h2o

import h2o from h2o.estimators.gbm import H2OGradientBoostingEstimator import pandas as pd # Initialize H2O cluster (adjust max_mem_size based on your system's RAM and data size) h2o.init(max_mem_size="4G", nthreads=-1) # Create a sample Pandas DataFrame data = { 'feature1': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10], 'feature2': [10, 9, 8, 7, 6, 5, 4, 3, 2, 1], 'target': [0, 1, 0, 1, 0, 1, 0, 1, 0, 1] } df_pandas = pd.DataFrame(data) # Convert Pandas DataFrame to H2OFrame df_h2o = h2o.H2OFrame(df_pandas) # Convert target to factor for classification problems df_h2o['target'] = df_h2o['target'].asfactor() # Define predictors and response variables predictors = ['feature1', 'feature2'] response = 'target' # Split data into training and testing sets train, test = df_h2o.split_frame(ratios=[0.7], seed=42) # Build a Gradient Boosting Machine (GBM) model gbm_model = H2OGradientBoostingEstimator( ntrees=50, max_depth=5, seed=42 ) gbm_model.train(x=predictors, y=response, training_frame=train) # Make predictions on the test set predictions = gbm_model.predict(test) print("\nPredictions on test data (first 5 rows):\n") print(predictions.head()) # Shutdown H2O cluster (crucial for resource management) h2o.shutdown(prompt=False)