def read_combine_data(corpus_files,
dev_files,
rebuild_maps=False,
mini_count=0):
assert len(corpus_files) == len(dev_files)
corpus_data = []
for i, corpus_f in enumerate(corpus_files):
curr_data = []
with codecs.open(corpus_f, 'r', 'utf-8') as f:
curr_data += f.readlines()
curr_data += ['\n']
with codecs.open(dev_files[i], 'r', 'utf-8') as df:
curr_data += df.readlines()
corpus_data.append(curr_data)
tokens = []
labels = []
token2idx = dict()
tag2idx = dict()
chr_cnt = dict()
chr2idx = dict()
for data in corpus_data:
if rebuild_maps:
print('constructing coding table')
# here token2idx, tag2idx and chr_cnt are doing argmentaion
curr_tokens, curr_labels, token2idx, tag2idx, chr_cnt = utils.generate_corpus_char(
data,
token2idx,
tag2idx,
chr_cnt,
c_thresholds=mini_count,
if_shrink_w_feature=False)
else:
curr_tokens, curr_labels = utils.read_corpus(data)
tokens.append(curr_tokens)
labels.append(curr_labels)
shrink_char_count = [
k for (k, v) in iter(chr_cnt.items()) if v >= mini_count
]
chr2idx = {
shrink_char_count[ind]: ind
for ind in range(0, len(shrink_char_count))
}
chr2idx['<u>'] = len(chr2idx) # unk for char
chr2idx[' '] = len(chr2idx) # concat for char
chr2idx['\n'] = len(chr2idx) # eof for char
if rebuild_maps:
return tokens, labels, token2idx, tag2idx, chr2idx
else:
return tokens, labels
print("loading checkpoint: '{}'".format(args.load_check_point))
checkpoint_file = torch.load(args.load_check_point)
args.start_epoch = checkpoint_file['epoch']
f_map = checkpoint_file['f_map']
c_map = checkpoint_file['c_map']
in_doc_words = checkpoint_file['in_doc_words']
train_features, train_labels = utils.read_corpus(lines)
else:
print("no checkpoint found at: '{}'".format(args.load_check_point))
sys.exit()
else:
print('constructing coding table')
train_features, train_labels, f_map, _, c_map = \
utils.generate_corpus_char(lines, if_shrink_c_feature=True,
c_thresholds=args.mini_count,
if_shrink_w_feature=False)
f_set = {v for v in f_map}
f_map = utils.shrink_features(f_map, train_features, args.mini_count)
dt_f_set = functools.reduce(lambda x, y: x | y, map(lambda t: set(t), dev_features), f_set)
dt_f_set = functools.reduce(lambda x, y: x | y, map(lambda t: set(t), test_features), dt_f_set)
f_map, embedding_tensor, in_doc_words = utils.load_embedding(args.emb_file, ' ', f_map, dt_f_set, args.unk, args.word_embedding_dim, shrink_to_corpus=args.shrink_embedding)
l_set = functools.reduce(lambda x, y: x | y, map(lambda t: set(t), dev_labels))
l_set = functools.reduce(lambda x, y: x | y, map(lambda t: set(t), test_labels), l_set)
print('constructing dataset')
dataset, dataset_onlycrf = utils.construct_bucket_mean_vb_wc(train_features, train_labels, CRF_l_map, SCRF_l_map, c_map, f_map, SCRF_stop_tag=SCRF_l_map['<STOP>'], ALLOW_SPANLEN=args.allowspan, train_set=True)
checkpoint_file = torch.load(args.load_check_point)
args.start_epoch = checkpoint_file['epoch']
f_map = checkpoint_file['f_map']
l_map = checkpoint_file['l_map']
c_map = checkpoint_file['c_map']
in_doc_words = checkpoint_file['in_doc_words']
train_features, train_labels = utils.read_corpus(lines[i])
else:
print("no checkpoint found at: '{}'".format(
args.load_check_point))
else:
print('constructing coding table')
train_features0, train_labels0, f_map, l_map, char_count = utils.generate_corpus_char(
lines[i],
f_map,
l_map,
char_count,
c_thresholds=args.mini_count,
if_shrink_w_feature=False)
train_features.append(train_features0)
train_labels.append(train_labels0)
train_features_tot += train_features0
shrink_char_count = [
k for (k, v) in iter(char_count.items()) if v >= args.mini_count
]
char_map = {
shrink_char_count[ind]: ind
for ind in range(0, len(shrink_char_count))
checkpoint_file = torch.load(args.load_check_point)
args.start_epoch = checkpoint_file['epoch']
f_map = checkpoint_file['f_map']
l_map = checkpoint_file['l_map']
c_map = checkpoint_file['c_map']
in_doc_words = checkpoint_file['in_doc_words']
train_features, train_labels = utils.read_corpus(lines)
else:
print("no checkpoint found at: '{}'".format(args.load_check_point))
else:
print('constructing coding table')
# converting format
train_features, train_labels, f_map, l_map, c_map = utils.generate_corpus_char(
lines,
if_shrink_c_feature=True,
c_thresholds=args.mini_count,
if_shrink_w_feature=False)
f_set = {v for v in f_map}
f_map = utils.shrink_features(f_map, train_features, args.mini_count)
