def load_benchmark(data, vocab, extend_with=0):
# Decode data
try:
texts = [x for x in data['text']]
except UnicodeDecodeError:
texts = [x for x in data['text']]
# Extract labels
labels = [x for x in data['sent']]
batch_size, maxlen = calculate_batchsize_maxlen(texts)
st = SentenceTokenizer(vocab, maxlen)
# Split up dataset. Extend the existing vocabulary with up to extend_with
# tokens from the training dataset.
texts, labels, added = st.split_train_val_test(texts,
labels,
extend_with=extend_with)
return {
'texts': texts,
'labels': labels,
'added': added,
'batch_size': batch_size,
'maxlen': maxlen
}
def load_benchmark(path, vocab, extend_with=0):
""" Loads the given benchmark dataset.
Tokenizes the texts using the provided vocabulary, extending it with
words from the training dataset if extend_with > 0. Splits them into
three lists: training, validation and testing (in that order).
Also calculates the maximum length of the texts and the
suggested batch_size.
# Arguments:
path: Path to the dataset to be loaded.
vocab: Vocabulary to be used for tokenizing texts.
extend_with: If > 0, the vocabulary will be extended with up to
extend_with tokens from the training set before tokenizing.
# Returns:
A dictionary with the following fields:
texts: List of three lists, containing tokenized inputs for
training, validation and testing (in that order).
labels: List of three lists, containing labels for training,
validation and testing (in that order).
added: Number of tokens added to the vocabulary.
batch_size: Batch size.
maxlen: Maximum length of an input.
"""
# Pre-processing dataset
with open(path) as dataset:
data = pickle.load(dataset)
# Decode data
try:
texts = [unicode(x) for x in data['texts']]
except UnicodeDecodeError:
texts = [x.decode('utf-8') for x in data['texts']]
# Extract labels
labels = [x['label'] for x in data['info']]
batch_size, maxlen = calculate_batchsize_maxlen(texts)
st = SentenceTokenizer(vocab, maxlen)
# Split up dataset. Extend the existing vocabulary with up to extend_with
# tokens from the training dataset.
texts, labels, added = st.split_train_val_test(
texts,
labels, [data['train_ind'], data['val_ind'], data['test_ind']],
extend_with=extend_with)
return {
'texts': texts,
'labels': labels,
'added': added,
'batch_size': batch_size,
'maxlen': maxlen
}
def print_examples_sentences(filename: str = "example.txt",
output_filename: str = "output.txt"):
examples = read_examples(filename)
with open(output_filename, 'w') as f:
for example in examples:
sentences = SentenceTokenizer().tokenize(example)
for sentence in sentences:
f.write(sentence + "\n")
f.close()
def load_model_1():
# load the pre-trained Keras model (here we are using a model
# pre-trained on ImageNet and provided by Keras, but you can
# substitute in your own networks just as easily)
global model
#model = ResNet50(weights="imagenet")
"""
.h5 created externally and sent here. The attentionlayer from .py
"""
model = load_model(
'emoji.h5',
custom_objects={'AttentionWeightedAverage': AttentionWeightedAverage},
compile=True)
global st
with open("vocabulary.json", 'r') as f:
vocabulary = json.load(f)
st = SentenceTokenizer(vocabulary, 30)
from sentence_tokenizer import SentenceTokenizer
import json
import numpy as np
def top_elements(array, k):
ind = np.argpartition(array, -k)[-k:]
return ind[np.argsort(array[ind])][::-1]
maxlen = 50
batch_size = 32
vocabulary = json.load(open('servers/deepmoji/data/vocabulary.json', 'r'))
st = SentenceTokenizer(vocabulary, maxlen)
model = deepmoji_emojis(maxlen, 'servers/deepmoji/data/deepmoji_weights.hdf5')
#print('Ready')
while True:
sentence = input()
tokenized, _, _ = st.tokenize_sentences([sentence])
prob = model.predict(tokenized)[0]
scores = []
"""
t_token = tokenized[0]
t_score = [sentence]
t_prob = prob[0]
ind_top = top_elements(t_prob, 5)
t_score.append(sum(t_prob[ind_top]))
t_score.extend(ind_top)
# load data
data_pair = load_data(data_path)
# split 5 fold
data_5fold = prepare_5fold(data_pair)
# load vocabulary and label2index dict
with open(vocab_path, "r") as f_vocab:
vocabulary = json.load(f_vocab)
with open(label2index_path, "r") as f_label:
label2index = json.load(f_label)
index2label = {i: l for (l, i) in label2index.items()}
# sentence tokenizer (MAXLEN means the max length of input text)
st = SentenceTokenizer(vocabulary, MAX_LEN)
fold = 0
# 5 fold
for item in data_5fold:
# prepare training, validation, testing set
train_text = [p[0] for p in item[0]]
train_label = [p[1] for p in item[0]]
test_text = [p[0] for p in item[1]]
test_label = [p[1] for p in item[1]]
train_X, _, _ = st.tokenize_sentences(train_text)
test_X, _, _ = st.tokenize_sentences(test_text)
train_y = np.array([label2index[l] for l in train_label])
test_y = np.array([label2index[l] for l in test_label])
def load_benchmark(path, vocab, extend_with=0):
""" Loads the given benchmark dataset.
