我正在计算训练集上的 MSE,所以我希望 MSE 在使用更高的多项式时会降低。但是,从 4 级到 5 级,MSE 显着增加。可能是什么原因?
import pandas as pd, numpy as np
from sklearn.preprocessing import PolynomialFeatures, StandardScaler
from sklearn.linear_model import LinearRegression
from sklearn.pipeline import Pipeline
from sklearn.metrics import mean_squared_error
import matplotlib.pyplot as plt
path = "https://s3-api.us-geo.objectstorage.softlayer.net/cf-courses-data/CognitiveClass/DA0101EN/automobileEDA.csv"
df = pd.read_csv(path)
r=[]
max_degrees = 10
y = df['price'].astype('float')
x = df[['horsepower', 'curb-weight', 'engine-size', 'highway-mpg']].astype('float')
for i in range(1,max_degrees+1):
Input = [('scale', StandardScaler()), ('polynomial', PolynomialFeatures(degree=i)), ('model', LinearRegression())]
pipe = Pipeline(Input)
pipe.fit(x,y)
yhat = pipe.predict(x)
r.append(mean_squared_error(yhat, y))
print("MSE for MLR of degree "+str(i)+" = "+str(round(mean_squared_error(yhat, y)/1e6,1)))
plt.figure(figsize=(10,3))
plt.plot(list(range(1,max_degrees+1)),r)
plt.show()
结果: