A decision tree classifier is a simple machine learning model suitable for getting started with classification tasks. Refer to the chapter on decision tree regression for background on decision trees.
import graphlab as gl # Load the data # The data can be downloaded using data = gl.SFrame.read_csv('https://static.turi.com/datasets/xgboost/mushroom.csv') # Label 'c' is edible data['label'] = data['label'] == 'c' # Make a train-test split train_data, test_data = data.random_split(0.8) # Create a model. model = gl.decision_tree_classifier.create(train_data, target='label', max_depth = 3) # Save predictions to an SArray. predictions = model.predict(test_data) # Evaluate the model and save the results into a dictionary results = model.evaluate(test_data)
We can visualize the models using
model.show(view="Tree", tree_id=0) model.show(view="Tree", tree_id=1)
Refer to the earlier chapters for the following features: