Improve PCBA comments; ran yapf (58e6eb13) · Commits · 钟慕尧 / deepchem

examples/pcba/pcba_datasets.py

+42 −37

Original line number	Diff line number	Diff line
		@@ -10,8 +10,9 @@ import numpy as np
		import shutil
		import deepchem as dc


		def load_pcba(featurizer='ECFP', split='random'):
		"""Load PCBA datasets. Does not do train/test split"""
		"""Load PCBA datasets."""

		current_dir = os.path.dirname(os.path.realpath(__file__))
		print("About to load PCBA dataset.")
		@@ -48,7 +49,8 @@ def load_pcba(featurizer='ECFP', split='random'):
		'PCBA-720711', 'PCBA-743255', 'PCBA-743266', 'PCBA-875', 'PCBA-881',
		'PCBA-883', 'PCBA-884', 'PCBA-885', 'PCBA-887', 'PCBA-891', 'PCBA-899',
		'PCBA-902', 'PCBA-903', 'PCBA-904', 'PCBA-912', 'PCBA-914', 'PCBA-915',
		'PCBA-924','PCBA-925','PCBA-926','PCBA-927','PCBA-938','PCBA-995']
		'PCBA-924', 'PCBA-925', 'PCBA-926', 'PCBA-927', 'PCBA-938', 'PCBA-995'
		]

		loader = dc.data.CSVLoader(
		tasks=PCBA_tasks, smiles_field="smiles", featurizer=featurizer)
		@@ -56,15 +58,18 @@ def load_pcba(featurizer='ECFP', split='random'):
		dataset = loader.featurize(dataset_file)
		# Initialize transformers
		transformers = [
		dc.trans.BalancingTransformer(transform_w=True, dataset=dataset)]
		dc.trans.BalancingTransformer(transform_w=True, dataset=dataset)
		]

		print("About to transform data")
		for transformer in transformers:
		dataset = transformer.transform(dataset)

		splitters = {'index': dc.splits.IndexSplitter(),
		splitters = {
		'index': dc.splits.IndexSplitter(),
		'random': dc.splits.RandomSplitter(),
		'scaffold': dc.splits.ScaffoldSplitter()}
		'scaffold': dc.splits.ScaffoldSplitter()
		}
		splitter = splitters[split]
		print("Performing new split.")
		train, valid, test = splitter.train_valid_test_split(dataset)

Admin message