From 612a8c1aa9aa58e69850517c6253eb0a0f46c533 Mon Sep 17 00:00:00 2001 From: tiphainebrt <330786940+tiphainebrt@users.noreply.github.com> Date: Tue, 10 Nov 2026 16:52:48 +0100 Subject: [PATCH 1/4] Implement OneNearestNeighbor --- sklearn_questions.py | 64 ++++++++++++++++++++++++++++++++++---------- 1 file changed, 50 insertions(+), 14 deletions(-) diff --git a/sklearn_questions.py b/sklearn_questions.py index f65038c6..54f711c2 100644 --- a/sklearn_questions.py +++ b/sklearn_questions.py @@ -28,47 +28,83 @@ from sklearn.utils.multiclass import check_classification_targets -class OneNearestNeighbor(BaseEstimator, ClassifierMixin): - "OneNearestNeighbor classifier." +class OneNearestNeighbor(ClassifierMixin, BaseEstimator): + """OneNearestNeighbor classifier.""" def __init__(self): # noqa: D107 pass def fit(self, X, y): - """Write docstring. - - And describe parameters + """Fit the classifier by storing the training data. + + Parameters + ---------- + X : ndarray of shape (n_samples, n_features) + Training sample. + y : ndarray of shape(n_samples) + Target labels of the training sample. + Returns + ------- + Fitted classifier. """ X, y = check_X_y(X, y) check_classification_targets(y) self.classes_ = np.unique(y) self.n_features_in_ = X.shape[1] - # XXX fix + self.X_train_ = X + self.y_train_ = y return self def predict(self, X): - """Write docstring. - - And describe parameters + """Predict the class of each sample using nearest neighbor classifier. + + Parameters + ---------- + X : ndarray of shape (n_samples, n_features) + Testing sample to classify. + Returns + ---------- + y_pred : ndarray of shape (n_samples) + The classes predicted for each sample """ check_is_fitted(self) X = check_array(X) + + if X.shape[1] != self.n_features_in_: + raise ValueError( + f"X has {X.shape[1]} features, but " + f"{self.__class__.__name__} is expecting " + f"{self.n_features_in_} features as input" + ) + y_pred = np.full( shape=len(X), fill_value=self.classes_[0], dtype=self.classes_.dtype ) - # XXX fix + for i, x in enumerate(X): + distances = np.linalg.norm(self.X_train_ - x, axis=1) + y_pred[i] = self.y_train_[np.argmin(distances)] return y_pred def score(self, X, y): - """Write docstring. - - And describe parameters + """Compute the accuracy of the classifier. + + Parameters + ---------- + X : ndarray of shape (n_samples, n_features) + Testing sample. + y : ndarray of shape(n_samples) + Labels of the testing sample. + + Returns + ---------- + score : float + Fraction of samples correctly classified """ X, y = check_X_y(X, y) y_pred = self.predict(X) - # XXX fix + y_pred = (y_pred == y) / len(y) return y_pred.sum() From b17fbaae86b7be6360a60685e4f465f5c68f5c3b Mon Sep 17 00:00:00 2001 From: tiphainebrt <330786940+tiphainebrt@users.noreply.github.com> Date: Tue, 10 Nov 2026 16:55:34 +0100 Subject: [PATCH 2/4] Complete numpy exercises --- numpy_questions.py | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/numpy_questions.py b/numpy_questions.py index 21fcec4b..c0b53ebd 100644 --- a/numpy_questions.py +++ b/numpy_questions.py @@ -37,11 +37,11 @@ def max_index(X): If the input is not a numpy array or if the shape is not 2D. """ - i = 0 - j = 0 - - # TODO - + if not isinstance(X, np.ndarray): + raise ValueError("The input must be a numpy array.") + if X.ndim != 2: + raise ValueError("The input must be a 2D array.") + i, j = np.unravel_index(np.argmax(X), X.shape) return i, j @@ -64,4 +64,8 @@ def wallis_product(n_terms): """ # XXX : The n_terms is an int that corresponds to the number of # terms in the product. For example 10000. - return 0. + if n_terms == 0: + return 1 + n = np.arange(1, n_terms + 1) + terms = 4 * n**2 / (4 * n**2 - 1) + return 2 * np.prod(terms) From c34fcc84b55f82d89c7f5ab45dd01071a8bb7d07 Mon Sep 17 00:00:00 2001 From: tiphainebrt <330786940+tiphainebrt@users.noreply.github.com> Date: Tue, 10 Nov 2026 17:17:58 +0100 Subject: [PATCH 3/4] Remove unused import to pass the test for ONN --- sklearn_questions.py | 1 - 1 file changed, 1 deletion(-) diff --git a/sklearn_questions.py b/sklearn_questions.py index 7d4cec34..54f711c2 100644 --- a/sklearn_questions.py +++ b/sklearn_questions.py @@ -25,7 +25,6 @@ from sklearn.utils.validation import check_X_y from sklearn.utils.validation import check_array from sklearn.utils.validation import check_is_fitted -from sklearn.utils.validation import validate_data from sklearn.utils.multiclass import check_classification_targets From fcc15e194d8788130e2939bce94aa7abba1d7888 Mon Sep 17 00:00:00 2001 From: tiphainebrt <330786940+tiphainebrt@users.noreply.github.com> Date: Tue, 10 Nov 2026 18:10:23 +0100 Subject: [PATCH 4/4] Changed code to use the validate_data function instead of coding it manually to align with repo --- sklearn_questions.py | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/sklearn_questions.py b/sklearn_questions.py index 54f711c2..93f23630 100644 --- a/sklearn_questions.py +++ b/sklearn_questions.py @@ -25,6 +25,7 @@ from sklearn.utils.validation import check_X_y from sklearn.utils.validation import check_array from sklearn.utils.validation import check_is_fitted +from sklearn.utils.validation import validate_data from sklearn.utils.multiclass import check_classification_targets @@ -69,14 +70,11 @@ def predict(self, X): The classes predicted for each sample """ check_is_fitted(self) - X = check_array(X) - if X.shape[1] != self.n_features_in_: - raise ValueError( - f"X has {X.shape[1]} features, but " - f"{self.__class__.__name__} is expecting " - f"{self.n_features_in_} features as input" - ) + X = check_array(X) + X = validate_data(self, X, reset=False) + # reset = False: reads n_features_in_ from the estimator + # and comapres it with the number of features in the new X y_pred = np.full( shape=len(X), fill_value=self.classes_[0],