New upstream version 2019.10.0+dfsg (16b1e8c6) · Commits · Debian Med / q2-feature-table

q2_feature_table/_heatmap/_visualizer.py

+21 −5

Original line number	Diff line number	Diff line
		@@ -65,7 +65,7 @@ heatmap_choices = {
		'summer_r', 'tab10', 'tab10_r', 'tab20', 'tab20_r',
		'tab20b', 'tab20b_r', 'tab20c', 'tab20c_r', 'terrain',
		'terrain_r', 'viridis', 'viridis_r', 'vlag', 'vlag_r',
		'winter', 'winter_r'}
		'winter', 'winter_r', 'cividis', 'cividis_r'}
		}


		@@ -75,7 +75,7 @@ _clustering_map = {'both': {'col_cluster': True, 'row_cluster': True},
		'none': {'col_cluster': False, 'row_cluster': False}}


		def _munge_metadata(metadata, table, cluster):
		def _munge_sample_metadata(metadata, table, cluster):
		metadata = metadata.filter_ids(table.index)
		column_name = metadata.name

		@@ -97,16 +97,32 @@ def _munge_metadata(metadata, table, cluster):
		return table


		def _munge_feature_metadata(metadata, table, cluster):
		metadata = metadata.filter_ids(table.columns)
		column_name = metadata.name
		metadata_df = metadata.to_dataframe()
		# replace feature IDs with feature metadata annotations
		table.columns = metadata_df.reindex(table.columns)[column_name].values
		if cluster == 'samples':
		table = table.sort_index(axis=1)
		return table


		def heatmap(output_dir, table: pd.DataFrame,
		metadata: qiime2.CategoricalMetadataColumn = None,
		sample_metadata: qiime2.CategoricalMetadataColumn = None,
		feature_metadata: qiime2.CategoricalMetadataColumn = None,
		normalize: bool = True, title: str = None,
		metric: str = 'euclidean', method: str = 'average',
		cluster: str = 'both', color_scheme: str = 'rocket') -> None:
		if table.empty:
		raise ValueError('Cannot visualize an empty table.')

		if metadata is not None:
		table = _munge_metadata(metadata, table, cluster)
		if sample_metadata is not None:
		table = _munge_sample_metadata(sample_metadata, table, cluster)

		# relabel feature table feature IDs with feature metadata column values
		if feature_metadata is not None:
		table = _munge_feature_metadata(feature_metadata, table, cluster)

		cbar_label = 'frequency'
		if normalize:

q2_feature_table/_version.py

+3 −3

Original line number	Diff line number	Diff line
		@@ -23,9 +23,9 @@ def get_keywords():
		# setup.py/versioneer.py will grep for the variable names, so they must
		# each be defined on a line of their own. _version.py will just call
		# get_keywords().
		git_refnames = " (tag: 2019.7.0)"
		git_full = "7e18386b0948bb436e76daf0d72691ba0dc636b9"
		git_date = "2019-07-30 18:15:52 +0000"
		git_refnames = " (tag: 2019.10.0)"
		git_full = "6cc22b63649fb3fc24855f1bdb8e4864c9e6081b"
		git_date = "2019-11-01 01:04:23 +0000"
		keywords = {"refnames": git_refnames, "full": git_full, "date": git_date}
		return keywords

q2_feature_table/plugin_setup.py

+10 −4

Original line number	Diff line number	Diff line
		@@ -440,7 +440,8 @@ plugin.visualizers.register_function(
		'table': FeatureTable[Frequency]
		},
		parameters={
		'metadata': MetadataColumn[Categorical],
		'sample_metadata': MetadataColumn[Categorical],
		'feature_metadata': MetadataColumn[Categorical],
		'normalize': Bool,
		'title': Str,
		'metric': Str % Choices(q2_feature_table.heatmap_choices['metric']),
		@@ -459,9 +460,14 @@ plugin.visualizers.register_function(
		'table': 'The feature table to visualize.'
		},
		parameter_descriptions={
		'metadata': 'Annotate the sample IDs with these metadata values. '
		'When metadata is present and `cluster`=\'feature\', '
		'samples will be sorted by the metadata values.',
		'sample_metadata': 'Annotate the sample IDs with these sample '
		'metadata values. When metadata is present and '
		'`cluster`=\'feature\', samples will be sorted by '
		'the metadata values.',
		'feature_metadata': 'Annotate the feature IDs with these feature '
		'metadata values. When metadata is present and '
		'`cluster`=\'sample\', features will be sorted by '
		'the metadata values.',
		'normalize': 'Normalize the feature table by adding a psuedocount '
		'of 1 and then taking the log10 of the table.',
		'title': 'Optional custom plot title.',

q2_feature_table/tests/test_heatmap.py

+104 −16

Original line number	Diff line number	Diff line
		@@ -16,7 +16,8 @@ from pandas.testing import assert_frame_equal
		import qiime2

		from q2_feature_table import heatmap
		from q2_feature_table._heatmap._visualizer import _munge_metadata
		from q2_feature_table._heatmap._visualizer import (
		_munge_sample_metadata, _munge_feature_metadata)


