数据降维——KernelPCA

模型原型
class sklearn.decomposition.KernelPCA(n_components=None,kernel=’linear’,gamma=None,degress=3,coef0=1,kernel_params=None,alpha=1.0,fit_inverse_transform=False,eigen_solver=’auto’,tol=0,max_iter=None,remove_zero_eig=False)
参数

• n_components
• kernel:指定核函数
  
  • ’linear’:线性核
    $$K(\vec{x},\vec{z})=\vec{x}\cdot\vec{z}$$
  • ‘poly’:多项式核
    $$K(\vec{x},\vec{z})=(\gamma(\vec{x}\cdot\vec{z}+1)+r)^p$$
  • ‘rbf’:高斯核函数
    $$K(\vec{x},\vec{z})=exp(-\gamma||\vec{x}-\vec{z}||^2)$$
  • ‘sigmoid’:
    $$K(\vec{x},\vec{z})=tanh(\gamma(\vec{x}\cdot\vec{z})+r)$$
  • ‘precomputed’:表示提供kernel matrix提供一个可调用对象:用于计算kernel matrix
• gamma
  
  • 核函数为’rbf’,’poly’,’sigmoid’时:核函数的系数
  • ‘auto’:系数为1/n_features
• degree:当核函数是多项式时，指定多项式的系数，对于其他核函数无效
• coef0:指定函数中的自由项（当核函数是’poly’和’sigmoid’有效时才使用它）
• kernel_params:当核函数是可调用对象时才使用它
• alpha:岭回归的超参数，用于计算逆转换矩阵（当fit_inverse_transform=True时有效）
• fit_inverse_transform:当为True时,用于计算逆转换矩阵
• eigen_solver:指定求解特征值的算法
  
  • ’auto’:自动选择
  • ‘dense’:dense特征值求解器
  • ‘arpack’:arpack特征值求解器,用于特征数量远小于样本数量的情形
• tol:指定arpock特征值求解器的收敛阙值（0表示自动选择阙值）
• max_iter:指定arpock特征值求解器的最大迭代次数（None表示自动选择）
• remove_zero_eig:如果为True则会移除所有为零的特征值;n_coments=None也会移除所有为零的特征值

属性
- lambdas_:核化矩阵的特征值
- alphas:核化矩阵的特征向量
- dual_coef_:逆转换矩阵

方法
- fit(X[,y])
- transform(X)
- fit_transform(X,[,y])
- inverse_transform(X)

import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets,decomposition,manifold

加载数据

def load_data():
    iris=datasets.load_iris()
    return iris.data,iris.target

使用PCA类

def test_KPCA(*data):
    X,y=data
    kernels=['linear','poly','rbf','sigmoid']
    for kernel in kernels:
        kpca=decomposition.KernelPCA(n_components=None,kernel=kernel)
        kpca.fit(X)
        print('kernel=%s --> lambdas:%s '%(kernel,kpca.lambdas_))

X,y=load_data()
test_KPCA(X,y)

降维后样本分布图

def polt_KPCA(*data):
    X,y=data
    kernels=['linear','poly','rbf','sigmoid']
    fig=plt.figure()
    colors=((1,0,0),(0,1,0),(0,0,1),(0.5,0.5,0),(0,0.5,0.5),(0.5,0,0.5),
           (0.4,0.6,0),(0.6,0.4,0),(0,0.6,0.4),(0.5,0.3,0.2))
    for i ,kernel in enumerate(kernels):
        kpca=decomposition.KernelPCA(n_components=2,kernel=kernel)
        kpca.fit(X)
        X_r=kpca.transform(X)
        ax=fig.add_subplot(2,2,i+1)
        for label,color in zip(np.unique(y),colors):
            position=y==label
            ax.scatter(X_r[position,0],X_r[position,1],label='target=%d'%label,color=color)
        ax.set_xlabel('X[0]')
        ax.set_ylabel('X[1]')
        ax.legend(loc='best')
        ax.set_title('kernel=%s'%kernel)
    plt.suptitle('KPCA')
    plt.show()

polt_KPCA(X,y)

