def get_per_site_stats(alignment, cfg, a_subset):
if cfg.kmeans == 'entropy':
sub_align = SubsetAlignment(alignment, a_subset)
return entropy.sitewise_entropies(sub_align)
elif cfg.kmeans == 'fast_tiger':
a_subset.make_alignment(cfg, alignment)
phylip_file = a_subset.alignment_path
return sitewise_tiger_rates(cfg, str(phylip_file))
elif cfg.kmeans == 'tiger' and cfg.datatype == 'morphology':
sub_align = SubsetAlignment(alignment, a_subset)
set_parts = mt.create_set_parts(sub_align)
rates = mt.calculate_rates(set_parts)
return rates
elif cfg.kmeans == 'tiger':
sub_align = SubsetAlignment(alignment, a_subset)
tiger = the_config.TigerDNA()
tiger.build_bitsets(sub_align)
rate_array = tiger.calc_rates()
rate_array.shape = rate_array.shape[0], 1
return rate_array
else: #wtf
log.error(
"Unkown option passed to 'kmeans'. Please check and try again")
raise PartitionFinderError
def get_per_site_stats(alignment, cfg, a_subset):
if cfg.kmeans == 'entropy':
sub_align = SubsetAlignment(alignment, a_subset)
return entropy.sitewise_entropies(sub_align)
elif cfg.kmeans == 'tiger' and cfg.datatype == 'morphology':
sub_align = SubsetAlignment(alignment, a_subset)
set_parts = mt.create_set_parts(sub_align)
rates = mt.calculate_rates(set_parts)
return rates
else: #wtf
log.error("Unkown option passed to 'kmeans'. Please check and try again")
raise PartitionFinderError
def get_per_site_stats(alignment, cfg, a_subset):
if cfg.kmeans == 'entropy':
sub_align = SubsetAlignment(alignment, a_subset)
return entropy.sitewise_entropies(sub_align)
elif cfg.kmeans == 'tiger' and cfg.datatype == 'morphology':
sub_align = SubsetAlignment(alignment, a_subset)
set_parts = mt.create_set_parts(sub_align)
rates = mt.calculate_rates(set_parts)
return rates
else: #wtf
log.error(
"Unkown option passed to 'kmeans'. Please check and try again")
raise PartitionFinderError
def reassign_invariant_sites(self, subsets):
#TODO add a skip:
#if(len(subsets)==1):
# return(subsets)
# get entropies for whole alignment for this subset
onesub = subset_ops.merge_subsets(subsets)
entropies = entropy.sitewise_entropies(
SubsetAlignment(self.alignment, onesub))
# find nearest site for each invariant site
# replacements is a dict of: key: invariant col; value: replacement col,
# e.g.
# {512: 513, 514: 513, 515: 513, 516: 517}
replacements = entropy.get_replacement_sites(entropies, onesub.columns)
# now make a dict of the CURRENT subsets: key: site; value: subset
sch_dict = {}
for i, sub in enumerate(subsets):
for site in sub.columns:
sch_dict[site] = i
# then reassign the sites as necessary based on replacements
for r in replacements:
sch_dict[r] = sch_dict[replacements[r]]
# now build subsets according to the new sites
sub_dict = {} # this gives us the subsets to build
for k, v in sch_dict.iteritems():
sub_dict.setdefault(v, []).append(k)
new_subsets = []
for s in sub_dict:
n = Subset(the_config, set(sub_dict[s]))
new_subsets.append(n)
return (new_subsets)
def reassign_invariant_sites(self, subsets):
#TODO add a skip:
#if(len(subsets)==1):
# return(subsets)
# get entropies for whole alignment for this subset
onesub = subset_ops.merge_subsets(subsets)
entropies = entropy.sitewise_entropies(SubsetAlignment(self.alignment, onesub))
# find nearest site for each invariant site
# replacements is a dict of: key: invariant col; value: replacement col,
# e.g.
# {512: 513, 514: 513, 515: 513, 516: 517}
replacements = entropy.get_replacement_sites(entropies, onesub.columns)
# now make a dict of the CURRENT subsets: key: site; value: subset
sch_dict = {}
for i, sub in enumerate(subsets):
for site in sub.columns:
sch_dict[site] = i
# then reassign the sites as necessary based on replacements
for r in replacements:
sch_dict[r] = sch_dict[replacements[r]]
# now build subsets according to the new sites
sub_dict = {} # this gives us the subsets to build
for k, v in sch_dict.iteritems():
sub_dict.setdefault(v, []).append(k)
new_subsets = []
for s in sub_dict:
n = Subset(the_config, set(sub_dict[s]))
new_subsets.append(n)
return(new_subsets)