def processData(args):
data = dataset.Dataset.load(args.input_data, args.dataset)
wvout = args.wvfile
if os.path.exists(wvout):
wordvecf = wvout
else:
wordvecf = args.wvsource
features = {x for x in args.basefeatures.split(',') if x != ''}
matchers = {x for x in args.matchers.split(',') if x != ''}
printd("Loading Word Vectors")
wordvec = WordVec(wordvecf)
printd("Vectorizing")
data.vectorize(wordvec)
maxwords = data.maxShortSentence()
if wvout != wordvecf:
printd("Rereading word vectors to optimize...")
wv_toks = data.wv_sentences()
wordvec = WordVec(wordvecf, sentences=wv_toks, wvout=wvout, size=wordvec.originalsize)
data.vectorize(wordvec)
conf.wvsize = wordvec.size
# Train data
printd("Computing basic WV Features")
fs = FeatureSet(data, features)
if "Pair" in matchers:
printd("Computing Pair Features")
matcher = vectorsim.PairFeatures(dimfeatures=args.dimfeatures)
fs.addMatcher(matcher)
if "Shingle" in matchers:
printd("Computing Shingle Features")
matcher = Shingler(slop=12, lmbda=0.95)
fs.addMatcher(matcher)
vocab = None
if "MinDistSim" in matchers:
printd("Computing MinDist")
vocab = fs.data.wv_vocab()
data.weight()
comparator = 'cosine'
matcher = vectorsim.MinDistSim(metric=comparator, df=vocab, maxsent=maxwords, dimfeatures=args.dimfeatures)
fs.addMatcher(matcher, 'cos')
printd("Computing MinDist-Euclidean")
comparator = 'euclidean'
matcher = vectorsim.MinDistSim(metric=comparator, df=vocab, maxsent=maxwords, dimfeatures=args.dimfeatures)
fs.addMatcher(matcher, 'euc')
if "NGram" in matchers:
printd("Computing MinDist-Ngram")
vocab = fs.data.wv_vocab()
if vocab is None:
vocab = fs.data.wv_vocab()
comparator = 'cosine'
matcher = vectorsim.MinDistSim(metric=comparator, df=vocab, maxsent=maxwords, ngram=2, dimfeatures=args.dimfeatures)
fs.addMatcher(matcher, 'cos-bigram')
comparator = 'cosine'
matcher = vectorsim.MinDistSim(metric=comparator, df=vocab, maxsent=maxwords, ngram=3, dimfeatures=args.dimfeatures)
fs.addMatcher(matcher, 'cos-trigram')
if "WWSim" in matchers:
printd("Computing WWSim")
matcher = vectorsim.WWSim(wordvec=wordvec, dimfeatures=args.dimfeatures)
fs.addMatcher(matcher)
if "InfRankSim" in matchers:
printd("Computing InfRankSim")
matcher = vectorsim.InfRankSim(data=data, wordvec=wordvec, dimfeatures=args.dimfeatures)
printd("InfRankSim Matching")
fs.addMatcher(matcher)
if "InfSim" in matchers:
# We normalize after so primary features are raw word vectors
# InfSim
printd("Computing InfSim")
wordvec.normalize()
data.vectorize(wordvec)
matcher = vectorsim.InfSim(data=data, wordvec=wordvec, dimfeatures=args.dimfeatures)
fs.addMatcher(matcher)
return fs
def main(args):
global wordvec, wordvecf
conf.debug = args.debug or args.verbose
conf.verbose = args.verbose
conf.args = args
#nf = args.nuggets
#uf = args.updates
#mf = args.matches
sf = args.shingles
vf = args.wordvec
#ef = args.evalfile
wvout = args.wvfile
sim_thr = args.sim_thr
dset = args.dataset
limit = args.limit
#if args.dataset == "auto":
# if ef is not None:
# dset = "semeval"
# else:
# with open(glob.glob(nf)[0]) as nh:
# nfhead = nh.readline()
# if nfhead.startswith("query_id\tnugget_id"):
# dset = "ts"
# elif nfhead.startswith("query_id\tvs_id"):
# dset = "mclick"
# else:
# dset = "1click"
if os.path.exists(wvout) and not args.force:
wordvecf = wvout
if vf:
printd("Reading word vector...")
