def __init__(self):
self.data = []
self.dictionary = Dictionary()
self.max_sent_len = 0
# Read the positive reviews
with open(POSITIVE_REVIEWS_FILE, encoding='utf-8') as f:
positive_reviews = f.readlines()
for review in positive_reviews:
review = normalize_string(review)
review_words = word_tokenize(review)
self.dictionary.add_words(review_words)
self.data.append((review, 1))
self.max_sent_len = max(self.max_sent_len, 2 + len(review_words))
# Read the negative reviews
with open(NEGAGIVE_REVIEWS_FILE, encoding='utf-8') as f:
negative_reviews = f.readlines()
for review in negative_reviews:
review = normalize_string(review)
review_words = word_tokenize(review)
self.dictionary.add_words(review_words)
self.data.append((review, 0))
self.max_sent_len = max(self.max_sent_len, 2 + len(review_words))
# Split the original dataset into train/test
random.shuffle(self.data)
split_index = int(0.9 * len(self.data))
self.train = AugmentedList(self.data[:split_index])
self.test = AugmentedList(self.data[split_index:])
class ReviewDataset:
def __init__(self):
self.data = []
self.dictionary = Dictionary()
self.max_sent_len = 0
# Read the positive reviews
with open(POSITIVE_REVIEWS_FILE, encoding='utf-8') as f:
positive_reviews = f.readlines()
for review in positive_reviews:
review = normalize_string(review)
review_words = word_tokenize(review)
self.dictionary.add_words(review_words)
self.data.append((review, 1))
self.max_sent_len = max(self.max_sent_len, 2 + len(review_words))
# Read the negative reviews
with open(NEGAGIVE_REVIEWS_FILE, encoding='utf-8') as f:
negative_reviews = f.readlines()
for review in negative_reviews:
review = normalize_string(review)
review_words = word_tokenize(review)
self.dictionary.add_words(review_words)
self.data.append((review, 0))
self.max_sent_len = max(self.max_sent_len, 2 + len(review_words))
# Split the original dataset into train/test
random.shuffle(self.data)
split_index = int(0.9 * len(self.data))
self.train = AugmentedList(self.data[:split_index])
self.test = AugmentedList(self.data[split_index:])
def next_batch(self, batch_size, mode=TRAIN_MODE):
review_lengths, reviews, targets = [], [], []
data = self.train if mode == TRAIN_MODE else self.test
batch = data.next_items(batch_size)
for (review, target) in batch:
review_length = len(word_tokenize(normalize_string(review)))
review = indexes_from_sentence(review, self.dictionary,
self.max_sent_len)
target = one_hot_encoding(2, target)
reviews.append(review)
targets.append(target)
review_lengths.append(review_length)
return review_lengths, reviews, targets
def __init__(self,
video_path,
translation_path,
spatial_transform=None,
temporal_transform=None,
sample_duration=4,
get_loader=get_default_video_loader):
self.dictionary = Dictionary()
self.data = make_dataset(video_path, translation_path, sample_duration,
self.dictionary)
self.spatial_transform = spatial_transform
self.temporal_transform = temporal_transform
self.loader = get_loader()
def __init__(self, sql=None, mongo=None, **kwargs):
super(TweetTagger, self).__init__()
if not sql:
self._sql = SQLConnector(host=kwargs['host'],
port=kwargs['port'],
user=kwargs['user'],
passwd=kwargs['password'],
db=kwargs['db'])
else:
self._sql = sql
if not mongo:
self._mongo = MongoConnector(host=kwargs['H'], port=kwargs['mongoport'], db=kwargs['db'])
else:
self._mongo = mongo
self._keyword = None
self._bing = BingSearch()
self._binged = Dictionary()
def __init__(self, path, maxlen, vocab_size=11000, lowercase=False, dictionary=None):
self.dictionary = Dictionary()
self.maxlen = maxlen
if maxlen == -1:
self.maxlen = np.inf
self.lowercase = lowercase
self.vocab_size = vocab_size
self.train_path = path
self.text = []
self.hiddens = []
self.labels = []
