def print_true_partition(self):
print ' true partition'
print ' clonal? ids'
true_partition = utils.get_true_partition(self.reco_info)
for cluster in true_partition:
print ' %d %s' % (utils.from_same_event(self.reco_info, cluster),
':'.join([str(uid) for uid in cluster]))
def get_bad_clusters(part):
bad_clusters = [
] # inferred clusters that aren't really all from the same event
for ic in range(len(part)):
same_event = utils.from_same_event(
reco_info,
part[ic]) # are all the sequences from the same event?
entire_cluster = True # ... and if so, are they the entire true cluster?
if same_event:
reco_id = reco_info[part[ic][0]][
'reco_id'] # they've all got the same reco_id then, so pick an aribtrary one
true_cluster = true_partition[reco_id]
for uid in true_cluster:
if uid not in part[ic]:
entire_cluster = False
break
else:
entire_cluster = False
if not same_event or not entire_cluster:
bad_clusters.append(':'.join(part[ic]))
if len(bad_clusters) > 25:
bad_clusters = ['too', 'long']
return bad_clusters
def print_partition(self, ip, reco_info=None, extrastr='', abbreviate=True, highlight_cluster_indices=None, print_cluster_indices=False, right_extrastr=''): # NOTE <highlight_cluster_indices> and <print_cluster_indices> are quite different despite sounding similar, but I can't think of something else to call the latter that makes more sense
# NOTE it's nicer to *not* sort by cluster size here, since preserving the order tends to frequently make it obvious which clusters are merging as your eye scans downwards through the output
if ip > 0: # delta between this logprob and the previous one
delta_str = '%.1f' % (self.logprobs[ip] - self.logprobs[ip-1])
else:
delta_str = ''
print ' %s %-12.2f%-7s %s%-5d %4d' % (extrastr, self.logprobs[ip], delta_str, ('%-5d ' % ip) if print_cluster_indices else '', len(self.partitions[ip]), self.n_procs[ip]),
print ' ' + self.get_ccf_str(ip),
# clusters
sorted_clusters = sorted(self.partitions[ip], key=lambda c: len(c), reverse=True)
for iclust in range(len(sorted_clusters)):
cluster = sorted_clusters[iclust]
if abbreviate:
cluster_str = ':'.join(['o' if len(uid) > 3 else uid for uid in cluster])
else:
# cluster_str = ':'.join(sorted([str(uid) for uid in cluster]))
cluster_str = ':'.join([str(uid) for uid in cluster])
if reco_info is not None and not utils.from_same_event(reco_info, cluster):
cluster_str = utils.color('red', cluster_str)
if self.seed_unique_id is not None and self.seed_unique_id in cluster:
cluster_str = utils.color('reverse_video', cluster_str)
if highlight_cluster_indices is not None and iclust in highlight_cluster_indices:
cluster_str = utils.color('red', cluster_str)
if abbreviate:
print ' %s' % cluster_str,
else:
print ' %s' % cluster_str,
print '%s' % right_extrastr,
print ''
def get_bad_clusters(self, partition, reco_info, true_partition):
bad_clusters = [
] # inferred clusters that aren't really all from the same event
for ic in range(len(partition)):
same_event = utils.from_same_event(
reco_info,
partition[ic]) # are all the sequences from the same event?
entire_cluster = True # ... and if so, are they the entire true cluster?
