def run():
# params
dims = 10
negrate = 1
batsize = 300
epochs = 300
#paths
datafileprefix = "../../data/nycfilms/"
dirfwdsuffix = "direct_forward.plustypes.ssd"
# get the data and split
dirfwdf = open(datafileprefix+dirfwdsuffix)
datadf = readdata(dirfwdf)
traind, validd, testd = datadf.split((70, 15, 15), random=True)
numents = int(datadf.ix[:, 0].max())+1
print numents
numrels = int(datadf.ix[:, 1].max())+1
print numrels
# define model
inp = Input(T.imatrix())
eemb = VectorEmbed.indim(numents).outdim(dims).Wreg(l2reg(0.00001))()
remb = VectorEmbed.indim(numrels).outdim(dims).Wreg(l2reg(0.00001))()
# for debugging
eembd = SymTensor(T.fmatrix())
rembd = SymTensor(T.fmatrix())
dotp = SymTensor(T.fmatrix())
out = ((inp[:, 0] >> eemb >> eembd) & (inp[:, 1] >> remb >> rembd)) >> DotProduct() >> dotp >> Tanh()
# for plotting purposes: relation to relation dot product (or relation-type)
r2rinp = Input(T.imatrix())
rel2rel = ((r2rinp[:, 0] >> remb) & (r2rinp[:, 1] >> remb)) >> DotProduct()
outtest = Output(T.fvector())
loss = (out & outtest) >> HingeLoss()
trainer = Trainer\
.batsize(batsize)\
.epochs(epochs)\
.onrun(getonrun())\
.offrun(offrun)\
.offepoch(getoffepoch(out, rel2rel))\
.onbatch(getonbatch(negrate, numents, numrels))\
.optimizer(sgd(lr=1.))\
.batchtransformer(transbat)
trainer\
.loss(loss)\
trainer.train(traind.values, validd.values)\
.test(testd.values)
explore(eemb, remb)
# functions for interactive exploration
embed()
def run():
dims = 20
negrate = 1
batsize = 100
epochs = 3000
path = "../../data/Family/SN-"
traind, valid, test = family.getdata(path)
lemb = VectorEmbed.indim(traind.numsubjs+2).outdim(dims).Wreg(l2reg(0.000001))()
remb = VectorEmbed.indim(traind.numsubjs+2).outdim(dims).Wreg(l2reg(0.000001))()
inp = Input(T.imatrix())
out = ((inp[:, 0] >> lemb) & (inp[:, 2] >> remb)) >> DotProduct() >> Sigmoid()
outtest = Output(T.fvector())
loss = (out & outtest) >> MSELoss()
trainer = Trainer\
.batsize(batsize)\
.epochs(epochs)\
.onrun(getonrun())\
.offrun(offrun)\
.offepoch(getoffepoch(out))\
.onbatch(getonbatch(negrate))\
.optimizer(sgd(lr=1.))\
.batchtransformer(transbat)
trainer\
.loss(loss)\
trainer.train(traind, valid)\
.test(test)
def run():
dims = 60
negrate = 1
batsize = 100
epochs = 800
path = "../../data/Family/SN-"
traind, valid, test = family.getdata(path)
semb = VectorEmbed.indim(traind.numsubjs+2).outdim(dims).Wreg(l2reg(0.000000001))()
oemb = VectorEmbed.indim(traind.numsubjs+2).outdim(dims).Wreg(l2reg(0.000000001))()
remb = MatrixEmbed.indim(traind.numrels).outdim(dims).idxoffset(traind.numsubjs+2).Wreg(l2reg(0.000000001))()
inp = Input(T.imatrix())
sembvec = (inp[:, 0] >> semb)
sremb = (inp[:, 1] & sembvec) >> remb
out = (sremb & (inp[:, 2] >> oemb)) >> DotProduct() >> Sigmoid()
print out(np.asarray([[1, 720, 6]], dtype="int32"))
outtest = Output(T.fvector())
loss = (out & outtest) >> MSELoss()
trainer = Trainer\
.batsize(batsize)\
.epochs(epochs)\
.onrun(getonrun())\
.offrun(offrun)\
.offepoch(getoffepoch(out))\
.onbatch(getonbatch(negrate))\
.optimizer(sgd(lr=1.))\
.batchtransformer(transbat)
trainer\
.loss(loss)\
trainer.train(traind, valid)\
.test(test)
def run():
# params
dims = 10
negrate = 1
batsize = 300
epochs = 300
lr = 0.3
wreg = 0.000001
#paths
datafileprefix = "../../data/nycfilms/"
