def main():
parser = argparse.ArgumentParser(
description='Computes distances between word pairs.')
parser.add_argument("--input",
"-i",
type=openfile,
metavar="FILE",
help='The input vector space.')
parser.add_argument('--pairsfile',
'-w',
metavar='FILE',
type=openfile,
help='The list of tab separated word pairs.')
parser.add_argument(
'words',
nargs='*',
metavar='WORD',
help=('Additional word pairs specified at the command line. '
'Every two specifies an additional word pair. Must be '
'given an even number of words.'))
parser.add_argument('--pos',
'-p',
action='store_true',
help='Marks that the word pairs are POS tagged.')
parser.add_argument('--distance-metric',
'-d',
action='append',
choices=METRICS.keys(),
help='Distance metrics to use.')
args = parser.parse_args()
pairs = set()
if args.pairsfile:
pairs.update(read_pairs(args.pairsfile))
if len(args.words) % 2 != 0:
raise ValueError, "You need to specify an even number of pair words."
if not args.distance_metric:
args.distance_metric = ['cosine']
pairs.update(zip(args.words[::2], args.words[1::2]))
vecspace = read_vector_file(args.input)
if not args.pos:
# need to strip the POS from the targets
vecspace = df_remove_pos(vecspace)
distance_metric_names = args.distance_metric
distance_metrics = [METRICS[name] for name in distance_metric_names]
output_measures = calculate_distance_metrics(vecspace, pairs,
distance_metrics)
output_measures.to_csv(sys.stdout, sep="\t", index=False)
def main():
parser = argparse.ArgumentParser(
description='Computes distances between word pairs.')
parser.add_argument("--input", "-i", type=openfile,
metavar="FILE", help='The input vector space.')
parser.add_argument('--pairsfile', '-w', metavar='FILE', type=openfile,
help='The list of tab separated word pairs.')
parser.add_argument('words', nargs='*', metavar='WORD',
help=('Additional word pairs specified at the command line. '
'Every two specifies an additional word pair. Must be '
'given an even number of words.'))
parser.add_argument('--pos', '-p', action='store_true',
help='Marks that the word pairs are POS tagged.')
parser.add_argument('--distance-metric', '-d', action='append',
choices=METRICS.keys(),
help='Distance metrics to use.')
args = parser.parse_args()
pairs = set()
if args.pairsfile:
pairs.update(read_pairs(args.pairsfile))
if len(args.words) % 2 != 0:
raise ValueError, "You need to specify an even number of pair words."
if not args.distance_metric:
args.distance_metric = ['cosine']
pairs.update(zip(args.words[::2], args.words[1::2]))
vecspace = read_vector_file(args.input)
if not args.pos:
# need to strip the POS from the targets
vecspace = df_remove_pos(vecspace)
distance_metric_names = args.distance_metric
distance_metrics = [METRICS[name] for name in distance_metric_names]
output_measures = calculate_distance_metrics(vecspace, pairs, distance_metrics)
output_measures.to_csv(sys.stdout, sep="\t", index=False)
def main():
parser = argparse.ArgumentParser(
description='Computes correlations with compositionality ratings.')
parser.add_argument('--input', '-i', action="append", type=openfile,
metavar="FILE", help='Input vector space.')
parser.add_argument('--ratings', '-r', metavar='COMPFILE', type=openfile,
help='The compositionality ratings file.')
parser.add_argument('--self', '-s', action="store_true",
help='Whether we should include self-comp ratings.')
parser.add_argument('--no-tsv', '-T', action="store_true",
help="*Don't* output the TSV containing comp and model ratings.")
parser.add_argument('--corrs', '-c', action="store_true",
help='Specifies whether correlations should be computed and outputed.')
parser.add_argument('--pdf', '-p', metavar="FILE", default=None,
help='Output plots as a PDF to the given filename.')
