def main():
###########################
#### create dictionary ####
###########################
if os.path.exists('./data/corpus/dictionary.dict'):
if args.lang == 'ja':
corpus = ProposalConvCorpus(file_path=None,
batch_size=batchsize,
size_filter=True)
else:
corpus = ConvCorpus(file_path=None,
batch_size=batchsize,
size_filter=True)
corpus.load(load_dir='./data/corpus/')
else:
if args.lang == 'ja':
corpus = ProposalConvCorpus(file_path=data_file,
batch_size=batchsize,
size_filter=True)
else:
corpus = ConvCorpus(file_path=data_file,
batch_size=batchsize,
size_filter=True)
corpus.save(save_dir='./data/corpus/')
print('Vocabulary Size (number of words) :', len(corpus.dic.token2id))
print('Emotion size: ', len(corpus.emotion_set))
# search word_threshold (general - emotional)
ma = 0
mi = 999999
for word in corpus.emotion_set:
wid = corpus.dic.token2id[word]
if wid > ma:
ma = wid
if wid < mi:
mi = wid
# print(corpus.dic.token2id['<start>'], corpus.dic.token2id['<eos>'], corpus.dic.token2id['happy'], mi, ma)
word_threshold = mi
######################
#### create model ####
######################
model = Seq2Seq(all_vocab_size=len(corpus.dic.token2id),
emotion_vocab_size=len(corpus.emotion_set),
feature_num=feature_num,
hidden_num=hidden_num,
batch_size=batchsize,
label_num=label_num,
label_embed_num=label_embed,
gpu_flg=args.gpu)
if args.gpu >= 0:
model.to_gpu()
optimizer = optimizers.Adam(alpha=0.001)
optimizer.setup(model)
optimizer.add_hook(chainer.optimizer.WeightDecay(0.0001))
##########################
#### create ID corpus ####
##########################
input_mat = []
output_mat = []
input_mat_rev = []
label_mat = []
max_input_ren = max_output_ren = 0
print('start making corpus matrix...')
for input_text, output_text in zip(corpus.rough_posts, corpus.rough_cmnts):
# reverse an input and add eos tag
output_text.append(corpus.dic.token2id["<eos>"]) # 出力の最後にeosを挿入
# update max sentence length
max_input_ren = max(max_input_ren, len(input_text))
max_output_ren = max(max_output_ren, len(output_text))
# make a list of lists
input_mat.append(input_text)
output_mat.append(output_text)
# make label lists TODO: 3値分類
n_num = p_num = 0
for word in output_text:
if corpus.dic[word] in corpus.neg_words:
n_num += 1
if corpus.dic[word] in corpus.pos_words:
p_num += 1
if (n_num + p_num) == 0:
label_mat.append([1 for _ in range(len(output_text))])
elif n_num <= p_num:
label_mat.append([2 for _ in range(len(output_text))])
elif n_num > p_num:
label_mat.append([0 for _ in range(len(output_text))])
else:
raise ValueError
# make reverse corpus
for input_text in input_mat:
input_mat_rev.append(input_text[::-1])
# padding (inputの文頭・outputの文末にパディングを挿入する)
print('start labeling...')
for li in input_mat:
insert_num = max_input_ren - len(li)
for _ in range(insert_num):
li.append(corpus.dic.token2id['<pad>'])
for li in output_mat:
insert_num = max_output_ren - len(li)
for _ in range(insert_num):
li.append(corpus.dic.token2id['<pad>'])
for li in input_mat_rev:
insert_num = max_input_ren - len(li)
for _ in range(insert_num):
li.insert(0, corpus.dic.token2id['<pad>'])
for li in label_mat:
insert_num = max_output_ren - len(li)
for _ in range(insert_num):
li.append(corpus.dic.token2id['<pad>'])
if len(output_mat) != len(label_mat):
print('Output matrix and label matrix should have the same dimension.')
raise ValueError
# create batch matrix
print('transpose...')
input_mat = np.array(input_mat, dtype=np.int32).T
input_mat_rev = np.array(input_mat_rev, dtype=np.int32).T
output_mat = np.array(output_mat, dtype=np.int32).T
label_mat = np.array(label_mat, dtype=np.int32).T
# separate corpus into Train and Test TODO:実験時はテストデータとトレーニングデータに分離する
print('split train and test...')
train_input_mat = input_mat
train_output_mat = output_mat
train_input_mat_rev = input_mat_rev
train_label_mat = label_mat
#############################
#### train seq2seq model ####
#############################
accum_loss = 0
train_loss_data = []
print('start training...')
