def test2():
dataMat = pca.replaceNanWithMean()
meanVals = mean(dataMat, axis=0)
meanRemoved = dataMat - meanVals
covMat = cov(meanRemoved, rowvar=0)
eigVals, eigVects = linalg.eig(mat(covMat))
print(eigVals)
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(eigVals[:8])
plt.show()
#coding:utf-8
from numpy import *
import matplotlib
import matplotlib.pyplot as plt
import pca
dataMat = pca.replaceNanWithMean()
#below is a quick hack copied from pca.pca()
meanVals = mean(dataMat, axis=0)
meanRemoved = dataMat - meanVals #remove mean
covMat = cov(meanRemoved, rowvar=0)
eigVals,eigVects = linalg.eig(mat(covMat))
eigValInd = argsort(eigVals) #sort, sort goes smallest to largest
eigValInd = eigValInd[::-1]#reverse
sortedEigVals = eigVals[eigValInd]
total = sum(sortedEigVals)
varPercentage = sortedEigVals/total*100
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(range(1, 21), varPercentage[:20], marker='^')
plt.xlabel('Principal Component Number')
plt.ylabel('Percentage of Variance')
plt.show()
import matplotlib.pyplot as plt
from pylab import *
dataMat=pca.loadDataSet('testSet.txt')
print(shape(dataMat))
lowDMat,reconMat=pca.pca(dataMat,1)
print(shape(lowDMat))
fig=plt.figure(1)
ax=fig.add_subplot(111)
ax.scatter(dataMat[:,0].flatten().A[0],reconMat[:,1].flatten().A[0],marker='^',s=90)
ax.scatter(reconMat[:,0].flatten().A[0],reconMat[:,1].flatten().A[0],marker='o',s=50,c='red')
show()
lowDMat,reconMat=pca.pca(dataMat,2)
print(shape(lowDMat))
fig2=plt.figure(2)
ax=fig2.add_subplot(111)
ax.scatter(dataMat[:,0].flatten().A[0],reconMat[:,1].flatten().A[0],marker='^',s=90)
ax.scatter(reconMat[:,0].flatten().A[0],reconMat[:,1].flatten().A[0],marker='o',s=50,c='red')
show()
dataMat=pca.replaceNanWithMean()
meanVals=mean(dataMat,axis=0)
meanRemoved=dataMat-meanVals
covMat=cov(meanRemoved,rowvar=0)
eigVals,eigVects=linalg.eig(mat(covMat))
print(eigVals) # 特征值
"""
import pca
from imp import reload
import numpy as np
import matplotlib.pyplot as plt
reload(pca)
dataMat = pca.loadDataSet('testSet.txt') # 读取数据，这个数据集是二维的
lowDMat, reconMat = pca.pca(dataMat, 1) # 降维
np.shape(lowDMat)
# 画图
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(dataMat[:, 0].flatten().A[0],
dataMat[:, 1].flatten().A[0],
marker='^',
s=90)
ax.scatter(reconMat[:, 0].flatten().A[0],
reconMat[:, 1].flatten().A[0],
marker='o',
s=50,
c='red')
# 在500维的数据上进行降维
reload(pca)
dataMat = pca.replaceNanWithMean() # 获取处理后的数据
pca.createFig() # 根据这个可以看到特征数量在20左右就覆盖了数据集的绝大部分的方差了，可以根据这个选择降维的参数
lowDMat, reconMat = pca.pca(dataMat, 20) # 降维