h2o_random_forest_iris_classification_quickstart.py

1import h2o
2from h2o.estimators import H2ORandomForestEstimator
3
4# Initialize the H2O cluster
5h2o.init()
6
7# Import the iris dataset
8path = "https://raw.githubusercontent.com/h2oai/h2o-3/master/h2o-py/datasets/iris_wheader.csv"
9iris = h2o.import_file(path)
10
11# Split the data into training and testing sets
12train, test = iris.split_frame(ratios=[0.8])
13
14# Define features and response
15x = iris.columns[:-1]
16y = iris.columns[-1]
17
18# Initialize and train the model
19model = H2ORandomForestEstimator(ntrees=50, max_depth=20, nbins=100)
20model.train(x=x, y=y, training_frame=train)
21
22# View model performance
23performance = model.model_performance(test)
24print(performance)