Job5 基于深度学习的文本分类2-1Word2Vec
使用gensim训练word2vec
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 = './data/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.app