sklearn.metrics.precision_recall_fscore_support
https://scikit-learn.org/stable/modules/generated/sklearn.metrics.precision_recall_fscore_support.html
#Classification_metrics_(sklearn)
Compute precision, recall, F-measure and support for each class.
sklearn.metrics.precision_score
sklearn.metrics.recall_score
sklearn.metrics.f1_score
一発で返してくれて便利そう
具体スコアの実装ではこれを共通で使っている
例：fbeta_score https://github.com/scikit-learn/scikit-learn/blob/1.3.0/sklearn/metrics/_classification.py#L1411
precision_recall_fscore_supportの例
実装 https://github.com/scikit-learn/scikit-learn/blob/1.3.0/sklearn/metrics/_classification.py#L1551
_check_zero_division関数を呼び出して、zero_division_value（zero_divisionの場合の値）を得る
ref: https://github.com/scikit-learn/scikit-learn/blob/1.3.0/sklearn/metrics/_classification.py#L1720
_check_zero_division関数 https://github.com/scikit-learn/scikit-learn/blob/1.3.0/sklearn/metrics/_classification.py#L48
文字列の"warn"だったら、intやfloatの0や1だったら
sklearn.metrics.multilabel_confusion_matrixを呼び出す
ref: https://github.com/scikit-learn/scikit-learn/blob/1.3.0/sklearn/metrics/_classification.py#L1725-L1731
TODO
_nanaverage
_prf_divide
_warn_prf
テスト
https://github.com/scikit-learn/scikit-learn/blob/1.3.0/sklearn/metrics/tests/test_classification.py#L228-L347
https://github.com/scikit-learn/scikit-learn/blob/1.3.0/sklearn/metrics/tests/test_classification.py#L985-L1089