Martin, Dias Pinto (Part B)

numpy_questions.py

@@ -40,7 +40,13 @@ def max_index(X):
     i = 0
     j = 0
 
-    # TODO
+    if not isinstance(X, np.ndarray):
+        raise ValueError("Error: input not a numpy array")
+    if X.ndim != 2:
+        raise ValueError("Error: input array must be 2D")
+
+    idx = np.argmax(X)
+    i, j = np.unravel_index(idx, X.shape)
 
     return i, j
 
@@ -62,6 +68,16 @@ def wallis_product(n_terms):
     pi : float
         The approximation of order `n_terms` of pi using the Wallis product.
     """
-    # XXX : The n_terms is an int that corresponds to the number of
-    # terms in the product. For example 10000.
-    return 0.
+    if not isinstance(n_terms, int) or n_terms < 0:
+        raise ValueError("Error: Input invalid")
+
+    if n_terms == 0:
+        return 1.0
+
+    product = 1.0
+    for k in range(1, n_terms + 1):
+        num = (2 * k) ** 2
+        denom = num - 1
+        product *= num / denom
+
+    return 2.0 * product

sklearn_questions.py

@@ -28,47 +28,104 @@
 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
+    This estimator implements the 1-Nearest Neighbor classification algorithm.
+    It predicts the label of a new sample based on the label of the single
+    closest training sample (nearest neighbor) using Euclidean distance.
+
+    Parameters
+    ----------
+    No parameters are needed for this simple implementation.
+    """
+
+    def __init__(self):
+        """
+        Init function.
+
+        Returns
+        -------
+        None.
+
+        """
         pass
 
     def fit(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """
+        Fit the OneNearestNeighbor classifier.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            The training input samples.
+        y : array-like of shape (n_samples,)
+            The target values (class labels).
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
         """
         X, y = check_X_y(X, y)
         check_classification_targets(y)
-        self.classes_ = np.unique(y)
+
         self.n_features_in_ = X.shape[1]
+        self.X_ = X
+        self.y_ = y
+        self.classes_ = np.unique(y)
 
-        # XXX fix
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """
+        Predict the class label for the provided data.
 
-        And describe parameters
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            The input samples to predict.
+
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            The predicted class labels for the input samples.
         """
         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
+        if X.shape[1] != self.n_features_in_:
+            raise ValueError(
+                f"X has {X.shape[1]} features, but OneNearestNeighbor "
+                f"is expecting {self.n_features_in_} features as input."
+            )
+
+        diff = X[:, None, :] - self.X_[None, :, :]
+        distances = np.linalg.norm(diff, axis=2)
+
+        nearest_idx = np.argmin(distances, axis=1)
+        y_pred = self.y_[nearest_idx]
+
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """
+        Return the mean accuracy on the given test data and labels.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Test samples.
+        y : array-like of shape (n_samples,)
+            True labels for X.
+
+        Returns
+        -------
+        score : float
+            Mean accuracy of self.predict(X) vs. y.
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
 
-        # XXX fix
-        return y_pred.sum()
+        return np.mean(y_pred == y)