import tensorflow as tf
import numpy as np
import tool as tool
import time
# data loading
data_path = './newscorpus.csv'
title, contents = tool.loading_data(data_path, eng=False, num=False, punc=False)
test_title, test_content = tool.loading_data("sample.csv", eng=False, num=False, punc=False)
for i in range(len(test_title)):
test_title[i] = ""
word_to_ix, ix_to_word = tool.make_dict_all_cut(title + contents + test_content, minlength=0, maxlength=3,
jamo_delete=True)
# parameters
multi = True
forward_only = False
hidden_size = 300
vocab_size = len(ix_to_word)
num_layers = 3
learning_rate = 0.001
batch_size = 16
encoder_size = 100
decoder_size = tool.check_doclength(title, sep=True) # (Maximum) number of time steps in this batch
steps_per_checkpoint = 20
# transform data
encoderinputs, decoderinputs, targets_, targetweights = \
tool.make_inputs(contents, title, word_to_ix,
encoder_size=encoder_size, decoder_size=decoder_size, shuffle=False)
test_encoderinputs, test_decoderinputs, test_targets_, test_targetweights = \
import tensorflow as tf
import numpy as np
import tool as tool
import time
# data loading
data_path = 'C:/newscorpus.csv'
title, contents = tool.loading_data(data_path, eng=False, num=False, punc=False)
word_to_ix, ix_to_word = tool.make_dict_all_cut(title+contents, minlength=0, maxlength=3, jamo_delete=True)
# parameters
multi = True
forward_only = False
hidden_size = 300
vocab_size = len(ix_to_word)
num_layers = 3
learning_rate = 0.001
batch_size = 16
encoder_size = 100
decoder_size = tool.check_doclength(title,sep=True) # (Maximum) number of time steps in this batch
steps_per_checkpoint = 10
# transform data
encoderinputs, decoderinputs, targets_, targetweights = \
tool.make_inputs(contents, title, word_to_ix,
encoder_size=encoder_size, decoder_size=decoder_size, shuffle=False)
class seq2seq(object):
def __init__(self, multi, hidden_size, num_layers, forward_only,
learning_rate, batch_size,