1.引入所需包
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split # 划分数据集
2.读取数据
train_data = pd.read_csv("messages.csv")
3.进行分割
# 拆分数据
print("拆分数据中。。。")
split_ratio = 0.75 # 75%的训练数据
seed = 5 # 随机种子
# 分割训练集与测试集
xtrain, xtest, ytrain, ytest = train_test_split(
train_data, range(train_data.shape[0]), test_size=split_ratio, random_state=seed)
print(xtest)
print("------------------")
print(xtrain)