零基础入门NLP-Task05基于深度学习的文本分类2-1Word2Vec

基于深度学习的文本分类2-1Word2Vec

词向量

使用gensim训练word2vec
word2vec模型背后的基本思想是对出现在上下文环境里的词进行预测。对于每一条输入文本,我们选取一个上下文窗口和一个中心词,并基于这个中心词去预测窗口里其他词出现的频率。

import logging
import random

import numpy as np
import torch

logging.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 = 'C:/Users/BAO/Desktop/天池/train_set.csv/train_set.csv'
import pandas as pd


def all_data2fold(fold_num, num=10000):
    fold_data = []
    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 = [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 = labels

        assert 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 = {'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_data


fold_data = all_data2fold(10)
# build train data for word2vec
fold_id = 9

train_texts = []
for i in range(0, fold_id):
    data = fold_data[i]
    train_texts.extend(data['text'])
    
logging.info('Total %d docs.' % len(train_texts))
logging.info('Start training...')
from gensim.models.word2vec import Word2Vec

num_features = 100     # Word vector dimensionality
num_workers = 8       # Number of threads to run in parallel

train_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")
# load model
model = Word2Vec.load("./word2vec.bin")

# convert format
model.wv.save_word2vec_format('./word2vec.txt', binary=False)

模型是训练好了,怎么用啊

基于TextCNN、TextRnn的文本表示
额,运行不了代码,不知道为什么
本章小结
不会吧,明天再补补知识看看

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值