#wordvec = load_wordvec()
wordvec = WordVec(wordvecf)
if args.sim == "minsim":
matcher = MinDistSim
elif args.sim == "infsim":
matcher = InfSim
else:
matcher = VecSim
if args.sim == "infsim" or args.comparator == "infsim":
wordvec.normalize()
#if dset == "ts":
# nuggfn = Nuggets
# updfn = Updates
# outfn = MatchWriter
#elif dset == "1click":
# nuggfn = CLNuggets
# updfn = CLUpdates
# outfn = CLMatchWriter
#elif dset == "mclick":
# nuggfn = MCNuggets
# updfn = Updates
# outfn = MCMatchWriter
#elif dset == "semeval":
# data = SemEvalDataset(args.input_data, args.evalfile)
# outfn = data.writer
# if vf is not None:
# data.vectorize(wordvec)
#else:
# nuggfn = MCNuggets
# updfn = Updates
# outfn = MCMatchWriter
data = Dataset.load(args.input_data, dset)
if vf is not None:
data.vectorize(wordvec)
#if dset == "semeval":
# data = SemEvalDataset(args.input_data, args.evalfile)
# #outfn = data.writer
# if vf is not None:
# data.vectorize(wordvec)
#else:
# printd("Processing Nuggets...")
# #nuggets = nuggfn(nf, vectorize=vf is not None)
# printd("Processing Updates...")
# #updates = updfn(uf, vectorize=vf is not None)
# #data = NuggetDataset(nuggets, updates, mf)
# data = NuggetDataset(nf, uf, mf, dset=dset, vectorize=vf is not None)
if vf and wvout is not None and wvout != wordvecf:
printd("Rereading word vectors to optimize...")
wv_toks = data.wv_sentences()
#if dset == "semeval":
# wv_toks = data.wv_sentences()
#else:
# wv_toks = nuggets.wv_text() + updates.wv_text()
wordvec = WordVec(wordvecf,
sentences=wv_toks,
wvout=wvout,
size=wordvec.originalsize)
if args.sim == "infsim" or args.comparator == "infsim":
wordvec.normalize()
data.vectorize(wordvec)
with open(wvout + ".vocab", 'w') as wh:
wh.write("\n".join(wordvec.vocab().keys()))
with open(wvout + ".toks", 'w') as wh:
wh.write("\n".join([" ".join(x) for x in wv_toks]))
#vocab = nuggets.wv_vocab().union(updates.wv_vocab())
#wordvec.trim(lambda word, count, min_count: gensim.utils.RULE_KEEP if word in vocab else gensim.utils.RULE_DISCARD)
#wordvec.save(wvout)
vocab = None
if args.frequencies:
try:
with open(args.frequencies) as fh:
vocab = json.load(fh)
# For Term Frequencies instead of Document Frequencies
# Could also do len(vocab[word]) if wanted to mimic DF
if type(vocab.itervalues().next()) == dict:
for word in vocab:
vocab[word] = sum(vocab[word].itervalues())
except Exception:
pass
if vocab is None:
vocab = data.wv_vocab()
logdf = wordvec.logdf(vocab)
logdffile = wordvecf + ".logdf"
#if not os.path.exists(logdffile) or (os.path.getmtime(logdffile) < os.path.getmtime(wordvecf)):
# np.savetxt(logdffile, logdf, delimiter=" ", fmt="%g")
np.savetxt(logdffile, logdf, delimiter=" ", fmt="%g")
if args.comparator == "infsim" and args.sim != "infsim":
comparator = InfSim(logdf).pairwisedist
else:
comparator = args.comparator
matcher = matcher(df=logdf, metric=comparator)
data.normalize(matcher, logdf)
printd("Finding matches...")
matches = []
with data.writer(sf) as sw, data.writer(vf) as vw:
mcnt = 0
timer = Timer()
for pair in data.test():
if sf:
match = shingle(pair.s1["tokens"], pair.s2["tokens"])
if match.score >= min_score:
sw.write(pair, match)
if vf:
printd("Matching pair %s" % (pair.pid), level=1)
try:
sim = matcher.match(pair)
matches.append((matcher.tsim, unicode(matcher)))
except ValueError, err:
printd(err)
sim = sim_thr
printd("Match %0.4f for %s, %s" % (sim, pair.sid1, pair.sid2))
if sim < sim_thr:
sim = sim_thr
start = matcher.start
end = matcher.end - matcher.start
else:
start = -1
end = len(pair.s2["tokens"]) - 1
match = Match(sim, start, end)
vw.write(pair, match)
mcnt += 1
if (mcnt % 100000) == 0:
print >> sys.stderr, "%g tmps" % (100 / timer.mark())
if limit and mcnt >= limit:
return
if conf.verbose:
for tsim, match in sorted(matches):
print match
def processData(args):
data = dataset.Dataset.load(args.input_data, args.dataset)
wvout = args.wvfile
if os.path.exists(wvout):
wordvecf = wvout
else:
wordvecf = args.wvsource
features = {x for x in args.basefeatures.split(',') if x != ''}
matchers = {x for x in args.matchers.split(',') if x != ''}
printd("Loading Word Vectors")
wordvec = WordVec(wordvecf)
printd("Vectorizing")
data.vectorize(wordvec)
maxwords = data.maxShortSentence()
if wvout != wordvecf:
printd("Rereading word vectors to optimize...")