# make the vocabulary from training set
if dictionary is None:
self.make_vocab()
else:
self.dictionary = dictionary
self.train = self.tokenize(self.train_path)
self.Item = namedtuple('Item', ['text', 'hidden', 'label'])
def tag_tweets(ngrams, tweet_id):
tweet = Dictionary()
tweet.add("tweet_db_id", tweet_id)
prev_is_software = False
for i in range(len(ngrams), 0, -1):
for word in ngrams[i]:
if prev_is_software:
if check_version(word):
tweet.add("version", word)
prev_is_software = False
# Look for 'Get x free'
# This doesn't always work, eg 'get your free ...' / 'get it free'
# TODO: Also look for 'Get x on' etc
# Also look for 'Download x now' etc
elif re.match(r"^[Gg][Ee][Tt][\w.\s]*[Ff][Rr][Ee][Ee]$", word):
software = word.replace(re.findall(re.compile(r"^[Gg][Ee][Tt]"), word)[0], "").strip()
software = software.replace(re.findall(re.compile(r"[Ff][Rr][Ee][Ee]$"), word)[0], "").strip()
if not sql.isSoftware(software):
try:
if check_bing(software, bing):
# Add newly-found software names to list, add to dictionary at end
new_software.add(software, tweet)
possible_tags.append(tweet_id)
# sql.insertSoftware(software) # This task now done at end
except ServerError, e:
print e
raise IncompleteTaggingError()
tweet.add("price", "free")
# REQUIRES REFACTORING
elif re.match(r"^[Gg][Ee][Tt][\w.\s]*[Nn][Oo][Ww]$", word):
software = word.replace(re.findall(re.compile(r"^[Gg][Ee][Tt]"), word)[0], "").strip()
software = software.replace(re.findall(re.compile(r"[Nn][Oo][Ww]$"), word)[0], "").strip()
if not sql.isSoftware(software):
try:
if check_bing(software, bing):
# Add newly-found software names to list, add to dictionary at end
new_software.add(software, tweet)
possible_tags.append(tweet_id)
except ServerError, e:
print e
raise IncompleteTaggingError()
def _ngram_tagger(self, ngram, tweet_id):
tags = Dictionary()
tags.add('tweet_db_id', tweet_id)
if self._keyword:
keyword = self._keyword
if self._sql.isSoftware(keyword):
entry = self._sql.getSoftware()
tags.add('software_name', keyword)
tags.add('software_id', str(entry[0]))
elif self._sql.isCompany(keyword):
entry = self._sql.getCompany()
tags.add('company_name', keyword)
tags.add('company_id', str(entry[0]))
elif self._sql.isOS(keyword):
entry = self._sql.getOS()
tags.add('os_name', keyword)
tags.add('os_id', str(entry[0]))
for tagged_words in ngram:
self._tagger(tagged_words, tags)
print 'lol'
print '2',tags
return tags
class TweetTagger(object):
def __init__(self, sql=None, mongo=None, **kwargs):
super(TweetTagger, self).__init__()
if not sql:
self._sql = SQLConnector(host=kwargs['host'],
port=kwargs['port'],
user=kwargs['user'],
passwd=kwargs['password'],
db=kwargs['db'])
else:
self._sql = sql
if not mongo:
self._mongo = MongoConnector(host=kwargs['H'], port=kwargs['mongoport'], db=kwargs['db'])
else:
self._mongo = mongo
self._keyword = None
self._bing = BingSearch()
self._binged = Dictionary()
def _tag(self, tweet):
tweet_id = str(tweet[0])
original = tweet[1].decode('utf-8', 'ignore')
text = original.lower().replace('#','').strip()
#text = "download 60 hundred pounds 72 million $800 billion pounds holiday havoc v2 in itunes for free 99"
urls = find_url(original)
for url in urls:
text = text.replace(url.lower(), "").strip()
word_freqs = word_frequencies(text)
#print word_freqs
versions = find_version(text)
words = regexp_tokenize(text, pattern=r'\w+([.,]\w+)*|\S+')
prices = find_price(words)
five_gram = self._create_ngram(tokenized=words, gram_length=5)
tagged_tweet = self._ngram_tagger(five_gram, tweet_id)
tagged_tweet.add('sentiment', tweet[2])
tagged_tweet.add('tweet', original)
tagged_tweet.add('url', urls)
tagged_tweet.add('version', versions)
tagged_tweet.add('price', prices)
if tagged_tweet.contains('software_name'):
