4a1b752726028f02bd04fc7b766b048a859e7f97,deepchem/models/tests/test_api.py,TestModelAPI,test_singletask_sklearn_rf_RDKIT_descriptor_regression_API,#TestModelAPI#,150

Before Change

    Test of singletask RF RDKIT-descriptor regression API.
    splittype = "scaffold"
    featurizers = [RDKitDescriptors()]
    input_transformers = [NormalizationTransformer, ClippingTransformer]
    output_transformers = [NormalizationTransformer]
    tasks = ["log-solubility"]
    task_type = "regression"
    task_types = {task: task_type for task in tasks}
    model_params = {}
    input_file = "example.csv"
    train_dataset, test_dataset, _, transformers = self._featurize_train_test_split(
        splittype, featurizers, input_transformers, output_transformers,
        input_file, tasks)
    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

    task_type = "regression"
    task_types = {task: task_type for task in tasks}
    model_params = {}
    input_file = os.path.join(self.current_dir, "example.csv")
    featurizer = DataFeaturizer(tasks=tasks,
                                smiles_field=self.smiles_field,
                                featurizers=featurizers,
                                verbosity="low")
    dataset = featurizer.featurize(input_file, self.data_dir)

    splitter = ScaffoldSplitter()
    train_dataset, test_dataset = splitter.train_test_split(
        dataset, self.train_dir, self.test_dir)

    input_transformers = [
        NormalizationTransformer(transform_X=True, dataset=train_dataset),
        ClippingTransformer(transform_X=True, dataset=train_dataset)]

Instances