if same_event:
reco_id = reco_info[partition[ic][0]][
'reco_id'] # they've all got the same reco_id then, so pick an aribtrary one
true_clusters = [
cluster for cluster in true_partition
if reco_info[cluster[0]]['reco_id'] == reco_id
] # NOTE I think this doesn't work right with shm indels in the cdr3
assert len(true_clusters) == 1
true_cluster = true_clusters[0]
for uid in true_cluster:
if uid not in partition[ic]:
entire_cluster = False
break
else:
entire_cluster = False
if not same_event or not entire_cluster:
bad_clusters.append(':'.join(partition[ic]))
if len(bad_clusters) > 25:
bad_clusters = ['too', 'long']
return bad_clusters
def print_true_partition(self):
print ' true partition'
print ' clonal? ids'
true_partition = utils.get_true_partition(self.reco_info)
for cluster in true_partition:
print ' %d %s' % (utils.from_same_event(
self.reco_info, cluster), ':'.join(
[str(uid) for uid in cluster]))
def print_partition(self, ip, reco_info=None, extrastr='', one_line=True, abbreviate=True):
if one_line:
if ip > 0: # delta between this logprob and the previous one
delta_str = '%.1f' % (self.logprobs[ip] - self.logprobs[ip-1])
else:
delta_str = ''
print ' %5s %-12.2f%-7s %-5d %5d' % (extrastr, self.logprobs[ip], delta_str, len(self.partitions[ip]), self.n_procs[ip]),
# logweight (and inverse of number of potential parents)
if self.logweights[ip] is not None:
way_str, logweight_str = '', ''
expon = math.exp(self.logweights[ip])
n_ways = 0 if expon == 0. else 1. / expon
way_str = ('%.1f' % n_ways) if n_ways < 1e7 else ('%8.1e' % n_ways)
logweight_str = '%8.3f' % self.logweights[ip]
# adj mi
if reco_info is not None:
adj_mi_str = ''
if self.adj_mis[ip] is None:
adj_mi_str = 'na'
else:
if self.adj_mis[ip] > 1e-3:
adj_mi_str = '%-8.3f' % self.adj_mis[ip]
else:
adj_mi_str = '%-8.0e' % self.adj_mis[ip]
print ' %8s ' % (adj_mi_str),
if self.logweights[ip] is not None:
print ' %10s %8s ' % (way_str, logweight_str),
else:
print ' %5s partition %-15.2f' % (extrastr, self.logprobs[ip]),
if reco_info is not None:
print ' %-8.2f' % (self.adj_mis[ip]),
print ''
print ' clonal? ids'
# clusters
for cluster in self.partitions[ip]:
same_event = utils.from_same_event(reco_info is None, reco_info, cluster)
if same_event is None:
same_event = -1
if abbreviate:
cluster_str = ':'.join(['o' for uid in cluster])
else:
cluster_str = ':'.join([str(uid) for uid in cluster])
if not same_event:
cluster_str = utils.color('red', cluster_str)
if one_line:
if abbreviate:
print ' %s' % cluster_str,
else:
print ' %s' % cluster_str,
else:
print ' %d %s' % (int(same_event), cluster_str)
if one_line:
print ''
def print_true_partition(self):
print ' true partition'
print ' clonal? ids'
true_partition = utils.get_true_partition(self.reco_info)
for cluster in true_partition.values():
same_event = utils.from_same_event(self.reco_info is None, self.reco_info, cluster)
if same_event is None:
same_event = -1
print ' %d %s' % (int(same_event), ':'.join([str(uid) for uid in cluster]))
def peruse_forward_scores():
_, reco_info = seqfileopener.get_seqfile_info(simfname, is_data=False) #, n_max_queries=10000)
logprobs, partialcorr_logprobs, corr_logprobs = OrderedDict(), OrderedDict(), OrderedDict()
for n_set in n_set_list:
print n_set
# if n_set != 5:
# continue
logprobs[n_set], partialcorr_logprobs[n_set], corr_logprobs[n_set] = OrderedDict(), OrderedDict(), OrderedDict()
with open(outputdir + '/' + str(n_set) + '-forward.csv') as csvfile:
reader = csv.DictReader(csvfile)
for line in reader:
uidlist = line['unique_ids'].split(':')
assert utils.from_same_event(reco_info, uidlist)
reco_id = reco_info[uidlist[0]]['reco_id']
if reco_id in logprobs[n_set]:
raise Exception('already had %s' % reco_id)
logprobs[n_set][reco_id] = float(line['logprob'])
factor = 1. / n_set
partialcorr_logprobs[n_set][reco_id] = factor * float(line['logprob'])
factor = (1. - 0.24 / pow(float(n_set), 0.9)) / n_set
# factor = 1. / (0.77547824*n_set + 0.20327936)
corr_logprobs[n_set][reco_id] = factor * float(line['logprob'])
i_baseline = -1
deviations = get_deviations(logprobs, i_baseline)
# fit_stuff(n_set_list, deviations)
partialcorr_deviations = get_deviations(partialcorr_logprobs, i_baseline)
signed_partialcorr_deviations = get_deviations(partialcorr_logprobs, i_baseline, signed=True)
corr_deviations = get_deviations(corr_logprobs, i_baseline)
signed_corr_deviations = get_deviations(corr_logprobs, i_baseline, signed=True)
import plotting
fig, ax = plotting.mpl_init()
ax.plot(n_set_list, deviations, marker='.')
