def test_auto_mask_within_seq2vec(self):
Glove.defaultpath = "../../../data/glove/miniglove.%dd.txt"
batsize = 11
seqlen = 3
seqblank = 2
wordlen = 3
wordblank = 2
numchars = 20
numwords = 100
encdim = 4
embdim = 50
innerdim = 2
worddata = np.random.randint(0, numwords, (batsize, seqlen, 1))
worddatablank = np.zeros((batsize, seqblank, 1)).astype("int32") - 1
worddata = np.concatenate([worddata, worddatablank], axis=1)
chardata = np.random.randint(0, numchars, (batsize, seqlen, wordlen))
charblank = np.zeros((batsize, seqlen, wordblank)).astype("int32") - 1
chardata = np.concatenate([chardata, charblank], axis=2)
charblankblank = np.zeros(
(batsize, seqblank, wordlen + wordblank)).astype("int32") - 1
chardata = np.concatenate([chardata, charblankblank], axis=1)
data = np.concatenate([worddata, chardata], axis=2)
wordemb = WordEncoderPlusGlove(numchars=numchars,
numwords=numwords,
encdim=encdim,
embdim=embdim,
maskid=-1,
embtrainfrac=0)
rnn, lastdim = SimpleSeq2Vec.makernu(embdim + encdim,
innerdim,
bidir=False)
enc = Seq2Vec(wordemb, rnn, maskid=-1)
enc.enc.with_outputs()
finalpred, pred = enc.predict(data)
#print pred.shape, finalpred.shape
#print pred[0], finalpred[0]
i = 1
while i < pred.shape[1]:
self.assertEqual(np.allclose(pred[:, i - 1, :], pred[:, i, :]),
i >= seqlen)
i += 1
def test_auto_mask_within_seq2vec(self):
Glove.defaultpath = "../../../data/glove/miniglove.%dd.txt"
batsize = 11
seqlen = 3
seqblank = 2
wordlen = 3
wordblank = 2
numchars = 20
numwords = 100
encdim = 4
embdim = 50
innerdim = 2
worddata = np.random.randint(0, numwords, (batsize, seqlen, 1))
worddatablank = np.zeros((batsize, seqblank, 1)).astype("int32") - 1
worddata = np.concatenate([worddata, worddatablank], axis=1)
chardata = np.random.randint(0, numchars, (batsize, seqlen, wordlen))
charblank = np.zeros((batsize, seqlen, wordblank)).astype("int32") - 1
chardata = np.concatenate([chardata, charblank], axis=2)
charblankblank = np.zeros((batsize, seqblank, wordlen+wordblank)).astype("int32") - 1
chardata = np.concatenate([chardata, charblankblank], axis=1)
data = np.concatenate([worddata, chardata], axis=2)
wordemb = WordEncoderPlusGlove(numchars=numchars, numwords=numwords, encdim=encdim, embdim=embdim,
maskid=-1,
embtrainfrac=0)
rnn, lastdim = SimpleSeq2Vec.makernu(embdim + encdim, innerdim, bidir=False)
enc = Seq2Vec(wordemb, rnn, maskid=-1)
enc.enc.with_outputs
finalpred, pred = enc.predict(data)
#print pred.shape, finalpred.shape
#print pred[0], finalpred[0]
i = 1
while i < pred.shape[1]:
self.assertEqual(np.allclose(pred[:, i-1, :], pred[:, i, :]), i >= seqlen)
i += 1
def run(epochs=10,
numbats=100,
numsam=10000,
lr=0.1,
datap="../../../data/simplequestions/datamat.wordchar.pkl",
embdim=50,
encdim=50,
innerdim=200,
wreg=0.00005,
bidir=False,
keepmincount=5,
sameenc=False,
memaddr="dot",
memattdim=100,
layers=1,
embtrainfrac=0.0,
mem=False,
membidir=False,
memlayers=1,
sharedwordenc=False):
""" Memory match-based glove-based word-level relation classification """
(traindata, traingold), (validdata, validgold), (testdata, testgold), worddic, chardic, entdic\
= readdata(datap)
# get words from relation names, update word dic
memdata = getmemdata(entdic, worddic, chardic)
# get glove and transform word mats to glove index space
d2g, newdic, glove = getdic2glove(worddic,
dim=embdim,
trainfrac=embtrainfrac)
traindata, validdata, testdata, memdata = \
[np.concatenate([np.vectorize(d2g)(x[..., 0]).reshape(x.shape[:2] + (1,)), x[..., 1:]], axis=2)
for x in [traindata, validdata, testdata, memdata]]
print traindata.shape, testdata.shape
#embed()
numwords = max(worddic.values()) + 1 # don't use this, use glove
numchars = max(chardic.values()) + 1
numrels = max(entdic.values()) + 1
if bidir:
encinnerdim = [innerdim / 2] * layers
else:
encinnerdim = [innerdim] * layers