query = {'software_name':tagged_tweet.get('software_name')}
words = {}
for w in word_freqs:
words['words.'+w] = word_freqs[w]
#print query, words
self._mongo.update_freqs(query,words)
return tagged_tweet
def _create_ngram(self, tokenized, gram_length):
pos_ = pos(tokenized)
#print pos_
gram = None
while not gram: # In case tweet length less than gram_length
gram = ngrams(pos_, gram_length)
gram_length -= 1
return gram
def _ngram_tagger(self, ngram, tweet_id):
tags = Dictionary()
tags.add('tweet_db_id', tweet_id)
if self._keyword:
keyword = self._keyword
if self._sql.isSoftware(keyword):
entry = self._sql.getSoftware()
tags.add('software_name', keyword)
tags.add('software_id', str(entry[0]))
elif self._sql.isCompany(keyword):
entry = self._sql.getCompany()
tags.add('company_name', keyword)
tags.add('company_id', str(entry[0]))
elif self._sql.isOS(keyword):
entry = self._sql.getOS()
tags.add('os_name', keyword)
tags.add('os_id', str(entry[0]))
for tagged_words in ngram:
self._tagger(tagged_words, tags)
print 'lol'
print '2',tags
return tags
def _tagger(self, gram, tags):
words = []
tags_ = []
phrase = ""
pos_soft = ""
possible_software = False
# Compile regular expressions outside of for loop
# for efficiency purposes
free_price = re.compile(r'^free$', re.IGNORECASE)
check_is = re.compile(r'^is$|^for$', re.IGNORECASE)
check_get = re.compile(r'^download$|^get$', re.IGNORECASE)
check_on = re.compile(r'^on$|^for$', re.IGNORECASE)
for tagged_word in gram:
word = tagged_word[0]
tag = tagged_word[1]
phrase += word + " "
#print word, tag
try:
if tagIsNoun(tag):
if self._sql.isSoftware(word):
entry = self._sql.getSoftware()
try:
prev_tag = tags_.pop()
tags_.append(prev_tag)
if not tagIsDeterminantOrPreposition(prev_tag):
tags.add('software_name',word)
tags.add('software_id', str(entry[0]))
except:
possible_software = True
elif self._sql.isCompany(word):
entry = self._sql.getCompany()
try:
prev_tag = tags_.pop()
tags_.append(prev_tag)
if not tagIsDeterminantOrPreposition(prev_tag):
raise # Add to tags
except:
tags.add('company_name',word)
tags.add('company_id', str(entry[0]))
elif self._sql.isProgLang(word):
entry = self._sql.getProgLang()
try:
prev_tag = tags_.pop()
tags_.append(prev_tag)
if not tagIsDeterminantOrPreposition(prev_tag):
raise # Add to tags
except:
tags.add('programming_language_name', word)
tags.add('programming_language_id', str(entry[0]))
if self._sql.isOS(word):
entry = self._sql.getOS()
try:
prev_tag = tags_.pop()
tags_.append(prev_tag)
prev = words.pop()
words.append(prev)
if not tagIsDeterminantOrPreposition(prev_tag) or re.match(check_on, prev):
tags.add('os_name', word)
tags.add('os_id', str(entry[0]))
except:
possible_software = True
except ProgrammingError:
pass
if possible_software:
if tagIsNoun(tag):
pos_soft += word + " "
if word == gram[len(gram)-1][0]: # If 'word' is last word in n-gram
pos_soft = ""
else:
prev = words.pop()
words.append(prev)
if not re.match(check_get, prev):
if check_version(word):
tags.add('version', word)
possible_software = False
if re.match(free_price, word):
try:
prev = words.pop()
words.append(prev)
if re.match(check_is, prev):
tags.add('price', word)
else:
prev = tags_.pop()
tags_.append(prev)
if tagIsNoun(prev):
tags.add('price', word)
except:
# This is first word in phrase
pass
elif re.match(check_get, word):
possible_software = True
# Back in main part of loop
words.append(word)
tags_.append(tag)
# End of for loop
phrase = phrase.strip()
if len(pos_soft) > 0:
pos_soft = pos_soft.strip()
if not tags.get('software_name'):
if self._binged.contains(pos_soft):
if self._binged.get(pos_soft):
tags.add('software_name', pos_soft)
else:
try:
bool_ = check_bing(pos_soft, self._bing)
self._binged[pos_soft]= bool_
if bool_:
