4c14b496bb5d1a4dfb92a3f32d3478c9233bcc8a,deepchem/models/tests/test_api.py,TestModelAPI,test_singletask_sklearn_rf_ECFP_regression_sharded_API,#TestModelAPI#,136

Before Change

    Test of singletask RF ECFP regression API: sharded edition.
    splittype = "scaffold"
    featurizer = CircularFingerprint(size=1024)
    model_params = {}
    tasks = ["label"]
    task_type = "regression"
    task_types = {task: task_type for task in tasks}
    input_file = os.path.join(
        self.current_dir, "../../../datasets/pdbbind_core_df.pkl.gz")

    loader = DataLoader(tasks=tasks,
                        smiles_field=self.smiles_field,
                        featurizer=featurizer,
                        verbosity="low")
    dataset = loader.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 = []
    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)
    // We set shard size above to force the creation of multiple shards of the data.
    // pdbbind_core has ~200 examples.
    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)]

    model = SklearnModel(tasks, task_types, model_params, self.model_dir,
                         mode="regression",
                         model_instance=RandomForestRegressor())

    // Fit trained model
    model.fit(train_dataset)
    model.save()

After Change

                          Metric(metrics.mean_squared_error),
                          Metric(metrics.mean_absolute_error)]

    sklearn_model = RandomForestRegressor()
    model = SklearnModel(sklearn_model, self.model_dir)

    // Fit trained model
    model.fit(train_dataset)
    model.save()

Instances