parser.add_argument('-o', '--out-dir', help='Output directory')
args = parser.parse_args()
if args.out_dir:
if not os.path.exists(args.out_dir):
os.makedirs(args.out_dir)
elif not os.path.isdir(args.out_dir):
raise IOError('Output path exists and is not a directory')
if args.verbose:
print 'Getting sequence index'
seq_index = SeqIO.index(args.fasta, 'fasta')
if args.verbose:
print 'Reading clustering'
tt = ttable.read_mcl(args.clustering)
cl2seq = tt.invert()
if len(args.cid_list) > 0:
cid_list = args.cid_list
else:
cid_list = [ci for ci in cl2seq]
for ci in cid_list:
if args.verbose:
print 'Collecting sequences for cluster {0}'.format(ci)
seqs = []
for si in cl2seq[int(ci)]:
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)
print
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)
print
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)