style change (6d91f03c) · Commits · 钟慕尧 / deepchem

deepchem/molnet/check_availability.py

+122 −124

Original line number	Diff line number	Diff line
		@@ -62,7 +62,6 @@ CheckFeaturizer = {
		('toxcast', 'rf'): ['ECFP', 1024],
		('toxcast', 'irv'): ['ECFP', 1024],
		('toxcast', 'graphconv'): ['GraphConv', 75],

		('bace_r', 'tf_regression'): ['ECFP', 1024],
		('bace_r', 'rf_regression'): ['ECFP', 1024],
		('bace_r', 'graphconvreg'): ['GraphConv', 75],
		@@ -90,7 +89,6 @@ CheckFeaturizer = {
		('sampl', 'tf_regression'): ['ECFP', 1024],
		('sampl', 'rf_regression'): ['ECFP', 1024],
		('sampl', 'graphconvreg'): ['GraphConv', 75],

		('kaggle', 'tf_regression'): [None, 14293],
		('kaggle', 'rf_regression'): [None, 14293],
		('pdbbind', 'tf_regression'): ['grid', 2052],

deepchem/molnet/load_function/bace_datasets.py

+15 −10

Original line number	Diff line number	Diff line
		@@ -9,6 +9,7 @@ import os
		import deepchem
		from deepchem.molnet.load_function.bace_features import bace_user_specified_features


		def load_bace_regression(featurizer=None, split='random'):
		"""Load bace datasets."""
		# Featurize bace dataset
		@@ -34,7 +35,8 @@ def load_bace_regression(featurizer=None, split='random'):
		elif featurizer == 'Raw':
		featurizer = deepchem.feat.RawFeaturizer()
		elif featurizer == None:
		featurizer = deepchem.feat.UserDefinedFeaturizer(bace_user_specified_features)
		featurizer = deepchem.feat.UserDefinedFeaturizer(
		bace_user_specified_features)

		loader = deepchem.data.CSVLoader(
		tasks=bace_tasks, smiles_field="mol", featurizer=featurizer)
		@@ -42,7 +44,8 @@ def load_bace_regression(featurizer=None, split='random'):
		dataset = loader.featurize(dataset_file, shard_size=8192)
		# Initialize transformers
		transformers = [
		deepchem.trans.NormalizationTransformer(transform_y=True, dataset=dataset)
		deepchem.trans.NormalizationTransformer(
		transform_y=True, dataset=dataset)
		]

		print("About to transform data")
		@@ -57,6 +60,7 @@ def load_bace_regression(featurizer=None, split='random'):
		train, valid, test = splitter.train_valid_test_split(dataset)
		return bace_tasks, (train, valid, test), transformers


		def load_bace_classification(featurizer=None, split='random'):
		"""Load bace datasets."""
		# Featurize bace dataset
		@@ -82,7 +86,8 @@ def load_bace_classification(featurizer=None, split='random'):
		elif featurizer == 'Raw':
		featurizer = deepchem.feat.RawFeaturizer()
		elif featurizer == None:
		featurizer = deepchem.feat.UserDefinedFeaturizer(bace_user_specified_features)
		featurizer = deepchem.feat.UserDefinedFeaturizer(
		bace_user_specified_features)

		loader = deepchem.data.CSVLoader(
		tasks=bace_tasks, smiles_field="mol", featurizer=featurizer)

deepchem/molnet/load_function/bace_features.py

+221 −1

File changed.

Preview size limit exceeded, changes collapsed.

deepchem/molnet/load_function/hopv_datasets.py

+4 −3

Original line number	Diff line number	Diff line
		@@ -44,7 +44,8 @@ def load_hopv(featurizer='ECFP', split='index'):

		# Initialize transformers
		transformers = [
		deepchem.trans.NormalizationTransformer(transform_y=True, dataset=dataset)
		deepchem.trans.NormalizationTransformer(
		transform_y=True, dataset=dataset)
		]

		print("About to transform data")

deepchem/molnet/load_function/qm7_datasets.py

+8 −4

Original line number	Diff line number	Diff line
		@@ -20,8 +20,10 @@ def load_qm7_from_mat(featurizer=None, split='stratified'):
		dataset_file = os.path.join(data_dir, "qm7.mat")

		if not os.path.exists(dataset_file):
		os.system('wget -P ' + data_dir +
		' http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/qm7.mat')
		os.system(
		'wget -P ' + data_dir +
		' http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/qm7.mat'
		)

		dataset = scipy.io.loadmat(dataset_file)

		@@ -64,8 +66,10 @@ def load_qm7b_from_mat(featurizer=None, split='stratified'):
		dataset_file = os.path.join(data_dir, "qm7b.mat")

		if not os.path.exists(dataset_file):
		os.system('wget -P ' + data_dir +
		' http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/qm7b.mat')
		os.system(
		'wget -P ' + data_dir +
		' http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/qm7b.mat'
		)
		dataset = scipy.io.loadmat(dataset_file)

		X = dataset['X']

Admin message