def runTest(self):
y = True
n = False
for i, r in enumerate([y, y, y, n, y, n, n, y, y, n, n, y, n, y, y, y, y, y, y, n, y, n, n, y, y, n, n, y, n, y, y, y, ]):
self.assertEqual(r, treesplit.is_trivial_split(i, 0xF))
for i, r in enumerate([y, y, y, n, y, n, n, n, y, n, n, n, n, n, n, y, y, n, n, n, n, n, n, y, n, n, n, y, n, y, y, y, ]):
self.assertEqual(r, treesplit.is_trivial_split(i, 0x1F))
#0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
for i, r in enumerate([y, y, y, n, y, n, n, y, y, y, y, n, y, n, n, y, y, n, n, y, n, y, y, y, y, n, n, y, n, y, y, y, ]):
self.assertEqual(r, treesplit.is_trivial_split(i, 0x17))
def countSplits(self, tc, is_rooted):
_LOG.info(tc[0] + "; " + tc[1])
tree_filepaths = [pathmap.tree_source_path(tc[0])]
taxa_filepath = pathmap.tree_source_path(tc[1])
paup_sd = paup.get_split_distribution(tree_filepaths,
taxa_filepath,
is_rooted=is_rooted,
burnin=0)
taxon_set = paup_sd.taxon_set
dp_sd = treesplit.SplitDistribution(taxon_set=taxon_set)
dp_sd.ignore_edge_lengths = True
dp_sd.ignore_node_ages = True
dp_sd.is_rooted = is_rooted
_LOG.debug("Taxon set: %s" % [t.label for t in taxon_set])
taxa_mask = taxon_set.all_taxa_bitmask()
taxon_set.lock()
for tree_filepath in tree_filepaths:
for tree in dataio.tree_source_iter(stream=open(
tree_filepath, "rU"),
schema='nexus',
taxon_set=taxon_set,
as_rooted=is_rooted):
self.assertIs(tree.taxon_set, dp_sd.taxon_set)
self.assertIs(tree.taxon_set, taxon_set)
treesplit.encode_splits(tree)
dp_sd.count_splits_on_tree(tree)
self.assertEqual(dp_sd.total_trees_counted,
paup_sd.total_trees_counted)
# SplitsDistribution counts trivial splits, whereas PAUP*
# contree does not, so the following will not work
# assert len(dp_sd.splits) == len(paup_sd.splits),\
# "dp = %d, sd = %d" % (len(dp_sd.splits), len(paup_sd.splits))
taxa_mask = taxon_set.all_taxa_bitmask()
for split in dp_sd.splits:
if not treesplit.is_trivial_split(split, taxa_mask):
self.assertIn(split, paup_sd.splits)
self.assertEqual(dp_sd.split_counts[split],
paup_sd.split_counts[split])
paup_sd.splits.remove(split)
# if any splits remain, they were not
# in dp_sd or were trivial
remaining_splits = list(paup_sd.splits)
for split in remaining_splits:
if treesplit.is_trivial_split(split, taxa_mask):
paup_sd.splits.remove(split)
self.assertEqual(len(paup_sd.splits), 0)
def refSplitsConflictedNull():
global refSplitDictNull
bm = refTre.taxon_set.all_taxa_bitmask()
for split in refTre.split_edges:
if not treesplit.is_trivial_split(split, bm):
splits = refTre.taxon_set.split_as_newick_string(split)
refSplitDictNull[splits] = []
for j in range(0, 10000):
refSplitDict = {}
randomConflicts = random.sample(newickConflictedReferenceSplitList, len(targetTrees)/10)
for split in refTre.split_edges:
splits = refTre.taxon_set.split_as_newick_string(split)
refSplitDict[splits] = 0
for list in randomConflicts:
for split in list:
if split in refSplitDict:
refSplitDict[split] += 1
for key in refSplitDict:
if key in refSplitDictNull:
refSplitDictNull[key].append(refSplitDict[key])
with open('nullSplits.csv','wb') as file:
writer = csv.writer(file, delimiter='\t')
writer.writerow(refSplitDictNull.keys())
for row in izip_longest(*refSplitDictNull.values(), fillvalue=''):
writer.writerow(row)
file.close()