wv_toks = data.wv_sentences()
wordvec = WordVec(wordvecf,
sentences=wv_toks,
wvout=wvout,
size=wordvec.originalsize)
data.vectorize(wordvec)
conf.wvsize = wordvec.size
# Train data
printd("Computing basic WV Features")
fs = FeatureSet(data, features)
if "Pair" in matchers:
printd("Computing Pair Features")
matcher = vectorsim.PairFeatures(dimfeatures=args.dimfeatures)
fs.addMatcher(matcher)
if "Shingle" in matchers:
printd("Computing Shingle Features")
matcher = Shingler(slop=12, lmbda=0.95)
fs.addMatcher(matcher)
vocab = None
if "MinDistSim" in matchers:
printd("Computing MinDist")
vocab = fs.data.wv_vocab()
data.weight()
comparator = 'cosine'
matcher = vectorsim.MinDistSim(metric=comparator,
df=vocab,
maxsent=maxwords,
dimfeatures=args.dimfeatures)
fs.addMatcher(matcher, 'cos')
printd("Computing MinDist-Euclidean")
comparator = 'euclidean'
matcher = vectorsim.MinDistSim(metric=comparator,
df=vocab,
maxsent=maxwords,
dimfeatures=args.dimfeatures)
fs.addMatcher(matcher, 'euc')
if "NGram" in matchers:
printd("Computing MinDist-Ngram")
vocab = fs.data.wv_vocab()
if vocab is None:
vocab = fs.data.wv_vocab()
comparator = 'cosine'
matcher = vectorsim.MinDistSim(metric=comparator,
df=vocab,
maxsent=maxwords,
ngram=2,
dimfeatures=args.dimfeatures)
fs.addMatcher(matcher, 'cos-bigram')
comparator = 'cosine'
matcher = vectorsim.MinDistSim(metric=comparator,
df=vocab,
maxsent=maxwords,
ngram=3,
dimfeatures=args.dimfeatures)
fs.addMatcher(matcher, 'cos-trigram')
if "WWSim" in matchers:
printd("Computing WWSim")
matcher = vectorsim.WWSim(wordvec=wordvec,
dimfeatures=args.dimfeatures)
fs.addMatcher(matcher)
if "InfRankSim" in matchers:
printd("Computing InfRankSim")
matcher = vectorsim.InfRankSim(data=data,
wordvec=wordvec,
dimfeatures=args.dimfeatures)
printd("InfRankSim Matching")
fs.addMatcher(matcher)
if "InfSim" in matchers:
# We normalize after so primary features are raw word vectors
# InfSim
printd("Computing InfSim")
wordvec.normalize()
data.vectorize(wordvec)
matcher = vectorsim.InfSim(data=data,
wordvec=wordvec,
dimfeatures=args.dimfeatures)
fs.addMatcher(matcher)
return fs
def main(args):
global wordvec, wordvecf
conf.debug = args.debug or args.verbose
conf.verbose = args.verbose
conf.args = args
#nf = args.nuggets
#uf = args.updates
#mf = args.matches
sf = args.shingles
vf = args.wordvec
#ef = args.evalfile
wvout = args.wvfile
sim_thr = args.sim_thr
dset = args.dataset
limit = args.limit
#if args.dataset == "auto":
# if ef is not None:
# dset = "semeval"
# else:
# with open(glob.glob(nf)[0]) as nh:
# nfhead = nh.readline()
# if nfhead.startswith("query_id\tnugget_id"):
# dset = "ts"
# elif nfhead.startswith("query_id\tvs_id"):
# dset = "mclick"
# else:
# dset = "1click"
if os.path.exists(wvout) and not args.force:
wordvecf = wvout
if vf:
printd("Reading word vector...")
