import unittest
import importlib
import numpy as np
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split, cross_val_score
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import (
    accuracy_score, precision_score, recall_score, f1_score,
    roc_auc_score, confusion_matrix
)

def _dynamic_test(test_case, condition, success_msg, failure_msg):
    if condition:
        test_case._testMethodName = success_msg
        test_case.assertTrue(True, success_msg)
    else:
        test_case._testMethodName = failure_msg
        test_case.fail(failure_msg)

class TestClassificationMetricsExtended(unittest.TestCase):
    @classmethod
    def setUpClass(cls):
        cls.user = importlib.import_module("user_code")

        data = load_breast_cancer()
        X_train, X_test, y_train, y_test = train_test_split(
            data.data, data.target, test_size=0.3, random_state=42
        )

        model = LogisticRegression(max_iter=1000)
        model.fit(X_train, y_train)
        y_pred = model.predict(X_test)
        y_prob = model.predict_proba(X_test)[:, 1]

        cls.true_metrics = {
            "accuracy": accuracy_score(y_test, y_pred),
            "precision": precision_score(y_test, y_pred),
            "recall": recall_score(y_test, y_pred),
            "f1": f1_score(y_test, y_pred),
            "roc_auc": roc_auc_score(y_test, y_prob),
            "cm": confusion_matrix(y_test, y_pred),
            "mean_cv": cross_val_score(model, data.data, data.target, cv=5).mean(),
        }

    def test_accuracy(self):
        cond = abs(self.user.accuracy - self.true_metrics["accuracy"]) < 1e-6
        _dynamic_test(self, cond, "Accuracy computed correctly.", "Accuracy is incorrect.")

    def test_precision(self):
        cond = abs(self.user.precision - self.true_metrics["precision"]) < 1e-6
        _dynamic_test(self, cond, "Precision computed correctly.", "Precision is incorrect.")

    def test_recall(self):
        cond = abs(self.user.recall - self.true_metrics["recall"]) < 1e-6
        _dynamic_test(self, cond, "Recall computed correctly.", "Recall is incorrect.")

    def test_f1(self):
        cond = abs(self.user.f1 - self.true_metrics["f1"]) < 1e-6
        _dynamic_test(self, cond, "F1 score computed correctly.", "F1 score is incorrect.")

    def test_roc_auc(self):
        cond = abs(self.user.roc_auc - self.true_metrics["roc_auc"]) < 1e-6
        _dynamic_test(self, cond, "ROC–AUC computed correctly.", "ROC–AUC is incorrect.")

    def test_confusion_matrix(self):
        cond = np.array_equal(self.user.cm, self.true_metrics["cm"])
        _dynamic_test(self, cond, "Confusion matrix computed correctly.", "Confusion matrix is incorrect.")

    def test_cross_validation(self):
        cond = abs(self.user.mean_cv - self.true_metrics["mean_cv"]) < 1e-6
        _dynamic_test(self, cond, "Cross-validation mean accuracy computed correctly.", "Cross-validation mean accuracy is incorrect.")

if __name__ == "__main__":
    unittest.main(argv=["first-arg-is-ignored"], exit=False)

test_main.py

Pythonを用いた適切なパフォーマンス指標による教師あり学習モデルの評価に焦点を当てています。回帰および分類の結果を評価する方法、モデルを客観的に比較する方法、指標値を解釈して情報に基づいたモデリングの意思決定を行う方法について説明します。


チャレンジ：分類メトリクス

解答