Merge branch 'master' of https://github.com/apachecn/MachineLearning

src/python/13.PCA/pca.py

@@ -0,0 +1,45 @@
+#!/usr/bin/python
+# coding:utf8
+
+'''
+Created on Jun 1, 2011
+Update on 2017-04-06
+@author: Peter Harrington/片刻
+'''
+print(__doc__)
+from numpy import *
+
+
+def loadDataSet(fileName, delim='\t'):
+    fr = open(fileName)
+    stringArr = [line.strip().split(delim) for line in fr.readlines()]
+    datArr = [map(float,line) for line in stringArr]
+    return mat(datArr)
+
+
+def pca(dataMat, topNfeat=9999999):
+    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[:-(topNfeat+1):-1]  #cut off unwanted dimensions
+    redEigVects = eigVects[:,eigValInd]       #reorganize eig vects largest to smallest
+    lowDDataMat = meanRemoved * redEigVects#transform data into new dimensions
+    reconMat = (lowDDataMat * redEigVects.T) + meanVals
+    return lowDDataMat, reconMat
+
+
+def replaceNanWithMean():
+    datMat = 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
+
+
+if __name__ == "__main__":
+    dataMat = loadDataSet('data/13.PCA/testSet.txt')
+    lowDmat, reconMat = pca(dataMat, 1)
+    print shape(lowDmat)