def dcg_at_k()

in next_steps/data_science/offline_performance_evaluation/metrics.py [0:0]

• 10 lines of code
• 4 McCabe index (conditional complexity)

def dcg_at_k(r, k, method=0):
    """Score is discounted cumulative gain (dcg)

    Relevance is positive real values.  Can use binary
    as the previous methods.

    Example from
    http://www.stanford.edu/class/cs276/handouts/EvaluationNew-handout-6-per.pdf
    >>> r = [3, 2, 3, 0, 0, 1, 2, 2, 3, 0]
    >>> dcg_at_k(r, 1)
    3.0
    >>> dcg_at_k(r, 1, method=1)
    3.0
    >>> dcg_at_k(r, 2)
    5.0
    >>> dcg_at_k(r, 2, method=1)
    4.2618595071429155
    >>> dcg_at_k(r, 10)
    9.6051177391888114
    >>> dcg_at_k(r, 11)
    9.6051177391888114

    Args:
        r: Relevance scores (list or numpy) in rank order
            (first element is the first item)
        k: Number of results to consider
        method: If 0 then weights are [1.0, 1.0, 0.6309, 0.5, 0.4307, ...]
                If 1 then weights are [1.0, 0.6309, 0.5, 0.4307, ...]

    Returns:
        Discounted cumulative gain
    """
    r = np.asfarray(r)[:k]
    if np.size(r):
        if method == 0:
            return r[0] + np.sum(r[1:] / np.log2(np.arange(2, np.size(r) + 1)))
        elif method == 1:
            return np.sum(r / np.log2(np.arange(2, np.size(r) + 2)))
        else:
            raise ValueError('method must be 0 or 1.')
    return 0.