Matplotlib笔记-PCA

显示PCA中主成分方差占比情况：

from numpy import *

import numpy as np

import matplotlib.pyplot as plt

from matplotlib.pyplot import MultipleLocator

def pca(dataMat, topNfeat=9999999):

    meanVals = mean(dataMat, axis=0) #  calculate the every feat mean

    meanRemoved = dataMat - meanVals #remove mean

    covMat = cov(meanRemoved, rowvar=0)

    eigVals,eigVects = linalg.eig(np.mat(covMat))

#print(eigVals)

    eigValInd = argsort(eigVals)            #sort, sort goes smallest to largest, and return its index.

    eigValInd = eigValInd[:-(topNfeat+1):-1]  #cut off unwanted dimensions



    #plotPolyline(eigVals)

    #reorganize eig vects largest to smallest

    redEigVects = eigVects[:,eigValInd]



    lowDDataMat = meanRemoved * redEigVects #transform data into new dimensions

    reconMat = (lowDDataMat * redEigVects.T) + meanVals # Adding meanVals means every point add the bias data

    # translate the coordinate by adding meanVals



    return lowDDataMat, reconMat

def plotPolyline(eigVals): # eigVals表示根据PCA所获得特征值（可以理解为方差）

eigValsSorted= eigVals[argsort(-eigVals)] # 对输入的numpy.narray进行排序处理，从大到小排序

    covarPercent = eigValsSorted/ eigValsSorted.sum()

    plt.figure()

    X = np.arange(1, len(covarPercent) + 1)

    # plt.stem(X, covarPercent, markerfmt='C1o')

    # plt.plot(X, covarPercent, marker='^', color='r', ls='-', lw=3) #折线图

    plt.plot(X, covarPercent, 'r^-') #折线图

    plt.title("{}".format("主成分方差占比情况"))#显示图名

    ax=plt.gca() #ax为两条坐标轴的实例

    x_major_locator = MultipleLocator(5)

    ax.xaxis.set_major_locator(x_major_locator)

    plt.xlim(0, 20)

    plt.xlabel('主成分目录')

    plt.ylabel('方差的百分比')

    plt.rcParams['font.sans-serif'] = ['Microsoft YaHei']

    plt.show()