yapfed (6fe6e3a9) · Commits · 钟慕尧 / deepchem

deepchem/data/data_loader.py

+4 −1

Original line number	Diff line number	Diff line
		@@ -79,6 +79,7 @@ def featurize_smiles_df(df, featurizer, field, log_every_N=1000, verbose=True):
		features = [elt for (is_valid, elt) in zip(valid_inds, features) if is_valid]
		return np.squeeze(np.array(features)), valid_inds


		def featurize_smiles_np(arr, featurizer, log_every_N=1000, verbose=True):
		"""Featurize individual compounds in a numpy array.

		@@ -100,7 +101,9 @@ def featurize_smiles_np(arr, featurizer, log_every_N=1000, verbose=True):
		[1 if elt.size > 0 else 0 for elt in features], dtype=bool)
		features = [elt for (is_valid, elt) in zip(valid_inds, features) if is_valid]
		features = np.squeeze(np.array(features))
		return features.reshape(-1,)
		return features.reshape(
		-1,)


		def get_user_specified_features(df, featurizer, verbose=True):
		"""Extract and merge user specified features.

+4 −4

Original line number	Diff line number	Diff line
		@@ -931,8 +931,8 @@ class DiskDataset(Dataset):
		if indices_count + num_shard_elts >= len(indices):
		break
		# Need to offset indices to fit within shard_size
		shard_inds = indices[indices_count:indices_count +
		num_shard_elts] - count
		shard_inds = indices[indices_count:
		indices_count + num_shard_elts] - count
		X_sel = X[shard_inds]
		# Handle the case of datasets with y/w missing
		if y is not None:

+6 −4

Original line number	Diff line number	Diff line
		@@ -71,6 +71,7 @@ def pearson_r2_score(y, y_pred):
		"""Computes Pearson R^2 (square of Pearson correlation)."""
		return pearsonr(y, y_pred)[0]**2


		def prc_auc_score(y, y_pred):
		"""Compute area under precision-recall curve"""
		assert y_pred.shape == y.shape
		@@ -110,13 +111,14 @@ def kappa_score(y_true, y_pred):
		assert len(y_true) == len(y_pred), 'Number of examples does not match.'
		yt = np.asarray(y_true, dtype=int)
		yp = np.asarray(y_pred, dtype=int)
		assert np.array_equal(np.unique(yt), [0, 1]), (
		'Class labels must be binary: %s' % np.unique(yt))
		assert np.array_equal(
		np.unique(yt), [0,
		1]), ('Class labels must be binary: %s' % np.unique(yt))
		observed_agreement = np.true_divide(
		np.count_nonzero(np.equal(yt, yp)), len(yt))
		expected_agreement = np.true_divide(
		np.count_nonzero(yt == 1) * np.count_nonzero(yp == 1) + np.count_nonzero(
		yt == 0) * np.count_nonzero(yp == 0), len(yt)**2)
		np.count_nonzero(yt == 1) * np.count_nonzero(yp == 1) +
		np.count_nonzero(yt == 0) * np.count_nonzero(yp == 0), len(yt)**2)
		kappa = np.true_divide(observed_agreement - expected_agreement,
		1.0 - expected_agreement)
		return kappa

+6 −5

Original line number	Diff line number	Diff line
		@@ -151,7 +151,8 @@ class WeaveTensorGraph(TensorGraph):
		C0, C1 = np.meshgrid(np.arange(n_atoms), np.arange(n_atoms))
		atom_to_pair.append(
		np.transpose(
		np.array([C1.flatten() + start, C0.flatten() + start])))
		np.array([C1.flatten() + start,
		C0.flatten() + start])))
		# number of pairs for each atom
		pair_split.extend(C1.flatten() + start)
		start = start + n_atoms