Merge branch 'user_defined_features' of https://github.com/joegomes/deepchem

    df["smiles"] = ori_df[[self.smiles_field]]

    for task in self.tasks:

      df[task] = ori_df[[task]]

    if self.split_field is not None:

      for feature in self.user_specified_features:

        df[feature] = ori_df[[feature]]

    if self.split_field is not None:

      df["split"] = ori_df[[self.split_field]]

    if self.protein_pdb_field is not None:

  if feature_files is None:

    print("About to featurize.")

    feature_files = featurizer.featurize(input_file, feature_types,

                                         feature_dir, shard_size=8)

    samples = featurizer.featurize(input_file, feature_dir,

                                   samples_dir, shard_size=8)

    print("Completed Featurization")

  else:

    # Transform data into arrays for ML

    samples = FeaturizedSamples(samples_dir, feature_files,

                                reload_data=False)

  # Split into train/test

  train_samples, test_samples = samples.train_test_split(

      splittype, train_dir, test_dir)