plotting.mpl_finish(ax, baseplotdir, 'forwards', xlabel='N simultaneous seqs', ylabel='log prob deviation to ' + str(n_set_list[i_baseline])) #, ybounds=(-0.02, 0.02))
# fig, ax = plotting.mpl_init()
# ax.plot(n_set_list, partialcorr_deviations, marker='.')
# ax.plot([n_set_list[0], n_set_list[-1]], [0, 0])
# plotting.mpl_finish(ax, baseplotdir, 'partially-corrected-forwards', xlabel='N simultaneous seqs', ylabel='log prob deviation to ' + str(n_set_list[i_baseline])) #, ybounds=(-0.02, 0.02))
fig, ax = plotting.mpl_init()
ax.plot(n_set_list, partialcorr_deviations, marker='.', label='1/n (abs)')
ax.plot(n_set_list, signed_partialcorr_deviations, marker='.', label='1/n')
ax.plot(n_set_list, corr_deviations, marker='.', label='1/crap (abs)')
ax.plot(n_set_list, signed_corr_deviations, marker='.', label='1/crap')
ax.plot([n_set_list[0], n_set_list[-1]], [0, 0])
plotting.mpl_finish(ax, baseplotdir, 'corrected-forwards', xlabel='N simultaneous seqs', ylabel='log prob deviation to ' + str(n_set_list[i_baseline])) #, ybounds=(-0.02, 0.02))
fig, ax = plotting.mpl_init()
ax.plot(n_set_list, signed_corr_deviations, marker='.')
ax.plot([n_set_list[0], n_set_list[-1]], [0, 0])
plotting.mpl_finish(ax, baseplotdir, 'signed-corrected-forwards', xlabel='N simultaneous seqs', ylabel='log prob deviation to ' + str(n_set_list[i_baseline])) #, ybounds=(-0.02, 0.02))
def single_link(self, input_scores=None, infname=None, debug=False, reco_info=None, outfile=None):
if infname is None:
assert input_scores is not None
else:
assert input_scores is None # should only specify <input_scores> *or* <infname>
input_scores = []
with opener('r')(infname) as infile:
reader = csv.DictReader(infile)
for line in reader:
input_scores.append(line)
sorted_lines = sorted(input_scores, key=lambda k: float(k['logprob']))
for line in sorted_lines:
a_name = line['id_a']
b_name = line['id_b']
score = float(line['logprob'])
dbg_str_list = ['%22s %22s %8.3f' % (a_name, b_name, score), ]
if reco_info is None:
dbg_str_list[-1] += ' %s' % ('-')
else:
from_same_event = utils.from_same_event(reco_info, [a_name, b_name])
dbg_str_list[-1] += ' %d' % (from_same_event)
self.incorporate_into_clusters(a_name, b_name, score, dbg_str_list)
self.pairscores[(utils.get_key((a_name, b_name)))] = score
self.plotscores['all'].append(score)
if reco_info is not None:
if from_same_event:
self.plotscores['same'].append(score)
else:
self.plotscores['diff'].append(score)
if debug:
outstr = ''.join(dbg_str_list)
if outfile == None:
print outstr
else:
outfile.write(outstr + '\n')
for query, cluster_id in self.query_clusters.iteritems():
if cluster_id not in self.id_clusters:
self.id_clusters[cluster_id] = []
self.id_clusters[cluster_id].append(query)
for cluster_id, queries in self.id_clusters.items():
if len(queries) == 1:
self.singletons.append(queries[0])
# print 'nearest',self.nearest_true_mate
out_str_list = [' %d clusters:\n'%len(self.id_clusters), ]
for cluster_id in self.id_clusters:
out_str_list.append(' ' + ' '.join([str(x) for x in self.id_clusters[cluster_id]]) + '\n')
if outfile == None:
print ''.join(out_str_list)
else:
outfile.write(''.join(out_str_list))
def print_partition(self,
ip,
reco_info=None,
extrastr='',
abbreviate=True,
smc_print=False):
# NOTE it's nicer to *not* sort by cluster size here, since preserving the order tends to frequently make it obvious which clusters are merging as your eye scans downwards through the output
if ip > 0: # delta between this logprob and the previous one
