Merge pull request #1348 from rbharath/bbbc2

      return NumpyDataset(images)

    else:

      # from_numpy currently requires labels. Make dummy labels

      labels = np.zeros(len(images))

      labels = np.zeros((len(images), 1))

      return DiskDataset.from_numpy(images, labels)

from __future__ import unicode_literals

from deepchem.molnet.load_function.bace_datasets import load_bace_classification, load_bace_regression

from deepchem.molnet.load_function.bbbc_datasets import load_bbbc001

from deepchem.molnet.load_function.bbbc_datasets import load_bbbc001, load_bbbc002

from deepchem.molnet.load_function.bbbp_datasets import load_bbbp

from deepchem.molnet.load_function.cell_counting_datasets import load_cell_counting

from deepchem.molnet.load_function.chembl_datasets import load_chembl

    deepchem.utils.save.save_dataset_to_disk(save_dir, train, valid, test,

                                             transformers)

  return bbbc001_tasks, all_dataset, transformers

def load_bbbc002(split='index', reload=True):

  """Load BBBC002 dataset

  This dataset contains data corresponding to 5 samples of Drosophilia Kc167

  cells. There are 10 fields of view for each sample, each an image of size

  512x512. Ground truth labels contain cell counts for this dataset. Full

  details about this dataset are present at

  https://data.broadinstitute.org/bbbc/BBBC002/.

  """

  # Featurize BBBC002 dataset

  bbbc002_tasks = ["cell-count"]

  data_dir = deepchem.utils.get_data_dir()

  if reload:

    save_dir = os.path.join(data_dir, "bbbc002/" + str(split))

    loaded, all_dataset, transformers = deepchem.utils.save.load_dataset_from_disk(

        save_dir)

    if loaded:

      return bbbc002_tasks, all_dataset, transformers

  dataset_file = os.path.join(data_dir, "BBBC002_v1_images.zip")

  labels_file = os.path.join(data_dir, "BBBC002_v1_counts.txt")

  if not os.path.exists(dataset_file):

    deepchem.utils.download_url(

        'https://data.broadinstitute.org/bbbc/BBBC002/BBBC002_v1_images.zip')

  if not os.path.exists(labels_file):

    deepchem.utils.download_url(

        'https://data.broadinstitute.org/bbbc/BBBC002/BBBC002_v1_counts.txt')

  # Featurize Images into NumpyArrays

  loader = deepchem.data.ImageLoader()

  dataset = loader.featurize(dataset_file, in_memory=False)

  # Load text file with labels

  with open(labels_file) as f:

    content = f.readlines()

  # Strip the first line which holds field labels

  lines = [x.strip() for x in content][1:]

  # Format is: Image_name count1 count2

  lines = [x.split("\t") for x in lines]

  counts = [(float(x[1]) + float(x[2])) / 2.0 for x in lines]

  y = np.reshape(np.array(counts), (len(counts), 1))

  ids = [x[0] for x in lines]

  # This is kludgy way to add y to dataset. Can be done better?

  dataset = deepchem.data.DiskDataset.from_numpy(dataset.X, y, ids=ids)

  if split == None:

    return bbbc002_tasks, (dataset, None, None), transformers

  splitters = {

      'index': deepchem.splits.IndexSplitter(),

      'random': deepchem.splits.RandomSplitter(),

  }

  if split not in splitters:

    raise ValueError("Only index and random splits supported.")

  splitter = splitters[split]

  train, valid, test = splitter.train_valid_test_split(dataset)

  all_dataset = (train, valid, test)

  if reload:

    deepchem.utils.save.save_dataset_to_disk(save_dir, train, valid, test,

                                             transformers)

  return bbbc002_tasks, all_dataset, transformers