PCA.py 文件源码

def PCA(dataset, topFeatNum = 2):
    #????
    #1???????????? 
    #2??????????? 
    #3?????????????? 
    #4???xx?????????? 
    #5?????????????
    datasetMat = np.mat(dataset)
    meanValues = np.mean(datasetMat, axis = 0)
    stds = np.std(datasetMat, axis = 0)
    adjustedDatasetMat = datasetMat - meanValues
    adjustedDatasetMat = adjustedDatasetMat / stds
    plt.plot(adjustedDatasetMat[:, 0], adjustedDatasetMat[:, 1], "r^")
    plt.show()
    covMat = np.cov(adjustedDatasetMat, rowvar = 0)
    #covMat = (adjustedDatasetMat.T * adjustedDatasetMat) / datasetMat.shape[0] #?????0????????
    eigenVals, eigenVecs = np.linalg.eig(np.mat(covMat))
    draw(eigenVals) #?????????????????
    eigenValsIndex = np.argsort(eigenVals) #?eigenVals???????????????
    eigenValsIndex = eigenValsIndex[: -(topFeatNum+1) : -1] #??eigenVals???topFeatNum?????
    eigenVecs = eigenVecs[:, eigenValsIndex] #????topFeatNum????????eigenValues????
    transformedDatasetMat = adjustedDatasetMat * eigenVecs

    return transformedDatasetMat