analyze_predictions.py 文件源码

def compare_clusters(X,Y,method='spectral',s=10000):
    A = (X/np.linalg.norm(X,axis=0)).T
    A[np.isnan(A)] = 0
    B = (Y/np.linalg.norm(Y,axis=0)).T
    B[np.isnan(B)] = 0
    random_samples = np.zeros(A.shape[0],dtype=np.bool)
    random_samples[:min(s,A.shape[0])] = True
    np.random.shuffle(random_samples)
    A = A[random_samples]
    B = B[random_samples]
    dA = 1 - A.dot(A.T)
    dA = np.exp(-dA**2/2.)
    dB = 1 - B.dot(B.T)
    dB = np.exp(-dB**2/2.)
    del A,B
    if method == 'spectral':
        n = max(5,min(30,X.shape[1]/50))
        lA = SpectralClustering(n_clusters=n,affinity='precomputed').fit_predict(dA)
        lB = SpectralClustering(n_clusters=n,affinity='precomputed').fit_predict(dB)
    elif method == 'ap':
        lA = AffinityPropagation(affinity='precomputed').fit_predict(dA)
        lB = AffinityPropagation(affinity='precomputed').fit_predict(dB)
    return adjusted_mutual_info_score(lA,lB)