autogluon-tabular

import pandas as pd from autogluon.tabular import TabularPredictor, TabularDataset # Create dummy dataframes if not using S3 URLs for demonstration train_data = pd.DataFrame({ 'feature_1': [1, 2, 3, 4, 5], 'feature_2': ['A', 'B', 'A', 'C', 'B'], 'target_column': [0, 1, 0, 1, 0] }) test_data = pd.DataFrame({ 'feature_1': [6, 7], 'feature_2': ['C', 'A'] }) # Or load directly from AutoGluon's S3 bucket (uncomment for real usage) # data_root = 'https://autogluon.s3.amazonaws.com/datasets/Inc/' # train_data = TabularDataset(data_root + 'train.csv') # test_data = TabularDataset(data_root + 'test.csv') # Initialize and train the predictor predictor = TabularPredictor(label='target_column', path='./AutogluonModels').fit(train_data, presets='best') # Make predictions predictions = predictor.predict(test_data) print("Predictions:\n", predictions) # Evaluate the model (requires a label column in test_data, not present in dummy test_data) # Assuming test_data_with_labels exists: # test_data_with_labels = pd.DataFrame({ # 'feature_1': [6, 7], # 'feature_2': ['C', 'A'], # 'target_column': [1, 0] # }) # leaderboards = predictor.leaderboard(test_data_with_labels, silent=True) # print("Leaderboard:\n", leaderboards)