WandB Ray Tune Nested Config Test Case

raytune-nested-test.py

import wandb
from wandb.sweeps.config import tune
from wandb.sweeps.config.tune.suggest.hyperopt import HyperOptSearch
from wandb.sweeps.config.hyperopt import hp

tune_config = tune.run(
    'example.py',
    search_alg=HyperOptSearch(
        hp.choice('classifier_type', [
            {
                'type': 'naive_bayes',
            },
            {
                'type': 'svm',
                'C': hp.uniform('svm_C', 0, 1),
                'kernel': hp.choice('svm_kernel', [
                    {'ktype': 'linear'},
                    {'ktype': 'RBF', 'width': hp.uniform('svm_rbf_width', 0, 1)},
                ]),
            },
            {
                'type': 'dtree',
                'criterion': hp.choice('dtree_criterion', ['gini', 'entropy']),
                'max_depth': hp.choice('dtree_max_depth',
                                       [None, hp.uniform('dtree_max_depth_int', 3, 1, 1)]),
                'min_samples_split': hp.uniform('dtree_min_samples_split', 2, 1, 1),
            },
        ]),
        metric="valid/accuracy",
        mode="max"),
    num_samples=100)

# Save sweep as yaml config file
tune_config.save("raytune-nested-test.yaml")

# Create the sweep
wandb.sweep(tune_config)