def test_prior_model_no_admixes(start_tree,
sim_length=100000,
summaries=None,
thinning_coef=1):
posterior = initialize_prior_as_posterior()
if summaries is None:
summaries = [
s_variable('posterior'),
s_variable('mhr'),
s_no_admixes()
]
proposal = adaptive_proposal_no_admix()
#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}
final_tree, final_posterior, results, _ = basic_chain(
start_tree,
summaries,
posterior,
proposal,
post=None,
N=sim_length,
sample_verbose_scheme=sample_verbose_scheme,
overall_thinning=int(thinning_coef + sim_length / 60000),
i_start_from=0,
temperature=1.0,
proposal_update=None,
check_trees=False)
save_to_csv(results, summaries)
return results
def test_prior_model(start_tree,
sim_length=100000,
summaries=None,
thinning_coef=1):
posterior = initialize_prior_as_posterior()
if summaries is None:
summaries = [
s_variable('posterior'),
s_variable('mhr'),
s_no_admixes()
]
proposal = adaptive_proposal() #basic_meta_proposal()
sample_verbose_scheme = {summary.name: (1, 0) for summary in summaries}
sample_verbose_scheme['posterior'] = (1, 1000)
final_tree, final_posterior, results, _ = basic_chain(
start_tree,
summaries,
posterior,
proposal,
post=None,
N=sim_length,
sample_verbose_scheme=sample_verbose_scheme,
overall_thinning=int(thinning_coef + sim_length / 60000),
i_start_from=0,
temperature=1.0,
proposal_update=None,
check_trees=True)
print results
save_to_csv(results, summaries)
return results
def run_c():
n = 3
s_trees = [
Rtree_operations.create_trivial_tree(n),
Rtree_operations.create_burled_leaved_tree(n, 1.0),
Rtree_operations.create_balanced_tree(n, 1.0)
]
summaries = [
summary.s_variable('posterior'),
summary.s_variable('mhr'),
summary.s_no_admixes(),
summary.s_tree_identifier(),
summary.s_average_branch_length(),
summary.s_total_branch_length(),
summary.s_basic_tree_statistics(
Rtree_operations.get_number_of_ghost_populations,
'ghost_pops',
output='integer'),
summary.s_basic_tree_statistics(
Rtree_operations.get_max_distance_to_root, 'max_root'),
summary.s_basic_tree_statistics(
Rtree_operations.get_min_distance_to_root, 'min_root'),
summary.s_basic_tree_statistics(
Rtree_operations.get_average_distance_to_root, 'average_root'),
summary.s_variable('proposal_type', output='string'),
summary.s_tree_identifier_new_tree()
] + [
summary.s_variable(s, output='double')
for s in ['prior', 'branch_prior', 'no_admix_prior', 'top_prior']
]
simulation_sanity.test_prior_model_several_chains(s_trees,
100000,
summaries=summaries,
thinning_coef=3)
print 'finished mcmc chains'
list_of_summaries = summaries[2:10]
nsim = 100000
prior_distribution = generate_prior_trees.get_distribution_under_prior(
leaves=n, sim_length=nsim,
list_of_summaries=list_of_summaries) #, thinning_criteria=max_two)
analyse_results.save_to_csv(
[tuple(range(nsim))] +
[tuple(prior_distribution[summ.name]) for summ in list_of_summaries],
list_of_summaries,
filename='sim_prior.csv',
origin_layer=None)
analyse_results.generate_summary_csv(summaries)
def func(nstart_tree):
n, start_tree = nstart_tree
final_tree, final_posterior, results, _ = basic_chain(
start_tree,
summaries,
posterior,
proposal,
post=None,
N=sim_length,
sample_verbose_scheme=sample_verbose_scheme,
overall_thinning=int(thinning_coef + sim_length / 60000),
i_start_from=0,
temperature=1.0,
proposal_update=None,
check_trees=True)
save_to_csv(results,
summaries,
filename='results_' + str(n + 1) + 'csv',
origin_layer=(n + 1, 1))
def trivial_simulation(start_val, reps, thinning_coef=1):
posterior = initialize_trivial_posterior()
summaries = [Trivial_Summary()]
proposal = trivial_proposal()
sample_verbose_scheme = {summary.name: (1, 0) for summary in summaries}
final_tree, final_posterior, results, _ = basic_chain(
start_val,
summaries,
posterior,
proposal,
post=None,
N=reps,
sample_verbose_scheme=sample_verbose_scheme,
overall_thinning=int(thinning_coef + reps / 60000),
i_start_from=0,
temperature=1.0,
proposal_update=None,
check_trees=False)
print results
save_to_csv(results, summaries)
return results
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