if args.rand_embedding:
print("embedding size: '{}'".format(len(f_map)))
in_doc_words = len(f_map)
else:
dt_f_set = functools.reduce(lambda x, y: x | y,
map(lambda t: set(t), dev_features),
f_set)
dt_f_set = functools.reduce(lambda x, y: x | y,
map(lambda t: set(t), test_features),
if os.path.isfile(args.load_check_point):
print("loading checkpoint: '{}'".format(args.load_check_point))
checkpoint_file = torch.load(args.load_check_point)
args.start_epoch = checkpoint_file['epoch']
f_map = checkpoint_file['f_map']
l_map = checkpoint_file['l_map']
c_map = checkpoint_file['c_map']
in_doc_words = checkpoint_file['in_doc_words']
train_features, train_labels = utils.read_corpus(lines)
else:
print("no checkpoint found at: '{}'".format(args.load_check_point))
else:
print('constructing coding table')
# converting format
train_features, train_labels, f_map, l_map, c_map = utils.generate_corpus_char(lines, if_shrink_c_feature=True, c_thresholds=args.mini_count, if_shrink_w_feature=False)
f_set = {v for v in f_map}
f_map = utils.shrink_features(f_map, train_features, args.mini_count)
if args.rand_embedding:
print("embedding size: '{}'".format(len(f_map)))
in_doc_words = len(f_map)
else:
dt_f_set = functools.reduce(lambda x, y: x | y, map(lambda t: set(t), dev_features), f_set)
dt_f_set = functools.reduce(lambda x, y: x | y, map(lambda t: set(t), test_features), dt_f_set)
print("feature size: '{}'".format(len(f_map)))
print('loading embedding')
if args.fine_tune: # which means does not do fine-tune
f_map = {'<eof>': 0}
f_map, embedding_tensor, in_doc_words = utils.load_embedding_wlm(args.emb_file, ' ', f_map, dt_f_set, args.caseless, args.unk, args.word_dim, shrink_to_corpus=args.shrink_embedding)
if os.path.isfile(args.load_check_point):
print("loading checkpoint: '{}'".format(args.load_check_point))
checkpoint_file = torch.load(args.load_check_point)
args.start_epoch = checkpoint_file['epoch']
f_map = checkpoint_file['f_map']
l_map = checkpoint_file['l_map']
c_map = checkpoint_file['c_map']
in_doc_words = checkpoint_file['in_doc_words']
train_features, train_labels = utils.read_corpus(train_lines)
else:
print("no checkpoint found at: '{}'".format(args.load_check_point))
else:
print('constructing coding table')
# converting format
all_features, all_labels, f_map, l_map, c_map = utils.generate_corpus_char(train_lines+dev_lines+test_lines+cotrain_lines, if_shrink_c_feature=True, c_thresholds=args.mini_count, if_shrink_w_feature=False)
with open('c_map.json','w') as f:
json.dump(c_map,f)
f_set = {v for v in f_map}
f_map = utils.shrink_features(f_map, all_features, args.mini_count)
if args.rand_embedding:
print("embedding size: '{}'".format(len(f_map)))
in_doc_words = len(f_map)
else:
dt_f_set = functools.reduce(lambda x, y: x | y, map(lambda t: set(t), dev_features), f_set)
dt_f_set = functools.reduce(lambda x, y: x | y, map(lambda t: set(t), test_features), dt_f_set)
print("feature size: '{}'".format(len(f_map)))
print('loading embedding')
if args.fine_tune: # which means does not do fine-tune
f_map = {'<eof>': 0}
def read_dataset(self, file_dict, dataset_name, *args, **kwargs):
print('loading corpus')
self.file_num = len(self.args.train_file)
for i in range(self.file_num):
with codecs.open(self.args.train_file[i], 'r', 'utf-8') as f:
lines0 = f.readlines()
lines0 = lines0[0:2000]
# print (len(lines0))
self.lines.append(lines0)
for i in range(self.file_num):
with codecs.open(self.args.dev_file[i], 'r', 'utf-8') as f:
dev_lines0 = f.readlines()
dev_lines0 = dev_lines0[0:2000]
self.dev_lines.append(dev_lines0)
for i in range(self.file_num):
with codecs.open(self.args.test_file[i], 'r', 'utf-8') as f:
test_lines0 = f.readlines()
test_lines0 = test_lines0[0:2000]
self.test_lines.append(test_lines0)
for i in range(self.file_num):
dev_features0, dev_labels0 = utils.read_corpus(self.dev_lines[i])
test_features0, test_labels0 = utils.read_corpus(
self.test_lines[i])
self.dev_features.append(dev_features0)
self.test_features.append(test_features0)
self.dev_labels.append(dev_labels0)
self.test_labels.append(test_labels0)
if self.args.output_annotation: # NEW
test_word0, test_word_tag0 = utils.read_features(
self.test_lines[i])
self.test_word.append(test_word0)
self.test_word_tag.append(test_word_tag0)
#print (len(self.test_word), len(self.test_labels))
