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

    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 = []
    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)]

Instances