ydf

import ydf import pandas as pd import os # Load dataset with Pandas ds_path = "https://raw.githubusercontent.com/google/yggdrasil-decision-forests/main/yggdrasil_decision_forests/test_data/dataset/" try: train_ds = pd.read_csv(f"{ds_path}adult_train.csv") test_ds = pd.read_csv(f"{ds_path}adult_test.csv") except Exception as e: print(f"Could not load datasets: {e}. Ensure internet connection or provide local paths.") exit() # Train a Gradient Boosted Trees model # 'label' is the target column for prediction. # verbose=0 to suppress training logs for cleaner output, default is 1. model = ydf.GradientBoostedTreesLearner(label="income", verbose=0).train(train_ds) # Evaluate the model print("Model Evaluation:") print(model.evaluate(test_ds)) # Generate predictions predictions = model.predict(test_ds) print("\nFirst 5 predictions:") print(predictions.head()) # Save and Load the model model_path = "/tmp/my_ydf_model" model.save(model_path) loaded_model = ydf.load_model(model_path) print(f"\nModel saved to '{model_path}' and reloaded successfully.")