## with this program. If not, see <http://www.gnu.org/licenses/>.
##
############################################################################
"""
Test character generation
"""
import unittest
import subprocess
import re
import os
import sys
from dendropy import dataio
from dendropy import get_logger
_LOG = get_logger("CharacterSimulationAndGeneration")
from dendropy.tests import paup, is_test_enabled, TestLevel
from dendropy import chargen
tree_model_string = """
#NEXUS
BEGIN TAXA;
DIMENSIONS NTAX=5;
TAXLABELS
A
B
C
D
E
;
#!/usr/bin/env python
import sys
import shutil
import os
import re
import random
from dendropy import get_logger
_LOG = get_logger("igarli_master.py")
num_bootstrap_reps = 100
script_dir = os.path.dirname(os.path.abspath(sys.argv[0]))
if len(sys.argv) < 2:
sys.exit("Expecting a data file (NEXUS) as an argument")
dataf = open(sys.argv[1], 'rU')
dim_pat = re.compile(r'\s*dimensions\s*ntax\s*=\s*(\d+)\s*nchar\s*=\s*(\d+)',
re.I)
rev_dim_pat = re.compile(
r'\s*dimensions\s*nchar\s*=\s*(\d+)\s*ntax\s*=\s*(\d+)', re.I)
n_taxa = None
n_char = None
for line in dataf:
m = dim_pat.match(line)
if m:
n_taxa, n_char = [int(i) for i in m.groups()]
break
else:
m = rev_dim_pat.match(line)
if m:
## with this program. If not, see <http://www.gnu.org/licenses/>.
##
############################################################################
"""
dendropy testing suite
"""
import unittest
import os
import re
import sys
from dendropy import get_logger
from dendropy.utils import find_files
_LOG = get_logger("tests")
class TestLevel:
FAST, NORMAL, SLOW, EXHAUSTIVE = 0, 10, 20, 30
def name(i):
if i <= TestLevel.FAST:
return "FAST"
if i <= TestLevel.NORMAL:
return "NORMAL"
if i <= TestLevel.SLOW:
return "SLOW"
return "EXHAUSTIVE"
name = staticmethod(name)
def name_to_int(l):
try:
import getpass
except:
pass
import platform
import dendropy
from dendropy import nexus
from dendropy import splits
from dendropy import treesum
from dendropy import datasets
from dendropy import trees
from dendropy import treegen
from dendropy import get_logger
from dendropy.datasets import Dataset
from dendropy.dataio import MultiFileTreeIterator
_LOG = get_logger("symmdiff_by_split_cutoff")
_program_name = 'symmdiff_by_split_cutoff'
_program_version = "0.01"
_program_author = 'Mark T. Holder'
_program_contact = '*****@*****.**'
_program_copyright = "Copyright (C) 2008 Mark T. Holder.\n" \
"License GPLv3+: GNU GPL version 3 or later.\n" \
"This is free software: you are free to change\nand redistribute it. " \
"There is NO WARRANTY,\nto the extent permitted by law."
def main_cli():
description = '%s %s ' % (_program_name, _program_version)
usage = "%prog [options] <TREES FILE> [<TREES FILE> [<TREES FILE> [...]]"
import getpass
except:
pass
import platform
import dendropy
from dendropy import nexus
from dendropy import splits
from dendropy import treesum
from dendropy import datasets
from dendropy import trees
from dendropy import treegen
from dendropy import get_logger
from dendropy.datasets import Dataset
from dendropy.dataio import MultiFileTreeIterator
_LOG = get_logger("symmdiff_by_split_cutoff")
_program_name = 'symmdiff_by_split_cutoff'
_program_version = "0.01"
_program_author = 'Mark T. Holder'
_program_contact = '*****@*****.**'
_program_copyright = "Copyright (C) 2008 Mark T. Holder.\n" \
"License GPLv3+: GNU GPL version 3 or later.\n" \
"This is free software: you are free to change\nand redistribute it. " \
"There is NO WARRANTY,\nto the extent permitted by law."
def main_cli():
description = '%s %s ' % (_program_name, _program_version)
usage = "%prog [options] <TREES FILE> [<TREES FILE> [<TREES FILE> [...]]"
## with this program. If not, see <http://www.gnu.org/licenses/>.
##
############################################################################
"""
Tests optional tree modifiers.
"""
import random
import unittest
import itertools
from dendropy import get_logger
from dendropy.datasets import Dataset
from dendropy.tests.debugging_random import DebuggingRandom
from dendropy.tests.util_for_testing import assert_vec_approx_equal, assert_approx_equal
import dendropy.tests
_LOG = get_logger("TreeModification")
### MODULE THAT WE ARE TESTING ###
from dendropy.treecalc import pybus_harvey_gamma
### MODULE THAT WE ARE TESTING ###
class CalcTreeTest(unittest.TestCase):
def testPHGamma(self):
newick = "((t5:0.161175,t6:0.161175):0.392293,((t4:0.104381,(t2:0.075411,t1:0.075411):0.028969):0.065840,t3:0.170221):0.383247);"
d = Dataset()
tree = d.trees_from_string(string=newick, format="NEWICK")[0]
assert_approx_equal(pybus_harvey_gamma(tree), 0.546276)
if __name__ == "__main__":
## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
## GNU General Public License for more details.
##
## You should have received a copy of the GNU General Public License along
## with this program. If not, see <http://www.gnu.org/licenses/>.
##
############################################################################
"""
Tests tree traversal.
"""
import unittest
from dendropy import get_logger
from dendropy.datasets import Dataset
import dendropy.tests
_LOG = get_logger("TreeStructureAndTraversal")
### MODULE THAT WE ARE TESTING ###
from dendropy import trees
### MODULE THAT WE ARE TESTING ###
class TreeIterTest(unittest.TestCase):
def build_fixed_basic_tree1(self):
"""
Returns a bifurcating basic tree looking like:
http://en.wikipedia.org/wiki/Tree_traversal
( ( A,
( C,
E
## You should have received a copy of the GNU General Public License along
## with this program. If not, see <http://www.gnu.org/licenses/>.
##
############################################################################
import sys
import re
import copy
from cStringIO import StringIO
from dendropy.taxa import TaxaBlock
from dendropy.datasets import Dataset
from dendropy.splits import encode_splits, is_trivial_split, find_edge_from_split, SplitDistribution
from dendropy.treesum import TreeSummarizer
from dendropy import get_logger
_LOG = get_logger("igarli_neighborhood.py")
#garli_dna_model_pattern = r'\[!GarliModel r ([.0-9]*) ([.0-9]*) ([.0-9]*) ([.0-9]*) ([.0-9]*) e ([.0-9]*) ([.0-9]*) ([.0-9]*) [.0-9]* a ([.0-9]*) p ([.0-9]*) \]'
garli_dna_model_pattern = r'\[!GarliModel\s*(r [.0-9]* [.0-9]* [.0-9]* [.0-9]* [.0-9]* e [.0-9]* [.0-9]* [.0-9]* [.0-9]* a [.0-9]* p [.0-9]*)\s*\]'
garli_after_name_tm_pattern = r'\s*=\s*\[&U\]\[!GarliScore ([-.0-9]*)\]\s*%s\s*(\(.*\))\s*;' % garli_dna_model_pattern
garli_after_name_tree_pattern = r'\s*=\s*\[&U\]\[!GarliScore ([-.0-9]*)\]\s*(\(.*\))\s*;'
tree_prefix = r'\[iGarli\s*(\d+)\s*\] tree [a-zA-Z0-9_]+'
tm_pat_string = tree_prefix + garli_after_name_tm_pattern
tree_pat_string = tree_prefix + garli_after_name_tree_pattern
garli_tree_model_pat = re.compile(tm_pat_string)
garli_tree_pat = re.compile(tree_pat_string)
"""
Various calls to PAUP* to calculate stuff.
"""
import os
import sys
import subprocess
import tempfile
import re
import csv
import unittest
import dendropy.tests
from dendropy import get_logger
_LOG = get_logger("PAUPWrapper")
from dendropy import datasets
from dendropy import dataio
from dendropy import taxa
from dendropy import splits
from dendropy import utils
if "PAUP_PATH" in os.environ:
PAUP_PATH = os.environ["PAUP_PATH"]
else:
PAUP_PATH = "paup"
###############################################################################
##
## You should have received a copy of the GNU General Public License along
## with this program. If not, see <http://www.gnu.org/licenses/>.
##
############################################################################
"""
Tests dataset reading & writing
"""
import unittest
import csv
from dendropy import get_logger
import dendropy.tests
_LOG = get_logger("DatsetReadWrite")
from dendropy import datasets
class DatasetReadTest(unittest.TestCase):
def compare_chars(self, src, format, expected):
"""Reads 'src', checks against 'expected'"""
_LOG.info("Reading %s" % src.name)
d = datasets.Dataset()
d.read(src, format)
taxa_block = d.taxa_blocks[0]
char_block = d.char_blocks[0]
assert len(expected) == len(char_block)
trees, models etc.
"""
import os
import sys
if sys.version_info > (3, ):
from io import StringIO
else:
from cStringIO import StringIO
from dendropy import base
from dendropy import taxa
from dendropy import characters
from dendropy import trees
from dendropy import get_logger
_LOG = get_logger("dendropy.datasets")
def cache_reader_state(reader, **kwargs):
cache = {
"encode_splits": reader.encode_splits,
"finish_node_func": reader.finish_node_func,
}
reader.encode_splits = kwargs.get("encode_splits", False)
reader.finish_node_func = kwargs.get("finish_node_func")
r = kwargs.get("default_rooting")
if r is not None:
cache["default_rooting"] = reader.default_rooting
reader.default_rooting = r
return cache
"""
Tests of the strict consensus merger
"""
import os
import sys
import unittest
import copy
from dendropy import get_logger
from dendropy.taxa import TaxaBlock
from dendropy.splits import encode_splits
from dendropy.dataio import trees_from_newick
from dendropy.tests import is_test_enabled, TestLevel
from dendropy.treedists import symmetric_difference
from dendropy.tests.debugging_random import DebuggingRandom
from dendropy.treegen import randomly_reorient_tree
_LOG = get_logger("StrictConsensusMerger")
### MODULE THAT WE ARE TESTING ###
from dendropy.scripts.strict_consensus_merge import strict_consensus_merge
### MODULE THAT WE ARE TESTING ###
_counter = 0
class SCMTest(unittest.TestCase):
def kernelOfTest(self, trees):
expected = trees[-1]
input = trees[:-1]
output = strict_consensus_merge(input)
encode_splits(output)
encode_splits(expected)
############################################################################
"""
This module handles the core definition of tree data structure class,
as well as all the structural classes that make up a tree.
"""
import sys
if sys.version_info > (3, ):
from io import StringIO
else:
from cStringIO import StringIO
from dendropy import base
from dendropy import taxa
import math
from dendropy import get_logger
_LOG = get_logger('dendropy.trees')
##############################################################################
## TreesBlock
class TreesBlock(list, taxa.TaxaLinked):
"Tree manager."
def __init__(self, *args, **kwargs):
"Inits. Handles keyword arguments: `oid`, `label` and `taxa_block`."
list.__init__(self, *args)
taxa.TaxaLinked.__init__(self, *args, **kwargs)
def normalize_taxa(self, taxa_block=None, clear=True):
"""
#!/usr/bin/env python
import sys
import copy
import logging
from dendropy import dataio
from dendropy.splits import encode_splits, split_to_list, count_bits, lowest_bit_only
from dendropy import get_logger
from dendropy.treemanip import collapse_clade, collapse_edge
from dendropy.trees import format_split
_LOG = get_logger('scripts.strict_consensus_merge')
verbose = False
IS_DEBUG_LOGGING = _LOG.isEnabledFor(logging.DEBUG)
from dendropy.utils import NormalizedBitmaskDict
def reroot_on_lowest_common_index_path(t, common_mask):
"""This operation is only for unrooted trees that are being merged using
SCM. The path the separates the lowest index taxon in the leaf set
intersection is placed as the first descendant path of the "seed_node" for
the tree.
This assures that all split representations are oriented in the same way
for subsequent operations.
The mask most contain more that 2 bits (there must be an internal node in
the tree that is has degree > 2 wrt the common leafset).
"""
l = lowest_bit_only(common_mask)
assert (l > 0)
assert (count_bits(common_mask) > 2)
## You should have received a copy of the GNU General Public License along
## with this program. If not, see <http://www.gnu.org/licenses/>.
##
############################################################################
"""
Split calculation and management.
"""
import sys
from dendropy import taxa
from dendropy import trees
from dendropy import treegen
from dendropy import utils
from dendropy import get_logger
_LOG = get_logger("dendropy.splits")
def lowest_bit_only(s):
m = s & (s - 1)
return m ^ s
__n_bits_set = (0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4)
def count_bits(a):
'''Returns the number of bits set to one.'''
global __n_bits_set
if sys.version_info >= (3, ):
c = int(a)
"""
Test split summarization, consensus tree building etc.
"""
import unittest
import subprocess
import re
import os
import sys
from dendropy import nexus
from dendropy import get_logger
import dendropy.tests
from dendropy.tests import paup, is_test_enabled, TestLevel
_LOG = get_logger("Splits")
from dendropy import nexus
from dendropy import treesum
from dendropy import taxa
from dendropy import splits
large_cases = [ #('7180.tre', '7180.tre'),
#('terrarana.random.unrooted.100.tre', 'terrarana.random.unrooted.100.tre'),
('terrarana.random.unrooted.30.tre', 'terrarana.random.rooted.30.tre'),
('anolis.mcmct.trees.nexus', 'anolis.chars.nexus'),
]
small_cases = [
('feb032009.tre', 'feb032009.tre'),
('maj-rule-bug1.tre', 'maj-rule-bug1.tre'),
('maj-rule-bug2.tre', 'maj-rule-bug2.tre'),
##
## You should have received a copy of the GNU General Public License along
## with this program. If not, see <http://www.gnu.org/licenses/>.
##
############################################################################
"""
Tests character block manipulations.
"""
import unittest
from copy import deepcopy
from dendropy import get_logger
from dendropy import get_logging_level
import dendropy.tests
from dendropy import datasets
_LOG = get_logger("CharacterBlockStructure")
from dendropy import characters
class CharStructTest(unittest.TestCase):
def testCharBlockMerge(self):
ds1 = datasets.Dataset()
tb1 = ds1.add_taxa_block(label="Dataset 1, Taxa Block 1")
for i in range(1, 11):
tb1.add_taxon(label="T%02d" % i)
cb1 = ds1.add_char_block(char_block=characters.DnaCharactersBlock(
label="Dataset 2, Taxa Block 1"))
for t in tb1:
cb1.append_taxon_sequence(t, state_symbols="AAAAAAAAAA")
##
## This program is distributed in the hope that it will be useful,
## but WITHOUT ANY WARRANTY; without even the implied warranty of
## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
## GNU General Public License for more details.
##
## You should have received a copy of the GNU General Public License along
## with this program. If not, see <http://www.gnu.org/licenses/>.
##
############################################################################
"""
This module provides classes and methods for managing taxa.
"""
import sys
from dendropy import base, get_logger
_LOG = get_logger('dendropy.taxa')
if sys.version_info[1] > 5 or sys.version_info[0] > 2:
def int_to_bitstring(n):
assert n >= 0
return bin(n)[2:]
else:
def int_to_bitstring(n):
m = 1
sl = []
while m <= n:
if m & n:
sl.insert(0, '1')
else:
## but WITHOUT ANY WARRANTY; without even the implied warranty of
## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
## GNU General Public License for more details.
##
## You should have received a copy of the GNU General Public License along
## with this program. If not, see <http://www.gnu.org/licenses/>.
##
############################################################################
"""
Tests coalescence calculations.
"""
import unittest
from dendropy import get_logger
from dendropy import datasets
_LOG = get_logger("TreeCoal")
### MODULE THAT WE ARE TESTING ###
from dendropy import coalescent
### MODULE THAT WE ARE TESTING ###
class CalcIntervalsTest(unittest.TestCase):
def testSimple1(self):
d = datasets.Dataset()
t = d.trees_from_string(
"((((a:1, b:1):1, c:2):1, d:3, e:3):2, (f:4, g:4):1)", "newick")[0]
i1 = coalescent.coalescence_intervals(t)
assert i1 == [1.0, 1.0, 1.0, 1.0,
1.0], "intervals found = %s" % ", ".join(intervals)
i2 = coalescent.num_genes_waiting_times_pairs(t)
## with this program. If not, see <http://www.gnu.org/licenses/>.
##
############################################################################
"""
Tests tree distances.
"""
import random
import unittest
import math
import copy
from dendropy import get_logger
from dendropy.treedists import symmetric_difference
from dendropy.splits import encode_splits, split_to_list, count_bits, lowest_bit_only
import dendropy.tests
_LOG = get_logger("TreeGenerationAndSimulation")
from dendropy import dataio
from dendropy.tests.util_for_testing import assert_approx_equal, assert_vec_approx_equal, assert_mat_approx_equal
### MODULE THAT WE ARE TESTING ###
from dendropy.treemanip import *
### MODULE THAT WE ARE TESTING ###
class TreeManipTest(unittest.TestCase):
def testCollapseEdge(self):
tree = dataio.trees_from_newick(["((t5,t6),((t4,(t2,t1)),t3));"
]).trees_blocks[0][0]
root = tree.seed_node
self.assertEqual(str(tree), "((t5,t6),((t4,(t2,t1)),t3))")
## GNU General Public License for more details.
##
## You should have received a copy of the GNU General Public License along
## with this program. If not, see <http://www.gnu.org/licenses/>.
##
############################################################################
"""
Tests various utilities
"""
import unittest
from dendropy import get_logger
import dendropy.tests
_LOG = get_logger("Utilities")
### MODULES THAT WE ARE TESTING ###
from dendropy import utils
### MODULES THAT WE ARE TESTING ###
class NormalizedBitmaskDict(unittest.TestCase):
def test_complementing(self):
mask = 0xFF # 1111 1111
splits = [
((0x03, '0000 0011'), (0x03, '0000 0011')),
((0x34, '0011 0100'), (0xCB, '1100 1011')),
((0x44, '0100 0100'), (0xBB, '1011 1011')),
import cStringIO
from optparse import OptionParser
from subprocess import Popen, PIPE
from dendropy import nexus
from dendropy.splits import encode_splits, lowest_bit_only, iter_split_indices, find_edge_from_split, collapse_conflicting, is_trivial_split, split_as_string_rev
from dendropy.characters import CharactersBlock
from dendropy.taxa import TaxaBlock
from dendropy.treedists import symmetric_difference
from dendropy import treesum
from dendropy.trees import format_split, TreesBlock
from dendropy import treegen
from dendropy import get_logger
from dendropy.datasets import Dataset
from dendropy.utils import LineReadingThread, Event
_LOG = get_logger("incrGarl.py")
_program_name = 'incrGarl.py'
_program_version = "0.01"
_program_author = 'Mark T. Holder'
_program_contact = '*****@*****.**'
_program_copyright = "Copyright (C) 2008 Mark T. Holder.\n" \
"License GPLv3+: GNU GPL version 3 or later.\n" \
"This is free software: you are free to change\nand redistribute it. " \
"There is NO WARRANTY,\nto the extent permitted by law."
TAXON_TO_TRANSLATE = {}
GARLI_GENERAL = (
"datafname",
"constraintfile",
import os
import sys
from dendropy import nexus
from dendropy import get_logger
import dendropy.tests
from dendropy.tests import is_test_enabled, TestLevel
import itertools
from dendropy.treedists import symmetric_difference
from dendropy.splits import SplitDistribution
from dendropy.treesum import TreeSummarizer
from dendropy import dataio
from dendropy.nexus import RootingInterpretation
from dendropy.splits import encode_splits
from dendropy.datasets import Dataset
_LOG = get_logger("SumTreesTesting")
class SumTreesTest(unittest.TestCase):
def setUp(self):
self.sumtrees_path = dendropy.tests.scripts_source_path("sumtrees.py")
def compose_sumtrees_command(self, args):
return "%s %s" % (self.sumtrees_path, " ".join(args))
def runSumTrees(self, args):
command = self.compose_sumtrees_command(args)
_LOG.debug("Invocation:\n" + command)
run = subprocess.Popen(command,
shell=True,
stdout=subprocess.PIPE,
##
## You should have received a copy of the GNU General Public License along
## with this program. If not, see <http://www.gnu.org/licenses/>.
##
############################################################################
"""
Tree summarization.
"""
import sys
from dendropy import splits
from dendropy import taxa
from dendropy import trees
from dendropy import treegen
from dendropy import get_logger
_LOG = get_logger("dendropy.treesum")
def shallowest_containing_node(start_node, split, taxa_mask):
"""Returns the shallowest node in the tree (the node furthest from
`start_node`) that has all of the taxa that are specified in `split` or
None if no appropriate node is found.
Assumes that edges on tree have been decorated with splits.
It is possible that split is not compatible with the subtree that is
returned! (compatibility tests are not fully performed).
This function is used to find the "insertion point" for a new split via a
root to tip search.
"""
import os
import sys
import itertools
import copy
from optparse import OptionParser
from dendropy import nexus
from dendropy.splits import encode_splits, lowest_bit_only
from dendropy import treesum
from dendropy import datasets
from dendropy.trees import format_split
from dendropy import treegen
from dendropy import get_logger
from dendropy.datasets import Dataset
_LOG = get_logger("incrGarl.py")
_program_name = 'incrGarl.py'
_program_version = "0.01"
_program_author = 'Mark T. Holder'
_program_contact = '*****@*****.**'
_program_copyright = "Copyright (C) 2008 Mark T. Holder.\n" \
"License GPLv3+: GNU GPL version 3 or later.\n" \
"This is free software: you are free to change\nand redistribute it. " \
"There is NO WARRANTY,\nto the extent permitted by law."
TAXON_TO_TRANSLATE = {}
GARLI_GENERAL = (
"datafname",
"constraintfile",
import os
from optparse import OptionGroup
from optparse import OptionParser
import sys
if sys.version_info > (3, ):
from io import StringIO
else:
from cStringIO import StringIO
from dendropy import get_logger
from dendropy.datasets import Dataset
from dendropy import get_logging_level
import dendropy.tests
_LOG = get_logger("TreeParsingAndWriting")
from dendropy import taxa
from dendropy import trees
from dendropy import utils
from dendropy.splits import encode_splits
from dendropy import treedists
from dendropy import datasets
### MODULES THAT WE ARE TESTING ###
from dendropy import nexus
# from dendropy import nexml
### MODULES THAT WE ARE TESTING ###
def iterate_on_trees(tree_files, tf_iterator=nexus.iterate_over_trees):
## You should have received a copy of the GNU General Public License along
## with this program. If not, see <http://www.gnu.org/licenses/>.
##
############################################################################
import sys
import re
import copy
from cStringIO import StringIO
from dendropy.taxa import TaxaBlock
from dendropy.datasets import Dataset
from dendropy.splits import encode_splits, is_trivial_split, find_edge_from_split, SplitDistribution
from dendropy.treesum import TreeSummarizer
from dendropy import get_logger
_LOG = get_logger("igarli_select.py")
# this should not be hard coded
MAX_TREES_CARRIED_OVER = 1000
SPLIT_DIVERSITY_MULTIPLIER = 1.0
#garli_dna_model_pattern = r'\[!GarliModel r ([.0-9]*) ([.0-9]*) ([.0-9]*) ([.0-9]*) ([.0-9]*) e ([.0-9]*) ([.0-9]*) ([.0-9]*) [.0-9]* a ([.0-9]*) p ([.0-9]*) \]'
garli_dna_model_pattern = r'\[!GarliModel\s*(r [.0-9]* [.0-9]* [.0-9]* [.0-9]* [.0-9]* e [.0-9]* [.0-9]* [.0-9]* [.0-9]* a [.0-9]* p [.0-9]*)\s*\]'
garli_after_name_tm_pattern = r'\s*=\s*\[&U\]\[!GarliScore ([-.0-9]*)\]\s*%s\s*(\(.*\))\s*;' % garli_dna_model_pattern
garli_after_name_tree_pattern = r'\s*=\s*\[&U\]\[!GarliScore ([-.0-9]*)\]\s*(\(.*\))\s*;'
tree_prefix = r'\[iGarli\s*(\d+)\s*\] tree [a-zA-Z0-9_]+'
