B_preprocessing_clustering.py 文件源码

def trainingPCA(features, n_components=256, whiten=True, pca_model_name=None):
    print 'loaded features! {}'.format(features.shape)
    print np.sqrt(sum(features[0,:]**2))

    #print 'Features l2 normalization'
    #features = normalize(features)
    #print np.sqrt(sum(features[0,:]**2))

    print 'Feature PCA-whitenning'
    pca_model = PCA(n_components=n_components, whiten=whiten)
    features = pca_model.fit_transform(features)
    print np.sqrt(sum(features[0,:]**2))

    print 'Features l2 normalization'
    features = normalize(features)
    print np.sqrt(sum(features[0,:]**2))

    if pca_model_name is not None:
        print 'saving model...'
        check_path_file(pca_model_name, create_if_missing=True)
        save_obj(pca_model, pca_model_name)

    print 'done! {}'.format(pca_model_name)

    return pca_model