		class TestHeatmap(unittest.TestCase):
		@@ -59,7 +60,27 @@ class TestHeatmap(unittest.TestCase):
		md = qiime2.CategoricalMetadataColumn(
		pd.Series(['milo', 'summer', 'russ'], name='pet',
		index=pd.Index(['S1', 'S2', 'S3'], name='id')))
		heatmap(self.output_dir, self.table, metadata=md)
		heatmap(self.output_dir, self.table, sample_metadata=md)

		self.assertBasicVizValidity(self.output_dir)

		def test_with_feature_metadata(self):
		feature_md = qiime2.CategoricalMetadataColumn(
		pd.Series(['peanut', 'dog'], name='species',
		index=pd.Index(['O1', 'O2'], name='id')))
		heatmap(self.output_dir, self.table, feature_metadata=feature_md)

		self.assertBasicVizValidity(self.output_dir)

		def test_with_sample_and_feature_metadata(self):
		md = qiime2.CategoricalMetadataColumn(
		pd.Series(['milo', 'summer', 'russ'], name='pet',
		index=pd.Index(['S1', 'S2', 'S3'], name='id')))
		feature_md = qiime2.CategoricalMetadataColumn(
		pd.Series(['peanut', 'dog'], name='species',
		index=pd.Index(['O1', 'O2'], name='id')))
		heatmap(self.output_dir, self.table, sample_metadata=md,
		feature_metadata=feature_md)

		self.assertBasicVizValidity(self.output_dir)

		@@ -75,14 +96,14 @@ class TestHeatmap(unittest.TestCase):
		index=pd.Index(['S1', 'S3'], name='id')))

		with self.assertRaisesRegex(ValueError, 'not present.*S2'):
		heatmap(self.output_dir, self.table, metadata=md)
		heatmap(self.output_dir, self.table, sample_metadata=md)

		def test_extra_metadata_ids(self):
		md = qiime2.CategoricalMetadataColumn(
		pd.Series(['milo', 'summer', 'russ', 'peanut'], name='pet',
		index=pd.Index(['S1', 'S2', 'S3', 'S4'], name='id')))

		heatmap(self.output_dir, self.table, metadata=md)
		heatmap(self.output_dir, self.table, sample_metadata=md)

		self.assertBasicVizValidity(self.output_dir)

		@@ -96,7 +117,8 @@ class TestHeatmap(unittest.TestCase):
		pd.Series(['milo', 'summer', 'russ'], name='pet',
		index=pd.Index(['S1', 'S2', 'S3'], name='id')))

		heatmap(self.output_dir, self.table, metadata=md, cluster='features')
		heatmap(self.output_dir, self.table, sample_metadata=md,
		cluster='features')

		self.assertBasicVizValidity(self.output_dir)

		@@ -105,7 +127,8 @@ class TestHeatmap(unittest.TestCase):
		pd.Series(['milo', 'summer', 'russ'], name='pet',
		index=pd.Index(['S1', 'S2', 'S3'], name='id')))

		heatmap(self.output_dir, self.table, metadata=md, cluster='none')
		heatmap(self.output_dir, self.table, sample_metadata=md,
		cluster='none')

		self.assertBasicVizValidity(self.output_dir)

		@@ -116,11 +139,11 @@ class TestPrivateHelpers(unittest.TestCase):
		columns=['O1', 'O2'],
		index=['S1', 'S2', 'S3'])

		def test_munge_metadata_simple(self):
		def test_munge_sample_metadata_simple(self):
		md = qiime2.CategoricalMetadataColumn(
		pd.Series(['milo', 'russ', 'russ'], name='pet',
		index=pd.Index(['S1', 'S2', 'S3'], name='id')))
		obs = _munge_metadata(md, self.table, 'both')
		obs = _munge_sample_metadata(md, self.table, 'both')

		exp_idx = pd.Index(['milo \| S1', 'russ \| S2', 'russ \| S3'],
		name='pet \| id')
		@@ -128,11 +151,11 @@ class TestPrivateHelpers(unittest.TestCase):
		index=exp_idx)
		assert_frame_equal(exp, obs)

		def test_munge_metadata_ids_different_order(self):
		def test_munge_sample_metadata_ids_different_order(self):
		md = qiime2.CategoricalMetadataColumn(
		pd.Series(['russ', 'milo', 'russ'], name='pet',
		index=pd.Index(['S2', 'S1', 'S3'], name='id')))
		obs = _munge_metadata(md, self.table, 'both')
		obs = _munge_sample_metadata(md, self.table, 'both')

		exp_idx = pd.Index(['milo \| S1', 'russ \| S2', 'russ \| S3'],
		name='pet \| id')
		@@ -140,18 +163,18 @@ class TestPrivateHelpers(unittest.TestCase):
		index=exp_idx)
		assert_frame_equal(exp, obs)

