if __name__ == '__main__':
modelpath = ''
#### .pkl file ##########
parameter_path = ''
#### .para file #############
parameterlist = cPickle.load(open(parameter_path, 'rb'))
traindatapath = './data'
print 'loading dataset.. ',
if not os.path.isfile(traindatapath + '/test.p'):
import dataset
dataset.data2pickle(traindatapath + '/test_filtered.data',
traindatapath + '/test.p')
if not os.path.isfile(traindatapath + '/train.p'):
import dataset
dataset.data2pickle(traindatapath + '/train_filtered.data',
traindatapath + '/train.p')
testData = cPickle.load(open(traindatapath + '/test.p'))
trainData = cPickle.load(open(traindatapath + '/train.p'))
# testData = testData[1:5]
# trainData = trainData[1:15]
tmp = traindatapath.split('_')
test = data2cv.make_idx_data_cv(testData, parameterlist['filter_size'],
int(parameterlist['max_sentence_word']))
train = data2cv.make_idx_data_cv(trainData, parameterlist['filter_size'],
int(parameterlist['max_sentence_word']))
modelpath = runpath + 'PCNN_C2SA.pkl'
traindatapath = './data'
print 'model save in: ', modelpath
# save_log = modelpath + '1.pkl\n'
# log_file = open(log_path, 'a')
# log_file.write(save_log)
# log_file.close()
print 'loading dataset.. '
if not os.path.isfile(traindatapath + '/test_57w.p'):
import dataset
dataset.data2pickle(traindatapath + '/test_data.txt',
traindatapath + '/test_57w.p')
if not os.path.isfile(traindatapath + '/train_57w.p'):
import dataset
dataset.data2pickle(traindatapath + '/train_data.txt',
traindatapath + '/train_57w.p')
if not os.path.isfile(traindatapath + '/wv.p'):
import dataset
dataset.wv2pickle('./data/wv.txt', 50, './data/wv.p')
testData = cPickle.load(open(traindatapath + '/test_57w.p'))
trainData = cPickle.load(open(traindatapath + '/train_57w.p'))
# testData = testData[1:5]
# trainData = trainData[1:15]
tmp = traindatapath.split('_')
if not os.path.isfile(inputdir+'/'+str(dimension)+'/Wv.p'):
import dataset
dataset.wv2pickle(inputdir+'/'+str(dimension)+'/wv.txt', dimension, inputdir+'/'+str(dimension)+'/Wv.p')
resultdir = './e_'+str(epochs)+'_s_'+str(static)+'_u_'+\
hidden_units_str+'_b_'+str(batch_size)+'_w_'+\
str(window_size)+'_c_'+conv_non_linear+'_d_'+\
str(dimension)+'_i_'+inputdir+'_n_'+str(norm)+'/'
print 'result dir='+resultdir
if not os.path.exists(resultdir):
os.mkdir(resultdir)
if not os.path.isfile(inputdir+'/test.p'):
import dataset
dataset.data2pickle(inputdir+'/test_filtered.data', inputdir+'/test.p')
if not os.path.isfile(inputdir+'/train.p'):
import dataset
dataset.data2pickle(inputdir+'/train_filtered.data', inputdir+'/train.p')
testData = cPickle.load(open(inputdir+'/test.p'))
trainData = cPickle.load(open(inputdir+'/train.p'))
# testData = testData[1:5]
# trainData = trainData[1:15]
tmp = inputdir.split('_')
test = data2cv.make_idx_data_cv(testData, window_size, int(tmp[3]))
train = data2cv.make_idx_data_cv(trainData, window_size, int(tmp[3]))
print 'load Wv ...'
Wv = cPickle.load(open(inputdir+'/'+str(dimension)+'/Wv.p'))