前の章で示したように、モデルの予測は**k**（近傍点の数）の値によって異なる場合があります。k-NNモデルを構築する際には、**最も高いパフォーマンス**を示すk値を選択することが重要です。

一般的な方法として、**交差検証**を用いてモデルのパフォーマンスを評価します。ループを実行し、**さまざまなk値**に対して交差検証スコアを計算し、最も高いスコアを持つものを選択します。これは最も広く使われている手法です。

この作業を行うために、`sklearn`は便利なツールである`GridSearchCV`クラスを提供しています。

`param_grid`パラメータには、キーがパラメータ名、値が試すオプションのリストとなる**辞書**を指定します。たとえば、`1`に対して`99`から`n_neighbors`までの値をテストする場合、次のように記述します。
```python
param_grid = {'n_neighbors': range(1, 100)}
```
`.fit(X, y)`オブジェクトで`GridSearchCV`メソッドを呼び出すと、パラメータグリッド全体を探索して最適なパラメータを見つけ、その最適なパラメータで**全データセットを使ってモデルを再学習**します。

**最良のスコア**は`.best_score_`属性で取得でき、最適化されたモデルで予測を行うには`.predict()`メソッドを使用します。同様に、**最良のモデル**自体は`.best_estimator_`属性で取得できます。

import unittest
import importlib


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


class TestUserCode(unittest.TestCase):

    def test_param_grid_is_declared(self):
        import user_code

        variable = 'param_grid'
        _dynamic_test(
            self,
            hasattr(user_code, variable),
            f"The `{variable}` variable is declared.",
            f"Expected `{variable}` to be declared."
        )

    def test_para_grid_is_dict(self):
        import user_code

        try:
            condition = isinstance(user_code.param_grid, dict)
            failure_message = f"Expected `param_grid` to be a `dict`, but got `{type(user_code.param_grid).__name__}`."
        except AttributeError:
            condition = False
            failure_message = "The `param_grid` variable is not declared."

        _dynamic_test(
            self,
            condition,
            "`param_grid` is a `dict`.",
            failure_message
        )

    def test_param_grid_is_correct(self):
        import user_code
        expected_value = {'n_neighbors': [3, 9, 18, 27]}

        variable = 'param_grid'
        actual_value = getattr(user_code, variable, None)
        if actual_value is None:
            condition = False
            failure_message = f"The `{variable}` variable is not declared."
        elif isinstance(actual_value, dict):
            condition = actual_value == expected_value
            failure_message = f"Expected `{variable}` to contain `{expected_value}`, but got `{actual_value}`."
        else:
            condition = False
            failure_message = f"`{variable}` is not a `dict`."

        _dynamic_test(
            self,
            condition,
            f"`{variable}` contains the correct values.",
            failure_message
        )

    def test_grid_search_is_declared(self):
        import user_code

        variable = 'grid_search'
        _dynamic_test(
            self,
            hasattr(user_code, variable),
            f"The `{variable}` variable is declared.",
            f"Expected `{variable}` to be declared."
        )

    def test_grid_search_is_correct(self):
        import user_code
        from sklearn.model_selection import GridSearchCV
        from sklearn.neighbors import KNeighborsClassifier

        knn = KNeighborsClassifier()
        param_grid = {'n_neighbors': [3, 9, 18, 27]}

        variable = 'grid_search'
        actual_value = getattr(user_code, variable, None)
        if actual_value is None:
            condition = False
            failure_message = f"The `{variable}` variable is not declared."
        elif isinstance(actual_value, GridSearchCV):
            condition = isinstance(actual_value.estimator, KNeighborsClassifier) and actual_value.param_grid == param_grid and actual_value.cv == 4
            failure_message = f"Expected `{variable}` to be a `GridSearchCV` with `knn` as the model, `4` folds, and `param_grid` as the grid of parameters, but got `estimator={actual_value.estimator}`, `param_grid={actual_value.param_grid}`, and `cv={actual_value.cv}`."
        else:
            condition = False
            failure_message = f"`{variable}` is not a `GridSearchCV`."

        _dynamic_test(
            self,
            condition,
            "`grid_search` is a `GridSearchCV` with `estimator=knn`, `param_grid=param_grid`, and `cv=4`.",
            failure_message
        )

    def test_best_model_is_declared(self):
        import user_code

        variable = 'best_model'
        _dynamic_test(
            self,
            hasattr(user_code, variable),
            f"The `{variable}` variable is declared.",
            f"Expected `{variable}` to be declared."
        )

    def test_best_model_is_correct(self):
        import user_code
        from sklearn.neighbors import KNeighborsClassifier

        variable = 'best_model'
        actual_value = getattr(user_code, variable, None)
        if actual_value is None:
            condition = False
            failure_message = f"The `{variable}` variable is not declared."
        elif isinstance(actual_value, KNeighborsClassifier):
            condition = actual_value.n_neighbors == 27
            failure_message = f"Expected `{variable}` to be a `KNeighborsClassifier` with `27` neighbors, but got `n_neighbors={actual_value.n_neighbors}`."
        else:
            condition = False
            failure_message = f"`{variable}` is not a `KNeighborsClassifier`."

        _dynamic_test(
            self,
            condition,
            "`best_model` is a `KNeighborsClassifier` with `27` neighbors.",
            failure_message
        )

    def test_best_score_is_declared(self):
        import user_code

        variable = 'best_score'
        _dynamic_test(
            self,
            hasattr(user_code, variable),
            f"The `{variable}` variable is declared.",
            f"Expected `{variable}` to be declared."
        )

    def test_best_score_is_correct(self):
        import user_code
        expected_value = 0.8039505464098539

        variable = 'best_score'
        actual_value = getattr(user_code, variable, None)
        if actual_value is None:
            condition = False
            failure_message = f"The `{variable}` variable is not declared."
        elif isinstance(actual_value, float):
            condition = actual_value == expected_value
            failure_message = f"Expected `{variable}` to contain `{expected_value}`, but got `{actual_value}`."
        else:
            condition = False
            failure_message = f"`{variable}` is not a `float`."

        _dynamic_test(
            self,
            condition,
            f"`{variable}` is correct.",
            failure_message
        )


if __name__ == '__main__':
    unittest.main()

test_main.py

Pythonを使用したカテゴリカルな結果を予測するための分類手法を紹介します。分類モデルの構築、トレーニング、評価、決定境界の解釈、一般的なアルゴリズムの実世界データセットへの適用に焦点を当てます。


チャレンジ：最適なK値の選択

解答