		def test_munge_metadata_missing_samples(self):
		def test_munge_sample_metadata_missing_samples(self):
		md = qiime2.CategoricalMetadataColumn(
		pd.Series(['milo', 'russ'], name='pet',
		index=pd.Index(['S1', 'S3'], name='id')))
		with self.assertRaisesRegex(ValueError, 'not present.*S2'):
		_munge_metadata(md, self.table, 'both')
		_munge_sample_metadata(md, self.table, 'both')

		def test_munge_metadata_empty_values(self):
		def test_munge_sample_metadata_empty_values(self):
		md = qiime2.CategoricalMetadataColumn(
		pd.Series([None, 'russ', np.nan], name='pet',
		index=pd.Index(['S1', 'S2', 'S3'], name='id')))
		obs = _munge_metadata(md, self.table, 'both')
		obs = _munge_sample_metadata(md, self.table, 'both')

		exp_idx = pd.Index(['[No Value] \| S1', 'russ \| S2', '[No Value] \| S3'],
		name='pet \| id')
		@@ -159,11 +182,11 @@ class TestPrivateHelpers(unittest.TestCase):
		index=exp_idx)
		assert_frame_equal(exp, obs)

		def test_munge_metadata_sort_samples(self):
		def test_munge_sample_metadata_sort_samples(self):
		md = qiime2.CategoricalMetadataColumn(
		pd.Series(['peanut', 'milo', 'russ'], name='pet',
		index=pd.Index(['S1', 'S2', 'S3'], name='id')))
		obs = _munge_metadata(md, self.table, 'features')
		obs = _munge_sample_metadata(md, self.table, 'features')

		exp_idx = pd.Index(['milo \| S2', 'peanut \| S1', 'russ \| S3'],
		name='pet \| id')
		@@ -171,6 +194,71 @@ class TestPrivateHelpers(unittest.TestCase):
		index=exp_idx)
		assert_frame_equal(exp, obs)

		def test_munge_feature_metadata_simple(self):
		feature_md = qiime2.CategoricalMetadataColumn(
		pd.Series(['peanut', 'dog'], name='species',
		index=pd.Index(['O1', 'O2'], name='id')))
		obs = _munge_feature_metadata(feature_md, self.table, 'both')

		exp = pd.DataFrame(
		[[0, 10], [10, 12], [10, 11]], columns=['peanut', 'dog'],
		index=pd.Index(['S1', 'S2', 'S3']))
		assert_frame_equal(exp, obs)

		def test_munge_feature_metadata_ids_different_order(self):
		feature_md = qiime2.CategoricalMetadataColumn(
		pd.Series(['dog', 'peanut'], name='species',
		index=pd.Index(['O2', 'O1'], name='id')))
		obs = _munge_feature_metadata(feature_md, self.table, 'both')

		exp = pd.DataFrame(
		[[0, 10], [10, 12], [10, 11]], columns=['peanut', 'dog'],
		index=pd.Index(['S1', 'S2', 'S3']))
		assert_frame_equal(exp, obs)

		def test_munge_feature_metadata_missing_features(self):
		feature_md = qiime2.CategoricalMetadataColumn(
		pd.Series(
		['dog'], name='species', index=pd.Index(['O2'], name='id')))
		with self.assertRaisesRegex(ValueError, 'not present.*O1'):
		_munge_feature_metadata(feature_md, self.table, 'both')

		def test_munge_feature_metadata_is_superset(self):
		feature_md = qiime2.CategoricalMetadataColumn(
		pd.Series(['peanut', 'dog', 'cujo'], name='species',
		index=pd.Index(['O1', 'O2', 'O3'], name='id')))
		obs = _munge_feature_metadata(feature_md, self.table, 'both')

		exp = pd.DataFrame(
		[[0, 10], [10, 12], [10, 11]], columns=['peanut', 'dog'],
		index=pd.Index(['S1', 'S2', 'S3']))
		assert_frame_equal(exp, obs)

		def test_munge_feature_metadata_sort_samples(self):
		feature_md = qiime2.CategoricalMetadataColumn(
		pd.Series(['peanut', 'dog'], name='species',
		index=pd.Index(['O1', 'O2'], name='id')))
		obs = _munge_feature_metadata(feature_md, self.table, 'samples')

		exp = pd.DataFrame(
		[[10, 0], [12, 10], [11, 10]], columns=['dog', 'peanut'],
		index=pd.Index(['S1', 'S2', 'S3']))
		assert_frame_equal(exp, obs)

		def test_munge_feature_metadata_sort_duplicate_feature_names(self):
		new_tab = self.table.copy()
		new_tab['O3'] = [1, 2, 3]
		feature_md = qiime2.CategoricalMetadataColumn(
		pd.Series(['peanut', 'dog', 'peanut'], name='species',
		index=pd.Index(['O1', 'O2', 'O3'], name='id')))
		obs = _munge_feature_metadata(feature_md, new_tab, 'samples')

		exp = pd.DataFrame(
		[[10, 0, 1], [12, 10, 2], [11, 10, 3]],
		columns=['dog', 'peanut', 'peanut'],
		index=pd.Index(['S1', 'S2', 'S3']))
		assert_frame_equal(exp, obs)


		if __name__ == "__main__":
		unittest.main()