def LModel(eta,batchsize,dSize,relSize, updatewords):
trainSize = [50]
acti = ['relu','tanh']
evaT = ['sum','max','cause']
layersize =dSize
params.frac = 1.0
params.outfile = 'Model_FA'+'_eta_'+str(eta)+'_dSize_'+ str(dSize) + '_batchsize_'+ str(batchsize) + '_relSize_'+ str(relSize) + '_trainSize_'+str(trainSize[0]) + '_updatewords_' + str(updatewords)
#params.dataf = '../data/conceptnet/AddModelData/omcs_train_new'+str(trainSize[0])+'.txt'
#params.dataf = '../data/conceptnet/AddModelData/causes_omcs.txt'
params.dataf = '../data/conceptnet/AddModelData/new_omcs100.txt'
params.batchsize = batchsize
params.hiddensize = 25
params.type = "MAX"
params.save = True
params.constraints = False
params.embedsize = dSize
params.relsize = relSize
params.activation = acti[0]
params.evaType = evaT[0]
params.usepeep = True
params.LC = 0.00001
params.Lw = 0.01
params.eta = eta
params.margin = 1
params.save= True
(words, We) = getWordmap('../data/conceptnet/embeddings/embeddings.skip.newtask.en.d'+str(dSize)+'.m1.w5.s0.it20.txt')
#print We.shape
rel = getRelation('../data/conceptnet/rel.txt')
params.outfile = "../models/"+params.outfile+"_"+str(params.LC)+"_"+str(params.Lw)+".txt"
#examples are shuffled data
examples = getData(params.dataf)
params.data = examples[0:int(params.frac*len(examples))]
#print "Using Training Data"+params.dataf
#print "Using Word Embeddings with Dimension "+str(dSize[0])
#print "Training on "+str(len(params.data))
#print "Saving models to: "+params.outfile
Rel_init = np.zeros((35,params.relsize,params.relsize))
for k in range(35):
for i in range(params.relsize):
for j in range(params.relsize):
if(i==j):
Rel_init[k][i][j] = 1+random.uniform(-0.2,0.2)
else:
Rel_init[k][i][j] = random.uniform(-0.2,0.2)
tm = theano_word_model(We, words, layersize, params.embedsize, rel, params.relsize, Rel_init, params.LC, params.Lw, params.eta, params.margin, params.usepeep, updatewords)
tm.train( params.data, params)
params.outfile = 'Bilinear_Hinge' + 'trainSize100dSize' + str(
sys.argv[1]) + 'relSize' + str(sys.argv[2]) + 'acti' + str(sys.argv[3])
params.dataf = '../commonsendata/Training/new_omcs100.txt'
#if you want to save the model, just change this to 'True'
params.save = False
params.constraints = False
params.activation = 'tanh'
params.evaType = 'cause'
params.usepeep = True
params.margin = 1
# (words, We) = getWordmap('../commonsendata/embeddings/tuples/embeddings.skip.newtask.en.d'+str(sys.argv[1])+'.m1.w5.s0.it20.txt')
# print We.shape
# if downloading data from http://ttic.uchicago.edu/~kgimpel/commonsense.html
(words, We) = getWordmap('../commonsendata/embeddings/embeddings.txt')
rel = getRelation('../commonsendata/Training/rel.txt')
params.outfile = "../models/" + params.outfile + "." + str(
params.lam) + "." + str(
params.batchsize
) + "." + params.type + "." + params.activation + "." + str(
params.frac) + ".txt"
#Examples are shuffled data
examples = getData(params.dataf)
params.data = examples[0:int(params.frac * len(examples))]
print "Using Training Data" + params.dataf
print "Using Word Embeddings with Dimension " + str(sys.argv[1])
print "Training on " + str(len(params.data)) + " examples using lambda=" + str(
binaryScore = []
Exp_S_sorted = sorted(Exp_S)
for j in xrange(len(Exp_S)):
temp_thr = Exp_S_sorted[j]
for j1 in xrange(int(len(Exp_S) / 2)):
if (Exp_S[j1] >= temp_thr):
right = right + 1
else:
wrong = wrong + 1
for j2 in xrange(int(len(Exp_S) / 2), int(len(Exp_S)), 1):
if (Exp_S[j2] <= temp_thr):
right = right + 1
else:
wrong = wrong + 1
if ((right / (len(Exp_S))) > accurancy):
accurancy = (1.0 * right / (len(Exp_S)))
threshold = temp_thr
right = 0
wrong = 0
#print 'Dev1-Accurancy',accurancy
return threshold, accurancy
if __name__ == "__main__":
(words, We) = getWordmap('../data/conceptnet/embeddings.txt')
tm = theano_word_model(We)
rel = getRelation('../data/conceptnet/rel.txt')
Rel = tm.getRel()
evaluate_adagrad(We, words, Rel, rel)