Fix type issues (13420ce1) · Commits · 钟慕尧 / deepchem

deepchem/data/datasets.py

+4 −3

Original line number	Diff line number	Diff line
		@@ -1421,7 +1421,7 @@ class DiskDataset(Dataset):
		y = None if y_file is None else np.array(load_from_disk(y_file))
		w = None if w_file is None else np.array(load_from_disk(w_file))
		ids = np.array(load_from_disk(ids_file))
		X, y, w = transformer.transform_array(X, y, w)
		X, y, w, ids = transformer.transform_array(X, y, w, ids)
		basename = "shard-%d" % shard_num
		return DiskDataset.write_data_to_disk(out_dir, basename, tasks, X, y, w,
		ids)
		@@ -2151,8 +2151,9 @@ class ImageDataset(Dataset):
		-------
		a newly constructed Dataset object
		"""
		newx, newy, neww = transformer.transform_array(self.X, self.y, self.w)
		return NumpyDataset(newx, newy, neww, self.ids[:])
		newx, newy, neww, newids = transformer.transform_array(
		self.X, self.y, self.w, self.ids)
		return NumpyDataset(newx, newy, neww, newids)

		def select(self, indices: Sequence[int],
		select_dir: str = None) -> "ImageDataset":

+2 −2

Original line number	Diff line number	Diff line
		@@ -395,7 +395,7 @@ class MultitaskFitTransformRegressor(MultitaskRegressor):
		for transformer in fit_transformers:
		assert transformer.transform_X and not (transformer.transform_y or
		transformer.transform_w)
		X_b, _, _ = transformer.transform_array(X_b, None, None)
		X_b, _, _, _ = transformer.transform_array(X_b, None, None, None)
		n_features = X_b.shape[1]
		logger.info("n_features after fit_transform: %d", int(n_features))
		super(MultitaskFitTransformRegressor, self).__init__(
		@@ -418,7 +418,7 @@ class MultitaskFitTransformRegressor(MultitaskRegressor):
		if X_b is not None:
		if mode == 'fit':
		for transformer in self.fit_transformers:
		X_b, _, _ = transformer.transform_array(X_b, None, None)
		X_b, _, _, _ = transformer.transform_array(X_b, None, None, None)
		if mode == 'predict':
		dropout = np.array(0.0)
		else:

+7 −4

Original line number	Diff line number	Diff line
		@@ -10,7 +10,7 @@ import time
		import deepchem as dc
		import tensorflow as tf
		import warnings
		from typing import Optional, Tuple, List
		from typing import Optional, Tuple, List, Any
		from deepchem.data import Dataset
		from deepchem.data import NumpyDataset
		from deepchem.feat.mol_graphs import ConvMol
		@@ -903,7 +903,7 @@ class BalancingTransformer(Transformer):
		`ValueError` if `y` or `w` aren't of shape `(N,)` or `(N, n_tasks)`.
		"""

		def __init__(self, dataset: Optional[Dataset] = None):
		def __init__(self, dataset: Dataset):
		# BalancingTransformer can only transform weights.
		super(BalancingTransformer, self).__init__(
		transform_w=True, dataset=dataset)
		@@ -1048,6 +1048,9 @@ class CDFTransformer(Transformer):
		super(CDFTransformer, self).__init__(
		transform_X=transform_X, transform_y=transform_y)
		self.bins = bins
		if transform_y:
		if dataset is None:
		raise ValueError("dataset must be specified when transforming y")
		self.y = dataset.y

		def transform_array(self, X, y, w, ids):
		@@ -1687,7 +1690,7 @@ class DAGTransformer(Transformer):
		DAG = []
		# list of lists, elements represent the calculation orders
		# for atoms in the current graph
		parent = [[] for i in range(n_atoms)]
		parent: List[Any] = [[] for i in range(n_atoms)]
		# starting from the target atom with index `count`
		current_atoms = [count]
		# flags of whether the atom is already included in the DAG