Complete part B - GABIN LASSUS

numpy_questions.py

@@ -29,39 +29,45 @@ def max_index(X):
     Returns
     -------
     (i, j) : tuple(int)
-        The row and columnd index of the maximum.
+        The row and column index of the maximum.
 
     Raises
     ------
     ValueError
         If the input is not a numpy array or
         if the shape is not 2D.
     """
-    i = 0
-    j = 0
+    if not isinstance(X, np.ndarray):  # check if X is a numpy array
+        raise ValueError("Input must be a numpy array")
+    if X.ndim != 2:  # check if X is 2D
+        raise ValueError("Input must be a 2D array")
 
-    # TODO
+    flat_index = np.argmax(X)  # index of max value
+    i, j = np.unravel_index(flat_index, X.shape)
 
     return i, j
 
 
 def wallis_product(n_terms):
-    """Implement the Wallis product to compute an approximation of pi.
-
-    See:
-    https://en.wikipedia.org/wiki/Wallis_product
+    """Compute an approximation of pi using the Wallis product.
 
     Parameters
     ----------
     n_terms : int
-        Number of steps in the Wallis product. Note that `n_terms=0` will
-        consider the product to be `1`.
+        Number of terms in the product. If `n_terms=0`, the result is 1.
 
     Returns
     -------
     pi : float
-        The approximation of order `n_terms` of pi using the Wallis product.
+        Approximation of pi of order `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 1.0
+
+    product = 1.0
+    for k in range(1, n_terms + 1):
+        numerator = 4 * k * k
+        term = numerator / (numerator - 1)
+        product *= term
+
+    return 2 * product

sklearn_questions.py

@@ -28,47 +28,100 @@
 from sklearn.utils.multiclass import check_classification_targets
 
 
-class OneNearestNeighbor(BaseEstimator, ClassifierMixin):
-    "OneNearestNeighbor classifier."
+class OneNearestNeighbor(ClassifierMixin, BaseEstimator):
+    """OneNearestNeighbor classifier.
+
+    This classifier predicts the label of each
+    sample based on the label of the closest
+    training sample using Euclidean distance.
+    """
 
     def __init__(self):  # noqa: D107
         pass
 
     def fit(self, X, y):
-        """Write docstring.
+        """Fit the OneNearestNeighbor classifier.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data.
+
+        y : array-like of shape (n_samples,)
+            Target labels.
 
-        And describe parameters
+        Returns
+        -------
+        self : object
+            Fitted estimator.
         """
         X, y = check_X_y(X, y)
         check_classification_targets(y)
+
+        self.X_ = X
+        self.y_ = y
         self.classes_ = np.unique(y)
         self.n_features_in_ = X.shape[1]
 
-        # XXX fix
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """Predict class labels for the samples in X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Test samples.
 
-        And describe parameters
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            Predicted class labels.
         """
         check_is_fitted(self)
         X = check_array(X)
-        y_pred = np.full(
-            shape=len(X), fill_value=self.classes_[0],
-            dtype=self.classes_.dtype
-        )
 
-        # XXX fix
+        # manual sklearn-required feature consistency check
+        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.empty(X.shape[0], dtype=self.y_.dtype)
+
+        for i, x in enumerate(X):
+            distances = np.linalg.norm(self.X_ - x, axis=1)
+            nearest_idx = np.argmin(distances)
+            y_pred[i] = self.y_[nearest_idx]
+
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
+        """Compute the accuracy of the classifier.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Test samples.
+
+        y : array-like of shape (n_samples,)
+            True labels.
 
-        And describe parameters
+        Returns
+        -------
+        score : float
+            Mean accuracy of the classifier.
         """
         X, y = check_X_y(X, y)
-        y_pred = self.predict(X)
 
-        # XXX fix
-        return y_pred.sum()
+        # same feature count check
+        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 = self.predict(X)
+        return np.mean(y_pred == y)