def testClusterNamingWithBootstraps(self):
tree = TreeNode.read(
StringIO(
"((F:20, ((A:11, B:12):10, (H:8, D:9):3):20)'0.7:G':30)root;"))
clusters = Tree2Tax().named_clusters(tree, 40)
self.assertSameClusters([['F'], _('A B D H')], clusters)
assert_equals(_('G.2 G.1'), [c.name() for c in clusters])
def testNaming(self):
tree = TreeNode.read(
StringIO('((F:20, ((A:11, B:12):10, (H:8, D:9):3):20)G:30)root;'))
clusters = Tree2Tax().named_clusters_for_several_thresholds(
tree, [40, 25])
self.assertSameClusterSets(
[[25, [['F'], _('A B'), _('D H')]],
[40, [['F'], _('A B D H')]]], clusters)
assert_equals(_('G.3 G.1 G.2'),
[c.name() for c in clusters[0].clusters])
assert_equals(_('G.2 G.1'), [c.name() for c in clusters[1].clusters])
def testTipToCluster(self):
tree = TreeNode.read(StringIO('((F:20, ((A:11, B:12):10, (H:8, D:9):3):20)G:30)root;'))
clusters = Tree2Tax().named_clusters_for_several_thresholds(tree, [40, 25])
self.assertSameClusterSets([[25,[['F'], _('A B'), _('D H')]], [40,[['F'], _('A B D H')]]], clusters)
assert_equals(_('G.3 G.1 G.2'), [c.name() for c in clusters[0].clusters])
assert_equals(_('G.2 G.1'), [c.name() for c in clusters[1].clusters])
tip = tree.find('F')
assert_equals('G.3', clusters[0].tip_to_cluster(tip).name())
assert_equals('G.2', clusters[1].tip_to_cluster(tip).name())
tip = tree.find('D')
assert_equals('G.2', clusters[0].tip_to_cluster(tip).name())
assert_equals('G.1', clusters[1].tip_to_cluster(tip).name())
def welcome(name):
_("Hello"+"There")
_(17)
_("Hi, {0}".format(name))
# pylint: disable=translation-of-non-string
_(name)
# pylint: enable=translation-of-non-string
gettext("hi, %s" % name)
def testOppositeSorting(self):
tree = TreeNode.read(StringIO('((A:0.11, B:0.12)C:0.1, D:0.2)root;'))
clusters = Tree2Tax().named_clusters_for_several_thresholds(
tree, [0.05, 0.25])
self.assertSameClusterSets(
[[0.05, [['A'], ['B'], ['D']]], [0.25, [['A', 'B'], ['D']]]],
clusters)
assert_equals(_('C.1 C.2 Root'),
[c.name() for c in clusters[0].clusters])
def testNamingWithBootstraps(self):
tree = TreeNode.read(StringIO('((A:0.11, B:0.12)0.091:0.1, D:0.2)root;'))
clusters = Tree2Tax().named_clusters(tree, 0.05)
self.assertSameClusters([['A'],['B'],['D']], clusters)
assert_equals(_('Root.1 Root.2 Root.3'), [c.name() for c in clusters])
def testClusterNamingOnTwoInternalNodesReverseOrder(self):
tree = TreeNode.read(StringIO('((F:20, ((A:11, B:12):10, (H:8, D:9):3):20)G:30)root;'))
clusters = Tree2Tax().named_clusters(tree, 40)
self.assertSameClusters([['F'], _('A B D H')], clusters)
assert_equals(_('G.2 G.1'), [c.name() for c in clusters])
def testClusterIntoThree(self):
tree = TreeNode.read(StringIO('((((A:11, B:12)C:10, (H:8, D:9)I:3)E:20, F:20)G:30)root;'))
clusters = Tree2Tax().named_clusters(tree, 25)
self.assertSameClusters([_('A B'), _('D H'), ['F']], clusters)
def testClusterOnTwoInternalNodes(self):
tree = TreeNode.read(StringIO('((((A:11, B:12)C:10, (H:8, D:9)I:3)E:20, F:20)G:30)root;'))
clusters = Tree2Tax().named_clusters(tree, 40)
self.assertSameClusters([_('A B D H'), ['F']], clusters)
def testNoClusering(self):
tree = TreeNode.read(StringIO('((A:0.11, B:0.12)C:0.1, D:0.2)root;'))
clusters = Tree2Tax().named_clusters(tree, 0.05)
self.assertSameClusters([['A'],['B'],['D']], clusters)
assert_equals(_('C.1 C.2 Root'), [c.name() for c in clusters])
"""These are all good uses of _()"""
from string import lower as _
_("Hello")
_(
"""
This is a long string.
