parser.add_argument("--no_domain_ig", action="store_true", default=False, help="use only per-langugage IG in LD calculation")
parser.add_argument("model", metavar='MODEL_DIR', help="read index and produce output in MODEL_DIR")
args = parser.parse_args()
lang_w_path = os.path.join(args.model, 'IGweights.lang.bin')
domain_w_path = os.path.join(args.model, 'IGweights.domain')
feature_path = args.output if args.output else os.path.join(args.model, 'LDfeats')
# display paths
if not SILENT:
print "model path:", args.model
print "lang weights path:", lang_w_path
print "domain weights path:", domain_w_path
print "feature output path:", feature_path
lang_w = read_weights(lang_w_path)
domain_w = read_weights(domain_w_path) if not args.no_domain_ig else None
features_per_lang = select_LD_features(lang_w, domain_w, args.feats_per_lang, ignore_domain=args.no_domain_ig)
if args.per_lang:
with open(feature_path + '.perlang', 'w') as f:
writer = csv.writer(f)
for i in range(len(features_per_lang)):
writer.writerow(map(repr,features_per_lang[i]))
final_feature_set = reduce(set.union, map(set, features_per_lang.values()))
if not SILENT:
print 'selected %d features' % len(final_feature_set)
write_features(sorted(final_feature_set), feature_path)
parser.add_argument("--per_lang", action="store_true", default=False, help="produce a list of features selecter per-language")
parser.add_argument("--no_domain_ig", action="store_true", default=False, help="use only per-langugage IG in LD calculation")
parser.add_argument("model", metavar='MODEL_DIR', help="read index and produce output in MODEL_DIR")
args = parser.parse_args()
lang_w_path = os.path.join(args.model, 'IGweights.lang.bin')
domain_w_path = os.path.join(args.model, 'IGweights.domain')
feature_path = args.output if args.output else os.path.join(args.model, 'LDfeats')
# display paths
print "model path:", args.model
print "lang weights path:", lang_w_path
print "domain weights path:", domain_w_path
print "feature output path:", feature_path
lang_w = read_weights(lang_w_path)
domain_w = read_weights(domain_w_path)
features_per_lang = select_LD_features(lang_w, domain_w, args.feats_per_lang, ignore_domain=args.no_domain_ig)
if args.per_lang:
with open(feature_path + '.perlang', 'w') as f:
writer = csv.writer(f)
for i in range(len(features_per_lang)):
writer.writerow(map(repr,features_per_lang[i]))
final_feature_set = reduce(set.union, map(set, features_per_lang.values()))
print 'selected %d features' % len(final_feature_set)
write_features(sorted(final_feature_set), feature_path)
print 'wrote features to "%s"' % feature_path
metavar='MODEL_DIR',
help="read index and produce output in MODEL_DIR")
args = parser.parse_args()
lang_w_path = os.path.join(args.model, 'IGweights.lang.bin')
domain_w_path = os.path.join(args.model, 'IGweights.domain')
feature_path = args.output if args.output else os.path.join(
args.model, 'LDfeats')
# display paths
print "model path:", args.model
print "lang weights path:", lang_w_path
print "domain weights path:", domain_w_path
print "feature output path:", feature_path
lang_w = read_weights(lang_w_path)
domain_w = read_weights(domain_w_path) if not args.no_domain_ig else None
features_per_lang = select_LD_features(lang_w,
domain_w,
args.feats_per_lang,
ignore_domain=args.no_domain_ig)
if args.per_lang:
with open(feature_path + '.perlang', 'w') as f:
writer = csv.writer(f)
for i in range(len(features_per_lang)):
writer.writerow(map(repr, features_per_lang[i]))
final_feature_set = reduce(set.union, map(set, features_per_lang.values()))
print 'selected %d features' % len(final_feature_set)
"""
Select the most highly-weighted N features across any number of files.
Marco Lui, February 2013
"""
import argparse
from common import read_weights, write_features
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("-n","--number", type=int, default=200, metavar='N',
help="keep top N features per file")
parser.add_argument("output", metavar='PATH', help="output to PATH")
parser.add_argument("files", metavar="FILE", nargs='*', help="read weighted features from FILE")
args = parser.parse_args()
out_f = open(args.output, 'w') if args.output else sys.stdout
feats = set()
for path in args.files:
w = read_weights(path)
feats |= set(sorted(w, key=w.get, reverse=True)[:args.number])
write_features(sorted(feats), args.output)
metavar='MODEL_DIR',
help="read index and produce output in MODEL_DIR")
args = parser.parse_args()
lang_w_path = os.path.join(args.model, 'IGweights.lang.bin')
domain_w_path = os.path.join(args.model, 'IGweights.domain')
feature_path = args.output if args.output else os.path.join(
args.model, 'LDfeats')
# display paths
print "model path:", args.model
print "lang weights path:", lang_w_path
print "domain weights path:", domain_w_path
print "feature output path:", feature_path
lang_w = read_weights(lang_w_path)
domain_w = read_weights(domain_w_path)
features_per_lang = select_LD_features(lang_w,
domain_w,
args.feats_per_lang,
ignore_domain=args.no_domain_ig)
if args.per_lang:
with open(feature_path + '.perlang', 'w') as f:
writer = csv.writer(f)
for i in range(len(features_per_lang)):
writer.writerow(map(repr, features_per_lang[i]))
final_feature_set = reduce(set.union, map(set, features_per_lang.values()))
print 'selected %d features' % len(final_feature_set)
