Python如何实现拆分数据集

# 导入第三方模块
import pandas as pd
# 读入数据
df = pd.read_csv(r'splitfeatures.csv')
df.head()

X = df[['age','sex','income','profession']]
y = df['is_buy']

X1 = df.iloc[:,[0,1,2,4]]
y1 = df.iloc[:,[3]]
X2 = df.loc[:,['age','sex','income','profession']]
y2 = df.loc[:,['is_buy']]

X3 = df.drop(['is_buy'],axis=1)
y3 = df.is_buy

col = df.columns[[0,1,2,4]]
X4 = df.loc[:,col]
X5 = df.iloc[:, df.columns != 'is_buy']
y5 = df.iloc[:, df.columns == 'is_buy']

from sklearn import model_selection
# 将数据集拆分为训练集和测试集
X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y, test_size = 0.2, random_state = 1234)

import numpy as np
from sklearn.model_selection import train_test_split

from sklearn.datasets import load_iris
iris = load_iris()
X = iris.data
y = iris.target

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

print("训练集长度：", len(X_train))
print("测试集长度：", len(X_test))

# 在训练集上训练模型
model.fit(X_train, y_train)
# 在测试集上测试模型性能
accuracy = model.score(X_test, y_test)
print("模型准确率：", accuracy)