if self.args.load_check_point:
if os.path.isfile(self.args.load_check_point):
print("loading checkpoint: '{}'".format(
self.args.load_check_point))
self.checkpoint_file = torch.load(
self.args.load_check_point)
self.args.start_epoch = self.checkpoint_file['epoch']
self.f_map = self.checkpoint_file['f_map']
self.l_map = self.checkpoint_file['l_map']
c_map = self.checkpoint_file['c_map']
self.in_doc_words = self.checkpoint_file['in_doc_words']
self.train_features, self.train_labels = utils.read_corpus(
self.lines[i])
else:
print("no checkpoint found at: '{}'".format(
self.args.load_check_point))
else:
print('constructing coding table')
train_features0, train_labels0, self.f_map, self.l_map, self.char_count = utils.generate_corpus_char(
self.lines[i],
self.f_map,
self.l_map,
self.char_count,
c_thresholds=self.args.mini_count,
if_shrink_w_feature=False)
self.train_features.append(train_features0)
self.train_labels.append(train_labels0)
self.train_features_tot += train_features0
shrink_char_count = [
k for (k, v) in iter(self.char_count.items())
if v >= self.args.mini_count
]
self.char_map = {
shrink_char_count[ind]: ind
for ind in range(0, len(shrink_char_count))
}
self.char_map['<u>'] = len(self.char_map) # unk for char
self.char_map[' '] = len(self.char_map) # concat for char
self.char_map['\n'] = len(self.char_map) # eof for char
f_set = {v for v in self.f_map}
dt_f_set = f_set
self.f_map = utils.shrink_features(self.f_map, self.train_features_tot,
self.args.mini_count)
l_set = set()
for i in range(self.file_num):
dt_f_set = functools.reduce(
lambda x, y: x | y, map(lambda t: set(t),
self.dev_features[i]), dt_f_set)
dt_f_set = functools.reduce(
lambda x, y: x | y, map(lambda t: set(t),
self.test_features[i]), dt_f_set)
l_set = functools.reduce(lambda x, y: x | y,
map(lambda t: set(t), self.dev_labels[i]),
l_set)
l_set = functools.reduce(
lambda x, y: x | y, map(lambda t: set(t), self.test_labels[i]),
l_set)
if not self.args.rand_embedding:
print("feature size: '{}'".format(len(self.f_map)))
print('loading embedding')
if self.args.fine_tune: # which means does not do fine-tune
self.f_map = {'<eof>': 0}
self.f_map, self.embedding_tensor, self.in_doc_words = utils.load_embedding_wlm(
self.args.emb_file,
' ',
self.f_map,
dt_f_set,
self.args.caseless,
self.args.unk,
self.args.word_dim,
shrink_to_corpus=self.args.shrink_embedding)
print("embedding size: '{}'".format(len(self.f_map)))
for label in l_set:
if label not in self.l_map:
self.l_map[label] = len(self.l_map)
print('constructing dataset')
for i in range(self.file_num):
# construct dataset
dataset, forw_corp, back_corp = utils.construct_bucket_mean_vb_wc(
self.train_features[i], self.train_labels[i], self.l_map,
self.char_map, self.f_map, self.args.caseless)
dev_dataset, forw_dev, back_dev = utils.construct_bucket_mean_vb_wc(
self.dev_features[i], self.dev_labels[i], self.l_map,
self.char_map, self.f_map, self.args.caseless)
test_dataset, forw_test, back_test = utils.construct_bucket_mean_vb_wc(
self.test_features[i], self.test_labels[i], self.l_map,
self.char_map, self.f_map, self.args.caseless)
self.dataset_loader.append([
torch.utils.data.DataLoader(tup,
self.args.batch_size,
shuffle=True,
drop_last=False) for tup in dataset
])
self.dev_dataset_loader.append([
torch.utils.data.DataLoader(tup,
50,
shuffle=False,
drop_last=False)
for tup in dev_dataset
])
self.test_dataset_loader.append([
torch.utils.data.DataLoader(tup,
50,
shuffle=False,
drop_last=False)
for tup in test_dataset
])
print('setting:')
print(args)
# load corpus
print('loading corpus')
with codecs.open(args.train_file, 'r', 'utf-8') as f:
lines = f.readlines()
with codecs.open(args.dev_file, 'r', 'utf-8') as f:
dev_lines = f.readlines()
with codecs.open(args.test_file, 'r', 'utf-8') as f:
test_lines = f.readlines()
train_features, train_labels, _, _, _ = utils.generate_corpus_char(
lines,
if_shrink_c_feature=True,
c_thresholds=5,
if_shrink_w_feature=False)
dev_features, dev_labels = utils.read_corpus(dev_lines)
test_features, test_labels = utils.read_corpus(test_lines)
with open(args.pre_path + "train.txt", "w") as train_file:
print(len(train_features))
for train_feature in train_features:
sentence = ""
for w in train_feature:
sentence += w + " "
train_file.write(sentence.rstrip() + "\n")
with open(args.pre_path + "dev.txt", "w") as dev_file:
print(len(dev_features))
