article_learner.py 文件源码

 复制代码def test_probabilities(model: ClassifierMixin, X: np.array, y: pd.Series,
                       bins: int = 10, threshold: float = 0.5):
    """Print confusion matrix based on class probability."""
    probs = [p[1] for p in model.predict_proba(X)]
    print('\tProbabilities')
    df = pd.DataFrame({'prob': probs, 'label': y})
    step = 1 / bins
    cut_labels = [round(step * f, 1) for f in range(10)]
    by_prob = (df.groupby(pd.cut(df['prob'], bins, labels=cut_labels))
                 .agg(['sum', 'count'])['label'])
    print('\t\tprobs\t1\t0\tacc')
    for index, row in by_prob.iloc[::-1].iterrows():
        ones = row['sum']
        if math.isnan(ones):
            ones = 0
        else:
            ones = int(ones)
        count = row['count']
        zeros = int(count) - ones
        if count > 0:
            acc = zeros / count if index < threshold else ones / count
        else:
            acc = 0.0
        print(f'\t\t{index}\t{ones}\t{zeros}\t{acc:.3f}')