Wage数据集多项式回归绘图

import pandas as pd
import numpy as np
from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt
wage = pd.read_csv('https://liangdaima.com/static/data/statistics/Wage.csv')
X = wage['age'].values.reshape(-1, 1)
y = wage['wage'].values
poly = PolynomialFeatures(4, include_bias=False)
X_poly = poly.fit_transform(X)
model = LinearRegression().fit(X_poly, y)
age_grid = np.linspace(X.min(), X.max(), 100).reshape(-1, 1)
age_grid_poly = poly.transform(age_grid)
pred = model.predict(age_grid_poly)
plt.figure(figsize=(10, 6))
plt.scatter(X, y, alpha=0.5, label='数据点')
plt.plot(age_grid, pred, 'r-', linewidth=2, label='4次多项式拟合')
plt.xlabel('Age')
plt.ylabel('Wage')
plt.legend()
plt.title('Wage vs Age 多项式回归')
plt.show()