print pd.DataFrame(b,
columns=['Sum'] + df.columns.values.tolist(),
index=['Sum'] + df.index.values.tolist())
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Calculate F1 metric')
parser.add_argument('-s', '--min-score', type=int, help='minimum truth object score', default=0)
parser.add_argument('truth', nargs=1, help='truth table in yaml format')
parser.add_argument('pred', nargs=1, help='prediction in MCL format')
parser.add_argument('output', nargs='?', type=argparse.FileType('w'), default=sys.stdout, help='Output file')
args = parser.parse_args()
print 'Reading truth table...'
truth = tt.read_truth(args.truth[0], args.min_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)
#!/usr/bin/env python
import truthtable as tt
import numpy as np
import sys
table = tt.read_truth(sys.argv[1])
num_class = []
for k, v in table.asgn_dict.iteritems():
num_class.append(len(v))
print '#objects\tmean_size\tsd_size'
print '{0}\t{1}\t{2}'.format(len(num_class), np.mean(num_class), np.std(num_class))
parser.add_argument('-s',
'--min-score',
type=int,
help='minimum truth object score',
default=0)
parser.add_argument('truth', nargs=1, help='truth table in yaml format')
parser.add_argument('pred', nargs=1, help='prediction in MCL format')
parser.add_argument('output',
nargs='?',
type=argparse.FileType('w'),
default=sys.stdout,
help='Output file')
args = parser.parse_args()
print 'Reading truth table...'
truth = tt.read_truth(args.truth[0], args.min_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'
#!/usr/bin/env python
import truthtable as tt
import numpy as np
import sys
table = tt.read_truth(sys.argv[1])
num_class = []
for k, v in table.asgn_dict.iteritems():
num_class.append(len(v))
print '#objects\tmean_size\tsd_size'
print '{0}\t{1}\t{2}'.format(len(num_class), np.mean(num_class),
np.std(num_class))
with open(filename, 'w') as hout:
hout.write(msg + '\n')
parser = argparse.ArgumentParser(description='Calculate extended bcubed metric')
parser.add_argument('truth', metavar='TRUTH', help='Truth table (yaml format)')
parser.add_argument('pred', metavar='PREDICTION', help='Prediction table (mcl format)')
parser.add_argument('output', metavar='OUTPUT',nargs='?', type=argparse.FileType('w'),
default=sys.stdout, help='Output file (stdout)')
parser.add_argument('-w','--weighted', default=False, action='store_true', help='Use truth object weights')
parser.add_argument('-v', '--verbose', action='store_true', default=False, help='Verbose output')
parser.add_argument('--hard', action='store_true', default=False, help='Extract hard truth prior to analysis')
args = parser.parse_args()
try:
# read truth and convert to basic soft table
truth = tt.read_truth(args.truth)
if len(truth) == 0:
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)
