def replaceNanWithMeam():
datMat = pca.loadDataSet("./data/secom.data", " ")
numFeat = shape(datMat)[1]
for i in range(numFeat):
meanVal = mean(datMat[nonzero(~isnan(datMat[:, i].A))[0], i])
datMat[nonzero(isnan(datMat[:, i].A))[0], i] = meanVal
return datMat
def replaceNanWithMean():
datMat = pca.loadDataSet('secom.data', ' ')
numFeat = shape(datMat)[1]
for i in range(numFeat):
meanVal = mean(datMat[nonzero(~isnan(datMat[:,i].A))[0],i]) #values that are not NaN (a number)
datMat[nonzero(isnan(datMat[:,i].A))[0],i] = meanVal #set NaN values to mean
return datMat
def replaceNanWithMean():
datMat = pca.loadDataSet('secom.data', ' ')
numFeat = shape(datMat)[1]
for i in range(numFeat):
meanVal = mean(datMat[nonzero(~isnan(datMat[:, i].A))[0],
i]) #values that are not NaN (a number)
datMat[nonzero(isnan(datMat[:, i].A))[0],
i] = meanVal #set NaN values to mean
return datMat
def replaceNanWithMean():
datMat = pca.loadDataSet(
'/Users/weiwenjing/Desktop/M.L./machinelearninginaction/Ch13/secom.data',
' ')
numFeat = shape(datMat)[1]
for i in range(numFeat):
meanVal = mean(datMat[nonzero(~isnan(datMat[:, i].A))[0],
i]) #values that are not NaN (a number)
datMat[nonzero(isnan(datMat[:, i].A))[0],
i] = meanVal #set NaN values to mean
return datMat
def replaceNanWithMean():
datMat = pca.loadDataSet('secom.data', ' ')
numFeat = shape(datMat)[1]
for i in range(numFeat):
meanVal = mean(datMat[nonzero(~isnan(datMat[:, i].A))[0],
i]) # 求非NAN值的平均值
datMat[nonzero(isnan(datMat[:, i]))[0], i] = meanVal
return datMat
import numpy as np
from numpy import *
import matplotlib.pyplot as plt
def is_num(str):
try:
if str == 'NaN':
return False
float(str)
return True
except ValueError:
return False
datastring = pca.loadDataSet('imports-85.data', ',')
relist = [[], [],
[
'alfa-romero', 'audi', 'bmw', 'chevrolet', 'dodge', 'honda',
'isuzu', 'jaguar', 'mazda', 'mercedes-benz', 'mercury',
'mitsubishi', 'nissan', 'peugot', 'plymouth', 'porsche',
'renault', 'saab', 'subaru', 'toyota', 'volkswagen', 'volvo'
], ['diesel', 'gas'], ['std', 'turbo'], ['four', 'two'],
['hardtop', 'wagon', 'sedan', 'hatchback', 'convertible'],
['4wd', 'fwd', 'rwd'], ['front', 'rear'], [], [], [], [], [],
['dohc', 'dohcv', 'l', 'ohc', 'ohcf', 'ohcv', 'rotor'],
[
'', '', 'two', 'three', 'four', 'five', 'six', '', 'eight', '',
'', '', 'twelve'
], [],
['1bbl', '2bbl', '4bbl', 'idi', 'mfi', 'mpfi', 'spdi',
ycord1.append(y)
elif groupNum == 2:
x = r0 + 0.0
y = 1.0 * r1 + x
xcord2.append(x)
ycord2.append(y)
fw.write("%f\t%f\t%d\n" % (x, y, groupNum))
fw.close()
fig = plt.figure()
ax = fig.add_subplot(211)
ax.scatter(xcord0, ycord0, marker='^', s=90)
ax.scatter(xcord1, ycord1, marker='o', s=50, c='red')
ax.scatter(xcord2, ycord2, marker='v', s=50, c='yellow')
ax = fig.add_subplot(212)
myDat = pca.loadDataSet('../data/ch13/testSet3.txt')
lowDDat, reconDat = pca.pca(myDat[:, 0:2], 1)
label0Mat = lowDDat[np.nonzero(
myDat[:, 2] == 0)[0], :2][0] # get the items with label 0
label1Mat = lowDDat[np.nonzero(
myDat[:, 2] == 1)[0], :2][0] # get the items with label 1
label2Mat = lowDDat[np.nonzero(
myDat[:, 2] == 2)[0], :2][0] # get the items with label 2
ax.scatter(label0Mat[:, 0].tolist(),
np.zeros(np.shape(label0Mat)[0]),
marker='^',
s=90)
ax.scatter(label1Mat[:, 0].tolist(),
np.zeros(np.shape(label1Mat)[0]),
marker='o',
s=50,
x = r0 + 8.0
y = 1.0*r1 + x
xcord1.append(x)
ycord1.append(y)
elif groupNum == 2:
x = r0 + 0.0
y = 1.0*r1 + x
xcord2.append(x)
ycord2.append(y)
fw.write("%f\t%f\t%d\n" % (x, y, groupNum))
fw.close()
fig = plt.figure()
ax = fig.add_subplot(211)
ax.scatter(xcord0,ycord0, marker='^', s=90)
ax.scatter(xcord1,ycord1, marker='o', s=50, c='red')
ax.scatter(xcord2,ycord2, marker='v', s=50, c='yellow')
ax = fig.add_subplot(212)
myDat = pca.loadDataSet('testSet3.txt')
lowDDat,reconDat = pca.pca(myDat[:,0:2],1)
label0Mat = lowDDat[nonzero(myDat[:,2]==0)[0],:2][0] #get the items with label 0
label1Mat = lowDDat[nonzero(myDat[:,2]==1)[0],:2][0] #get the items with label 1
label2Mat = lowDDat[nonzero(myDat[:,2]==2)[0],:2][0] #get the items with label 2
#ax.scatter(label0Mat[:,0],label0Mat[:,1], marker='^', s=90)