# Insert into dictionary db?
tags.add('software_name', pos_soft)
except ServerError, e:
print e
raise IncompleteTaggingError()
print '1',tags
if not best_acc or acc > best_acc:
with open(MODEL_PATH % (dev_loss, acc), 'wb') as f:
torch.save(model, f)
best_acc = acc
stop_counter = 0
else:
for param_group in optimizer.param_groups:
param_group['lr'] = param_group['lr'] * 0.2
if EARLY_STOP != 0:
stop_counter += 1
return stop_counter
dictionary = Dictionary(path=DICT_PATH)
n_token = len(dictionary)
best_dev_loss = None
best_acc = None
model = Classifier({
'dropout': DROPOUT,
'n_tokens': n_token,
'n_layers': N_LAYERS,
'hidden_dim': HIDDEN_DIM,
'embed_dim': EMBED_DIM,
'pooling': POOLING,
'dictionary': dictionary,
'pretrained_wordvec': PRETRAINED_WORDVEC,
import jieba
import jieba.posseg #需要另外加载一个词性标注模块
import pandas as pd
# from nltk.tokenize import word_tokenize
P2P = 'total'
# ********************************************************************* #
datapath = '../../data/' + P2P + '/' + P2P + '.csv'
outpath = '../../data/' + P2P + '/data(%s).json'
dictpath = '../../data/' + P2P + '/mydict(%s).json'
debug_flag = False
stop = False
# ********************************************************************* #
mydict = Dictionary()
mydict.add_word('<pad>')
# mydict.add_word('<unk>')
stopping_word = open('../../data/stopping_word', 'r',
encoding='utf-8').readlines()
for i in range(len(stopping_word)):
stopping_word[i] = stopping_word[i].strip()
reviews = pd.read_csv(datapath, index_col=0, header=0, encoding='utf-8')
labels = list(reviews['reviewEvaluation'])
reviews = list(reviews['reviewContent'])
# reviews = open(datapath).readlines()
n_reviews = len(reviews)
print('%d条评论将被载入...' % n_reviews)
if debug_flag:
path = 'wili'
print(os.listdir(path))
# Init random seed to get reproducible results
seed = 1111
random.seed(seed)
np.random.RandomState(seed)
torch.manual_seed(seed)
