fixes to multitask

      for j in range(len(interval_points)-1):

        indices = range(interval_points[j], interval_points[j+1])

        y_pred_on_batch = self.predict_on_batch(X[indices, :])

        y_pred_on_batch = np.reshape(y_pred_on_batch, (len(indices),))

        #y_pred_on_batch = np.reshape(y_pred_on_batch, (len(indices),))

        y_preds.append(y_pred_on_batch)

      y_pred = np.concatenate(y_preds)

  add_model_command(subparsers)

  return parser.parse_args(input_args)

def shard_inputs(input_file):

  input_file_no_ext = os.path.splitext(input_file)

def featurize_inputs(feature_dir, data_dir, input_files,

                     user_specified_features, tasks, smiles_field,

                     split_field, id_field, threshold, protein_pdb_field, 

                              ligand_mol2_field=ligand_mol2_field,

                              user_specified_features=user_specified_features,

                              verbose=True)

  out = os.path.join(

      feature_dir, "%s.joblib" %(os.path.splitext(os.path.basename(input_file))[0]))

  featurizer.featurize(input_file, FeaturizedSamples.feature_types, out)

  featurizer.featurize(input_file, FeaturizedSamples.feature_types, feature_dir)

def train_test_split(input_transforms, output_transforms,

                     feature_types, splittype, data_dir):

import gzip

import cPickle as pickle

import pandas as pd

import numpy as np

def save_to_disk(dataset, filename):

  """Save a dataset to file."""

  else:

    # First line of user-specified CSV *must* be header.

    df = pd.read_csv(filename, header=0)

    df = df.replace(np.nan,str(""), regex=True)

    return df