wordemb = WordEncoderPlusGlove(numchars=numchars,
encdim=encdim,
embdim=embdim,
maskid=-1,
embtrainfrac=embtrainfrac)
rnn, lastdim = SimpleSeq2Vec.makernu(embdim + encdim,
encinnerdim,
bidir=bidir)
enc = Seq2Vec(wordemb, rnn, maskid=-1)
if mem:
memembdim = embdim
memencdim = encdim
if membidir:
innerdim = [innerdim / 2] * memlayers
else:
innerdim = [innerdim] * memlayers
if not sharedwordenc:
memwordemb = WordEncoderPlusGlove(numchars=numchars,
encdim=encdim,
embdim=embdim,
maskid=-1,
embtrainfrac=embtrainfrac)
else:
memwordemb = wordemb
memrnn, memlastdim = SimpleSeq2Vec.makernu(memembdim + memencdim,
innerdim,
bidir=membidir)
memenc = Seq2Vec(memwordemb, memrnn, maskid=-1)
if memaddr is None or memaddr == "dot":
memaddr = DotMemAddr
elif memaddr == "lin":
memaddr = LinearGateMemAddr
dec = MemVec2Idx(memenc,
memdata,
memdim=innerdim,
memaddr=memaddr,
memattdim=memattdim)
else:
dec = SimpleVec2Idx(indim=innerdim, outdim=numrels)
m = Seq2Idx(enc, dec)
m = m.train([traindata], traingold).adagrad(lr=lr).l2(wreg).grad_total_norm(1.0).cross_entropy()\
.validate_on([validdata], validgold).accuracy().cross_entropy().takebest()\
.train(numbats=numbats, epochs=epochs)
pred = m.predict(testdata)
print pred.shape
evalres = evaluate(np.argmax(pred, axis=1), testgold)
print str(evalres) + "%"
def run(
epochs=10,
numbats=100,
numsam=10000,
lr=0.1,
datap="../../../data/simplequestions/datamat.wordchar.pkl",
embdim=50,
encdim=50,
innerdim=200,
wreg=0.00005,
bidir=False,
keepmincount=5,
sameenc=False,
memaddr="dot",
memattdim=100,
layers=1,
embtrainfrac=0.0,
mem=False,
membidir=False,
memlayers=1,
sharedwordenc=False
):
""" Memory match-based glove-based word-level relation classification """
(traindata, traingold), (validdata, validgold), (testdata, testgold), worddic, chardic, entdic\
= readdata(datap)
# get words from relation names, update word dic
memdata = getmemdata(entdic, worddic, chardic)
# get glove and transform word mats to glove index space
d2g, newdic, glove = getdic2glove(worddic, dim=embdim, trainfrac=embtrainfrac)
traindata, validdata, testdata, memdata = \
[np.concatenate([np.vectorize(d2g)(x[..., 0]).reshape(x.shape[:2] + (1,)), x[..., 1:]], axis=2)
for x in [traindata, validdata, testdata, memdata]]
print traindata.shape, testdata.shape
#embed()
numwords = max(worddic.values()) + 1 # don't use this, use glove
numchars = max(chardic.values()) + 1
numrels = max(entdic.values()) + 1
if bidir:
encinnerdim = [innerdim/2]*layers
else:
encinnerdim = [innerdim]*layers
wordemb = WordEncoderPlusGlove(numchars=numchars, encdim=encdim, embdim=embdim, maskid=-1, embtrainfrac=embtrainfrac)
rnn, lastdim = SimpleSeq2Vec.makernu(embdim+encdim, encinnerdim, bidir=bidir)
enc = Seq2Vec(wordemb, rnn, maskid=-1)
if mem:
memembdim = embdim
memencdim = encdim
if membidir:
innerdim = [innerdim/2]*memlayers
else:
innerdim = [innerdim]*memlayers
if not sharedwordenc:
memwordemb = WordEncoderPlusGlove(numchars=numchars, encdim=encdim, embdim=embdim, maskid=-1,
embtrainfrac=embtrainfrac)
else:
memwordemb = wordemb
memrnn, memlastdim = SimpleSeq2Vec.makernu(memembdim+memencdim, innerdim, bidir=membidir)
memenc = Seq2Vec(memwordemb, memrnn, maskid=-1)
if memaddr is None or memaddr == "dot":
memaddr = DotMemAddr
elif memaddr == "lin":
memaddr = LinearGateMemAddr
dec = MemVec2Idx(memenc, memdata, memdim=innerdim, memaddr=memaddr, memattdim=memattdim)
else:
dec = SimpleVec2Idx(indim=innerdim, outdim=numrels)
m = Seq2Idx(enc, dec)
m = m.train([traindata], traingold).adagrad(lr=lr).l2(wreg).grad_total_norm(1.0).cross_entropy()\
.validate_on([validdata], validgold).accuracy().cross_entropy().takebest()\
.train(numbats=numbats, epochs=epochs)
pred = m.predict(testdata)
print pred.shape
evalres = evaluate(np.argmax(pred, axis=1), testgold)
print str(evalres) + "%"
