knn_scikit.py 文件源码

def k_vs_rms(START_K, END_K, STEP_K, training_data, labels, test_data, expected_labels, weights='distance'):
    num_points = int((END_K - START_K) / STEP_K) + 1
    points = np.zeros([num_points, 2])
    index = -1
    for K in range(START_K, END_K, STEP_K):
        print "k = " + str(K)
        index += 1
        output = knn_regression(K, training_data, labels, test_data, weights)
        v = np.column_stack((output, expected_labels))
        v = v[~np.isnan(v[:,0]),:]
        RMSE = mean_squared_error(v[:,0], v[:,1])**0.5
        points[index,0] = K
        points[index,1] = RMSE
    if points[-1,0] == 0 and points[-1,1] == 0:
        points = points[:-1,:]
    return points

# Test parameters