#wordvec = load_wordvec()
wordvec = WordVec(wordvecf)
if args.sim == "minsim":
matcher = MinDistSim
elif args.sim == "infsim":
matcher = InfSim
else:
matcher = VecSim
if args.sim == "infsim" or args.comparator == "infsim":
wordvec.normalize()
#if dset == "ts":
# nuggfn = Nuggets
# updfn = Updates
# outfn = MatchWriter
#elif dset == "1click":
# nuggfn = CLNuggets
# updfn = CLUpdates
# outfn = CLMatchWriter
#elif dset == "mclick":
# nuggfn = MCNuggets
# updfn = Updates
# outfn = MCMatchWriter
#elif dset == "semeval":
# data = SemEvalDataset(args.input_data, args.evalfile)
# outfn = data.writer
# if vf is not None:
# data.vectorize(wordvec)
#else:
# nuggfn = MCNuggets
# updfn = Updates
# outfn = MCMatchWriter
data = Dataset.load(args.input_data, dset)
if vf is not None:
data.vectorize(wordvec)
#if dset == "semeval":
# data = SemEvalDataset(args.input_data, args.evalfile)
# #outfn = data.writer
# if vf is not None:
# data.vectorize(wordvec)
#else:
# printd("Processing Nuggets...")
# #nuggets = nuggfn(nf, vectorize=vf is not None)
# printd("Processing Updates...")
# #updates = updfn(uf, vectorize=vf is not None)
# #data = NuggetDataset(nuggets, updates, mf)
# data = NuggetDataset(nf, uf, mf, dset=dset, vectorize=vf is not None)
if vf and wvout is not None and wvout != wordvecf:
printd("Rereading word vectors to optimize...")
wv_toks = data.wv_sentences()
#if dset == "semeval":
# wv_toks = data.wv_sentences()
#else:
# wv_toks = nuggets.wv_text() + updates.wv_text()
wordvec = WordVec(wordvecf, sentences=wv_toks, wvout=wvout, size=wordvec.originalsize)
if args.sim == "infsim" or args.comparator == "infsim":
wordvec.normalize()
data.vectorize(wordvec)
with open(wvout + ".vocab", 'w') as wh:
wh.write("\n".join(wordvec.vocab().keys()))
with open(wvout + ".toks", 'w') as wh:
wh.write("\n".join([" ".join(x) for x in wv_toks]))
#vocab = nuggets.wv_vocab().union(updates.wv_vocab())
#wordvec.trim(lambda word, count, min_count: gensim.utils.RULE_KEEP if word in vocab else gensim.utils.RULE_DISCARD)
#wordvec.save(wvout)
vocab = None
if args.frequencies:
try:
with open(args.frequencies) as fh:
vocab = json.load(fh)
# For Term Frequencies instead of Document Frequencies
# Could also do len(vocab[word]) if wanted to mimic DF
if type(vocab.itervalues().next()) == dict:
for word in vocab:
vocab[word] = sum(vocab[word].itervalues())
except Exception:
pass
if vocab is None:
vocab = data.wv_vocab()
logdf = wordvec.logdf(vocab)
logdffile = wordvecf + ".logdf"
#if not os.path.exists(logdffile) or (os.path.getmtime(logdffile) < os.path.getmtime(wordvecf)):
# np.savetxt(logdffile, logdf, delimiter=" ", fmt="%g")
np.savetxt(logdffile, logdf, delimiter=" ", fmt="%g")
if args.comparator == "infsim" and args.sim != "infsim":
comparator = InfSim(logdf).pairwisedist
else:
comparator = args.comparator
matcher = matcher(df=logdf, metric=comparator)
data.normalize(matcher, logdf)
printd("Finding matches...")
matches = []
with data.writer(sf) as sw, data.writer(vf) as vw:
mcnt = 0
timer = Timer()
for pair in data.test():
if sf:
match = shingle(pair.s1["tokens"], pair.s2["tokens"])
if match.score >= min_score:
sw.write(pair, match)
if vf:
printd("Matching pair %s" % (pair.pid), level=1)
try:
sim = matcher.match(pair)
matches.append((matcher.tsim, unicode(matcher)))
except ValueError, err:
printd(err)
sim = sim_thr
printd("Match %0.4f for %s, %s" % (sim, pair.sid1, pair.sid2))
if sim < sim_thr:
sim = sim_thr
start = matcher.start
end = matcher.end - matcher.start
else:
start = -1
end = len(pair.s2["tokens"]) - 1
match = Match(sim, start, end)
vw.write(pair, match)
mcnt += 1
if (mcnt % 100000) == 0:
print >>sys.stderr, "%g tmps" % (100 / timer.mark())
if limit and mcnt >= limit:
return
if conf.verbose:
for tsim, match in sorted(matches):
print match
