Tristan Khaw Numpy Commit

numpy_questions.py

@@ -37,10 +37,16 @@ def max_index(X):
         If the input is not a numpy array or
         if the shape is not 2D.
     """
+    if not isinstance(X, np.ndarray):
+        raise ValueError("Input must be an array")
+    if X.ndim != 2:
+        raise ValueError("Array must be 2D")
+
     i = 0
     j = 0
 
-    # TODO
+    i = np.argmax(np.max(X, axis=1))   # index of row with the largest value
+    j = np.argmax(X[i, :])             # index of max within that row
 
     return i, j
 
@@ -64,4 +70,16 @@ 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
+
+    product = 1
+
+    for n in range(1, n_terms + 1):
+        t = (2 * n / (2 * n - 1)) * (2 * n / (2 * n + 1))
+        product *= t
+
+    pi = 2 * product
+
+    return pi

sklearn_questions.py

@@ -29,46 +29,96 @@
 
 
 class OneNearestNeighbor(BaseEstimator, ClassifierMixin):
-    "OneNearestNeighbor classifier."
+    """One-Nearest-Neighbor classifier.
+
+    This classifier assigns to each sample the label of the closest
+    training point in Euclidean distance. Only a single neighbor is
+    considered.
+    """
 
     def __init__(self):  # noqa: D107
         pass
 
     def fit(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Fit the OneNearestNeighbor classifier.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Training data.
+
+        y : ndarray of shape (n_samples,)
+            Target labels.
+
+        Returns
+        -------
+        self : object
+            Fitted estimator.
+
+        Raises
+        ------
+        ValueError
+            If `X` and `y` have incompatible shapes or if `y`
+            is not a valid classification target.
         """
         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_ = X
+        self.y_ = y
+
         return self
 
     def predict(self, X):
-        """Write docstring.
-
-        And describe parameters
+        """Predict class labels for given samples.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Input samples.
+
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            Predicted class labels.
+
+        Raises
+        ------
+        ValueError
+            If estimator has not been fitted.
         """
         check_is_fitted(self)
         X = check_array(X)
-        y_pred = np.full(
-            shape=len(X), fill_value=self.classes_[0],
-            dtype=self.classes_.dtype
+
+        distances = np.linalg.norm(
+            X[:, np.newaxis, :] - self.X_[np.newaxis, :, :],
+            axis=2,
         )
 
-        # XXX fix
-        return y_pred
+        nearest_idx = np.argmin(distances, axis=1)
+
+        return self.y_[nearest_idx]
 
     def score(self, X, y):
-        """Write docstring.
+        """Return the accuracy of the classifier.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Test samples.
 
-        And describe parameters
+        y : ndarray of shape (n_samples,)
+            True labels.
+
+        Returns
+        -------
+        score : float
+            Classification accuracy, i.e. the proportion of correct
+            predictions.
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
-
-        # XXX fix
-        return y_pred.sum()
+        return np.mean(y_pred == y)