Cleanup (c5ac7e0c) · Commits · 钟慕尧 / deepchem

deepchem/datasets/init.py

+0 −6

Original line number	Diff line number	Diff line
		@@ -478,9 +478,6 @@ class Dataset(object):
		metadata_rows=metadata_rows,
		verbosity=self.verbosity)

		# TODO(rbharath): A subtle bug seems to arise with this. When splitting data,
		# we seem to get many shards that have no data. Can we make it so that empty
		# shards are removed?
		def to_singletask(self, task_dirs):
		"""Transforms multitask dataset in collection of singletask datasets."""
		tasks = self.get_task_names()
		@@ -502,10 +499,7 @@ class Dataset(object):
		w_nonzero = np.reshape(w_task[w_task != 0], (num_datapoints, 1))
		ids_nonzero = ids[w_task != 0]

		######################################################################## DEBUG
		# Control for case when this task has no data in this shard.
		if X_nonzero.size > 0:
		######################################################################## DEBUG
		task_metadata_rows[task].append(
		Dataset.write_data_to_disk(
		task_dirs[task_num], basename, [task],

+0 −9

Original line number	Diff line number	Diff line
		@@ -51,16 +51,7 @@ class SingletaskToMultitask(Model):
		shutil.rmtree(task_data_dir)
		os.makedirs(task_data_dir)
		task_data_dirs.append(task_data_dir)
		############################################################# DEBUG
		print("_create_task_datasets")
		print("task_data_dirs")
		print(task_data_dirs)
		############################################################# DEBUG
		task_datasets = dataset.to_singletask(task_data_dirs)
		############################################################# DEBUG
		print("[task_dataset.data_dir for task_dataset in task_datasets]")
		print([task_dataset.data_dir for task_dataset in task_datasets])
		############################################################# DEBUG
		if self.verbosity is not None:
		for task, task_dataset in zip(self.tasks, task_datasets):
		log("Dataset for task %s has shape %s"