flaml_automl_iris_classification_with_hyperparameter_tuning.py

1from flaml import AutoML
2from sklearn.datasets import load_iris
3from sklearn.model_selection import train_test_split
4
5# Load the dataset
6X, y = load_iris(return_X_y=True)
7X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)
8
9# Initialize an AutoML instance
10automl = AutoML()
11
12# Specify automl run settings
13settings = {
14    "time_budget": 10,  # total running time in seconds
15    "metric": 'accuracy',  # primary metric
16    "task": 'classification',  # task type
17    "log_file_name": 'iris.log',  # flaml log file
18}
19
20# Train with AutoML
21automl.fit(X_train=X_train, y_train=y_train, **settings)
22
23# Predict
24print(automl.predict(X_test))
25
26# Export the best model
27print('Best ML learner:', automl.best_estimator)
28print('Best hyperparameter config:', automl.best_config)
29print('Best accuracy on validation data: {0:.4g}'.format(1 - automl.best_loss))
30print('Training duration of best run: {0:.4g} s'.format(automl.best_config_train_time))