# Any results you write to the current directory are saved as output.
x_train_full = open(path + "/x_train.txt").read().splitlines()
y_train_full = open(path + "/y_train.txt").read().splitlines()
print('Example:')
print('LANG =', y_train_full[0])
print('TEXT =', x_train_full[0])
char_vocab = Dictionary()
pad_token = '<pad>' # reserve index 0 for padding
unk_token = '<unk>' # reserve index 1 for unknown token
pad_index = char_vocab.add_token(pad_token)
unk_index = char_vocab.add_token(unk_token)
# join all the training sentences in a single string
# and obtain the list of different characters with set
chars = set(''.join(x_train_full))
for char in sorted(chars):
char_vocab.add_token(char)
print("Vocabulary:", len(char_vocab), "UTF characters")
lang_vocab = Dictionary()
# use python set to obtain the list of languages without repetitions
languages = set(y_train_full)
from io import BytesIO
from PIL import Image
from utils import Dictionary, get_words, load_model
import base64
import difflib
import numpy as np
import torch.nn.functional as F
import torch
net_recog = load_model('../recog_params.pkl')
ug_dict = Dictionary('../../../data/ug_words.txt')
def img2str(pic):
# pic: numpy array
figfile = BytesIO()
pic = Image.fromarray(pic).convert('RGBA').save(figfile, format='PNG')
figfile.seek(0, 0)
figdata_png = base64.b64encode(figfile.getvalue()).decode('ascii')
return figdata_png
def compute(test_id='test'):
pic_path = 'static/' + test_id + '.png'
truth_path = 'static/' + test_id + '.txt'
base_image, pic_with_box, word_pics = get_words(pic_path)
word_pics = np.stack(word_pics)
pred = F.softmax(net_recog(torch.from_numpy(word_pics)), dim=1)
_, idxes = torch.max(pred, dim=1)
res = []
print(args)
start_time = time.time()
corpus_output_name = args.save + "corpus_index"
dictionary_output_name = args.save + "dictionary_index"
if not os.path.exists(args.save):
os.makedirs(args.save)
f_out = open(corpus_output_name, 'w')
my_open = open
byte_mode = False
dict_c = Dictionary(byte_mode)
total_num_w = 0
with my_open(args.data, 'r') as f_in:
for line_idx, line in enumerate(f_in):
sent_spacy, gpt2_idx, gpt2_mapping = line.rstrip().split('\t')
w_ind_list = []
for w in sent_spacy.split():
w_ind = dict_c.dict_check_add(w)
w_ind_list.append(w_ind)
total_num_w += 1
dict_c.append_eos(w_ind_list)
f_out.write(' '.join([str(x) for x in w_ind_list]) + '\t' + gpt2_idx + '\t' + gpt2_mapping + '\n')
if line_idx % 1000000 == 0:
print(line_idx)
sys.stdout.flush()
lines.append(indices)
print("Number of sentences dropped from {}: {} out of {} total".
format(path, dropped, linecount))
return lines
def __index__(self, i):
return self.Item(self.text[i], self.hiddens[i], self.labels[i])
model_args, idx2word, autoencoder, gan_gen, gan_disc \
= load_models(args.load_path)
# print(idx2word)
word2idx = {word : index for index, word in idx2word.items()}
dic = Dictionary()
dic.word2idx = word2idx
dic.idx2word = idx2word
corpus = EncodeCopus(args.inf, maxlen=-1, dictionary=dic)
batches = corpus.get_batches()
autoencoder.cuda()
autoencoder.eval()
with open(args.inf + '.corpus', 'wb') as b:
hiddens = []
for index, (source, target, length) in enumerate(batches):
# print(source, length)
hidden = autoencoder.encode(Variable(source), length,None)
# print(hidden)
def __init__(self,
corpus_dir,
w2v,
dictionary=None,
