Brendan O' Sullivan: github assignment complete

numpy_questions.py

@@ -29,20 +29,20 @@ 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) or X.ndim != 2:
+        raise ValueError("X must be a 2D numpy array")
 
-    # TODO
+    i, j = np.unravel_index(np.argmax(X), X.shape)
 
-    return i, j
+    return int(i), int(j)
 
 
 def wallis_product(n_terms):
@@ -62,6 +62,9 @@ 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
+    n = np.arange(1, n_terms + 1, dtype=float)
+    pi = 2 * np.prod(4 * n ** 2/(4 * n ** 2 - 1))
+
+    return pi

sklearn_questions.py

@@ -30,46 +30,84 @@
 
 
 class OneNearestNeighbor(ClassifierMixin, BaseEstimator):
-    "OneNearestNeighbor classifier."
+    """OneNearestNeighbor classifier."""
 
     def __init__(self):  # noqa: D107
         pass
 
     def fit(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Fit the classifier by using the training data.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The input array.
+        y : ndarray of shape (n_samples,)
+            The target array (class labels).
+
+        Returns
+        -------
+        self : OneNearestNeighbor
+            The fitted estimator.
         """
-        X, y = check_X_y(X, y)
+        X, y = validate_data(self, X, y)
         check_classification_targets(y)
         self.classes_ = np.unique(y)
-        self.n_features_in_ = X.shape[1]
+        self.X_ = X
+        self.y_ = y
+        return self
 
-        # XXX fix
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """Predict the class of each sample from its nearest neighbor.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The input array.
 
-        And describe parameters
+        Returns
+        -------
+        y : ndarray of shape(n_samples,)
+            The predicted class 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 {self.__class__.__name__} "
+                f"is expecting {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
+        diffs = X[:, np.newaxis, :] - self.X_[np.newaxis, :, :]
+        distances = np.sqrt((diffs ** 2).sum(axis=2))
+        nearest = np.argmin(distances, axis=1)
+        y_pred[:] = self.y_[nearest]
+
         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)
+            The input array.
+        y : ndarray of shape (n_samples,)
+            The target array (class 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 float(np.mean(y_pred == y))