Zixiao Guo PartB

numpy_questions.py

@@ -37,11 +37,13 @@ def max_index(X):
         If the input is not a numpy array or
         if the shape is not 2D.
     """
-    i = 0
-    j = 0
-
     # TODO
-
+    if not isinstance(X, np.ndarray):
+        raise ValueError("Input must be a numpy array")
+    if X.ndim != 2:
+        raise ValueError("Input array must be 2D")
+    flat_index = np.argmax(X, axis=None)
+    i, j = np.unravel_index(flat_index, X.shape)
     return i, j
 
 
@@ -64,4 +66,12 @@ def wallis_product(n_terms):
     """
     # 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
+    product = 1.0
+    for n in range(1, n_terms + 1):
+        term1 = (2.0 * n) / (2.0 * n - 1.0)
+        term2 = (2.0 * n) / (2.0 * n + 1.0)
+        product = product * term1 * term2
+    pi_approx = 2.0 * product
+    return pi_approx

sklearn_questions.py

@@ -28,8 +28,8 @@
 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
@@ -43,8 +43,8 @@ def fit(self, X, y):
         check_classification_targets(y)
         self.classes_ = np.unique(y)
         self.n_features_in_ = X.shape[1]
-
-        # XXX fix
+        self.X_ = X
+        self.y_ = y
         return self
 
     def predict(self, X):
@@ -53,12 +53,20 @@ def predict(self, X):
         And describe parameters
         """
         check_is_fitted(self)
-        X = check_array(X)
+        X = check_array(X, ensure_2d=True)
+        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
         )
-
+        for i, x_test in enumerate(X):
+            distances = np.sqrt(np.sum((self.X_ - x_test) ** 2, axis=1))
+            nearest_idx = np.argmin(distances)
+            y_pred[i] = self.y_[nearest_idx]
         # XXX fix
         return y_pred
 
@@ -69,6 +77,6 @@ def score(self, X, y):
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
-
         # XXX fix
-        return y_pred.sum()
+        accuracy = np.mean(y_pred == y)
+        return accuracy