changed load disk method to accept list of multiple csv files and other random small issues

import sys

import numpy as np

import shutil

from deepchem.utils.save import load_twofiles_from_disk

from deepchem.utils.save import load_multfiles_from_disk

from deepchem.datasets import Dataset

from deepchem.featurizers.featurize import DataFeaturizer

from deepchem.featurizers.fingerprints import CircularFingerprint

      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)

  dataset_paths = [dataset_file1_path, dataset_file2_path]

  dataset = load_multfiles_from_disk(dataset_paths)

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

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

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

  return combined_df

def load_multfiles_from_disk(filenameList):

  """Load a dataset from multiple files. Each file MUST have same column headers"""

  dataframeList = []

  for name in filenameList:

    placeholderName = name

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

      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)

  #combine dataframes

  combined_df = dataframeList[0]

  for i in range(0, len(dataframeList) - 1):

    combined_df = combined_df.append(dataframeList[i+1])

  combined_df = combined_df.reset_index(drop=True)  

  return combined_df

def load_pickle_from_disk(filename):

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

  if ".gz" in filename:

    with open(filename, "rb") as f:

      df = pickle.load(f)

  return df

reload = False

verbosity = "high"

#base_data_dir = "/scratch/users/rbharath/muv"

base_data_dir = "/home/apappu/deepchem/examples/nci/dataset"

nci_tasks, dataset, transformers = load_nci(

os.makedirs(model_dir)

def model_builder(tasks, task_types, model_params, model_dir, verbosity=None):

  return SklearnModel(tasks, task_types, model_params, model_dir,

                      #model_instance=LogisticRegression(class_weight="balanced"),

                      model_instance=RandomForestClassifier(

                          class_weight="balanced",

                          n_estimators=500),