def plot_subgraph(filename, conf_interval_alpha=None, confidence_file=None):
if confidence_file is None:
confidence_filename = '.'.join(filename.split('.')[:-1]) + '_conf.txt'
else:
confidence_filename = confidence_file
outp = make_plottable_graph(filename,
conf_interval_alpha=conf_interval_alpha)
(percentage, ess,
(min_ess, max_ess)), stree, nodes, smean_branches, smean_admixtures = outp
branch_generator = generate_predefined_list_string(
[' c' + str(i) for i in range(1,
len(smean_branches) + 1)])
admix_generator = generate_predefined_list_string(
['a' + str(i) for i in range(1,
len(smean_admixtures) + 1)])
nodes_generator = generate_predefined_list_string(deepcopy(nodes))
tree = identifier_to_tree(stree,
leaves=nodes_generator,
branch_lengths=branch_generator,
admixture_proportions=admix_generator)
print pretty_string(tree)
plot_as_directed_graph(tree, plot_edge_lengths=True)
with open(confidence_filename, 'w') as f:
for n, row in enumerate(smean_branches):
f.write('c' + str(n + 1) + ': ' + row + '\n')
for n, row in enumerate(smean_admixtures):
f.write('a' + str(n + 1) + ': ' + row + '\n')
def visualize_topology(stree):
numba=str(np.random.randint(0,1000000))
filename='tree'+numba+'.png'
if ';' in stree:
plot_as_directed_graph(identifier_to_tree_clean(stree), drawing_name= filename, popup=False)
else:
plot_as_directed_graph(topological_identifier_to_tree_clean(stree), drawing_name= filename, popup=False)
return filename
def topological_support(start_tree, n=10000, nodes=None):
from tree_plotting import plot_as_directed_graph, plot_graph, pretty_print, pretty_string
tree = start_tree
score = 0
for i in range(n):
prop_index = choice(3, 1)
if prop_index == 0 and get_number_of_admixes(tree) > 0:
new_tree = deladmix(tree)[0]
score -= 1
elif prop_index == 1:
new_tree = make_regraft(tree, _get_new_nodes(i, prop_index))[0]
elif prop_index == 2:
new_tree = addadmix(tree, _get_new_nodes(i, prop_index))[0]
score += 1
else:
new_tree = tree
consistent, information = make_consistency_checks(new_tree, nodes)
if consistent:
if get_number_of_admixes(new_tree) < 50:
tree = new_tree
else:
print information
print 'last_good_tree', tree
print 'new_bad_tree', new_tree
plot_as_directed_graph(tree, drawing_name='before.png')
wait(1)
plot_as_directed_graph(new_tree, drawing_name='after.png')
wait(1)
if i % 1000 == 0:
plot_as_directed_graph(tree,
drawing_name='number_' + str(i) + 'K.png')
wait(1)
plot_as_directed_graph(tree, drawing_name='final_tree.png')
wait(1)
return score
def extend_summary(filename,
df=10,
resfile='test.csv',
other_trees=[],
other_trees_tree_files=[]):
ad = file_to_list_of_rows(filename)
print ad
_, names, _, values = ad
print values[11]
true_tree = identifier_to_tree_clean(values[11])
plot_as_directed_graph(true_tree)
summaries = get_summaries(true_tree, df)
analyse_results.generate_summary_csv(summaries,
reference_tree=true_tree,
filename=resfile)
def many_admixes(self, n=100):
for i in xrange(n):
self.tree = addadmix(
self.tree,
new_node_names=['n' + str(i) + a for a in ['o', 'n']])
#plot_graph(self.tree)
if self.no_admixes + 1 == get_number_of_admixes(self.tree):
print 'INCREASED NUMBER OF ADMIXTURES BY ONE= ' + 'TRUE'
else:
print 'INCREASED NUMBER OF ADMIXTURES BY ONE= ' + 'FALSE'
self.no_admixes = get_number_of_admixes(self.tree)
ad = make_consistency_checks(self.tree, ['s1', 's2', 's3', 's4'])
if not ad[0]:
print ad
plot_graph(self.tree, drawing_name='bad.png')
break
plot_as_directed_graph(self.tree)
def autogenerate_tree(no_leaves,
no_admixtures,
minimum_number_of_nonzeros=1,
minimum_number_of_zeros=1):
while True:
tree = generate_phylogeny(no_leaves, no_admixtures)
cov = make_covariance(tree)
zeros = [get_number_of_zeros(row) for row in cov]
no_non_zeros = cov.shape[0] - max(zeros)
if no_non_zeros >= minimum_number_of_nonzeros and max(
zeros) >= minimum_number_of_zeros:
break
tree = add_outgroup(tree, 'z', 0.234, 1.96, 'Aa')
cov = make_covariance(tree)
print cov
print reduce_covariance(cov, 0)
plot_as_directed_graph(tree)
suffix = str(no_leaves) + '_' + str(no_admixtures) + '_' + str(
minimum_number_of_nonzeros) + '_' + str(minimum_number_of_zeros)
return unique_identifier_and_branch_lengths(tree), suffix
def __call__(self, tree, **not_needed):
#print tree
#print not_needed
#print tree
Rtree = identifier_to_tree_clean(
tree, leaves=generate_predefined_list_string(deepcopy(self.nodes)))
#print pretty_string(Rtree)
if self.subnodes: #DETTE TAGER IKKE ORDENTLIG HOJDE FOR KOVARIANSMATRICERNE SOM BLIVER FORKERTE
try:
Rtree = get_subtree(Rtree, self.subnodes)
except AssertionError:
print pretty_string(Rtree)
from tree_plotting import plot_as_directed_graph
plot_as_directed_graph(Rtree)
print 'input_tree', tree
print 'nodes', self.nodes
print 'subnodes', self.subnodes
assert False
if self.remove_sadtrees and (not admixes_are_sadmixes(Rtree)):
print 'returned true because adtrees are not sad'
return {'Rtree': Rtree}, True
return {'Rtree': Rtree}, False
def plot_big_tree(stree):
plot_as_directed_graph(identifier_to_tree_clean(stree))
from tree_plotting import plot_as_directed_graph, pretty_string
from tree_statistics import topological_identifier_to_tree_clean, identifier_to_tree_clean, identifier_file_to_tree_clean
from Rtree_to_coefficient_matrix import get_numbers
import sys
count = 0
if len(sys.argv) <= 1:
while True:
var = raw_input("Please enter something: ")
if var == 'q' or var == 'exit' or var == 'q()' or var == 'exit()':
break
if ';' in var:
tree = identifier_to_tree_clean(var)
print get_numbers(tree)
plot_as_directed_graph(tree,
drawing_name='tmp' + str(count) + '.png')
else:
tree = topological_identifier_to_tree_clean(var)
print get_numbers(tree)
plot_as_directed_graph(tree,
drawing_name='tmp' + str(count) + '.png')
count += 1
else:
files = sys.argv[1:]
for fil in files:
tree = identifier_file_to_tree_clean(fil)
print get_numbers(tree)
plot_as_directed_graph(tree, drawing_name='tmp' + str(count) + '.png')
count += 1
# filename_treeout='../../../../trmx2.treeout'
# filename_vertices='../../../../trmx2.vertices'
# filename_edges='../../../../trmx2.edges'
tree = treemix_file_to_admb_files(
filename_treeout,
filename_vertices,
filename_edges,
outgroup='out',
snodes=['s' + str(i) for i in range(1, 11)],
prefix='sletmig' + os.sep,
return_format='outgroup_rooted')
#tree=read_treemix_file2('../../../../Dropbox/Bioinformatik/AdmixtureBayes/treemix_example3/new_one2.treeout',
# '../../../../Dropbox/Bioinformatik/AdmixtureBayes/treemix_example3/new_one2.vertices',
# '../../../../Dropbox/Bioinformatik/AdmixtureBayes/treemix_example3/new_one2.edges', outgroup='out')
import tree_plotting
tree_plotting.plot_as_directed_graph(tree)
from tree_warner import check
check(tree)
print pretty_string(tree)
import numpy as np
print pretty_string(tree)
from Rtree_to_covariance_matrix import make_covariance
from reduce_covariance import reduce_covariance, Areduce
cov = make_covariance(tree,
node_keys=['out'] +
['s' + str(i) for i in range(1, 10)])
print cov
cov2 = np.loadtxt(
'../../../../Dropbox/Bioinformatik/AdmixtureBayes/treemix_example3/anew.txt'
from tree_statistics import identifier_to_tree_clean
from tree_plotting import plot_as_directed_graph, pretty_string
#from sphinx.util.nodes import _new_copy
true_tree_s= 'w.w.w.w.w.w.a.a.w-c.w.c.c.w.c.5.0.w.3.2-c.w.w.0.c.4.w-c.w.0.c.4-w.c.1-c.0;0.07-0.974-1.016-0.089-0.81-0.086-1.499-0.052-1.199-2.86-0.403-0.468-0.469-1.348-1.302-1.832-0.288-0.18-0.45-0.922-2.925-3.403;0.388-0.485'
true_tree=identifier_to_tree_clean(true_tree_s)
wrong_trees_s=['w.w.a.w.w.a.a.a.w-c.w.c.c.w.w.c.0.w.w.6.3.2-c.w.w.0.w.c.5.w.w-c.w.0.c.4.w.w-c.w.c.4.0-w.c.1-c.0;0.828-0.21-0.197-0.247-0.568-1.06-0.799-1.162-2.632-2.001-0.45-1.048-0.834-0.469-0.191-2.759-0.871-1.896-0.473-0.019-1.236-0.287-0.179-0.981-0.456-0.91-2.114-3.368;0.655-0.506-0.389-0.23',
'w.w.w.w.w.w.a.a.w-w.w.w.c.w.c.5.a.w.3.a-c.w.c.w.c.4.w.w.0.2.a-w.w.w.w.c.c.4.5.w-c.c.w.w.1.0.w-c.w.w.0.w-c.w.0.w-a.w.w-c.w.0.w-c.w.0-c.0;0.387-0.087-0.806-0.082-2.062-0.803-0.122-0.544-0.061-0.733-0.474-1.342-0.871-0.798-0.753-0.288-0.024-0.174-0.754-0.282-0.45-0.924-0.416-1.081-0.467-1.296-1.171-0.54-1.944-0.258-8.813-0.76-0.073-3.416;0.388-0.467-0.098-0.185-0.019-0.44']
wrong_trees=[identifier_to_tree_clean(tree) for tree in wrong_trees_s]
plot_as_directed_graph(true_tree, drawing_name= 'tmp0.bmp')
plot_as_directed_graph(wrong_trees[0], drawing_name = 'tmp1.bmp')
print pretty_string(wrong_trees[0])
t=wrong_trees[0]
from Rproposal_admix import deladmix
pks={}
from Rtree_to_covariance_matrix import make_covariance
from posterior import initialize_big_posterior
true_cov=make_covariance(true_tree)
posterior_f=initialize_big_posterior(true_cov, M=10000)
nt, f,b=deladmix(t,pks=pks, fixed_remove=('a1',1))
plot_as_directed_graph(nt)
new_likelihood_value, new_prior_value, (new_branch_prior, new_no_admix_prior, new_admix_prop_prior, new_top_prior), new_covariance= posterior_f((nt,0))
old_likelihood_value, old_prior_value, (old_branch_prior, old_no_admix_prior, old_admix_prop_prior, old_top_prior), old_covariance= posterior_f((t,0))
def main(args):
parser = ArgumentParser(
usage='pipeline for plotting posterior distribution summaries.',
version='1.0.0')
parser.add_argument(
'--posterior_distribution_file',
required=True,
type=str,
help=
'The file containing posterior distributions from the "AdmixtureBayes posterior" command. It needs the two columns "pops" and topology.'
)
parser.add_argument(
'--plot',
choices=['consensus_trees', 'top_node_trees', 'top_trees'],
required=True,
help='The type of plot to make. Choose between: 1) consensus_trees. '
'It plots an admixture graph based on all nodes that have a higher (marginal) posterior probability of X. '
'Different X\'s can be supplied with the command --consensus_threshold \n'
'2) top_node_trees. It plots the X highest posterior combinations of node types '
'and creates the corresponding minimal topologies. X can be supplied through the command --top_node_trees_to_plot'
'3) top_trees. It plots the X highest posterior topologies. X can be supplied by the command --top_trees_to_plot'
)
parser.add_argument('--outgroup',
default='outgroup',
help='name of the outgroup to plot')
parser.add_argument(
'--consensus_threshold',
default=[0.25, 0.5, 0.75, 0.9, 0.95, 0.99],
type=float,
nargs='+',
help=
'The posterior thresholds for which to draw different consensus trees.'
)
parser.add_argument(
'--top_node_trees_to_plot',
type=int,
default=3,
help='The number of node trees (or minimal topologies) to plot')
parser.add_argument('--top_trees_to_plot',
type=int,
default=3,
help='The number of trees (or topologies) to plot ')
parser.add_argument(
'--write_ranking_to_file',
type=str,
default='',
help=
'if a file is supplied here, the natural rankings for each of the plots is written here.'
)
parser.add_argument(
'--rankings_to_write_to_file',
type=int,
default=1000,
help=
'the number of rankings(nodes, min topology or topology depending on --plot) to write to the ranking file.'
)
parser.add_argument(
'--dont_annotate_node_posterior',
default=False,
action='store_true',
help=
'This will not color the nodes according to their posterior probability.'
)
parser.add_argument('--nodes',
default='',
type=str,
help='file where the first line is the leaf nodes')
parser.add_argument('--suppress_plot', default=False, action='store_true')
parser.add_argument(
'--no_sort',
default=False,
action='store_true',
help=
'often the tree is sorted according to the leaf names. no_sort willl assumed that they are not sorted according to this but sorted according to '
)
parser.add_argument('--sep',
default=',',
type=str,
help='the separator used in the input file')
#parser.add_argument('--no_header', default=False, action='store_true',help='will assume that there is no header in the file')
#parser.add_argument('--burn_in_rows', default=0, type=int, help='the number of rows that will be skipped in the input file as burn-in period')
#parser.add_argument('--burn_in_fraction', default=0.0, type=float, help='the proportion of the rows that are discarded as burn in period')
#parser.add_argument('--tree_column_name', default='tree', type=str, help='the name in the header of the column with all the trees.')
parser.add_argument(
'--consensus_method',
choices=['descendant_frequencies'],
default='descendant_frequencies',
help='Which method should be used to calculate the consensus tree?')
#parser.add_argument('--min_w', default=0.0, type=float, help='a lower threshold of which descendants matter when the consensus_method is descendant_frequencies.')
#parser.add_argument('--plot_tops_file', action='store_true', default=False, help='this will assume that the file is a tops file from downstream_analysis_parser and plot each line numbered.')
#parser.add_argument('--get_effective_number_of_admixtures', action='store_true', default=False, help='this will cancel all the other analysis and only print the effective number of admixes(tadmixes/sadmixes or admixes) to a a file.')
#parser.add_argument('--effective_number_of_admixtures_file', type=str, default='no_tadmixes.txt', help='this is the file in which to write the effective number of admixes in the file')
#parser.add_argument('--type_of_effective_admixtures', type=str, choices=['sadmix','tadmix','admix'], help='this is the type of admixes to write to the file.')
#parser.add_argument('--node_count_file', default='', type=str, help='if plot_tops option is supplied')
#parser.add_argument('--node_count_probs', default='', type=str, help='if supplied this will make a new ')
#parser.add_argument('--test_run', default=False, action='store_true',
# help='will overwrite everything and run a test function')
options = parser.parse_args(args)
def combine_nodes(node_structure, new_node, seen_sets):
candidate = new_node.name
seen = []
for lists_of_fixed_size in seen_sets[::-1]:
for attached_branch in lists_of_fixed_size:
if (attached_branch.issubset(candidate) and
((not attached_branch.issubset(seen)) or
(not node_structure[attached_branch].has_parent()))):
seen.extend(list(attached_branch))
new_node.add_child(node_structure[attached_branch])
node_structure[attached_branch].add_parent(new_node)
return node_structure
def get_number_of_tadmixtures(node_structure):
total = 0
for key in node_structure:
total += max(0, node_structure[key].get_number_of_parents() - 1)
return total
def node_combinations_to_node_structure(node_combinations):
length_sorted = {}
for node_combination in node_combinations:
leaves = frozenset(node_combination.split('.'))
k = len(leaves)
if k in length_sorted:
length_sorted[k].append(leaves)
else:
length_sorted[k] = [leaves]
length_sorted_list = [
length_sorted.get(k, [])
for k in range(1,
max(length_sorted.keys()) + 1)
]
#length_sorted_list is of the form [[[A],[B],[C]],[[A,B],[B,C]],...,[[A,B,C]]]
node_structure = {}
for leaf_node in length_sorted_list[0]:
node_structure[leaf_node] = Node(leaf_node)
added_sets = [length_sorted_list[0]]
for lists_of_fixed_size in length_sorted_list[1:]:
for branch_set in lists_of_fixed_size:
new_node = Node(branch_set)
combine_nodes(node_structure, new_node, added_sets)
node_structure[branch_set] = new_node
added_sets.append(lists_of_fixed_size)
return node_structure
# if options.node_count_file:
# with open(options.node_count_file, 'r') as f:
# node_count_dic={}
# for lin in f.readlines():
# key,freq=lin.rstrip().split()
# node_count_dic[frozenset(key.split('.'))]=float(freq)
# else:
# node_count_dic=None
if options.plot == 'consensus_trees' or options.plot == 'top_node_trees':
df = pd.read_csv(options.posterior_distribution_file,
sep=options.sep,
usecols=['pops'])
nodes_list = df['pops'].tolist()
#print(nodes_list)
seen_combinations = {}
for nodes in nodes_list:
#print(nodes)
for node in nodes.split('-'):
#print(node)
seen_combinations[node] = seen_combinations.get(node, 0) + 1
N = len(nodes_list)
#print(seen_combinations)
if options.plot == 'consensus_trees':
node_combinations = []
for threshold in options.consensus_threshold:
total_threshold = int(N * threshold)
final_node_combinations = [
k for k, v in seen_combinations.items()
if v > total_threshold
]
node_combinations.append(final_node_combinations)
if not options.dont_annotate_node_posterior:
node_count_dic = {
frozenset(k.split('.')): float(v) / N
for k, v in seen_combinations.items()
}
else:
node_count_dic = None
for i, final_node_combinations in enumerate(node_combinations):
#print(final_node_combinations)
final_node_structure = node_combinations_to_node_structure(
final_node_combinations)
if not options.suppress_plot:
from tree_plotting import plot_node_structure_as_directed_graph
plot_node_structure_as_directed_graph(
final_node_structure,
drawing_name='consensus_' +
str(int(100 * options.consensus_threshold[i])) +
'.png',
node_dic=node_count_dic)
if options.write_ranking_to_file:
with open(options.write_ranking_to_file, 'w') as f:
c = Counter(seen_combinations)
to_write = c.most_common(options.rankings_to_write_to_file)
for node, frequency in to_write:
f.write(node + ',' + str(float(frequency) / N) + '\n')
elif options.plot == 'top_node_trees':
c = Counter(nodes_list)
to_plots = c.most_common(options.top_node_trees_to_plot)
if options.write_ranking_to_file:
with open(options.write_ranking_to_file, 'w') as f:
for tree, frequency in c.most_common(
options.rankings_to_write_to_file):
f.write(tree + ',' + str(float(frequency) / N) + '\n')
if not options.dont_annotate_node_posterior:
c = Counter(seen_combinations)
node_count_dic = {
frozenset(key.split('.')): float(count) / N
for key, count in c.most_common(1000)
}
else:
node_count_dic = None
if not options.suppress_plot:
from tree_plotting import plot_node_structure_as_directed_graph
for i, (to_plot, count) in enumerate(to_plots):
node_structure = node_combinations_to_node_structure(
to_plot.split('-'))
plot_node_structure_as_directed_graph(
node_structure,
drawing_name='minimal_topology_' + str(i + 1) + '.png',
node_dic=node_count_dic)
elif options.plot == 'top_trees':
df = pd.read_csv(options.posterior_distribution_file,
sep=options.sep,
usecols=['pops', 'topology'])
trees_list = df['topology'].tolist()
no_leaves = len(trees_list[0].split('-')[0].split('.'))
N = len(trees_list)
c = Counter(trees_list)
to_plots = c.most_common(options.top_trees_to_plot)
#obtaining nodes:
if not options.nodes:
nodes = df['pops'].tolist()[0].split('-')
leaves = list(
set([leaf for node in nodes for leaf in node.split('.')]))
if len(leaves) == no_leaves:
pass #everything is good
elif len(leaves) == no_leaves - 1:
#adding outgroup
leaves.append(options.outgroup)
else:
assert False, 'The number of leaves could not be obtained'
assert not options.no_sort, 'When nodes are not specified, they will always be sorted'
leaves = sorted(leaves)
else:
leaves = read_one_line(options.nodes)
if not options.no_sort:
leaves = sorted(leaves)
if options.write_ranking_to_file:
with open(options.write_ranking_to_file, 'w') as f:
for tree, frequency in c.most_common(
options.rankings_to_write_to_file):
f.write(tree + ',' + str(float(frequency) / N) + '\n')
if not options.suppress_plot:
from tree_plotting import plot_as_directed_graph
for i, (to_plot, count) in enumerate(to_plots):
tree = topological_identifier_to_tree_clean(
to_plot,
leaves=generate_predefined_list_string(deepcopy(leaves)))
plot_as_directed_graph(tree,
drawing_name='topology_' + str(i + 1) +
'.png')
sys.exit()
if options.plot_tops_file:
with open(options.input_file, 'r') as f:
for n, lin in enumerate(f.readlines()):
rank, probability, combination = lin.rstrip().split(',')
all_nodes = [c.split('.') for c in combination.split('_')]
flattened = [item for sublist in all_nodes for item in sublist]
a = list(set(flattened))
code = rank + '_' + str(int(
100 * round(float(probability), 2))) + '_' + '_'.join(a)
print 'code', code
node_structure = node_combinations_to_node_structure(
combination.split('_'))
print node_structure
plot_node_structure_as_directed_graph(node_structure,
drawing_name=code +
'.png',
node_dic=node_count_dic)
sys.exit()
if options.test_run:
from generate_prior_trees import generate_phylogeny
from tree_statistics import unique_identifier_and_branch_lengths
from tree_plotting import plot_node_structure_as_directed_graph, plot_as_directed_graph
N = 5
tree1 = generate_phylogeny(N, 1)
plot_as_directed_graph(tree1, drawing_name='tree1.png')
tree2 = generate_phylogeny(N, 1)
plot_as_directed_graph(tree2, drawing_name='tree2.png')
stree1 = unique_identifier_and_branch_lengths(tree1)
stree2 = unique_identifier_and_branch_lengths(tree2)
with open('tmp_tree.txt', 'w') as f:
f.write(' '.join(['s' + str(i) for i in range(1, N + 1)]) + '\n')
f.write(stree1)
with open('trees.txt', 'w') as f:
f.write(stree1 + '\n' + stree2 + '\n' + stree1)
options.input_file = 'trees.txt'
options.nodes = 'tmp_tree.txt'
options.no_header = True
options.posterior_threshold = [0.25, 0.5, 0.9]
if options.input_file == options.node_count_file:
node_combinations = []
print 'using population sets from ', options.node_count_file
for threshold in options.posterior_threshold:
final_node_combinations = [
'.'.join(sorted(list(k))) for k, v in node_count_dic.items()
if v > threshold
]
node_combinations.append(final_node_combinations)
else:
print 'Reading file...'
#loading trees
if options.no_header:
strees = []
with open(options.input_file, 'r') as f:
for lin in f.readlines():
strees.append(lin.rstrip())
else:
df = pd.read_csv(options.input_file,
sep=options.sep,
usecols=[options.tree_column_name])
strees = df[options.tree_column_name].tolist()
n = len(strees)
print 'trees read: ', n
#thinning tree list
rows_to_remove_from_fraction = int(options.burn_in_fraction * n)
rows_to_remove = max(rows_to_remove_from_fraction,
options.burn_in_rows)
strees = strees[rows_to_remove:]
print 'removed burn-in:', rows_to_remove
print 'In list are now', len(strees), 'trees'
#thinning
distance_between = max(1, len(strees) // options.max_number_of_trees)
nstrees = []
for a, stree in enumerate(strees):
if a % distance_between == 0 and len(
nstrees) < options.max_number_of_trees:
nstrees.append(stree)
print 'thinned'
print 'In list are now', len(nstrees), 'trees'
N = len(nstrees)
seen_node_combinations = {}
nodes = read_one_line(options.nodes)
if not options.no_sort:
nodes = sorted(nodes)
tenth = len(nstrees) // 10
trees = []
for i, stree in enumerate(nstrees):
if tenth > 0 and i % tenth == 0:
print i // tenth * 10, '%'
if ';' in stree:
tree = identifier_to_tree_clean(
stree,
leaves=generate_predefined_list_string(deepcopy(nodes)))
else:
tree = topological_identifier_to_tree_clean(
stree,
leaves=generate_predefined_list_string(deepcopy(nodes)))
trees.append(tree)
ad = get_populations(tree, min_w=options.min_w)
for a in ad:
seen_node_combinations[a] = seen_node_combinations.get(a,
0) + 1
node_combinations = []
for threshold in options.posterior_threshold:
total_threshold = int(N * threshold)
final_node_combinations = [
k for k, v in seen_node_combinations.items()
if v > total_threshold
]
node_combinations.append(final_node_combinations)
for i, final_node_combinations in enumerate(node_combinations):
print 'final_node_combinations', final_node_combinations
final_node_structure = node_combinations_to_node_structure(
final_node_combinations)
if options.get_effective_number_of_admixtures:
with open(options.effective_number_of_admixtures_file, 'w') as f:
if options.type_of_effective_admixtures == 'tadmix':
effictive_admixtures = get_number_of_tadmixtures(
final_node_structure)
f.write(str(effictive_admixtures))
elif options.type_of_effective_admixtures == 'sadmix':
val = 0
count = 0
for tree in trees:
val += effective_number_of_admixes(tree)
count += 1
if count == 1:
f.write(str(int(val)))
else:
f.write(str(float(val) / count))
elif options.type_of_effective_admixtures == 'admix':
val = 0
count = 0
for tree in trees:
val += get_number_of_admixes(tree)
count += 1
if count == 1:
f.write(str(int(val)))
else:
f.write(str(float(val) / count))
if not options.suppress_plot:
from tree_plotting import plot_node_structure_as_directed_graph, plot_as_directed_graph
plot_node_structure_as_directed_graph(final_node_structure,
drawing_name='tmp' +
str(i + 1) + '.png',
node_dic=node_count_dic)
