targetTypesFile=config['typefile']
vectorFile=config['ent_vectors']
learning_rate = float(config['lrate'])
batch_size = 1#int(config['batchsize'])
n_epochs = int(config['nepochs'])
num_neg = int(config['numneg'])
testfile=sys.argv[2]
outf=sys.argv[3]
use_tanh_out = False
outputtype = config['outtype'] #hinge or softmax
usetypecosine = False
if 'typecosine' in config:
usetypecosine = utils.str_to_bool(config['typecosine'])
(t2ind, n_targets, wordvectors, vectorsize, typefreq_traindev) = utils.loadTypesAndVectors(targetTypesFile, vectorFile)
(rvt, input_matrix_test, iet,resvectstnall, ntrn) = utils.fillOnlyEntityData(testfile,vectorsize, wordvectors, t2ind, n_targets, upto=-1, ds='test', binoutvec=True)
# train network
rng = numpy.random.RandomState(23455)
if usetypecosine:
print 'using cosine(e,t) as another input feature'
typevecmatrix = utils.buildtypevecmatrix(t2ind, wordvectors, vectorsize) # a matrix with size: 102 * dim
e2simmatrix_test = utils.buildcosinematrix(input_matrix_test, typevecmatrix)
input_matrix_test = utils.extend_in_matrix(input_matrix_test, e2simmatrix_test)
dt = theano.config.floatX # @UndefinedVariable
index = T.lscalar() # index to a [mini]batch
x = T.matrix('x') # the data is presented as rasterized images
y = T.imatrix('y') # the labels are presented as 1D vector of
l_weight = float(config['loss_weight'])
use_tanh_out = False
if 'tanh' in config:
use_tanh_out = True
outputtype = config['outtype'] #hinge or softmax
leftsize = int(config['left'])
rightsize = int(config['right'])
sum_window = int(config['sumwindow'])
max_window = int(config['maxwindow'])
slotposition = max_window / 2
label_type = config['target'] #nt or ct
(typeIndMap, n_targets, wordvecs, vectorsize, typefreq_traindev) = utils.loadTypesAndVectors(targetTypesFile, vectorFile, -1)
logger.info('word2vec vectors are loaded')
(testcontexts,resultVectorTest, resultVectorTestAll) = utils.read_lines_data(testsetfile, typeIndMap, max_window, label_type, -1)
logger.info("number of test examples: %d", len(testcontexts))
inputMatrixTest = utils.adeltheanomatrix_flexible(slotposition, vectorsize, testcontexts, wordvecs, leftsize, rightsize, sum_window, useSum)
contextsize = leftsize + rightsize + 1
################# for memory ############
testcontexts = []; wordvecs = [];
##################### the network #######################
test_set_x = theano.shared(numpy.matrix(inputMatrixTest, dtype=theano.config.floatX)) # @UndefinedVariable
test_set_y = theano.shared(numpy.matrix(resultVectorTestAll, dtype=numpy.dtype(numpy.int32)))
rng = numpy.random.RandomState(23455)
n_test_batches = test_set_x.get_value(borrow=True).shape[0]
use_tanh_out = False
if 'tanh' in config:
use_tanh_out = True
outputtype = config['outtype'] #hinge or softmax
leftsize = int(config['left'])
rightsize = int(config['right'])
sum_window = int(config['sumwindow'])
label_type = config['target'] #nt or ct
max_window = int(config['maxwindow'])
slotposition = max_window / 2
logger.info('slotpostion is %d', slotposition)
(typeIndMap, n_targets, wordvecs, vectorsize,
typefreq_traindev) = utils.loadTypesAndVectors(targetTypesFile, vectorFile)
(traincontexts, resultVectorTrain,
resultVectorTrainAll) = utils.read_lines_data(trainfile, typeIndMap,
max_window, label_type, -1)
logger.info("number of training examples: %d", len(traincontexts))
inputMatrixTrain = utils.adeltheanomatrix_flexible(slotposition, vectorsize,
traincontexts, wordvecs,
leftsize, rightsize,
sum_window, useSum)
(contextlistDev, resultVectorDev,
resultVectorDevAll) = utils.read_lines_data(devfile, typeIndMap, max_window,
label_type, -1)
logger.info("number of validation examples: %d", len(contextlistDev))
l_reg = ''
l_weight = 0.000001
if 'loss_reg' in config:
l_reg = config['loss_reg']
l_weight = float(config['loss_weight'])
use_tanh_out = False
if 'tanh' in config:
use_tanh_out = True
outputtype = config['outtype'] #hinge or softmax
usetypecosine = False
if 'typecosine' in config:
usetypecosine = utils.str_to_bool(config['typecosine'])
upto = -1
(t2ind, n_targets, wordvectors, vectorsize, typefreq_traindev) = utils.loadTypesAndVectors(targetTypesFile, vectorFile, upto=upto)
(rvt, input_matrix_train, iet,resvectrnall, ntrn) = utils.fillOnlyEntityData(trainfile,vectorsize, wordvectors, t2ind, n_targets, upto=upto, binoutvec=True)
print "number of training examples:" + str(len(iet))
(rvd, input_matrix_dev, ied,resvecdevall, ntdev) = utils.fillOnlyEntityData(devfile,vectorsize, wordvectors, t2ind, n_targets, upto=upto, binoutvec=True)
print "number of validation examples:" + str(len(ied))
if usetypecosine:
print 'using cosine(e,t) as another input feature'
typevecmatrix = utils.buildtypevecmatrix(t2ind, wordvectors, vectorsize) # a matrix with size: 102 * dim
e2simmatrix_train = utils.buildcosinematrix(input_matrix_train, typevecmatrix)
e2simmatrix_dev = utils.buildcosinematrix(input_matrix_dev, typevecmatrix)
input_matrix_train = utils.extend_in_matrix(input_matrix_train, e2simmatrix_train)
input_matrix_dev = utils.extend_in_matrix(input_matrix_dev, e2simmatrix_dev)
