Default数据集验证集方法

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
default = pd.read_csv('https://liangdaima.com/static/data/statistics/Default.csv')
default['default'] = (default['default'] == 'Yes').astype(int)
X = default[['income', 'balance']]
y = default['default']
X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.3, random_state=42)
model = LogisticRegression()
model.fit(X_train, y_train)
pred = model.predict(X_val)
print('验证集错误率:', 1 - accuracy_score(y_val, pred))