使用机器学习完成中文文本分类

数据集来自七月在线练习

import jieba
import pandas as pd
import random
from sklearn.model_selection import train_test_split                #划分训练/测试集
from sklearn.feature_extraction.text import CountVectorizer         #抽取特征
from sklearn.naive_bayes import MultinomialNB
from sklearn.feature_extraction.text import TfidfVectorizer
'''
读入数据
'''
df_technology = pd.read_csv("H:/NLP_project/NLP_project/data/technology_news.csv")
df_technology = df_technology.dropna()

df_car = pd.read_csv("H:/NLP_project/NLP_project/data/car_news.csv")
df_car = df_car.dropna()

df_entertainment = pd.read_csv("H:/NLP_project/NLP_project/data/entertainment_news.csv")
df_entertainment = df_entertainment.dropna()

df_military = pd.read_csv("H:/NLP_project/NLP_project/data/military_news.csv")
df_military = df_military.dropna()

df_sports = pd.read_csv("H:/NLP_project/NLP_project/data/sports_news.csv")
df_sport