print 'Creating contingency table...'
ct = tt.crosstab(truth.hard(), pred.hard())
print
print 'Contigency table [rows=truth, cols=prediction] contains {0} elements'.format(
ct.shape[0] * ct.shape[1])
print_table(ct)
print
if over_clustered(ct):
add_padding_columns(ct)
print 'Squaring table with dummy classes'
print_table(ct)
print
# Write the table to stdout
print 'Matching labels using Munkres, algorithm suffers from high polynomial order...'
mct = match_labels(ct)
print 'Aligned contigency table'
print_table(mct)
# Calculate measure
score = {
'f1': f1_score_macro(mct),
'recall': recall_macro(mct),
'prec': precision_macro(mct)
}
# Write measure to file
pipeline_utils.write_to_stream(args.output, score)
print 'Reading prediction...'
pred = tt.read_mcl(args.pred[0])
print 'Creating contingency table...'
ct = tt.crosstab(truth.hard(), pred.hard())
print
print 'Contigency table [rows=truth, cols=prediction] contains {0} elements'.format(ct.shape[0] * ct.shape[1])
print_table(ct)
print
if over_clustered(ct):
add_padding_columns(ct)
print 'Squaring table with dummy classes'
print_table(ct)
print
# Write the table to stdout
print 'Matching labels using Munkres, algorithm suffers from high polynomial order...'
mct = match_labels(ct)
print 'Aligned contigency table'
print_table(mct)
# Calculate measure
score = {'f1': f1_score_macro(mct),
'recall': recall_macro(mct),
'prec': precision_macro(mct)}
# Write measure to file
pipeline_utils.write_to_stream(args.output, score)
raise RuntimeWarning('Truth table contains no assignments: {0}'.format(args.truth[0]))
# collect object weights if requested
weights = truth.get_weights() if args.weighted else None
if args.verbose:
print 'Truth Statistics'
truth.print_tally()
if args.hard:
truth = truth.hard(True)
else:
truth = truth.soft(True)
# read clustering and convert to basic soft table
clustering = tt.read_mcl(args.pred)
if len(clustering) == 0:
raise RuntimeWarning('Clustering contains no assignments: {0}'.format(args.pred[0]))
if args.verbose:
print 'Clustering Statistics'
clustering.print_tally()
clustering = clustering.soft(True)
except RuntimeWarning as wn:
write_msg(args.output, wn.message)
sys.exit(0)
result = bcubed_F(truth, clustering, weights)
pipeline_utils.write_to_stream(args.output, result)