Updating examples (b001cae8) · Commits · 钟慕尧 / deepchem

deepchem/utils/save.py

+0 −1

Original line number	Diff line number	Diff line
		@@ -143,4 +143,3 @@ def load_pickle_from_disk(filename):
		with open(filename, "rb") as f:
		df = pickle.load(f)
		return df

examples/delaney/delaney_datasets.py

+5 −7

Original line number	Diff line number	Diff line
		@@ -19,12 +19,11 @@ def load_delaney(featurizer='ECFP', split='index'):
		current_dir, "../../datasets/delaney-processed.csv")
		delaney_tasks = ['measured log solubility in mols per litre']
		if featurizer == 'ECFP':
		featurizer_func = dc.feat.CircularFingerprint(size=1024)
		featurizer = dc.feat.CircularFingerprint(size=1024)
		elif featurizer == 'GraphConv':
		featurizer_func = dc.feat.ConvMolFeaturizer()
		loader = dc.load.DataLoader(
		tasks=delaney_tasks, smiles_field="smiles",
		featurizer=featurizer_func, verbosity = 'high')
		featurizer = dc.feat.ConvMolFeaturizer()
		loader = dc.data.DataLoader(
		tasks=delaney_tasks, smiles_field="smiles", featurizer=featurizer)
		dataset = loader.featurize(
		dataset_file, shard_size=8192)

		@@ -40,6 +39,5 @@ def load_delaney(featurizer='ECFP', split='index'):
		'random': dc.splits.RandomSplitter(),
		'scaffold': dc.splits.ScaffoldSplitter()}
		splitter = splitters[split]
		train, valid, test = splitter.train_valid_test_split(dataset,
		compute_feature_statistics=False)
		train, valid, test = splitter.train_valid_test_split(dataset)
		return delaney_tasks, (train, valid, test), transformers

examples/kaggle/kaggle_datasets.py

+2 −3

Original line number	Diff line number	Diff line
		@@ -50,9 +50,8 @@ def load_kaggle(shard_size=2000, num_shards_per_batch=4,
		'NK1', 'OX1', 'OX2', 'PGP', 'PPB', 'RAT_F', 'TDI',
		'THROMBIN']

		loader = dc.load.DataLoader(
		tasks=KAGGLE_tasks, id_field="Molecule",
		featurizer=featurizer, verbosity="high")
		loader = dc.data.DataLoader(
		tasks=KAGGLE_tasks, id_field="Molecule", featurizer=featurizer)
		train_datasets, valid_datasets, test_datasets = [], [], []
		print("Featurizing train datasets")
		train_dataset = loader.featurize(

examples/low_data/datasets.py

+12 −20

Original line number	Diff line number	Diff line
		@@ -29,9 +29,8 @@ def load_tox21_ecfp(num_train=7200):
		'NR-ER-LBD', 'NR-PPAR-gamma', 'SR-ARE', 'SR-ATAD5',
		'SR-HSE', 'SR-MMP', 'SR-p53']

		loader = dc.load.DataLoader(
		tasks=tox21_tasks, smiles_field="smiles", featurizer=featurizer,
		verbosity="high")
		loader = dc.data.DataLoader(
		tasks=tox21_tasks, smiles_field="smiles", featurizer=featurizer)
		dataset = loader.featurize(
		dataset_file, shard_size=8192)

		@@ -59,9 +58,8 @@ def load_tox21_convmol(base_dir=None, num_train=7200):
		'NR-ER-LBD', 'NR-PPAR-gamma', 'SR-ARE', 'SR-ATAD5',
		'SR-HSE', 'SR-MMP', 'SR-p53']

		loader = dc.load.DataLoader(
		tasks=tox21_tasks, smiles_field="smiles",
		featurizer=featurizer, verbosity="high")
		loader = dc.data.DataLoader(
		tasks=tox21_tasks, smiles_field="smiles", featurizer=featurizer)
		dataset = loader.featurize(
		dataset_file, shard_size=8192)

		@@ -90,9 +88,8 @@ def load_muv_ecfp():
		'MUV-737', 'MUV-858', 'MUV-713', 'MUV-733', 'MUV-652',
		'MUV-466', 'MUV-832'])

		loader = dc.load.DataLoader(
		tasks=MUV_tasks, smiles_field="smiles",
		featurizer=featurizer, verbosity="high")
		loader = dc.data.DataLoader(
		tasks=MUV_tasks, smiles_field="smiles", featurizer=featurizer)
		dataset = loader.featurize(dataset_file)

		# Initialize transformers
		@@ -119,9 +116,8 @@ def load_muv_convmol():
		'MUV-737', 'MUV-858', 'MUV-713', 'MUV-733', 'MUV-652',
		'MUV-466', 'MUV-832'])

		loader = dc.load.DataLoader(
		tasks=MUV_tasks, smiles_field="smiles",
		featurizer=featurizer, verbosity="high")
		loader = dc.data.DataLoader(
		tasks=MUV_tasks, smiles_field="smiles", featurizer=featurizer)
		dataset = loader.featurize(dataset_file)

		# Initialize transformers
		@@ -148,10 +144,8 @@ def load_sider_ecfp():
		print("%d tasks in total" % len(SIDER_tasks))


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

		@@ -179,10 +173,8 @@ def load_sider_convmol():
		print("%d tasks in total" % len(SIDER_tasks))


		loader = dc.load.DataLoader(tasks=SIDER_tasks,
		smiles_field="smiles",
		featurizer=featurizer,
		verbosity="high")
		loader = dc.data.DataLoader(
		tasks=SIDER_tasks, smiles_field="smiles", featurizer=featurizer)
		dataset = loader.featurize(dataset_file, debug=True)
		print("%d datapoints in SIDER dataset" % len(dataset))

examples/muv/muv_datasets.py

+3 −5

Original line number	Diff line number	Diff line
		@@ -30,9 +30,8 @@ def load_muv(featurizer='ECFP', split='index'):
		'MUV-737', 'MUV-858', 'MUV-713', 'MUV-733', 'MUV-652',
		'MUV-466', 'MUV-832'])

		loader = dc.load.DataLoader(
		tasks=MUV_tasks, smiles_field="smiles",
		featurizer=featurizer_func, verbosity="high")
		loader = dc.data.DataLoader(
		tasks=MUV_tasks, smiles_field="smiles", featurizer=featurizer_func)
		dataset = loader.featurize(dataset_file)

		# Initialize transformers
		@@ -46,8 +45,7 @@ def load_muv(featurizer='ECFP', split='index'):
		'random': dc.splits.RandomSplitter(),
		'scaffold': dc.splits.ScaffoldSplitter()}
		splitter = splitters[split]
		train, valid, test = splitter.train_valid_test_split(
		dataset, compute_feature_statistics=False)
		train, valid, test = splitter.train_valid_test_split(dataset)
		return MUV_tasks, (train, valid, test), transformers

Admin message