w2v_lbound=16,
w2v_ubound=2**16,
corpus_lbound=2,
ctx_len=12,
pad=0,
is_wikitext=False,
is_chimera=False,
is_jnlpba=False):
if dictionary is None:
dictionary = Dictionary(w2v.vector_size)
if is_wikitext:
corpus = [
fi.lower().split()
for fi in (corpus_dir /
'wiki.train.tokens').open().readlines()
]
corpus += [
fi.lower().split()
for fi in (corpus_dir /
'wiki.valid.tokens').open().readlines()
]
corpus += [
fi.lower().split()
for fi in (corpus_dir / 'wiki.test.tokens').open().readlines()
]
corpus = np.array(corpus)
elif is_chimera:
corpus = []
with (corpus_dir / 'dataset.txt').open(encoding='latin1') as f:
lines = f.readlines()[1:]
for i in range(0, len(lines), 2):
fields = lines[i].rstrip('\n').split('\t')
nonce = fields[1].lower()
sents = fields[3].lower().split('@@')
pivot_comp = lines[i + 1].split('\t')[5].lower().split('_')
corpus += [
sent.replace(nonce, pivot_comp[0 if i %
2 == 0 else 1]).split()
for i, sent in enumerate(sents)
]
corpus = np.unique(corpus)
elif is_jnlpba:
ps = ['train/Genia4ERtask2.iob2', 'test/Genia4EReval2.iob2']
corpus = []
sent = []
for p in ps:
for w in (corpus_dir / p).open().readlines():
if w.startswith("###MEDLINE:"):
if sent:
corpus += [sent]
sent = []
continue
w = w.strip().lower()
if w != '':
w = w.split()
w = w[0]
sent += [w]
corpus += [sent]
corpus = np.array(corpus)
print(f"Corpus shape: {corpus.shape}")
word_count = defaultdict(int)
oov_words = []
oov_dataset = {}
for sent in corpus:
for w in sent:
word_count[w] += 1
dictionary.add_word(w, w2v)
if w not in oov_dataset and w not in dictionary.word2idx:
if w in string.punctuation:
continue
oov_words.append(w)
oov_dataset[w] = [[], []]
words = []
for w in dictionary.word2idx:
if w != '<unk>' and w2v_ubound > w2v.wv.vocab[
w].count > w2v_lbound and word_count[w] > corpus_lbound:
words.append(w)
print(f"Number of valid words: {len(words)}")
train_dataset = {}
valid_dataset = {}
for w, prob in zip(words, np.random.random(len(words))):
if prob < 0.9:
train_dataset[w] = [[], []]
else:
valid_dataset[w] = [[], []]
for sent in corpus:
words_valid = []
words_train = []
words_oov = []
for idx, w in enumerate(sent):
if w in valid_dataset:
words_valid += [[w, idx]]
elif w in train_dataset:
words_train += [[w, idx]]
elif w in oov_dataset:
words_oov += [[w, idx]]
if len(words_valid) > 0 or len(words_train) > 0 or len(
words_oov) > 0:
sent_word_ids = dictionary.sent2idx(sent)
if len(words_valid) > 0:
for w, idx in words_valid:
if np.count_nonzero(
sent_word_ids[idx - ctx_len:idx + 1 +
ctx_len]) > ctx_len:
valid_dataset[w][0] += [
sent_word_ids[idx - ctx_len:idx]
]
valid_dataset[w][1] += [
sent_word_ids[idx + 1:idx + 1 + ctx_len]
]
if len(words_train) > 0:
for w, idx in words_train:
if np.count_nonzero(
sent_word_ids[idx - ctx_len:idx + 1 +
ctx_len]) > ctx_len:
train_dataset[w][0] += [
sent_word_ids[idx - ctx_len:idx]
]
train_dataset[w][1] += [
sent_word_ids[idx + 1:idx + 1 + ctx_len]
]
if len(words_oov) > 0:
for w, idx in words_oov:
if np.count_nonzero(
sent_word_ids[idx - ctx_len:idx + 1 +
ctx_len]) > ctx_len:
oov_dataset[w][0] += [
sent_word_ids[idx - ctx_len:idx]
]
oov_dataset[w][1] += [
sent_word_ids[idx + 1:idx + 1 + ctx_len]
]
for w in valid_dataset:
lefts = pad_sequences(valid_dataset[w][0],
max_len=ctx_len,
pad=pad,
pre=True)
rights = pad_sequences(valid_dataset[w][1],
max_len=ctx_len,
