ee2bc2a8daaba5717e49917831ddf8229d1ebe70,deepchem/hyperparameters/tests/test_hyperparam_opt.py,TestHyperparamOptAPI,test_singletask_sklearn_rf_ECFP_regression_hyperparam_opt,#TestHyperparamOptAPI#,49

Before Change

    Test of hyperparam_opt with singletask RF ECFP regression API.
    splittype = "scaffold"
    compound_featurizers = [CircularFingerprint(size=1024)]
    complex_featurizers = []
    input_transformer_classes = []
    output_transformer_classes = [NormalizationTransformer]
    tasks = ["log-solubility"]
    task_type = "regression"
    task_types = {task: task_type for task in tasks}
    input_file = "example.csv"
    train_dataset, valid_dataset, _, output_transformers, = \
        self._featurize_train_test_split(
            splittype, compound_featurizers, 
            complex_featurizers, input_transformer_classes,
            output_transformer_classes, input_file, tasks)
    params_dict = {
      "n_estimators": [10, 100],
      "max_features": ["auto"],
      "data_shape": train_dataset.get_data_shape()

After Change

    train_dataset, valid_dataset, test_dataset = splitter.train_valid_test_split(
        dataset, self.train_dir, self.valid_dir, self.test_dir)

    input_transformers = []
    output_transformers = [
        NormalizationTransformer(transform_y=True, dataset=train_dataset)]
    transformers = input_transformers + output_transformers
    for dataset in [train_dataset, test_dataset]:
      for transformer in transformers:
        transformer.transform(dataset)
    params_dict = {
      "n_estimators": [10, 100],
      "max_features": ["auto"],
      "data_shape": train_dataset.get_data_shape()

Instances