Update test in genome metrics. (85117b85) · Commits · 钟慕尧 / deepchem

deepchem/data/data_loader.py

+3 −5

Original line number	Diff line number	Diff line
		@@ -18,7 +18,7 @@ import sys
		from deepchem.utils.save import log
		from deepchem.utils.save import load_csv_files
		from deepchem.utils.save import load_sdf_files
		from deepchem.utils.save import encode_fasta_sequence
		from deepchem.utils.genomics import encode_fasta_sequence
		from deepchem.feat import UserDefinedFeaturizer
		from deepchem.data import DiskDataset
		from deepchem.data import NumpyDataset
		@@ -230,8 +230,7 @@ class DataLoader(object):
		assert len(X) == len(ids)

		time2 = time.time()
		log(
		"TIMING: featurizing shard %d took %0.3f s" %
		log("TIMING: featurizing shard %d took %0.3f s" %
		(shard_num, time2 - time1), self.verbose)
		yield X, y, w, ids

		@@ -295,8 +294,7 @@ class SDFLoader(DataLoader):

		def featurize_shard(self, shard):
		"""Featurizes a shard of an input dataframe."""
		log(
		"Currently featurizing feature_type: %s" %
		log("Currently featurizing feature_type: %s" %
		self.featurizer.__class__.__name__, self.verbose)
		return featurize_mol_df(shard, self.featurizer, field=self.mol_field)

deepchem/metrics/tests/test_genomics.py

+4 −4

Original line number	Diff line number	Diff line
		@@ -27,7 +27,7 @@ class TestGenomicMetrics(unittest.TestCase):
		# Encode motif
		motif_name = "TAL1_known4"
		sequences = np.array(["ACGTA", "GATAG", "CGCGC"])
		sequences = dc.utils.save.seq_one_hot_encode(sequences, letters=LETTERS)
		sequences = dc.utils.genomics.seq_one_hot_encode(sequences, letters=LETTERS)
		# sequences now has shape (3, 4, 5, 1)
		self.assertEqual(sequences.shape, (3, 4, 5, 1))

		@@ -38,7 +38,7 @@ class TestGenomicMetrics(unittest.TestCase):
		"""Test get_pssm_scores returns correct shape."""
		motif_name = "TAL1_known4"
		sequences = np.array(["ACGTA", "GATAG", "CGCGC"])
		sequences = dc.utils.save.seq_one_hot_encode(sequences, letters=LETTERS)
		sequences = dc.utils.genomics.seq_one_hot_encode(sequences, letters=LETTERS)
		# sequences now has shape (3, 4, 5, 1)
		self.assertEqual(sequences.shape, (3, 4, 5, 1))
		pssm = np.array([[1, 0, 0, 0], [0, 1, 0, 0], [0, 0, 1, 0], [0, 0, 0, 1]])
		@@ -50,7 +50,7 @@ class TestGenomicMetrics(unittest.TestCase):
		"""Test in-silico mutagenesis returns correct shape."""
		# Construct and train SequenceDNN model
		sequences = np.array(["ACGTA", "GATAG", "CGCGC"])
		sequences = dc.utils.save.seq_one_hot_encode(sequences, letters=LETTERS)
		sequences = dc.utils.genomics.seq_one_hot_encode(sequences, letters=LETTERS)
		labels = np.array([1, 0, 0])
		labels = np.reshape(labels, (3, 1))
		self.assertEqual(sequences.shape, (3, 4, 5, 1))
		@@ -71,7 +71,7 @@ class TestGenomicMetrics(unittest.TestCase):
		"""Test in-silico mutagenesis returns nonzero output."""
		# Construct and train SequenceDNN model
		sequences = np.array(["ACGTA", "GATAG", "CGCGC"])
		sequences = dc.utils.save.seq_one_hot_encode(sequences, letters=LETTERS)
		sequences = dc.utils.genomics.seq_one_hot_encode(sequences, letters=LETTERS)
		labels = np.array([1, 0, 0])
		labels = np.reshape(labels, (3, 1))
		self.assertEqual(sequences.shape, (3, 4, 5, 1))

Admin message