pad=pad,
pre=False)
valid_dataset[w] = np.concatenate((lefts, rights), axis=1)
for w in train_dataset:
lefts = pad_sequences(train_dataset[w][0],
max_len=ctx_len,
pad=pad,
pre=True)
rights = pad_sequences(train_dataset[w][1],
max_len=ctx_len,
pad=pad,
pre=False)
train_dataset[w] = np.concatenate((lefts, rights), axis=1)
for w in oov_dataset:
lefts = pad_sequences(oov_dataset[w][0],
max_len=ctx_len,
pad=pad,
pre=True)
rights = pad_sequences(oov_dataset[w][1],
max_len=ctx_len,
pad=pad,
pre=False)
oov_dataset[w] = np.concatenate((lefts, rights), axis=1)
print(f"Train size: {len(train_dataset.keys())}")
print(f"Valid size: {len(valid_dataset.keys())}")
print(f"OOV size: {len(oov_words)}")
print(
f"Train >0 ctxts size: {len([w for w in train_dataset.keys() if len(train_dataset[w]) > 0])}"
)
print(
f"Valid >0 ctxts size: {len([w for w in valid_dataset.keys() if len(valid_dataset[w]) > 0])}"
)
print(
f"OOV >0 ctxts size: {len([w for w in oov_words if len(oov_dataset[w]) > 0])}"
)
train_ctxt_lens = [len(train_dataset[w]) for w in train_dataset.keys()]
valid_ctxt_lens = [len(valid_dataset[w]) for w in valid_dataset.keys()]
oov_ctxt_lens = [len(oov_dataset[w]) for w in oov_words]
print(
f"Number of Train with ctxts size = index {[train_ctxt_lens.count(i) for i in range(10)]}"
)
print(
f"Number of Valid with ctxts size = index {[valid_ctxt_lens.count(i) for i in range(10)]}"
)
print(
f"Number of OOV with ctxts size = index {[oov_ctxt_lens.count(i) for i in range(10)]}"
)
oov_word_counts = [word_count[w] for w in oov_words]
inds = np.argsort(-np.array(oov_word_counts))[:10]
print(
f"Number of OOV words with count = index {[oov_word_counts.count(i) for i in range(10)]}"
)
print(f"Most frequent OOV words: {[oov_words[i] for i in inds]} "
f"frequencies: {[oov_word_counts[i] for i in inds]}")
self.dictionary = dictionary
self.train_dataset = train_dataset
self.train_words = list(train_dataset.keys())
self.valid_dataset = valid_dataset
self.valid_words = list(valid_dataset.keys())
self.oov_dataset = oov_dataset
self.oov_words = list(oov_dataset.keys())
self.w2v = w2v
self.ctx_len = ctx_len
self.train_k2words = {}
self.valid_k2words = {}
logging.info('batch size: {}'.format(args.batch_size))
if args.algo == 'FL':
logging.info('epochs: {}'.format(args.train_epochs))
logging.info('*' * 52)
if args.model == 'LSTM':
# load shakespeare data (client: 715)
d_train = load_data('shakespeare_train.h5', args)
d_test = load_data('shakespeare_test.h5', args)
# split data into two parts: support client / test client
support_train_str, support_test_str, test_train_str, test_test_str = split_data(
d_train, d_test, args)
# preprocess data and construct a dictionary for whole data
corpus = Dictionary()
support_train, support_test = lstm_data_process(
support_train_str, support_test_str, corpus, args)
test_train, test_test = lstm_data_process(test_train_str,
test_test_str, corpus, args)
args.ntokens = len(corpus)
args.corpus = corpus
if args.algo == 'FL':
FL_LSTM(support_train, support_test, test_train, test_test, args)
elif args.algo == 'FR':
FR_LSTM(support_train, support_test, test_train, test_test, args)
else:
# load MNIST data (client: 3383 / train: 341873 / test: 40832)
d_train = load_data('fed_emnist_digitsonly_train.h5', args)
d_test = load_data('fed_emnist_digitsonly_test.h5', args)
