4a1b752726028f02bd04fc7b766b048a859e7f97,deepchem/models/tests/test_api.py,TestModelAPI,test_singletask_sklearn_rf_ECFP_regression_sharded_API,#TestModelAPI#,113

Before Change

    task_type = "regression"
    task_types = {task: task_type for task in tasks}
    input_file = "../../../datasets/pdbbind_core_df.pkl.gz"
    train_dataset, test_dataset, _, transformers = self._featurize_train_test_split(
        splittype, featurizers, input_transformers, output_transformers,
        input_file, tasks, shard_size=50)
    // We set shard size above to force the creation of multiple shards of the data.

After Change

    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")

    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)
    //train_dataset, test_dataset, _, transformers = self._featurize_train_test_split(
    //    splittype, featurizers, input_transformers, output_transformers,
    //    input_file, tasks, shard_size=50)
    input_transformers = []

Instances