def refSplitsConflictedNull():
global refSplitDictNull
bm = refTre.taxon_set.all_taxa_bitmask()
for split in refTre.split_edges:
if not treesplit.is_trivial_split(split, bm):
splits = refTre.taxon_set.split_as_newick_string(split)
refSplitDictNull[splits] = []
for j in range(0, 10000):
refSplitDict = {}
randomConflicts = random.sample(newickConflictedReferenceSplitList,
len(targetTrees) / 10)
for split in refTre.split_edges:
splits = refTre.taxon_set.split_as_newick_string(split)
refSplitDict[splits] = 0
for list in randomConflicts:
for split in list:
if split in refSplitDict:
refSplitDict[split] += 1
for key in refSplitDict:
if key in refSplitDictNull:
refSplitDictNull[key].append(refSplitDict[key])
with open('nullSplits.csv', 'wb') as file:
writer = csv.writer(file, delimiter='\t')
writer.writerow(refSplitDictNull.keys())
for row in izip_longest(*refSplitDictNull.values(), fillvalue=''):
writer.writerow(row)
file.close()
def countSplits(self, tc, is_rooted):
_LOG.info(tc[0] + "; " + tc[1])
tree_filepaths = [pathmap.tree_source_path(tc[0])]
taxa_filepath = pathmap.tree_source_path(tc[1])
paup_sd = paup.get_split_distribution(tree_filepaths, taxa_filepath, is_rooted=is_rooted, burnin=0)
taxon_set = paup_sd.taxon_set
dp_sd = treesplit.SplitDistribution(taxon_set=taxon_set)
dp_sd.ignore_edge_lengths = True
dp_sd.ignore_node_ages = True
dp_sd.is_rooted = is_rooted
_LOG.debug("Taxon set: %s" % [t.label for t in taxon_set])
taxa_mask = taxon_set.all_taxa_bitmask()
taxon_set.lock()
for tree_filepath in tree_filepaths:
for tree in dataio.tree_source_iter(
stream=open(tree_filepath, "rU"), schema="nexus", taxon_set=taxon_set, as_rooted=is_rooted
):
self.assertIs(tree.taxon_set, dp_sd.taxon_set)
self.assertIs(tree.taxon_set, taxon_set)
treesplit.encode_splits(tree)
dp_sd.count_splits_on_tree(tree)
self.assertEqual(dp_sd.total_trees_counted, paup_sd.total_trees_counted)
# SplitsDistribution counts trivial splits, whereas PAUP*
# contree does not, so the following will not work
# assert len(dp_sd.splits) == len(paup_sd.splits),\
# "dp = %d, sd = %d" % (len(dp_sd.splits), len(paup_sd.splits))
taxa_mask = taxon_set.all_taxa_bitmask()
for split in dp_sd.splits:
if not treesplit.is_trivial_split(split, taxa_mask):
self.assertIn(split, paup_sd.splits)
self.assertEqual(dp_sd.split_counts[split], paup_sd.split_counts[split])
paup_sd.splits.remove(split)
# if any splits remain, they were not
# in dp_sd or were trivial
remaining_splits = list(paup_sd.splits)
for split in remaining_splits:
if treesplit.is_trivial_split(split, taxa_mask):
paup_sd.splits.remove(split)
self.assertEqual(len(paup_sd.splits), 0)
def runTest(self):
y = True
n = False
for i, r in enumerate([
y,
y,
y,
n,
y,
n,
n,
y,
y,
n,
n,
y,
n,
y,
y,
y,
y,
y,
y,
n,
y,
n,
n,
y,
y,
n,
n,
y,
n,
y,
y,
y,
]):
self.assertEqual(r, treesplit.is_trivial_split(i, 0xF))
for i, r in enumerate([
y,
y,
y,
n,
y,
n,
n,
n,
y,
n,
n,
n,
n,
n,
n,
y,
y,
n,
n,
n,
n,
n,
n,
y,
n,
n,
n,
y,
n,
y,
y,
y,
]):
self.assertEqual(r, treesplit.is_trivial_split(i, 0x1F))
#0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
for i, r in enumerate([
y,
y,
y,
n,
y,
n,
n,
y,
y,
y,
y,
n,
y,
n,
n,
y,
y,
n,
n,
y,
n,
y,
y,
y,
y,
n,
n,
y,
n,
y,
y,
y,
]):
self.assertEqual(r, treesplit.is_trivial_split(i, 0x17))