Merge pull request #1260 from peastman/reshape (43814216) · Commits · 钟慕尧 / deepchem

deepchem/data/datasets.py

+7 −6

Original line number	Diff line number	Diff line
		@@ -308,13 +308,8 @@ class NumpyDataset(Dataset):

		def __init__(self, X, y=None, w=None, ids=None, n_tasks=1):
		n_samples = len(X)
		# The -1 indicates that y will be reshaped to have length -1
		if n_samples > 0:
		if y is not None:
		y = np.reshape(y, (n_samples, -1))
		if w is not None:
		w = np.reshape(w, (n_samples, -1))
		else:
		if y is None:
		# Set labels to be zero, with zero weights
		y = np.zeros((n_samples, n_tasks))
		w = np.zeros_like(y)
		@@ -322,6 +317,12 @@ class NumpyDataset(Dataset):
		ids = np.arange(n_samples)
		if w is None:
		w = np.ones_like(y)
		if not isinstance(X, np.ndarray):
		X = np.array(X)
		if not isinstance(y, np.ndarray):
		y = np.array(y)
		if not isinstance(w, np.ndarray):
		w = np.array(w)
		self._X = X
		self._y = y
		self._w = w

deepchem/data/supports.py

+10 −6

Original line number	Diff line number	Diff line
		@@ -85,10 +85,10 @@ def get_task_dataset_minus_support(dataset, support, task):
		# Get task specific entries
		w_task = w[:, task]
		X_task = X[w_task != 0]
		y_task = y[w_task != 0, task]
		y_task = np.expand_dims(y[w_task != 0, task], 1)
		ids_task = ids[w_task != 0]
		# Now just get weights for this task
		w_task = w[w_task != 0, task]
		w_task = np.expand_dims(w[w_task != 0, task], 1)

		return NumpyDataset(X_task, y_task, w_task, ids_task)

		@@ -99,10 +99,10 @@ def get_task_dataset(dataset, task):
		# Get task specific entries
		w_task = w[:, task]
		X_task = X[w_task != 0]
		y_task = y[w_task != 0, task]
		y_task = np.expand_dims(y[w_task != 0, task], 1)
		ids_task = ids[w_task != 0]
		# Now just get weights for this task
		w_task = w[w_task != 0, task]
		w_task = np.expand_dims(w[w_task != 0, task], 1)

		return NumpyDataset(X_task, y_task, w_task, ids_task)

		@@ -234,8 +234,12 @@ def get_task_support(dataset, n_episodes, n_pos, n_neg, task, log_every_n=50):
		X = np.vstack([dataset.X[pos_inds], dataset.X[neg_inds]])
		else:
		X = np.concatenate([dataset.X[pos_inds], dataset.X[neg_inds]])
		y = np.concatenate([dataset.y[pos_inds, task], dataset.y[neg_inds, task]])
		w = np.concatenate([dataset.w[pos_inds, task], dataset.w[neg_inds, task]])
		y = np.expand_dims(
		np.concatenate([dataset.y[pos_inds, task], dataset.y[neg_inds, task]]),
		1)
		w = np.expand_dims(
		np.concatenate([dataset.w[pos_inds, task], dataset.w[neg_inds, task]]),
		1)
		ids = np.concatenate([dataset.ids[pos_inds], dataset.ids[neg_inds]])
		supports.append(NumpyDataset(X, y, w, ids))
		return supports

deepchem/models/tensorgraph/models/symmetry_function_regression.py

+5 −4

Original line number	Diff line number	Diff line
		@@ -223,7 +223,8 @@ class ANIRegression(TensorGraph):
		Z[:A.shape[0], :A.shape[1]] = A
		X = Z
		dd = dc.data.NumpyDataset(
		np.array(X).reshape((1, self.max_atoms, 4)), np.array(0), np.array(1))
		np.array(X).reshape((1, self.max_atoms, 4)), np.zeros((1, 1)),
		np.ones((1, 1)))
		return self.predict(dd)[0]

		def grad_one(self, X, atomic_nums, constraints=None):

deepchem/models/tensorgraph/models/test_graph_models.py

+1 −1

Original line number	Diff line number	Diff line
		@@ -115,7 +115,7 @@ class TestGraphModels(unittest.TestCase):
		mol.SetProp("atom %08d %s" % (atom.GetIdx(), atom_feature_name),
		str(val))
		atom_features.append(np.random.normal())
		y.append(np.sum(atom_features))
		y.append([np.sum(atom_features)])

		featurizer = ConvMolFeaturizer(atom_properties=[atom_feature_name])
		X = featurizer.featurize(dataset.X)

deepchem/models/tensorgraph/models/test_symmetry_functions.py

+1 −1

Original line number	Diff line number	Diff line
		@@ -27,7 +27,7 @@ class TestANIRegression(unittest.TestCase):
		[0, 0, 0, 0],
		]])

		y = np.array([2.0, 1.1])
		y = np.array([[2.0], [1.1]])

		layer_structures = [128, 128, 64]
		atom_number_cases = [1, 6, 7, 8]

Admin message