Xiaoyu ZHAO's numpy and nearest neighbor exercises

numpy_questions.py

@@ -41,6 +41,11 @@ def max_index(X):
     j = 0
 
     # TODO
+    if not isinstance(X, np.ndarray) or X.ndim != 2:
+        raise ValueError("X must be a 2D numpy array.")
+
+    max_position = np.argmax(X)
+    return np.unravel_index(max_position, X.shape)
 
     return i, j
 
@@ -62,6 +67,9 @@ 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)
+    terms = (2 * k) ** 2 / ((2 * k - 1) * (2 * k + 1))
+    return 2.0 * np.prod(terms)

sklearn_questions.py

@@ -25,12 +25,11 @@
 from sklearn.utils.validation import check_X_y
 from sklearn.utils.validation import check_array
 from sklearn.utils.validation import check_is_fitted
-from sklearn.utils.validation import validate_data
 from sklearn.utils.multiclass import check_classification_targets
 
 
 class OneNearestNeighbor(ClassifierMixin, BaseEstimator):
-    "OneNearestNeighbor classifier."
+    """OneNearestNeighbor classifier."""
 
     def __init__(self):  # noqa: D107
         pass
@@ -44,6 +43,8 @@ def fit(self, X, y):
         check_classification_targets(y)
         self.classes_ = np.unique(y)
         self.n_features_in_ = X.shape[1]
+        self.X_train_ = X
+        self.y_train_ = y
 
         # XXX fix
         return self
@@ -55,11 +56,23 @@ def predict(self, X):
         """
         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 OneNearestNeighbor is "
+                f"expecting {self.n_features_in_} features as input."
+            )
+
         y_pred = np.full(
             shape=len(X), fill_value=self.classes_[0],
             dtype=self.classes_.dtype
         )
 
+        for i, sample in enumerate(X):
+            distances = np.sum((self.X_train_ - sample) ** 2, axis=1)
+            nearest_index = np.argmin(distances)
+            y_pred[i] = self.y_train_[nearest_index]
+
         # XXX fix
         return y_pred
 
@@ -72,4 +85,4 @@ def score(self, X, y):
         y_pred = self.predict(X)
 
         # XXX fix
-        return y_pred.sum()
+        return np.mean(y_pred == y)