#ax.scatter(label1Mat[:,0],label1Mat[:,1], marker='o', s=50, c='red')
#ax.scatter(label2Mat[:,0],label2Mat[:,1], marker='v', s=50, c='yellow')
ax.scatter(label0Mat[:,0],zeros(shape(label0Mat)[0]), marker='^', s=90)
#ax.scatter(label1Mat[:,0],zeros(shape(label1Mat)[0]), marker='o', s=50, c='red')
#ax.scatter(label2Mat[:,0],zeros(shape(label2Mat)[0]), marker='v', s=50, c='yellow')
plt.show()
#!/usr/bin/env python3
#-*- coding: UTF-8 -*-
from numpy import *
import pca
import matplotlib
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)
'''
Created on Jun 1, 2011
@author: Peter
'''
from numpy import *
import matplotlib
import matplotlib.pyplot as plt
import pca
dataMat = pca.loadDataSet('testSet.txt')
lowDMat, reconMat = pca.pca(dataMat, 1)
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(dataMat[:, 0], dataMat[:, 1], marker='^', s=90)
ax.scatter(reconMat[:, 0], reconMat[:, 1], marker='o', s=50, c='red')
plt.show()
# coding=utf-8
from numpy import shape, zeros
import matplotlib.pyplot as plt
import pca
sampMtx = pca.loadDataSet("testSet3.txt")
lowDDataMat, reconMat = pca.pca(sampMtx, 2)
print shape(lowDDataMat)
print lowDDataMat
print '-------'
print reconMat
fig = plt.figure()
ax = fig.add_subplot('221')
ax.scatter(sampMtx[:, 0].flatten().A[0], sampMtx[:, 1].flatten().A[0], s=10)
y = zeros(shape(lowDDataMat))
ax.scatter(reconMat[:, 0].flatten().A[0],
reconMat[:, 1].flatten().A[0],
marker='o',
s=10,
c='red')
ax2 = fig.add_subplot('222')
ax2.scatter(lowDDataMat[:].flatten().A[0], y[:], s=10, c='green')
print '变换后的坐标'
ax = fig.add_subplot('223')
ax.scatter(reconMat[:, 0].flatten().A[0], reconMat[:, 1].flatten().A[0], s=10)
fig.show()
''' Created on Jun 1, 2011 @author: Peter ''' from numpy import * import matplotlib import matplotlib.pyplot as plt import pca import os homedir = os.getcwd() + '/machinelearninginaction/ch13/' dataMat = pca.loadDataSet(homedir + 'testSet.txt') lowDMat, reconMat = pca.pca(dataMat, 1) fig = plt.figure() ax = fig.add_subplot(111) ax.scatter(dataMat[:, 0], dataMat[:, 1], marker='^', s=90) ax.scatter(reconMat[:, 0], reconMat[:, 1], marker='o', s=50, c='red') plt.show()
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# @Time : 2019/3/1 19:18
# @Author : Arrow and Bullet
# @FileName: run.py
# @Software: PyCharm
# @Blog ：https://blog.csdn.net/qq_41800366
import pca
from numpy import *
import matplotlib
import matplotlib.pyplot as plt
dataMat = pca.loadDataSet("./data/testSet.txt")
lowDMat, reconMat = pca.pca(dataMat, 2)
m, n = shape(lowDMat)
print(m, n)
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")
fig.show()
def test1():
dataMat = pca.loadDataSet('testSet.txt')
#pca.plot1(dataMat)
lowDMat, reconMat = pca.pca(dataMat, 1)
pca.plot2(dataMat, reconMat)
"""
把数据集中所有的NAN替换为平均值
:param datMat: 带有NaN的数据集
:return: 替换后的数据集
"""
numFeast = shape(datMat)[1]
for i in range(numFeast):
#对value不为NaN的求均值
meanVal = mean(datMat[nonzero(~isnan(datMat[:, i].A))[0], i])
#将value为NaN的值赋值为均值
datMat[nonzero(isnan(datMat[:,i].A))[0],i] = meanVal
return datMat
if __name__ == '__main__':
#加载数据
NonedatMat = pca.loadDataSet(r'C:\Users\v_wangdehong\PycharmProjects\MachineLearning_V\12.PCA\data\secom.data', ' ')
#替换数据集中所有的NAN
datMat = replaceNanWithMean(NonedatMat)
#去除均值
meanVals = mean(datMat,axis=0)
meanRemoved = datMat - meanVals
#计算协方差矩阵
covMat = cov(meanRemoved,rowvar=0)
#对该矩阵进行特征值分析
eigVals,eigVects = linalg.eig(mat(covMat))
print(eigVals)
print(eigVects)
"""
我们会看到一大堆值，但是其中很多值都是0，这就意味着这些特征都是其他特征的副本，也就是说，它们可以通过其他特征表示，而本身没有提供额外信息。
"""
lowDat,reconMat = pca.pca(datMat,40)
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# author:yiluzhang
import pca
if __name__ == "__main__":
data_mat = pca.loadDataSet("testSet.txt")
low_mat, recon_mat = pca.pca(data_mat, 1)
# -*- coding: utf-8 -*-
"""
Created on Wed May 17 14:26:16 2017
@author: 凯风
"""
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
def test_2():
dataMat = pca.loadDataSet('testSet.txt')
lowDMat, recomMat = pca.pca(dataMat, 2)
print lowDMat
print "---"
print recomMat
def test_590():
dataMat = pca.loadDataSet('secom.data')
lowDMat, recomMat = pca.pca(dataMat, 2)
print lowDMat
print "---"
print recomMat
