wrote load from two files function to handle nci dataset

import sys

import numpy as np

import shutil

from deepchem.utils.save import load_from_disk

from deepchem.utils.save import load_twofiles_from_disk

from deepchem.datasets import Dataset

from deepchem.featurizers.featurize import DataFeaturizer

from deepchem.featurizers.fingerprints import CircularFingerprint

  # Load nci dataset

  print("About to load NCI dataset.")

  dataset_file = os.path.join(

      current_dir, "../../datasets/nci.csv.gz")

  print(dataset_file)

  dataset = load_from_disk(dataset_file)

  dataset_file1_path = os.path.join(

      current_dir, "../../datasets/nci_1.csv.gz")

  dataset_file2_path = os.path.join(

      current_dir, "../../datasets/nci_2.csv.gz")

  dataset = load_twofiles_from_disk(dataset_file1_path, dataset_file2_path)

  print("Columns of dataset: %s" % str(dataset.columns.values))

  print("Number of examples in dataset: %s" % str(dataset.shape[0]))

  else:

    raise ValueError("Unrecognized filetype for %s" % filename)

# Only handles *.csv.gz files

def load_twofiles_from_disk(filename1, filename2):

  """Load a dataset from file."""

  name1 = filename1

  name2 = filename2

  filenameList = []

  filenameList.append(name1)

  filenameList.append(name2)

  dataframeList = []

  for name in filenameList:

    placeholderName = name

    if os.path.splitext(name)[1] == ".gz":

      #pandas read_csv() method handles gzipped csv files 

      name = os.path.splitext(name)[0]

    if os.path.splitext(name)[1] == ".csv":

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

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

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

      dataframeList.append(df)

    else:

      raise ValueError("Unrecognized filetype for %s" % filename)

  combined_df = dataframeList[0].append(dataframeList[1])

  return combined_df

def load_pickle_from_disk(filename):

  """Load dataset from pickle file."""

  if ".gz" in filename: