def generate_covariance(size, scale_metod='beta', return_tree=False):
tree = generate_phylogeny(size)
cov = make_covariance(tree)
s = calc_s(scale_metod)
if return_tree:
return cov * s, scale_tree(tree, s)
return cov * s
def simulate_tree_wrapper(nk_tuple, **kwargs):
if kwargs['sadmix']:
return generate_sadmix_tree(nk_tuple[0], no_sadmixes=nk_tuple[1], nodes=kwargs['before_added_outgroup_nodes'], starting_admixes=0)
return generate_phylogeny(size= nk_tuple[0],
admixes=nk_tuple[1],
leaf_nodes= kwargs['before_added_outgroup_nodes'],
skewed_admixture_prior=kwargs['skewed_admixture_prior_sim'])
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 simulate_tree(no_leaves, no_admixes=None):
if no_admixes is None:
no_admixes = geom.rvs(p=0.5) - 1
tree = generate_phylogeny(no_leaves, no_admixes)
return unique_identifier_and_branch_lengths(tree)
def initialize_posterior2(emp_cov=None,
true_tree=None,
M=None,
use_skewed_distr=False,
p=0.5,
rescale=False,
model_choice=[
'empirical covariance', 'true tree covariance',
'wishart on true tree covariance',
'empirical covariance on true tree',
'no likelihood'
],
simulate_true_tree=False,
true_tree_no_leaves=None,
true_tree_no_admixes=None,
nodes=None,
simulate_true_tree_with_skewed_prior=False,
reduce_cov=None,
add_outgroup_to_true_tree=False,
reduce_true_tree=False):
if not isinstance(model_choice, basestring):
model_choice = model_choice[0]
if model_choice == 'no likelihood':
return initialize_prior_as_posterior(), {}
if (model_choice == 'true tree covariance'
or model_choice == 'wishart on true tree covariance'
or model_choice == 'empirical covariance on true tree'):
if simulate_true_tree:
true_tree = generate_phylogeny(
true_tree_no_leaves, true_tree_no_admixes, nodes,
simulate_true_tree_with_skewed_prior)
elif isinstance(true_tree, basestring):
if ';' in true_tree: #this means that the true tree is a s_tree
true_tree_s = true_tree
true_tree = identifier_to_tree_clean(true_tree_s)
else:
with open(true_tree, 'r') as f:
true_tree_s = f.readline().rstrip()
true_tree = identifier_to_tree_clean(true_tree_s)
true_tree = Rtree_operations.simple_reorder_the_leaves_after_removal_of_s1(
true_tree)
no_leaves = get_number_of_leaves(true_tree)
no_admixes = get_number_of_admixes(true_tree)
cov = make_covariance(true_tree)
if reduce_cov is not None:
pass
if reduce_true_tree is not None:
true_tree = Rtree_operations.remove_outgroup(
true_tree, reduce_true_tree)
if reduce_true_tree == 's1' or reduce_true_tree == 0:
pass
if emp_cov is not None:
if isinstance(emp_cov, basestring):
pass
if M is None:
M = n_mark(emp_cov)
if rescale:
emp_cov, multiplier = rescale_empirical_covariance(emp_cov)
print 'multiplier is', multiplier
def posterior(x, pks={}):
#print tot_branch_length
prior_value = prior(x, p=p, use_skewed_distr=use_skewed_distr, pks=pks)
if prior_value == -float('inf'):
return -float('inf'), prior_value
likelihood_value = likelihood(x, emp_cov, M=M)
pks['prior'] = prior_value
pks['likelihood'] = likelihood_value
#pks['posterior']=prior_value+likelihood_value
return likelihood_value, prior_value
if rescale:
return posterior, multiplier
return posterior
def test_posterior_model_multichain(true_tree=None,
start_tree=None,
sim_lengths=[250] * 800,
summaries=None,
thinning_coef=1,
admixtures_of_true_tree=None,
no_leaves_true_tree=4,
wishart_df=None,
sim_from_wishart=False,
no_chains=8,
result_file='results_mc3.csv',
emp_cov=None,
emp_remove=-1,
rescale_empirical_cov=False):
if true_tree is None:
if admixtures_of_true_tree is None:
admixtures_of_true_tree = geom.rvs(p=0.5) - 1
true_tree = generate_phylogeny(no_leaves_true_tree,
admixtures_of_true_tree)
else:
no_leaves_true_tree = get_no_leaves(true_tree)
admixtures_of_true_tree = get_number_of_admixes(true_tree)
true_x = (true_tree, 0)
m = make_covariance(true_tree, get_trivial_nodes(no_leaves_true_tree))
if start_tree is None:
start_tree = true_tree
start_x = (start_tree, 0)
if wishart_df is None:
wishart_df = n_mark(m)
if sim_from_wishart:
r = m.shape[0]
print m
m = wishart.rvs(df=r * wishart_df - 1, scale=m / (r * wishart_df))
print m
if emp_cov is not None:
m = emp_cov
if rescale_empirical_cov:
posterior, multiplier = initialize_posterior(
m,
wishart_df,
use_skewed_distr=True,
rescale=rescale_empirical_cov)
else:
posterior = initialize_posterior(m,
wishart_df,
use_skewed_distr=True,
rescale=rescale_empirical_cov)
multiplier = None
print 'true_tree=', unique_identifier_and_branch_lengths(true_tree)
if rescale_empirical_cov:
post_ = posterior(
(scale_tree_copy(true_x[0],
1.0 / multiplier), true_x[1] / multiplier))
else:
post_ = posterior(true_x)
print 'likelihood(true_tree)', post_[0]
print 'prior(true_tree)', post_[1]
print 'posterior(true_tree)', sum(post_)
if summaries is None:
summaries = [
s_variable('posterior'),
s_variable('mhr'),
s_no_admixes()
]
proposal = basic_meta_proposal()
#proposal.props=proposal.props[2:] #a little hack under the hood
#proposal.params=proposal.params[2:] #a little hack under the hood.
sample_verbose_scheme = {summary.name: (1, 0) for summary in summaries}
sample_verbose_scheme_first = deepcopy(sample_verbose_scheme)
if 'posterior' in sample_verbose_scheme:
sample_verbose_scheme_first['posterior'] = (1, 1) #(1,1)
sample_verbose_scheme_first['no_admixes'] = (1, 1)
#if 'likelihood' in sample_verbose_scheme:
#sample_verbose_scheme_first['likelihood']=(1,1)
print sample_verbose_scheme_first
MCMCMC(starting_trees=[deepcopy(start_x) for _ in range(no_chains)],
posterior_function=posterior,
summaries=summaries,
temperature_scheme=fixed_geometrical(800.0, no_chains),
printing_schemes=[sample_verbose_scheme_first] +
[sample_verbose_scheme for _ in range(no_chains - 1)],
iteration_scheme=sim_lengths,
overall_thinnings=int(thinning_coef),
proposal_scheme=[adaptive_proposal() for _ in range(no_chains)],
cores=no_chains,
no_chains=no_chains,
multiplier=multiplier,
result_file=result_file,
store_permuts=False)
print 'finished MC3'
#save_pandas_dataframe_to_csv(results, result_file)
#save_permuts_to_csv(permuts, get_permut_filename(result_file))
return true_tree
def test_posterior_model(true_tree=None,
start_tree=None,
sim_length=100000,
summaries=None,
thinning_coef=19,
admixtures_of_true_tree=None,
no_leaves_true_tree=4,
filename='results.csv',
sim_from_wishart=False,
wishart_df=None,
sap_sim=False,
sap_ana=False,
resimulate_regrafted_branch_length=False,
emp_cov=None,
big_posterior=False,
rescale_empirical_cov=False):
if true_tree is None:
if admixtures_of_true_tree is None:
admixtures_of_true_tree = geom.rvs(p=0.5) - 1
true_tree = generate_phylogeny(no_leaves_true_tree,
admixtures_of_true_tree,
skewed_admixture_prior=sap_sim)
else:
no_leaves_true_tree = get_no_leaves(true_tree)
admixtures_of_true_tree = get_number_of_admixes(true_tree)
true_x = (true_tree, 0)
m = make_covariance(true_tree, get_trivial_nodes(no_leaves_true_tree))
if start_tree is None:
start_tree = true_tree
start_x = (start_tree, 0)
if wishart_df is None:
wishart_df = n_mark(m)
if sim_from_wishart:
r = m.shape[0]
print m
m = wishart.rvs(df=r * wishart_df - 1, scale=m / (r * wishart_df))
print m
if emp_cov is not None:
m = emp_cov
if big_posterior:
posterior = initialize_big_posterior(m,
wishart_df,
use_skewed_distr=sap_ana)
else:
posterior = initialize_posterior(m,
wishart_df,
use_skewed_distr=sap_ana,
rescale=rescale_empirical_cov)
print 'true_tree=', unique_identifier_and_branch_lengths(true_tree)
post_ = posterior(true_x)
print 'likelihood(true_tree)', post_[0]
print 'prior(true_tree)', post_[1]
print 'posterior(true_tree)', sum(post_[:2])
if summaries is None:
summaries = [s_posterior(), s_variable('mhr'), s_no_admixes()]
proposal = adaptive_proposal(
resimulate_regrafted_branch_length=resimulate_regrafted_branch_length)
#proposal.props=proposal.props[2:] #a little hack under the hood
#proposal.params=proposal.params[2:] #a little hack under the hood.
sample_verbose_scheme = {summary.name: (1, 0) for summary in summaries}
sample_verbose_scheme['posterior'] = (1, 1)
sample_verbose_scheme['no_admixes'] = (1, 1)
final_tree, final_posterior, results, _ = basic_chain(
start_x,
summaries,
posterior,
proposal,
post=None,
N=sim_length,
sample_verbose_scheme=sample_verbose_scheme,
overall_thinning=int(max(thinning_coef, sim_length / 60000)),
i_start_from=0,
temperature=1.0,
proposal_update=None,
check_trees=False)
save_to_csv(results, summaries, filename=filename)
return true_tree
updates=org.dot(normal(scale=0.01, size=org.shape[1]))
#print pretty_string(update_specific_branch_lengths(tree_good, branches_determined, updates, add=True))
#print make_covariance(tree_good, node_keys= nodes_determined)
#print org.T.dot(coef)
import sys
sys.exit()
from generate_prior_trees import generate_phylogeny
from numpy.linalg import matrix_rank
from Rtree_operations import get_number_of_admixes
from tree_plotting import plot_as_directed_graph
for _ in xrange(3):
tree=generate_phylogeny(3,2)
mat=make_coefficient_matrix(tree)[0]
rank=matrix_rank(mat, tol=0.001)
print rank, get_number_of_admixes(tree)
print mat
plot_as_directed_graph(tree, drawing_name='tmp'+str(_)+'.png')
return False
for i in range(r1.shape[0]):
for j in range(r2.shape[1]):
if abs(r1[i, j] - r2[i, j]) > 1e-4:
print r1[i, j], r2[i, j], r1[i, j] - r2[i, j]
return False
return True
print get_populations(tree_on_the_border2,
keys_to_include=['s1', 's2', 's4'])
import sys
sys.exit()
for _ in xrange(300):
t = generate_phylogeny(N)
r1 = make_covariance(t, ['s' + str(i + 1) for i in range(N)],
old_cov=False)
r2 = make_covariance(t, ['s' + str(i + 1) for i in range(N)],
old_cov=True)
if arrays_equal(r1, r2):
print 'arrays equal'
else:
print 'arrays not equal'
print r1
print r2
break
N = 40
tree = create_burled_leaved_tree(N, 1)
def accept_reject_generation(no_leaves, no_sadmixes, nodes=None):
tree=generate_phylogeny(no_leaves, no_sadmixes, leaf_nodes=nodes)
while not admixes_are_sadmixes(tree):
tree=generate_phylogeny(no_leaves, no_sadmixes, leaf_nodes=nodes)
return tree
upper_reverse = x_new.dot((A.T.dot(B) + identity(len(branches))))
lower_first_reverse = B.T.dot(B) + identity(len(branches))
mu_reverse = mm(U=upper_reverse,
L=lower_first_reverse,
initial_value=array(x_new))
#print 'matrix_rank , dimension (A)', matrix_rank(A), A.shape
#print 'matrix_rank , dimension (B)', matrix_rank(B), B.shape
#print 'x_reverse', reverse_mu_new
q_backward = sum(norm.logpdf(mu_reverse - x_A, scale=sigma))
#wear the new values
#print branches
new_tree = update_specific_branch_lengths(new_tree, branches, x_new)
#print sum((A.dot(mu_new)-B.dot(x_old))**2)
#print sum((A.dot(x_new)-B.dot(x_old))**2)
#print sum((B.dot(x_old)-A.dot(x_old))**2)
return new_tree, 1.0, exp(q_backward - q_forward)
if __name__ == '__main__':
from generate_prior_trees import generate_phylogeny
tree = generate_phylogeny(4, 1)
addmix_with_correction(tree)
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)
if __name__=='__main__':
#print reduce_covariance(identity(10), 5)
#print file_to_emp_cov('out_stem.cov',4)
from sys import exit
exit()
from generate_prior_trees import generate_phylogeny
from Rcatalogue_of_trees import *
from Rtree_operations import create_trivial_tree, scale_tree
tree2=scale_tree(generate_phylogeny(5,1),0.05)
print pretty_string(tree2)
print pretty_string(identifier_to_tree_clean(unique_identifier_and_branch_lengths(tree2)))
print supplementary_text_ms_string()
tree_good=generate_phylogeny(7)
a=tree_to_ms_command(tree_good, 50,20)
#print call_ms_string(a, 'supp.txt')
b=time_adjusted_tree_to_ms_command(tree_good,50,20)
#print call_ms_string(b, 'supp2.txt')
#print call_ms_string(tree_to_ms_command(tree2, 50,20), 'tmp.txt')
#cov= ms_to_treemix2('supp.txt', 20, 20,400)
#cov= ms_to_treemix2('tmp.txt', 50, 5,20)
#cov2=calculate_covariance_matrix('tmp.txt', 50, 5,20)
#print cov
#print cov2
#print make_covariance(tree2)