dirfwdsuffix = "direct_both.ssd"
# get the data and split
dirfwdf = open(datafileprefix+dirfwdsuffix)
datadf = readdata(dirfwdf)
traind, validd, testd = datadf.split((70, 15, 15), random=True)
numents = int(datadf.ix[:, 0].max())+1
numrels = int(datadf.ix[:, 1].max())+1
# test switcher
'''inp = Input(T.fmatrix())
outp = (inp[:, 0] & inp[:, 1]) >> Switcher(Sigmoid(), Ident())
res = outp(np.asarray([[-10, 0], [-10, 1]], dtype="float32"))
print res
print "tested switcher"'''
# define model
inp = Input(T.imatrix())
eemb = VectorEmbed.indim(numents).outdim(dims).Wreg(l2reg(wreg/10.))()
rembfwd = VectorEmbed.indim(numrels).outdim(dims).Wreg(l2reg(wreg))()
rembrev = VectorEmbed.indim(numrels).outdim(dims).Wreg(l2reg(wreg))()
remb = Switcher(rembfwd, rembrev)
# for debugging
eembd = SymTensor(T.fmatrix())
rembd = SymTensor(T.fmatrix())
dotp = SymTensor(T.fmatrix())
out = ((inp[:, 0] >> eemb >> eembd) & ((inp[:, 1] & inp[:, 2]) >> remb >> rembd)) \
>> DotProduct() >> dotp >> Tanh()
outtest = Output(T.fvector())
loss = (out & outtest) >> HingeLoss()
trainer = Trainer\
.batsize(batsize)\
.epochs(epochs)\
.onrun(getonrun())\
.offrun(offrun)\
.offepoch(getoffepoch(out))\
.onbatch(getonbatch(negrate, numents, numrels))\
.optimizer(sgd(lr=lr))\
.batchtransformer(transbat)
trainer\
.loss(loss)\
trainer.train(traind.values, validd.values)\
.test(testd.values)
explore(eemb, rembfwd, rembrev)
# functions for interactive exploration
embed()
def run():
# params
dims = 15
numbats = 1000
epochs = 20
wreg = 0.00000001
lr = 0.0001
#paths
datafileprefix = "../../data/nycfilms/"
dirfwdsuffix = "direct_both_typ.pd.pkl"
# get the data and split
srcdf = pickle.load(open(datafileprefix+dirfwdsuffix))
#datadf = readdata(srcdf)
def pairstomatrix(srcd):
datamatdf = pd.DataFrame.from_records(srcd["r"].apply(Counter)).fillna(value=0)
datamatdf["e"] = srcd["e"]
datamatdf.set_index("e", inplace=True)
return datamatdf
datamatdf = pairstomatrix(srcdf)
# build intermediate dics
imentdic = dict(zip(range(len(datamatdf.index.values)), datamatdf.index.values))
imreldic = dict(zip(range(len(datamatdf.columns)), datamatdf.columns))
revimentdic = {v: k for k, v in imentdic.items()}
revimreldic = {v: k for k, v in imreldic.items()}
numents = datamatdf.shape[0]
print numents
numrels = datamatdf.shape[1]
print numrels
# define model
inp = Input(T.imatrix())
eemb = VectorEmbed.indim(numents).outdim(dims).Wreg(l2reg(wreg))()
remb = VectorEmbed.indim(numrels).outdim(dims).Wreg(l2reg(wreg))()
# for debugging
eembd = SymTensor(T.fmatrix())
rembd = SymTensor(T.fmatrix())
out = ((inp[:, 0] >> eemb >> eembd) & (inp[:, 1] >> remb >> rembd)) >> DotProduct()
# for plotting purposes: relation to relation dot product (or relation-type)
r2rinp = Input(T.imatrix())
rel2rel = ((r2rinp[:, 0] >> remb) & (r2rinp[:, 1] >> remb)) >> DotProduct()
outtest = Output(T.fvector())
loss = (out & outtest) >> SSELoss()
sampler = SimpleRandomIdxBatcher(numbats=numbats)
trainer = Trainer\
.loss(loss)\
.batcher(sampler)\
.epochs(epochs)\
.optimizer(sgd(lr=lr))\
.onrun(getonrun())\
.offrun(offrun)\
.offepoch(getoffepoch(out, rel2rel))\
trainer.train(datamatdf.values)
explore(eemb, remb, lambda x: revimentdic[x], lambda x: revimreldic[x])
# functions for interactive exploration
embed()