tm_pat_string = tree_prefix + garli_after_name_tm_pattern
##
## You should have received a copy of the GNU General Public License along
## with this program. If not, see <http://www.gnu.org/licenses/>.
##
############################################################################
import sys
import re
import copy
from cStringIO import StringIO
from dendropy.taxa import TaxaBlock
from dendropy.datasets import Dataset
from dendropy.splits import encode_splits, is_trivial_split, find_edge_from_split, SplitDistribution
from dendropy.treesum import TreeSummarizer
from dendropy import get_logger
_LOG = get_logger("igarli_select.py")
# this should not be hard coded
MAX_TREES_CARRIED_OVER = 1000
SPLIT_DIVERSITY_MULTIPLIER = 1.0
#garli_dna_model_pattern = r'\[!GarliModel r ([.0-9]*) ([.0-9]*) ([.0-9]*) ([.0-9]*) ([.0-9]*) e ([.0-9]*) ([.0-9]*) ([.0-9]*) [.0-9]* a ([.0-9]*) p ([.0-9]*) \]'
garli_dna_model_pattern = r'\[!GarliModel\s*(r [.0-9]* [.0-9]* [.0-9]* [.0-9]* [.0-9]* e [.0-9]* [.0-9]* [.0-9]* [.0-9]* a [.0-9]* p [.0-9]*)\s*\]'
garli_after_name_tm_pattern = r'\s*=\s*\[&U\]\[!GarliScore ([-.0-9]*)\]\s*%s\s*(\(.*\))\s*;' % garli_dna_model_pattern
garli_after_name_tree_pattern = r'\s*=\s*\[&U\]\[!GarliScore ([-.0-9]*)\]\s*(\(.*\))\s*;'
tree_prefix = r'\[iGarli\s*(\d+)\s*\] tree [a-zA-Z0-9_]+'
tm_pat_string = tree_prefix + garli_after_name_tm_pattern
tree_pat_string = tree_prefix + garli_after_name_tree_pattern
garli_tree_model_pat = re.compile(tm_pat_string)
garli_tree_pat = re.compile(tree_pat_string)
## GNU General Public License for more details.
##
## You should have received a copy of the GNU General Public License along
## with this program. If not, see <http://www.gnu.org/licenses/>.
##
############################################################################
"""
Tests tree distances.
"""
import random
import unittest
import math
from dendropy import get_logger
import dendropy.tests
_LOG = get_logger("tree diste ")
from dendropy import dataio
from dendropy.splits import encode_splits
from dendropy.tests.util_for_testing import assert_approx_equal, assert_vec_approx_equal, assert_mat_approx_equal
### MODULE THAT WE ARE TESTING ###
from dendropy import treedists
### MODULE THAT WE ARE TESTING ###
class TreeDistTest(unittest.TestCase):
def testEuclideanDist(self):
d = dataio.trees_from_newick([
"((t5:0.161175,t6:0.161175):0.392293,((t4:0.104381,(t2:0.075411,t1:0.075411):1):0.065840,t3:0.170221):0.383247);",
"((t5:2.161175,t6:0.161175):0.392293,((t4:0.104381,(t2:0.075411,t1:0.075411):1):0.065840,t3:0.170221):0.383247);",
#!/usr/bin/env python
import sys
import shutil
import os
import re
import random
from dendropy import get_logger
_LOG = get_logger("igarli_master.py")
num_bootstrap_reps = 100
script_dir = os.path.dirname(os.path.abspath(sys.argv[0]))
if len(sys.argv) < 2:
sys.exit("Expecting a data file (NEXUS) as an argument")
dataf = open(sys.argv[1], 'rU')
dim_pat = re.compile(r'\s*dimensions\s*ntax\s*=\s*(\d+)\s*nchar\s*=\s*(\d+)', re.I)
rev_dim_pat = re.compile(r'\s*dimensions\s*nchar\s*=\s*(\d+)\s*ntax\s*=\s*(\d+)', re.I)
n_taxa = None
n_char = None
for line in dataf:
m = dim_pat.match(line)
if m:
n_taxa, n_char = [int(i) for i in m.groups()]
break
else:
m = rev_dim_pat.match(line)
import sys
if sys.version_info > (3, ):
from io import StringIO
else:
from cStringIO import StringIO
from dendropy.datasets import Dataset
from dendropy.trees import TreesBlock
from dendropy import nexus
from dendropy.nexus import RootingInterpretation
from dendropy import nexml
from dendropy import fasta
from dendropy import phylip
from dendropy import get_logger, deprecation
_LOG = get_logger('dataio')
############################################################################
## File Formats
NEXUS='NEXUS'
NEWICK='NEWICK'
NEXML='NEXML'
FASTA='FASTA'
PHYLIP='PHYLIP'
FORMATS = [NEXUS, NEXML, NEWICK, FASTA, PHYLIP]
READERS = {
NEXUS: nexus.NexusReader,
NEWICK: nexus.NewickReader,
NEXML: nexml.NexmlReader,