python文本预处理
import pandas as pd
import numpy as np
import jieba
import re
from sklearn.model_selection import train_test_split
# import model_evaluation_utils as meu
dataset = pd.read_csv(r'E:\python\python文本挖掘\作业7\DataSet.csv')
dataset.info()
# 去掉评论空白数据
# dataset.review.fillna('', inplace=True)
dataset.dropna(inplace=True)
dataset.info()
reviews = np