args = parser.parse_args()
compratings = pd.read_table(args.ratings)
if not args.self:
compratings = compratings[compratings["compound"] != compratings["const"]]
word_pairs = set(zip(compratings['compound'], compratings['const']))
named_vector_spaces = [
(basename(f.name), norm2_matrix(df_remove_pos(read_vector_file(f))))
for f in args.input
]
if len(named_vector_spaces) > 1:
# need to do concatenation
names, vses = zip(*named_vector_spaces)
concat_space = pd.concat(vses, keys=names)
named_vector_spaces.append(("<concat>", concat_space))
# compute all the distances AND keep the different measures independently named
distances = [
cdm(vs, word_pairs, [DISTANCE_METRIC])
.rename(columns={DISTANCE_METRIC.name: fn + ":" + DISTANCE_METRIC.name})
for fn, vs in named_vector_spaces
]
# now we need to join all the distance calculations:
joined_measures = reduce(pd.merge, distances).rename(
columns={"left": "compound", "right": "const"})
# finally join the similarity measures with the human ratings
dm_and_comp = pd.merge(compratings, joined_measures)
# output dm_and_comp unless the user specified not to
if not args.no_tsv:
dm_and_comp.to_csv(sys.stdout, index=False, sep="\t")
# nicer output
if not args.no_tsv and args.corrs:
# let's compute our correlations
print "\n" + "-" * 80 + "\n"
# compute and output correlations if the user asked
if args.corrs:
corrs = correlations(dm_and_comp).to_csv(sys.stdout, index=False, sep="\t")
# plot the measures if the user asked.
if args.pdf:
scatters(dm_and_comp, args.pdf)
def main():
parser = argparse.ArgumentParser(
description='Computes correlations with compositionality ratings.')
parser.add_argument('--input',
'-i',
action="append",
type=openfile,
metavar="FILE",
help='Input vector space.')
parser.add_argument('--ratings',
'-r',
metavar='COMPFILE',
type=openfile,
help='The compositionality ratings file.')
parser.add_argument('--self',
'-s',
action="store_true",
help='Whether we should include self-comp ratings.')
parser.add_argument(
'--no-tsv',
'-T',
action="store_true",
help="*Don't* output the TSV containing comp and model ratings.")
parser.add_argument(
'--corrs',
'-c',
action="store_true",
help='Specifies whether correlations should be computed and outputed.')
parser.add_argument('--pdf',
'-p',
metavar="FILE",
default=None,
help='Output plots as a PDF to the given filename.')
args = parser.parse_args()
compratings = pd.read_table(args.ratings)
if not args.self:
compratings = compratings[
compratings["compound"] != compratings["const"]]
word_pairs = set(zip(compratings['compound'], compratings['const']))
named_vector_spaces = [(basename(f.name),
norm2_matrix(df_remove_pos(read_vector_file(f))))
for f in args.input]
if len(named_vector_spaces) > 1:
# need to do concatenation
names, vses = zip(*named_vector_spaces)
concat_space = pd.concat(vses, keys=names)
named_vector_spaces.append(("<concat>", concat_space))
# compute all the distances AND keep the different measures independently named
distances = [
cdm(vs, word_pairs, [DISTANCE_METRIC]).rename(
columns={DISTANCE_METRIC.name: fn + ":" + DISTANCE_METRIC.name})
for fn, vs in named_vector_spaces
]
# now we need to join all the distance calculations:
joined_measures = reduce(pd.merge, distances).rename(columns={
"left": "compound",
"right": "const"
})
# finally join the similarity measures with the human ratings
dm_and_comp = pd.merge(compratings, joined_measures)
# output dm_and_comp unless the user specified not to
if not args.no_tsv:
dm_and_comp.to_csv(sys.stdout, index=False, sep="\t")
# nicer output
if not args.no_tsv and args.corrs:
# let's compute our correlations
print "\n" + "-" * 80 + "\n"
# compute and output correlations if the user asked
if args.corrs:
corrs = correlations(dm_and_comp).to_csv(sys.stdout,
index=False,
sep="\t")
# plot the measures if the user asked.
if args.pdf:
scatters(dm_and_comp, args.pdf)