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))