2020-08-17

代码实现

import numpy as np
from sklearn.linear_model import LinearRegression, RidgeCV, LassoCV, ElasticNetCV
from sklearn.preprocessing import PolynomialFeatures
import matplotlib.pyplot as plt
from sklearn.pipeline import Pipeline
# 处理warning
from sklearn.exceptions import ConvergenceWarning
import matplotlib as mpl
import warnings


def xss(y, y_hat):
    y = y.ravel()
    y_hat = y_hat.ravel()
    # Version 1
    tss = ((y - np.average(y)) ** 2).sum()
    rss = ((y_hat - y) ** 2).sum()
    ess = ((y_hat - np.average(y)) ** 2).sum()
    r2 = 1 - rss / tss
    # print 'RSS:', rss, '\t ESS:', ess
    # print 'TSS:', tss, 'RSS + ESS = ', rss + ess
    tss_list.append(tss)
    rss_list.append(rss)
    ess_list.append(ess)
    ess_rss_list.append(rss + ess)
    # Version 2
    # tss = np.var(y)
    # rss = np.average((y_hat - y) ** 2)
    # r2 = 1 - rss / tss
    corr_coef = np.corrcoef(y, y_hat)[0, 1]
    return r2, corr_coef


if __name__ == "__main__":
    # 设置将某类别的警告忽视
    warnings.filterwarnings(action='ignore', category=ConvergenceWarning)
    # 设置随机数种子，在试验模型中使用，但在工作中很少使用
    np.random.seed(0)
    # 设置输出样式-参数linewidth设置显示宽度
    np.set_printoptions(linewidth=1000)
    # 设置9个点
    N = 9
    # 设置x，0-6等间隔的数加上高斯噪声
    x = np.linspace(0, 6, N) + np.random.randn(N)
    x = np.sort(x)
    # 设置y
    y = x**2 - 4*x - 3 + np.random.randn(N)
    # 设置成列向量,将行变成列
    x.shape = -1, 1
    y.shape = -1, 1


    models = [Pipeline([
        # PolynomialFeatures用来生成关于x的矩阵，其中degree表示多项式的次数，include_bias默认为True表示会包含1
        ('poly', PolynomialFeatures()),
        # fit_intercept = False表示不去计算截距项，避免与上面的include_bias=True重复
        ('linear', LinearRegression(fit_intercept=False))]),
        Pipeline([
            ('poly', PolynomialFeatures()),
            # RidgeCV封装了网格搜索调优，相当于RidgeCV + GridsearchCV,alphas表示正则项
            ('linear', RidgeCV(alphas=np.logspace(-3, 2, 50), fit_intercept=False))]),
        Pipeline([
            ('poly', PolynomialFeatures()),