多项式回归没有给出正确的假设

Question

PFB代码，这里X是职位等级的数量（即等级1，等级2 ..），y是工资范围。多项式回归没有给出最佳拟合线，我怎么能算出X = 20。 请建议：）

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

X = [[ 1],[ 2],[ 3],[ 4],[ 5],[ 6],[ 7],[ 8],[ 9],[10]]
y = [45000,50000,60000,80000,110000,150000,200000,300000,500000,1000000]

from sklearn.linear_model import LinearRegression


from sklearn.preprocessing import PolynomialFeatures

poly_reg = PolynomialFeatures(degree = 2)
X_poly = poly_reg.fit_transform(X)


linearReg_2 = LinearRegression()
linearReg_2.fit(X_poly,y)

# plot polynomial linear regression
plt.scatter(X,y, color = "red")
plt.plot(X,linearReg_2.predict(X_poly), color = "blue")
plt.show()

Answer 1

您可以尝试将度数增加到3或4，以获得更合适的匹配。

poly_reg = PolynomialFeatures(degree = 3)

poly_reg = PolynomialFeatures(degree = 4)

要预测新值，您需要将其传递到同一个poly_reg对象，然后使用linearReg_2.predict()

这样的事情：

X_new = [[20]]

# Observe that I used transform() and not fit_transform()
X_new_poly = poly_reg.transform(X_new)

y_new = linearReg_2.predict(X_new_poly)