多项式核的参数影响

def plot_KPC_poly(*data):
    X,y=data
    fig=plt.figure()
    colors=((1,0,0),(0,1,0),(0,0,1),(0.5,0.5,0),(0,0.5,0.5),(0.5,0,0.5),
           (0.4,0.6,0),(0.6,0.4,0),(0,0.6,0.4),(0.5,0.3,0.2),)
    Params=[(3,1,1),(3,10,1),(3,1,10),(3,10,10),(10,1,1),(10,10,1),(10,1,10),(10,10,10)]
    for i,(p,gamma,r) in enumerate(Params):
        kpca=decomposition.KernelPCA(n_components=2,kernel='poly',gamma=gamma,degree=p,coef0=r)
        kpca.fit(X)
        X_r=kpca.transform(X)
        ax=fig.add_subplot(2,4,i+1)
        for label,color in zip(np.unique(y),colors):
            position=y==label
            ax.scatter(X_r[position,0],X_r[position,1],label='target=%d'%label,color=color)
        ax.set_xlabel("X[0]")
        ax.set_xticks([])
        ax.set_yticks([])
        ax.set_ylabel('X[1]')
        ax.legend(loc='best')
        ax.set_title(r'$(%s(x \cdot z+1)+%s)^{%s}$'%(gamma,r,p))
    plt.suptitle('KPCA-Poly')
    plt.show()

plot_KPC_poly(X,y)

高斯核的参数影响

def plot_KPCA_rbf(*data):
    X,y=data
    fig=plt.figure()
    colors=((1,0,0),(0,1,0),(0,0,1),(0.5,0.5,0),(0,0.5,0.5),(0.5,0,0.5),
           (0.4,0.6,0),(0.6,0.4,0),(0,0.6,0.4),(0.5,0.3,0.2),)
    Gammas=[0.5,1,4,10]
    for i,gamma in enumerate(Gammas):
        kpca=decomposition.KernelPCA(n_components=2,kernel='rbf',gamma=gamma)
        kpca.fit(X)
        X_r=kpca.transform(X)
        ax=fig.add_subplot(2,2,i+1)
        for label,color in zip(np.unique(y),colors):
            position=y==label
            ax.scatter(X_r[position,0],X_r[position,1],label='target=%d'%label,color=color)
        ax.set_xlabel('X[0]')
        ax.set_xticks([])
        ax.set_yticks([])
        ax.set_ylabel('X[1]')
        ax.legend(loc='best')
        ax.set_title(r'\exp(-%s||x-z||^2)$'%gamma)
    plt.suptitle('KPCA-rbf')
    plt.show()

plot_KPCA_rbf(X,y)

sigmoid核的参数影响

def plot_KPCA_sigmoid(*data):
    X,y=data
    fig=plt.figure()
    colors=((1,0,0),(0,1,0),(0,0,1),(0.5,0.5,0),(0,0.5,0.5),(0.5,0,0.5),
           (0.4,0.6,0),(0.6,0.4,0),(0,0.6,0.4),(0.5,0.3,0.2),)
    Params=[(0.01,0.1),(0.01,0.2),(0.1,0.1),(0.1,0.2),(0.2,0.1),(0.2,0.2)]
    for i,(gamma,r) in enumerate(Params):
        kpca=decomposition.KernelPCA(n_components=2,kernel='sigmoid',gamma=gamma,coef0=r)
        kpca.fit(X)
        X_r=kpca.transform(X)
        ax=fig.add_subplot(3,2,i+1)
        for label,color in zip(np.unique(y),colors):
            position=y==label
            ax.scatter(X_r[position,0],X_r[position,1],label='target=%d'%label,color=color)
        ax.set_xlabel('X[0]')
        ax.set_xticks([])
        ax.set_yticks([])
        ax.set_ylabel('X[1]')
        ax.legend(loc='best')
        ax.set_title(r'$tanh(%s(x\cdot z)+%s)$'%(gamma,r))
    plt.suptitle('KPCA-sigmoid')
    plt.show()

plot_KPCA_sigmoid(X,y)