Merge pull request #2148 from peastman/modelstutorial (1cbafde0) · Commits · 钟慕尧 / deepchem

deepchem/feat/init.py

+1 −5

Original line number	Diff line number	Diff line
		@@ -36,14 +36,10 @@ from deepchem.feat.material_featurizers import SineCoulombMatrix
		from deepchem.feat.material_featurizers import CGCNNFeaturizer

		try:
		from logging import getLogger
		logger = getLogger(__name__)
		import transformers
		from transformers import BertTokenizer

		from deepchem.feat.smiles_tokenizer import SmilesTokenizer
		from deepchem.feat.smiles_tokenizer import BasicSmilesTokenizer
		except ModuleNotFoundError:
		logger.warning(
		"HuggingFace transformers is not available. Please install using 'pip install transformers' to use the SmilesTokenizer"
		)
		pass

+2 −0

Original line number	Diff line number	Diff line
		@@ -2,6 +2,7 @@
		Topological fingerprints.
		"""
		from deepchem.feat.base_classes import MolecularFeaturizer
		import numpy as np


		class CircularFingerprint(MolecularFeaturizer):
		@@ -103,6 +104,7 @@ class CircularFingerprint(MolecularFeaturizer):
		useChirality=self.chiral,
		useBondTypes=self.bonds,
		useFeatures=self.features)
		fp = np.asarray(fp, dtype=np.float)
		return fp

		def __hash__(self):

+1 −8

Original line number	Diff line number	Diff line
		@@ -14,13 +14,6 @@ from transformers import BertTokenizer
		from logging import getLogger

		logger = getLogger(__name__)

		try:
		from transformers import BertTokenizer
		except ModuleNotFoundError:
		logger.warning(
		"HuggingFace transformers is not available. Please install using 'pip install transformers' to use the SmilesTokenizer"
		)
		"""
		SMI_REGEX_PATTERN: str
		SMILES regex pattern for tokenization. Designed by Schwaller et. al.

+4 −4

Original line number	Diff line number	Diff line
		@@ -90,9 +90,9 @@ def load_bace_regression(featurizer='ECFP',
		img_size=img_size, img_spec=img_spec)

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

		dataset = loader.featurize(dataset_file, shard_size=8192)
		dataset = loader.create_dataset(dataset_file, shard_size=8192)
		if split is None:
		# Initialize transformers
		transformers = [
		@@ -194,9 +194,9 @@ def load_bace_classification(featurizer='ECFP',
		img_size=img_size, img_spec=img_spec)

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

		dataset = loader.featurize(dataset_file, shard_size=8192)
		dataset = loader.create_dataset(dataset_file, shard_size=8192)

		if split is None:
		# Initialize transformers

+8 −8

Original line number	Diff line number	Diff line
		@@ -86,8 +86,8 @@ def load_delaney(featurizer='ECFP',
		img_size=img_size, img_spec=img_spec, res=res)

		loader = deepchem.data.CSVLoader(
		tasks=delaney_tasks, smiles_field="smiles", featurizer=featurizer)
		dataset = loader.featurize(dataset_file, shard_size=8192)
		tasks=delaney_tasks, feature_field="smiles", featurizer=featurizer)
		dataset = loader.create_dataset(dataset_file, shard_size=8192)

		if split is None:
		transformers = [