NLP入门 Task05 基于神经网络的文本分类-Word2Vec 学习

本文内容整理自DataWhale组织的NLP学习组队活动。
赛题名称
零基础入门NLP之新闻文本分类（https://tianchi.aliyun.com/competition/entrance/531810/introduction）
关于Word2Vec的资料

Word2Vec原理（一）CBOW与Skip-Gram模型基础（https://www.cnblogs.com/pinard/p/7160330.html）
gensim文档——对Word2Vec的介绍（https://radimrehurek.com/gensim/models/word2vec.html）

使用gensim训练Word2Vec

import logging import randomimport numpy as np import torchlogging.basicConfig(level=logging.INFO, format='%(asctime)-15s %(levelname)s: %(message)s')# set seed seed = 666 random.seed(seed) np.random.seed(seed) torch.cuda.manual_seed(seed) torch.manual_seed(seed)# split data to 10 fold fold_num = 10 data_file = '../data/train_set.csv' import pandas as pddef all_data2fold(fold_num, num=10000): fold_data = https://www.it610.com/article/[] f = pd.read_csv(data_file, sep='\t', encoding='UTF-8') texts = f['text'].tolist()[:num] labels = f['label'].tolist()[:num]total = len(labels)index = list(range(total)) np.random.shuffle(index)all_texts = [] all_labels = [] for i in index: all_texts.append(texts[i]) all_labels.append(labels[i])label2id = {} for i in range(total): label = str(all_labels[i]) if label not in label2id: label2id[label] = [i] else: label2id[label].append(i)all_index = [[] for _ in range(fold_num)] for label, data in label2id.items(): # print(label, len(data)) batch_size = int(len(data) / fold_num) other = len(data) - batch_size * fold_num for i in range(fold_num): cur_batch_size = batch_size + 1 if i < other else batch_size # print(cur_batch_size) batch_data = https://www.it610.com/article/[data[i * batch_size + b] for b in range(cur_batch_size)] all_index[i].extend(batch_data)batch_size = int(total / fold_num) other_texts = [] other_labels = [] other_num = 0 start = 0 for fold in range(fold_num): num = len(all_index[fold]) texts = [all_texts[i] for i in all_index[fold]] labels = [all_labels[i] for i in all_index[fold]]if num> batch_size: fold_texts = texts[:batch_size] other_texts.extend(texts[batch_size:]) fold_labels = labels[:batch_size] other_labels.extend(labels[batch_size:]) other_num += num - batch_size elif num < batch_size: end = start + batch_size - num fold_texts = texts + other_texts[start: end] fold_labels = labels + other_labels[start: end] start = end else: fold_texts = texts fold_labels = labelsassert batch_size == len(fold_labels)# shuffle index = list(range(batch_size)) np.random.shuffle(index)shuffle_fold_texts = [] shuffle_fold_labels = [] for i in index: shuffle_fold_texts.append(fold_texts[i]) shuffle_fold_labels.append(fold_labels[i])data = https://www.it610.com/article/{'label': shuffle_fold_labels, 'text': shuffle_fold_texts} fold_data.append(data)logging.info("Fold lens %s", str([len(data['label']) for data in fold_data]))return fold_datafold_data = https://www.it610.com/article/all_data2fold(10)''' Out 2020-07-30 23:30:04,912 INFO: Fold lens [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000] '''# build train data for word2vec fold_id = 9train_texts = [] for i in range(0, fold_id): data = https://www.it610.com/article/fold_data[i] train_texts.extend(data['text'])logging.info('Total %d docs.' % len(train_texts))''' Out 2020-07-18 23:30:04,929 INFO: Total 9000 docs. '''logging.info('Start training...') from gensim.models.word2vec import Word2Vecnum_features = 100# Word vector dimensionality num_workers = 8# Number of threads to run in paralleltrain_texts = list(map(lambda x: list(x.split()), train_texts)) model = Word2Vec(train_texts, workers=num_workers, size=num_features) model.init_sims(replace=True)# save model model.save("./word2vec.bin")''' Out （打印的log过长，省略） '''# load model model = Word2Vec.load("./word2vec.bin")# convert format model.wv.save_word2vec_format('./word2vec.txt', binary=False)''' Out （打印的log较长，省略） '''

【NLP入门 Task05 基于神经网络的文本分类-Word2Vec】