metrics.ndcg_score is busted #9921
Description
Description
metrics.ndcg_score is busted
Steps/Code to Reproduce
from sklearn import metrics
# test 1
y_true = [0, 1, 2, 1]
y_score = [[0.15, 0.55, 0.2], [0.7, 0.2, 0.1], [0.06, 0.04, 0.9], [0.1, 0.3, 0.6]]
metrics.ndcg_score(y_true, y_score)
# test 2
y_true = [0, 1, 0, 1]
y_score = [[0.15, 0.85], [0.7, 0.3], [0.06, 0.94], [0.7, 0.3]]
metrics.ndcg_score(y_true, y_score)Expected Results
No error is thrown.
Actual Results
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-3-35bb0e2c9b0e> in <module>()
----> 1 metrics.ndcg_score(y_true, y_score)
/Users/iancassidy/virtualenvs/upside/lib/python2.7/site-packages/sklearn/metrics/ranking.py in ndcg_score(y_true, y_score, k)
849
850 if binarized_y_true.shape != y_score.shape:
--> 851 raise ValueError("y_true and y_score have different value ranges")
ValueError: y_true and y_score have different value ranges
Versions
Darwin-16.7.0-x86_64-i386-64bit
('Python', '2.7.10 (default, Feb 7 2017, 00:08:15) \n[GCC 4.2.1 Compatible Apple LLVM 8.0.0 (clang-800.0.34)]')
('NumPy', '1.13.3')
('SciPy', '0.19.1')
('Scikit-Learn', '0.19.0')