feature_selection_using_cmeans.py 文件源码

def selecttop(CF, k):
    """
        Finds cosine similarity between SC and Wi and returns index of top features
    """
    NCF = np.zeros((CF.shape[1],CF.shape[1]))
    for i in range(CF.shape[1]):
        for j in range(CF.shape[1]):
            if (CF[i,j]+CF[j,j]-CF[i,j]) !=0:
                NCF[i,j]=CF[i,j]/(CF[i,j]+CF[j,j]-CF[i,j])
            else:
                NCF[i,j]=0

    SC = np.zeros(CF.shape[1])
    for i in range(CF.shape[1]):
        SC[i] = np.sum(NCF[i,:])

    print(np.isnan(SC).any())
    print(np.isnan(CF).any())
    cosim = cosine_similarity(SC,CF)
    return (-cosim).argsort()[0][:int(k*CF.shape[1])]

#Loading CF matrix for each cluster