delta_str = '%.1f' % (self.logprobs[ip] - self.logprobs[ip - 1])
else:
delta_str = ''
print ' %s %-12.2f%-7s %-5d %4d' % (
extrastr, self.logprobs[ip], delta_str, len(
self.partitions[ip]), self.n_procs[ip]),
# logweight (and inverse of number of potential parents)
if self.logweights[ip] is not None and smc_print:
way_str, logweight_str = '', ''
expon = math.exp(self.logweights[ip])
n_ways = 0 if expon == 0. else 1. / expon
way_str = ('%.1f' % n_ways) if n_ways < 1e7 else ('%8.1e' % n_ways)
logweight_str = '%8.3f' % self.logweights[ip]
print ' ' + self.get_ccf_str(ip),
if self.logweights[ip] is not None and smc_print:
print ' %10s %8s ' % (way_str, logweight_str),
# clusters
for cluster in sorted(self.partitions[ip],
key=lambda c: len(c),
reverse=True):
if abbreviate:
cluster_str = ':'.join(
['o' if len(uid) > 3 else uid for uid in cluster])
else:
# cluster_str = ':'.join(sorted([str(uid) for uid in cluster]))
cluster_str = ':'.join([str(uid) for uid in cluster])
if reco_info is not None and not utils.from_same_event(
reco_info, cluster):
cluster_str = utils.color('red', cluster_str)
if self.seed_unique_id is not None and self.seed_unique_id in cluster:
cluster_str = utils.color('reverse_video', cluster_str)
if abbreviate:
print ' %s' % cluster_str,
else:
print ' %s' % cluster_str,
print ''
def print_partition(self, ip, reco_info=None, extrastr="", abbreviate=True, smc_print=False):
# NOTE it's nicer to *not* sort by cluster size here, since preserving the order tends to frequently make it obvious which clusters are merging as your eye scans downwards through the output
if ip > 0: # delta between this logprob and the previous one
delta_str = "%.1f" % (self.logprobs[ip] - self.logprobs[ip - 1])
else:
delta_str = ""
print " %s %-12.2f%-7s %-5d %4d" % (
extrastr,
self.logprobs[ip],
delta_str,
len(self.partitions[ip]),
self.n_procs[ip],
),
# logweight (and inverse of number of potential parents)
if self.logweights[ip] is not None and smc_print:
way_str, logweight_str = "", ""
expon = math.exp(self.logweights[ip])
n_ways = 0 if expon == 0.0 else 1.0 / expon
way_str = ("%.1f" % n_ways) if n_ways < 1e7 else ("%8.1e" % n_ways)
logweight_str = "%8.3f" % self.logweights[ip]
print " " + self.get_ccf_str(ip),
if self.logweights[ip] is not None and smc_print:
print " %10s %8s " % (way_str, logweight_str),
# clusters
for cluster in self.partitions[ip]:
if abbreviate:
cluster_str = ":".join(["o" if len(uid) > 3 else uid for uid in cluster])
else:
# cluster_str = ':'.join(sorted([str(uid) for uid in cluster]))
cluster_str = ":".join([str(uid) for uid in cluster])
if reco_info is not None and not utils.from_same_event(reco_info, cluster):
cluster_str = utils.color("red", cluster_str)
if self.seed_unique_id is not None and self.seed_unique_id in cluster:
cluster_str = utils.color("reverse_video", cluster_str)
if abbreviate:
print " %s" % cluster_str,
else:
print " %s" % cluster_str,
print ""
def write_partitions(self, writer, is_data, reco_info, true_partition, smc_particles, path_index, n_to_write=None, calc_adj_mi=None):
for ipart in self.get_partition_subset(n_partitions=n_to_write):
part = self.partitions[ipart]
cluster_str = ''
bad_clusters = [] # inferred clusters that aren't really all from the same event
for ic in range(len(part)):
if ic > 0:
cluster_str += ';'
cluster_str += ':'.join(part[ic])
if not is_data:
same_event = utils.from_same_event(is_data, reco_info, part[ic]) # are all the sequences from the same event?
entire_cluster = True # ... and if so, are they the entire true cluster?
