《Python数据科学手册》-简单线性回归、多项式回归、学习曲线、网格搜索学习笔记

一、线性回归

import matplotlib.pyplot as plt
import seaborn as sns
sns.set()   #设置图形样式
import numpy as np

#简单线性回归
'''
创造数据
'''
rng = np.random.RandomState(1)
x = 10 * rng.rand(50)
y = 2 * x - 5 + rng.rand(50)

from sklearn.linear_model import LinearRegression
model = LinearRegression(fit_intercept=True)
model.fit(x[:, np.newaxis], y)
xfit = np.linspace(0, 10, 1000)
yfit = model.predict(xfit[:, np.newaxis])
plt.scatter(x, y, s = 10, color = 'black')
plt.plot(xfit, yfit, color = 'red')
plt.show()

print("Model slope:", model.coef_[0])   #斜率
print("Model intercept:", model.intercept_)    #截距

结果1：

结果2：

Model slope: 2.0082302432277497
Model intercept: -4.533652972099125

二、多项式回归

from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import LinearRegression
from sklearn.pipeline import make_pipeline


def PolynomialRegression(degree = 2, **kwargs):
    return make_pipeline(PolynomialFeatures(degree),
                         LinearRegression(**kwargs))

#创造些数据
import numpy as np
'''
定义函数，创建数据
'''
def make_data(N, err = 1.0, rseed = 1):
    # 随机抽样数据
    rng = np.random.RandomState(rseed)
    X = rng.rand(N,