Merge branch 'master' into gat-add-mode (973848a8) · Commits · 钟慕尧 / deepchem

.python-version

0 → 100644

+1 −0

Original line number	Diff line number	Diff line
		miniconda3-latest

deepchem/feat/adjacency_fingerprints.py→contrib/torch/adjacency_fingerprint.py

+0 −0

File moved.

View file

deepchem/data/data_loader.py

+1 −1

Original line number	Diff line number	Diff line
		@@ -13,7 +13,7 @@ import pandas as pd
		import numpy as np

		from deepchem.utils.typing import OneOrMany
		from deepchem.utils.save import load_image_files, load_csv_files, load_json_files, load_sdf_files
		from deepchem.utils.data_utils import load_image_files, load_csv_files, load_json_files, load_sdf_files
		from deepchem.utils.genomics_utils import encode_bio_sequence
		from deepchem.feat import UserDefinedFeaturizer, Featurizer
		from deepchem.data import Dataset, DiskDataset, NumpyDataset, ImageDataset

deepchem/data/datasets.py

+21 −7

Original line number	Diff line number	Diff line
		@@ -18,7 +18,7 @@ import pandas as pd

		import deepchem as dc
		from deepchem.utils.typing import OneOrMany, Shape
		from deepchem.utils.save import save_to_disk, load_from_disk, load_image_files
		from deepchem.utils.data_utils import save_to_disk, load_from_disk, load_image_files

		Batch = Tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray]

		@@ -420,6 +420,19 @@ class Dataset(object):
		"""
		raise NotImplementedError()

		def select(self, indices: Sequence[int],
		select_dir: Optional[str] = None) -> "Dataset":
		"""Creates a new dataset from a selection of indices from self.

		Parameters
		----------
		indices: Sequence
		List of indices to select.
		select_dir: str, optional (default None)
		Path to new directory that the selected indices will be copied to.
		"""
		raise NotImplementedError()

		def get_statistics(self, X_stats: bool = True,
		y_stats: bool = True) -> Tuple[float, ...]:
		"""Compute and return statistics of this dataset.
		@@ -1868,13 +1881,13 @@ class DiskDataset(Dataset):
		tasks=tasks)

		@staticmethod
		def merge(datasets: Iterable["DiskDataset"],
		def merge(datasets: Iterable["Dataset"],
		merge_dir: Optional[str] = None) -> "DiskDataset":
		"""Merges provided datasets into a merged dataset.

		Parameters
		----------
		datasets: Iterable[DiskDataset]
		datasets: Iterable[Dataset]
		List of datasets to merge.
		merge_dir: str, optional (default None)
		The new directory path to store the merged DiskDataset.
		@@ -1897,7 +1910,7 @@ class DiskDataset(Dataset):
		tasks = []
		for dataset in datasets:
		try:
		tasks.append(dataset.tasks)
		tasks.append(dataset.tasks) # type: ignore
		except AttributeError:
		pass
		if tasks:
		@@ -2033,7 +2046,7 @@ class DiskDataset(Dataset):

		def shuffle_each_shard(self,
		shard_basenames: Optional[List[str]] = None) -> None:
		"""Shuffles elements within each shard of the datset.
		"""Shuffles elements within each shard of the dataset.

		Parameters
		----------
		@@ -2282,8 +2295,9 @@ class DiskDataset(Dataset):

		Returns
		-------
		DiskDataset
		A Dataset containing the selected samples
		Dataset
		A dataset containing the selected samples. The default dataset is `DiskDataset`.
		If `output_numpy_dataset` is True, the dataset is `NumpyDataset`.
		"""
		if output_numpy_dataset and (select_dir is not None or
		select_shard_size is not None):

deepchem/data/tests/test_reload.py

+1 −1

Original line number	Diff line number	Diff line
		@@ -23,7 +23,7 @@ class TestReload(unittest.TestCase):
		# Load MUV dataset
		logger.info("About to featurize compounds")
		featurizer = dc.feat.CircularFingerprint(size=1024)
		raw_dataset = dc.utils.save.load_from_disk(dataset_file)
		raw_dataset = dc.utils.data_utils.load_from_disk(dataset_file)
		MUV_tasks = [
		'MUV-692', 'MUV-689', 'MUV-846', 'MUV-859', 'MUV-644', 'MUV-548',
		'MUV-852', 'MUV-600', 'MUV-810', 'MUV-712', 'MUV-737', 'MUV-858',

Admin message