if same_event:
reco_id = reco_info[part[ic][0]]['reco_id'] # they've all got the same reco_id then, so pick an aribtrary one
true_cluster = true_partition[reco_id]
for uid in true_cluster:
if uid not in part[ic]:
entire_cluster = False
break
else:
entire_cluster = False
if not same_event or not entire_cluster:
bad_clusters.append(':'.join(part[ic]))
if len(bad_clusters) > 25:
bad_clusters = ['too', 'long']
row = {'logprob' : self.logprobs[ipart],
'n_clusters' : len(part),
'n_procs' : self.n_procs[ipart],
'clusters' : cluster_str}
if smc_particles > 1:
row['path_index'] = path_index
row['logweight'] = self.logweights[ipart]
if not is_data:
if calc_adj_mi is None or self.adj_mis[ipart] != -1: # if we don't want to write any adj mis, or if we already calculated it
row['adj_mi'] = self.adj_mis[ipart]
else:
if calc_adj_mi == 'best' and ipart == self.i_best: # only calculate adj_mi for the best partition
row['adj_mi'] = utils.mutual_information(part, reco_info)
else:
row['adj_mi'] = self.adj_mis[ipart]
row['n_true_clusters'] = len(true_partition)
row['bad_clusters'] = ';'.join(bad_clusters)
writer.writerow(row)
def get_bad_clusters(part):
bad_clusters = [] # inferred clusters that aren't really all from the same event
for ic in range(len(part)):
same_event = utils.from_same_event(reco_info, part[ic]) # are all the sequences from the same event?
entire_cluster = True # ... and if so, are they the entire true cluster?
if same_event:
reco_id = reco_info[part[ic][0]]['reco_id'] # they've all got the same reco_id then, so pick an aribtrary one
true_cluster = true_partition[reco_id]
for uid in true_cluster:
if uid not in part[ic]:
entire_cluster = False
break
else:
entire_cluster = False
if not same_event or not entire_cluster:
bad_clusters.append(':'.join(part[ic]))
if len(bad_clusters) > 25:
bad_clusters = ['too', 'long']
return bad_clusters
def print_partition(self, ip, reco_info=None, extrastr='', abbreviate=True, smc_print=False):
if ip > 0: # delta between this logprob and the previous one
delta_str = '%.1f' % (self.logprobs[ip] - self.logprobs[ip-1])
else:
delta_str = ''
print ' %s %-12.2f%-7s %-5d %4d' % (extrastr, self.logprobs[ip], delta_str, len(self.partitions[ip]), self.n_procs[ip]),
# logweight (and inverse of number of potential parents)
if self.logweights[ip] is not None and smc_print:
way_str, logweight_str = '', ''
expon = math.exp(self.logweights[ip])
n_ways = 0 if expon == 0. else 1. / expon
way_str = ('%.1f' % n_ways) if n_ways < 1e7 else ('%8.1e' % n_ways)
logweight_str = '%8.3f' % self.logweights[ip]
print ' ' + self.get_ccf_str(ip),
if self.logweights[ip] is not None and smc_print:
print ' %10s %8s ' % (way_str, logweight_str),
# clusters
for cluster in self.partitions[ip]:
if abbreviate:
cluster_str = ':'.join(['o' if len(uid) > 3 else uid for uid in cluster])
else:
# cluster_str = ':'.join(sorted([str(uid) for uid in cluster]))
cluster_str = ':'.join([str(uid) for uid in cluster])
if reco_info is not None and not utils.from_same_event(reco_info, cluster):
cluster_str = utils.color('red', cluster_str)
if self.seed_unique_id is not None and self.seed_unique_id in cluster:
cluster_str = utils.color('reverse_video', cluster_str)
if abbreviate:
print ' %s' % cluster_str,
else:
print ' %s' % cluster_str,
print ''
def peruse_forward_scores():
_, reco_info = seqfileopener.get_seqfile_info(
simfname, is_data=False) #, n_max_queries=10000)
logprobs, partialcorr_logprobs, corr_logprobs = OrderedDict(), OrderedDict(
), OrderedDict()
for n_set in n_set_list:
print n_set
# if n_set != 5:
# continue
logprobs[n_set], partialcorr_logprobs[n_set], corr_logprobs[
n_set] = OrderedDict(), OrderedDict(), OrderedDict()
with open(outputdir + '/' + str(n_set) + '-forward.csv') as csvfile:
reader = csv.DictReader(csvfile)
for line in reader:
uidlist = line['unique_ids'].split(':')
assert utils.from_same_event(reco_info, uidlist)
reco_id = reco_info[uidlist[0]]['reco_id']
if reco_id in logprobs[n_set]:
raise Exception('already had %s' % reco_id)
logprobs[n_set][reco_id] = float(line['logprob'])
factor = 1. / n_set
partialcorr_logprobs[n_set][reco_id] = factor * float(
line['logprob'])
factor = (1. - 0.24 / pow(float(n_set), 0.9)) / n_set
# factor = 1. / (0.77547824*n_set + 0.20327936)
corr_logprobs[n_set][reco_id] = factor * float(line['logprob'])
i_baseline = -1
deviations = get_deviations(logprobs, i_baseline)
# fit_stuff(n_set_list, deviations)
partialcorr_deviations = get_deviations(partialcorr_logprobs, i_baseline)
signed_partialcorr_deviations = get_deviations(partialcorr_logprobs,
i_baseline,
signed=True)
corr_deviations = get_deviations(corr_logprobs, i_baseline)
signed_corr_deviations = get_deviations(corr_logprobs,
i_baseline,
signed=True)
import plotting
fig, ax = plotting.mpl_init()
ax.plot(n_set_list, deviations, marker='.')
