2999e509688a82f8be65600727a5922b5739822b,conceptnet5/vectors/evaluation/wordsim.py,,compute_semeval_score,#Any#Any#,309

Before Change

        low_harmonic_mean = float("NaN")
        high_harmonic_mean = float("NaN")
    else:
        acc_harmonic_mean = hmean([spearman_score["acc"], pearson_score["acc"]])
        low_harmonic_mean = hmean([spearman_score["low"], pearson_score["low"]])
        high_harmonic_mean = hmean([spearman_score["high"], pearson_score["high"]])

    return pd.Series(
        [acc_harmonic_mean, low_harmonic_mean, high_harmonic_mean],
        index=["acc", "low", "high"]
    )


def evaluate_semeval_monolingual(vectors, lang):
    

After Change

    measure was 0 or negative. Otherwise, take a harmonic mean of a Pearson correlation coefficient
    and a Spearman correlation coefficient.
    
    intervals = ["acc", "low", "high"]
    scores = []
    for interval in intervals:
        if any(np.isnan(x) for x in [spearman_score[interval], pearson_score[interval]]):
            scores.append(float("NaN"))
        elif any(x <= 0 for x in [spearman_score[interval], pearson_score[interval]]):
            scores.append(0)
        else:
            scores.append(hmean([spearman_score[interval], pearson_score[interval]]))

    return pd.Series(
        scores,
        index=intervals
    )


def evaluate_semeval_monolingual(vectors, lang):
    

Instances