Hayden Gatlin - Part B

numpy_questions.py

@@ -40,8 +40,10 @@ def max_index(X):
     i = 0
     j = 0
 
-    # TODO
+    if not isinstance(X, np.ndarray) or X.ndim != 2:
+        raise ValueError("X must be a two-dimensional numpy array.")
 
+    i, j = np.unravel_index(np.argmax(X), X.shape)
     return i, j
 
 
@@ -62,6 +64,9 @@ 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 1.0
+
+    k = np.arange(1, n_terms + 1, dtype=float)
+    factors = (4 * k**2) / (4 * k**2 - 1)
+    return 2 * np.prod(factors)

sklearn_questions.py

@@ -28,29 +28,48 @@
 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
+        """Store the training samples and their class labels.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Training samples.
+        y : ndarray of shape (n_samples,)
+            Class labels for the training samples.
+
+        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]
+        self.X_ = X.copy()
+        self.y_ = y.copy()
 
-        # XXX fix
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """Predict the class of each sample using its nearest neighbor.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Samples to classify.
 
-        And describe parameters
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            Predicted class labels.
         """
         check_is_fitted(self)
         X = check_array(X)
@@ -59,16 +78,35 @@ def predict(self, X):
             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"
+            )
+
+        for i, sample in enumerate(X):
+            distances = np.sum((self.X_ - sample) ** 2, axis=1)
+            nearest_index = np.argmin(distances)
+            y_pred[i] = self.y_[nearest_index]
+
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Return the classification accuracy on the given samples.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Samples to classify.
+        y : ndarray of shape (n_samples,)
+            True class labels.
+
+        Returns
+        -------
+        score : float
+            Fraction of samples classified correctly.
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
 
-        # XXX fix
-        return y_pred.sum()
+        return np.mean(y_pred == y)