plotting.mpl_finish(ax,
baseplotdir,
'forwards',
xlabel='N simultaneous seqs',
ylabel='log prob deviation to ' +
str(n_set_list[i_baseline])) #, ybounds=(-0.02, 0.02))
# fig, ax = plotting.mpl_init()
# ax.plot(n_set_list, partialcorr_deviations, marker='.')
# ax.plot([n_set_list[0], n_set_list[-1]], [0, 0])
# plotting.mpl_finish(ax, baseplotdir, 'partially-corrected-forwards', xlabel='N simultaneous seqs', ylabel='log prob deviation to ' + str(n_set_list[i_baseline])) #, ybounds=(-0.02, 0.02))
fig, ax = plotting.mpl_init()
ax.plot(n_set_list, partialcorr_deviations, marker='.', label='1/n (abs)')
ax.plot(n_set_list, signed_partialcorr_deviations, marker='.', label='1/n')
ax.plot(n_set_list, corr_deviations, marker='.', label='1/crap (abs)')
ax.plot(n_set_list, signed_corr_deviations, marker='.', label='1/crap')
ax.plot([n_set_list[0], n_set_list[-1]], [0, 0])
plotting.mpl_finish(ax,
baseplotdir,
'corrected-forwards',
xlabel='N simultaneous seqs',
ylabel='log prob deviation to ' +
str(n_set_list[i_baseline])) #, ybounds=(-0.02, 0.02))
fig, ax = plotting.mpl_init()
ax.plot(n_set_list, signed_corr_deviations, marker='.')
ax.plot([n_set_list[0], n_set_list[-1]], [0, 0])
plotting.mpl_finish(ax,
baseplotdir,
'signed-corrected-forwards',
xlabel='N simultaneous seqs',
ylabel='log prob deviation to ' +
str(n_set_list[i_baseline])) #, ybounds=(-0.02, 0.02))
def single_link(self,
input_scores=None,
infname=None,
debug=False,
reco_info=None,
outfile=None):
if infname is None:
assert input_scores is not None
else:
assert input_scores is None # should only specify <input_scores> *or* <infname>
input_scores = []
with open(infname, 'r') as infile:
reader = csv.DictReader(infile)
for line in reader:
input_scores.append(line)
sorted_lines = sorted(input_scores, key=lambda k: float(k['logprob']))
for line in sorted_lines:
a_name = line['id_a']
b_name = line['id_b']
score = float(line['logprob'])
dbg_str_list = [
'%22s %22s %8.3f' % (a_name, b_name, score),
]
if reco_info is None:
dbg_str_list[-1] += ' %s' % ('-')
else:
from_same_event = utils.from_same_event(
reco_info, [a_name, b_name])
dbg_str_list[-1] += ' %d' % (from_same_event)
self.incorporate_into_clusters(a_name, b_name, score, dbg_str_list)
self.pairscores[(utils.get_key((a_name, b_name)))] = score
self.plotscores['all'].append(score)
if reco_info is not None:
if from_same_event:
self.plotscores['same'].append(score)
else:
self.plotscores['diff'].append(score)
if debug:
outstr = ''.join(dbg_str_list)
if outfile == None:
print outstr
else:
outfile.write(outstr + '\n')
for query, cluster_id in self.query_clusters.iteritems():
if cluster_id not in self.id_clusters:
self.id_clusters[cluster_id] = []
self.id_clusters[cluster_id].append(query)
for cluster_id, queries in self.id_clusters.items():
if len(queries) == 1:
self.singletons.append(queries[0])
# print 'nearest',self.nearest_true_mate
out_str_list = [
' %d clusters:\n' % len(self.id_clusters),
]
for cluster_id in self.id_clusters:
out_str_list.append(
' ' +
' '.join([str(x)
for x in self.id_clusters[cluster_id]]) + '\n')
if outfile == None:
print ''.join(out_str_list)
else:
outfile.write(''.join(out_str_list))
