The evaluation function label_ranking_average_precision_score fails when the sublists are of different sizes. Although I understand that this may be out of implementation convenience, I think this should be documented or at least a more adequate error should be raised.

import numpy as np
from sklearn.metrics import label_ranking_average_precision_score
y_true = np.array([[1, 0, 0], [0, 1]])  #sublists have 3 and 2  elements
y_score = np.array([[0.75, 0.5, 1], [1, 0.1]]) #sublists have 3 and  2 elements

 label_ranking_average_precision_score(y_true, y_score)       

This code fails with an exception:

ValueError: setting an array element with a sequence.