Emilie Castellani – Assignment Part B

numpy_questions.py

@@ -41,8 +41,12 @@ def max_index(X):
     j = 0
 
     # TODO
+    if not isinstance(X, np.ndarray) or (X.ndim != 2):
+        raise ValueError("Input must be a numpy array.")
 
-    return i, j
+    i, j = np.unravel_index(np.argmax(X), X.shape)
+
+    return int(i), int(j)
 
 
 def wallis_product(n_terms):
@@ -62,6 +66,9 @@ 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 n_terms == 0:
+        return 1.
+    pi = 2.0
+    for n in range(1, n_terms + 1):
+        pi *= 4 * n**2 / (4 * n**2 - 1)
+    return pi

sklearn_questions.py

@@ -28,47 +28,84 @@
 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)
+            The training samples.
+        y : ndarray of shape (n_samples,)
+            The training labels.
+
+        Returns
+        -------
+        self : OneNearestNeighbor
+            The 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.
+        """Predict the label of each sample as that of its nearest neighbor.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The samples to classify.
 
-        And describe parameters
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            The predicted labels.
         """
         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
+        dist = np.linalg.norm(X[:, None, :] - self.X_train_[None], axis=2)
+        y_pred[:] = self.y_train_[np.argmin(dist, axis=1)]
+
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Return the accuracy of the classifier on the given data.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The test samples.
+        y : ndarray of shape (n_samples,)
+            The true labels.
+
+        Returns
+        -------
+        score : float
+            The fraction of correctly classified samples.
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
 
-        # XXX fix
-        return y_pred.sum()
+        return np.mean(y_pred == y)