How to use the deepchem.utils.save.load_from_disk function in deepchem

def get_data_shape(self):
    """
    Gets array shape of datapoints in this dataset.
    """
    if not len(self.metadata_df):
      raise ValueError("No data in dataset.")
    sample_X = load_from_disk(
        os.path.join(self.data_dir, next(self.metadata_df.iterrows())[1]['X']))
    return np.shape(sample_X)[1:]

def get_shard_size(self):
    """Gets size of shards on disk."""
    if not len(self.metadata_df):
      raise ValueError("No data in dataset.")
    sample_y = load_from_disk(
        os.path.join(
            self.data_dir,
            self.metadata_df.iterrows().next()[1]['y-transformed']))
    return len(sample_y)

def get_shard(self, i):
    """Retrieves data for the i-th shard from disk."""
    row = self.metadata_df.iloc[i]
    X = np.array(load_from_disk(
        os.path.join(self.data_dir, row['X-transformed'])))
    y = np.array(load_from_disk(
        os.path.join(self.data_dir, row['y-transformed'])))
    w = np.array(load_from_disk(
        os.path.join(self.data_dir, row['w-transformed'])))
    ids = np.array(load_from_disk(
        os.path.join(self.data_dir, row['ids'])), dtype=object)
    return (X, y, w, ids)

def get_shard(self, i):
    """Retrieves data for the i-th shard from disk."""
    row = self.metadata_df.iloc[i]
    X = np.array(load_from_disk(os.path.join(self.data_dir, row['X'])))

    if row['y'] is not None:
      y = np.array(load_from_disk(os.path.join(self.data_dir, row['y'])))
    else:
      y = None

    if row['w'] is not None:
      # TODO (ytz): Under what condition does this exist but the file itself doesn't?
      w_filename = os.path.join(self.data_dir, row['w'])
      if os.path.exists(w_filename):
        w = np.array(load_from_disk(w_filename))
      else:
        if len(y.shape) == 1:
          w = np.ones(y.shape[0], np.float32)
        else:
          w = np.ones((y.shape[0], 1), np.float32)
    else:
      w = None

    ids = np.array(
        load_from_disk(os.path.join(self.data_dir, row['ids'])), dtype=object)
    return (X, y, w, ids)

def _update_mean_and_std(self, df, X_stats, y_stats):
    """
    Compute means/stds of X/y from sums/sum_squares of tensors.
    """
    if X_stats:
      X_transform = []
      for _, row in df.iterrows():
        Xt = load_from_disk(os.path.join(self.data_dir, row['X-transformed']))
        Xs = np.sum(Xt,axis=0)
        Xss = np.sum(np.square(Xt),axis=0)
        save_to_disk(Xs, os.path.join(self.data_dir, row['X_sums']))
        save_to_disk(Xss, os.path.join(self.data_dir, row['X_sum_squares']))

    if y_stats:
      y_transform = []
      for _, row in df.iterrows():
        yt = load_from_disk(os.path.join(self.data_dir, row['y-transformed']))
        ys = np.sum(yt,axis=0)
        yss = np.sum(np.square(yt),axis=0)
        save_to_disk(ys, os.path.join(self.data_dir, row['y_sums']))
        save_to_disk(yss, os.path.join(self.data_dir, row['y_sum_squares']))

if not reload:
    if os.path.exists(base_dir):
      shutil.rmtree(base_dir)
  if not os.path.exists(base_dir):
    os.makedirs(base_dir)
  current_dir = os.path.dirname(os.path.realpath(__file__))
  #Make directories to store the raw and featurized datasets.
  data_dir = os.path.join(base_dir, "dataset")
  train_dir = os.path.join(base_dir, "train_dataset")
  valid_dir = os.path.join(base_dir, "valid_dataset")

  # Load SWEET dataset
  print("About to load SWEET dataset.")
  dataset_file = os.path.join(
      current_dir, "./sweet.csv.gz")
  dataset = load_from_disk(dataset_file)
  print("Columns of dataset: %s" % str(dataset.columns.values))
  print("Number of examples in dataset: %s" % str(dataset.shape[0]))

  # Featurize SWEET dataset
  print("About to featurize SWEET dataset.")
  featurizer = CircularFingerprint(size=1024)
  SWEET_tasks = dataset.columns.values[1:].tolist()

  loader = DataLoader(tasks=SWEET_tasks,
                      smiles_field="smiles",
                      featurizer=featurizer,
                      verbosity=verbosity)
  if not reload or not os.path.exists(data_dir):
    dataset = loader.featurize(dataset_file, data_dir)
    regen = True
  else:

def load_sider_convmol():
  """Load SIDER datasets. Does not do train/test split"""
  # Featurize SIDER dataset
  print("About to featurize SIDER dataset.")
  current_dir = os.path.dirname(os.path.realpath(__file__))
  dataset_file = os.path.join(
      current_dir, "../sider/sider.csv.gz")
  featurizer = dc.feat.ConvMolFeaturizer()

  dataset = dc.utils.save.load_from_disk(dataset_file)
  SIDER_tasks = dataset.columns.values[1:].tolist()
  print("SIDER tasks: %s" % str(SIDER_tasks))
  print("%d tasks in total" % len(SIDER_tasks))


  loader = dc.data.CSVLoader(
      tasks=SIDER_tasks, smiles_field="smiles", featurizer=featurizer)
  dataset = loader.featurize(dataset_file)
  print("%d datapoints in SIDER dataset" % len(dataset))

  # Initialize transformers
  transformers = [
      dc.trans.BalancingTransformer(transform_w=True, dataset=dataset)]
  print("About to transform data")
  for transformer in transformers:
    dataset = transformer.transform(dataset)

def __len__(self):
    """
    Finds number of elements in dataset.
    """
    total = 0
    for _, row in self.metadata_df.iterrows():
      y = load_from_disk(os.path.join(self.data_dir, row['ids']))
      total += len(y)
    return total

if row['w'] is not None:
      # TODO (ytz): Under what condition does this exist but the file itself doesn't?
      w_filename = os.path.join(self.data_dir, row['w'])
      if os.path.exists(w_filename):
        w = np.array(load_from_disk(w_filename))
      else:
        if len(y.shape) == 1:
          w = np.ones(y.shape[0], np.float32)
        else:
          w = np.ones((y.shape[0], 1), np.float32)
    else:
      w = None

    ids = np.array(
        load_from_disk(os.path.join(self.data_dir, row['ids'])), dtype=object)
    return (X, y, w, ids)

def load_sider(featurizer='ECFP', split='index'):
  current_dir = os.path.dirname(os.path.realpath(__file__))

	  # Load SIDER dataset
  print("About to load SIDER dataset.")
  dataset_file = os.path.join(
      current_dir, "./sider.csv.gz")
  dataset = dc.utils.save.load_from_disk(dataset_file)
  print("Columns of dataset: %s" % str(dataset.columns.values))
  print("Number of examples in dataset: %s" % str(dataset.shape[0]))

  # Featurize SIDER dataset
  print("About to featurize SIDER dataset.")
  if featurizer == 'ECFP':
    featurizer_func = dc.feat.CircularFingerprint(size=1024)
  elif featurizer == 'GraphConv':
    featurizer_func = dc.feat.ConvMolFeaturizer()

  SIDER_tasks = dataset.columns.values[1:].tolist()
  print("SIDER tasks: %s" % str(SIDER_tasks))
  print("%d tasks in total" % len(SIDER_tasks))

  loader = dc.load.DataLoader(tasks=SIDER_tasks,
                              smiles_field="smiles",