"""
)
_("This " "is " "also " "long.")
def testClusterNamingWithBootstraps(self):
tree = TreeNode.read(StringIO("((F:20, ((A:11, B:12):10, (H:8, D:9):3):20)'0.7:G':30)root;"))
clusters = Tree2Tax().named_clusters(tree, 40)
self.assertSameClusters([['F'], _('A B D H')], clusters)
assert_equals(_('G.2 G.1'), [c.name() for c in clusters])
def test_match_alignment_and_tree_sequence_ids_align_not_tree(self):
self.assertRaises(Exception, self.match, u'(a,(b,c));',_('a b c d'))
def testNamingWithBootstraps(self):
tree = TreeNode.read(
StringIO('((A:0.11, B:0.12)0.091:0.1, D:0.2)root;'))
clusters = Tree2Tax().named_clusters(tree, 0.05)
self.assertSameClusters([['A'], ['B'], ['D']], clusters)
assert_equals(_('Root.1 Root.2 Root.3'), [c.name() for c in clusters])
def testClusterNamingOnTwoInternalNodesReverseOrder(self):
tree = TreeNode.read(
StringIO('((F:20, ((A:11, B:12):10, (H:8, D:9):3):20)G:30)root;'))
clusters = Tree2Tax().named_clusters(tree, 40)
self.assertSameClusters([['F'], _('A B D H')], clusters)
assert_equals(_('G.2 G.1'), [c.name() for c in clusters])
def testClusterIntoThree(self):
tree = TreeNode.read(
StringIO(
'((((A:11, B:12)C:10, (H:8, D:9)I:3)E:20, F:20)G:30)root;'))
clusters = Tree2Tax().named_clusters(tree, 25)
self.assertSameClusters([_('A B'), _('D H'), ['F']], clusters)
def testClusterOnTwoInternalNodes(self):
tree = TreeNode.read(
StringIO(
'((((A:11, B:12)C:10, (H:8, D:9)I:3)E:20, F:20)G:30)root;'))
clusters = Tree2Tax().named_clusters(tree, 40)
self.assertSameClusters([_('A B D H'), ['F']], clusters)
def testNoClusering(self):
tree = TreeNode.read(StringIO('((A:0.11, B:0.12)C:0.1, D:0.2)root;'))
clusters = Tree2Tax().named_clusters(tree, 0.05)
self.assertSameClusters([['A'], ['B'], ['D']], clusters)
assert_equals(_('C.1 C.2 Root'), [c.name() for c in clusters])
def test_match_alignment_and_tree_sequence_ids(self):
self.match(u'(a,(b,c));',_('a b c'))
parser.add_argument('-i', '--input_taxonomy', help='output the taxonomy to this file', required=True)
parser.add_argument('-o', '--output_taxonomy', help='output the taxonomy to this file', required=True)
parser.add_argument('--debug', help='output debug information', action="store_true")
args = parser.parse_args()
if args.debug:
logging.basicConfig(level=logging.DEBUG)
else:
logging.basicConfig(level=logging.INFO)
# read in taxonomy file, keeping hashes of taxonomy => [[parent,count],..] and just an array of the taxonomies
taxonomy = []
expected_taxonomy_levels = 7
rank_bits = _('k p c o f g s')
child_to_parent_counts = [None] * (expected_taxonomy_levels-1)
for i in range(expected_taxonomy_levels-1):
child_to_parent_counts[i] = {}
regex = re.compile(r'^.__')
logging.info("Reading in taxonomy file..")
with open(args.input_taxonomy) as f:
for input_line1 in f:
input_line = input_line1.rstrip()
# split first by tab, then by '; '
splits = input_line.split("\t")
if len(splits) != 2:
def test_match_alignment_and_tree_sequence_ids_underscores(self):
self.match(u'(\'a_2\',(b,c));',_('a_2 b c'))
def testOppositeSorting(self):
tree = TreeNode.read(StringIO('((A:0.11, B:0.12)C:0.1, D:0.2)root;'))
clusters = Tree2Tax().named_clusters_for_several_thresholds(tree, [0.05, 0.25])
self.assertSameClusterSets([[0.05,[['A'],['B'],['D']]], [0.25,[['A','B'],['D']]]], clusters)
assert_equals(_('C.1 C.2 Root'), [c.name() for c in clusters[0].clusters])
