def train(maxlen=100, embedding_dim=128): # 主训练/测试代码
start = time.time()
l_trainX, r_trainX, ret_labels, l_topredictX, r_topredictX = do.load_data_bi_word2vec(maxlen=maxlen,
words_keep=50000,
validation_portion=0.,
embedding_dim=embedding_dim,
ma="A")
trainY = to_categorical(ret_labels, nb_classes=3)
del ret_labels
lnet = tflearn.input_data([None, maxlen, embedding_dim])
rnet = tflearn.input_data([None, maxlen, embedding_dim])
lnet = tflearn.gru(lnet, embedding_dim, dropout=0.8, return_seq=False, dynamic=True)
rnet = tflearn.gru(rnet, embedding_dim, dropout=0.8, return_seq=False, dynamic=True)
net = tflearn.layers.merge_outputs([lnet, rnet])
net = tflearn.fully_connected(net, 3, activation='softmax')
net = tflearn.regression(net, optimizer='adam', learning_rate=0.001,
loss='categorical_crossentropy')
# Training
model = tflearn.DNN(net, tensorboard_verbose=0)
model.fit([l_trainX, r_trainX], trainY, validation_set=0.1, show_metric=True,
batch_size=32)
model.save('MODELS/E_W2V_GRU_TC{}_{}.dy'.format(embedding_dim, maxlen))
# model.load('MODELS/E_W2V_GRU_TC{}_{}.dy'.format(embedding_dim, maxlen))
del l_trainX
del r_trainX
del trainY
idx2cla = {0: 'neu', 1: 'pos', 2: 'neg'}
filename = "Result/result_{}.csv".format(datetime.datetime.now().strftime("%Y%m%d%H%M"))
prefix = list(open('Result/A_AFTER_NRP_200', 'r').readlines())
f = open(filename, 'w')
f.write('SentenceId,View,Opinion\n')
a = [0, 5000, 10000, 15000, 20000, 25000, 30000, 35000, 40000, 45000, 50000, 55000]
b = [5000, 10000, 15000, 20000, 25000, 30000, 35000, 40000, 45000, 50000, 55000, 65000]
ANS = []
for i in range(12):
ans = model.predict([l_topredictX[a[i]:b[i]], r_topredictX[a[i]:b[i]]])
ANS.extend([s for s in ans])
print("ANS.LENGTH: {}".format(len(ans)))
for i, r in enumerate(ANS):
f.write(prefix[i].strip())
idx = int(np.argmax(r))
f.write(idx2cla[idx])
k = ""
for l in r:
k += ',{:.4f}'.format(l)
f.write(k)
f.write('\n')
f.close()
end = time.time()
print("TIME COST: {}".format(end-start))
outf = vote_by_score(filename)
add(outf)