Tokenizes the texts using the provided vocabulary, extending it with
words from the training dataset if extend_with > 0. Splits them into
three lists: training, validation and testing (in that order).
Also calculates the maximum length of the texts and the
suggested batch_size.
# Arguments:
path: Path to the dataset to be loaded.
vocab: Vocabulary to be used for tokenizing texts.
extend_with: If > 0, the vocabulary will be extended with up to
extend_with tokens from the training set before tokenizing.
# Returns:
A dictionary with the following fields:
texts: List of three lists, containing tokenized inputs for
training, validation and testing (in that order).
labels: List of three lists, containing labels for training,
validation and testing (in that order).
added: Number of tokens added to the vocabulary.
batch_size: Batch size.
maxlen: Maximum length of an input.
"""
# Pre-processing dataset
f = open(path, 'r')
texts = []
labels = []
for line in f:
line = line.strip().split('\t')
if len(line) < 2:
continue
texts.append(line[0])
labels.append(int(line[1]))
# Decode data
# try:
# texts = [unicode(x) for x in data['texts']]
# except UnicodeDecodeError:
# texts = [x.decode('utf-8') for x in data['texts']]
# Extract labels
# labels = [x['label'] for x in data['info']]
print(texts[0:10])
print(labels[0:10])
batch_size, maxlen = calculate_batchsize_maxlen(texts)
st = SentenceTokenizer(vocab, maxlen)
# Split up dataset. Extend the existing vocabulary with up to extend_with
# tokens from the training dataset.
texts, labels, added = st.split_train_val_test(texts,
labels, [0.88, 0.1, 0.02],
extend_with=extend_with)
return {
'texts': texts,
'labels': labels,
'added': added,
'batch_size': batch_size,
'maxlen': maxlen
}
raw_dpath = os.path.join(os.getenv("OPIE_DIR"), "data/raw/domains")
domain_path = os.path.join(os.getenv("OPIE_DIR"), "data/domains", domain)
pickle_head = "/pickles/without_parse_sentences/without_parse_sentences_"
fname = domain + ".json.gz"
mkdir(domain_path)
spath = os.path.join(domain_path, "sentences")
if os.path.exists(spath):
shutil.rmtree(spath)
mkdir(os.path.join(domain_path, "sentences"))
mkdir(os.path.join(domain_path, "pickles"))
mkdir(os.path.join(domain_path, "pickles/without_parse_sentences"))
sentences, i, k, review_index = [], 0, 1, 1
kk = 1
f = open(domain_path + "/sentences/sentences_1.txt", "a", encoding="utf8")
flag = False
myTokenizer = SentenceTokenizer()
for e in parse(os.path.join(raw_dpath, fname)):
text, score = e['reviewText'], float(e['overall'])
# 去除所有的控制字符，防止parse出错
text = re.sub(r'[\x00-\x1f]', '', text)
sents = myTokenizer.segment_text(text)
for sent in sents:
t = Sentence()
t.set_text_score_review(sent, score, review_index)
if len(sent.split(' ')) > 50:
continue
sentences.append(t)
print(sent, file=f)
# 60000个句子序列化一次
if len(sentences) == 60000:
save_pickle_file(domain_path + pickle_head +