for num, epoch in enumerate(range(n_epoch)):
total_loss = 0
batch_num = 0
perm = np.random.permutation(len(corpus.rough_posts))
# for training
for i in range(0, len(corpus.rough_posts), batchsize):
# select batch data
input_batch = remove_extra_padding(
train_input_mat[:, perm[i:i + batchsize]], reverse_flg=False)
input_batch_rev = remove_extra_padding(
train_input_mat_rev[:, perm[i:i + batchsize]],
reverse_flg=True)
output_batch = remove_extra_padding(
train_output_mat[:, perm[i:i + batchsize]], reverse_flg=False)
label_batch = remove_extra_padding(
train_label_mat[:, perm[i:i + batchsize]], reverse_flg=False)
# Encode a sentence
model.initialize(
batch_size=input_batch.shape[1]) # initialize cell
model.encode(input_batch, input_batch_rev,
train=True) # encode (output: hidden Variable)
# Decode from encoded context
input_ids = xp.array(
[corpus.dic.token2id["<start>"] for _ in range(batchsize)])
for w_ids, l_ids in zip(output_batch, label_batch):
loss, predict_mat = model.decode(input_ids,
w_ids,
label_id=l_ids,
word_th=word_threshold,
train=True)
input_ids = w_ids
accum_loss += loss
# learn model
model.cleargrads() # initialize all grad to zero
accum_loss.backward() # back propagation
optimizer.update()
total_loss += float(accum_loss.data)
batch_num += 1
print('Epoch: ', num, 'Batch_num', batch_num,
'batch loss: {:.2f}'.format(float(accum_loss.data)))
accum_loss = 0
train_loss_data.append(float(total_loss / batch_num))
# save model and optimizer
print('-----', epoch + 1, ' times -----')
print('save the model and optimizer')
serializers.save_hdf5('data/' + str(epoch) + '.model', model)
serializers.save_hdf5('data/' + str(epoch) + '.state', optimizer)
# save loss data
with open('./data/loss_train_data.pkl', 'wb') as f:
pickle.dump(train_loss_data, f)
def check_corpus():
"""
考察の章で使用するコーパス情報を取得する関数．
ポジティブ文，ネガティブ文，ニュートラル文の個数を数える．
:return:
"""
from proposal_util import ProposalConvCorpus
DATA_DIR = './proposal_model/data/corpus/'
# call dictionary class
corpus = ProposalConvCorpus(file_path=None)
corpus.load(load_dir=DATA_DIR)
print('Vocabulary Size (number of words) :', len(corpus.dic.token2id))
print('')
# check data
emotion_freq = {
'baseball': {
'pos': 0,
'neg': 0,
'neu': 0
},
'pokemongo': {
'pos': 0,
'neg': 0,
'neu': 0
}
}
for num, input_sentence in enumerate(corpus.fine_posts):
n_num = p_num = 0
topic_label = ''
for index, w_id in enumerate(corpus.fine_cmnts[num]):
# comment の最初にトピックラベルが付いているものとする
if index == 0:
if w_id == corpus.dic.token2id['__label__0']:
topic_label = 'baseball'
elif w_id == corpus.dic.token2id['__label__1']:
topic_label = 'pokemongo'
else:
print('no label error: ', w_id)
raise ValueError
# pos or neg word の判定
else:
if corpus.dic[w_id] in corpus.neg_words:
n_num += 1
if corpus.dic[w_id] in corpus.pos_words:
p_num += 1
if (n_num + p_num) == 0:
emotion_freq[topic_label]['neu'] += 1
elif n_num <= p_num:
emotion_freq[topic_label]['pos'] += 1
elif n_num > p_num:
emotion_freq[topic_label]['neg'] += 1
else:
raise ValueError
if num % 10000 == 0:
print(num, 'end...')
print(emotion_freq)
for topic in emotion_freq:
text = 0
for tag in emotion_freq[topic]:
text += emotion_freq[topic][tag]
print(topic, ':', text)
emotion_freq = {'pos': 0, 'neg': 0, 'neu': 0}
for num, input_sentence in enumerate(corpus.rough_posts):
n_num = p_num = 0
for index, w_id in enumerate(corpus.rough_cmnts[num]):
if corpus.dic[w_id] in corpus.neg_words:
n_num += 1
if corpus.dic[w_id] in corpus.pos_words:
p_num += 1
if (n_num + p_num) == 0:
emotion_freq['neu'] += 1
elif n_num <= p_num:
emotion_freq['pos'] += 1
elif n_num > p_num:
emotion_freq['neg'] += 1
else:
raise ValueError
if num % 100000 == 0:
print(num, 'end...')
print(emotion_freq)
text = 0
for tag in emotion_freq:
text += emotion_freq[tag]
print('fine texts: ', text)