    model.fit(X_tr, y_tr)\n    \n    val_probs = model.predict_proba(X_va)[:, 1]\n    oof_preds[val_idx] = val_probs\n    test_preds += model.predict_proba(X_test)[:, 1] / n_splits\n    \n    fold_auc = roc_auc_score(y_va, val_probs)\n    print(f\"Fold {fold + 1} ROC-AUC: {fold_auc:.5f}\")\n\noverall_auc = roc_auc_score(y_train, oof_preds)\nprint(f\"\\nOverall Out-Of-Fold ROC-AUC: {overall_auc:.5f}\")\n\n# 5. Save Submission File\nsubmission = pd.DataFrame({\n    'id': test_ids,\n    'target': test_preds\n})\nsubmission.to_csv('submission.csv', index=False)\nprint(\"Saved submission.csv successfully!\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-08-25T14:10:05.996124Z","iopub.execute_input":"2026-08-25T14:10:05.996453Z","iopub.status.idle":"2026-08-25T14:11:13.687348Z","shell.execute_reply.started":"2026-08-25T14:10:05.996420Z","shell.execute_reply":"2026-08-25T14:11:13.686545Z"}},"outputs":[],"execution_count":null}]}