{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":67356,"databundleVersionId":8006601,"sourceType":"competition"}],"dockerImageVersionId":30732,"isInternetEnabled":true,"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","execution":{"iopub.status.busy":"2024-06-15T11:56:32.389434Z","iopub.execute_input":"2024-06-15T11:56:32.389845Z","iopub.status.idle":"2024-06-15T11:56:33.546195Z","shell.execute_reply.started":"2024-06-15T11:56:32.389813Z","shell.execute_reply":"2024-06-15T11:56:33.545116Z"},"trusted":true},"execution_count":1,"outputs":[{"name":"stdout","text":"/kaggle/input/leash-BELKA/sample_submission.csv\n/kaggle/input/leash-BELKA/train.parquet\n/kaggle/input/leash-BELKA/test.parquet\n/kaggle/input/leash-BELKA/train.csv\n/kaggle/input/leash-BELKA/test.csv\n","output_type":"stream"}]},{"cell_type":"code","source":"import pandas as pd\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.metrics import average_precision_score\n\n# Load dataset with a more robust method\ntry:\n    data = pd.read_csv('/kaggle/input/leash-BELKA/train.csv', engine='python')\nexcept pd.errors.ParserError:\n    print(\"Error parsing the file. Check the file format and encoding.\")\n\n# Basic preprocessing\nif 'data' in locals():\n    X = data.drop(columns=['id', 'binds'])\n    y = data['binds']\n\n    # Train-test split\n    X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)\n\n    # Feature scaling\n    scaler = StandardScaler()\n    X_train_scaled = scaler.fit_transform(X_train)\n    X_val_scaled = scaler.transform(X_val)\n\n    # Train a simple logistic regression model\n    model = LogisticRegression(max_iter=1000)\n    model.fit(X_train_scaled, y_train)\n\n    # Evaluate the model\n    y_pred_proba = model.predict_proba(X_val_scaled)[:, 1]\n    average_precision = average_precision_score(y_val, y_pred_proba)\n    print(f'Average Precision: {average_precision}')\n\n    # Load test set and generate predictions\n    test_data = pd.read_csv('/kaggle/input/leash-BELKA/test.csv', engine='python')\n    X_test = test_data.drop(columns=['id'])\n    X_test_scaled = scaler.transform(X_test)\n    test_preds = model.predict_proba(X_test_scaled)[:, 1]\n\n    # Prepare submission file\n    submission = pd.DataFrame({\n        'id': test_data['id'],\n        'binds': test_preds\n    })\n    submission.to_csv('submission.csv', index=False)\nelse:\n    print(\"Failed to load data.\")","metadata":{"execution":{"iopub.status.busy":"2024-06-15T12:03:44.92797Z","iopub.execute_input":"2024-06-15T12:03:44.928409Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}