4a1b752726028f02bd04fc7b766b048a859e7f97,deepchem/models/tests/test_api.py,TestModelAPI,test_singletask_sklearn_rf_user_specified_regression_API,#TestModelAPI#,74

Before Change

  def test_singletask_sklearn_rf_user_specified_regression_API(self):
    Test of singletask RF USF regression API.
    splittype = "specified"
    split_field = "split"
    featurizers = []
    input_transformers = []
    output_transformers = [NormalizationTransformer]
    model_params = {}
    tasks = ["log-solubility"]
    task_type = "regression"
    task_types = {task: task_type for task in tasks}
    input_file = "user_specified_example.csv"
    user_specified_features = ["user-specified1", "user-specified2"]
    train_dataset, test_dataset, _, transformers, = self._featurize_train_test_split(
        splittype, featurizers, 
        input_transformers, output_transformers, input_file, tasks,
        user_specified_features=user_specified_features,
        split_field=split_field)
    model_params["data_shape"] = train_dataset.get_data_shape()
    regression_metrics = [Metric(metrics.r2_score),
                          Metric(metrics.mean_squared_error),
                          Metric(metrics.mean_absolute_error)]

After Change

    train_dataset, test_dataset = splitter.train_test_split(
        dataset, self.train_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)

    model_params["data_shape"] = train_dataset.get_data_shape()
    regression_metrics = [Metric(metrics.r2_score),
                          Metric(metrics.mean_squared_error),
                          Metric(metrics.mean_absolute_error)]

Instances