PR Assignment part B - Scott Mayette

numpy_questions.py

@@ -29,20 +29,31 @@ 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):
+        raise ValueError("Input must be a numpy array.")
+    if X.ndim != 2:
+        raise ValueError(
+            "Input must be a 2D array with shape (n_samples, n_features)."
+        )
 
-    # TODO
+    current_max = X[0, 0]
+    max_i, max_j = 0, 0
 
-    return i, j
+    for i in range(X.shape[0]):
+        for j in range(X.shape[1]):
+            if X[i, j] > current_max:
+                current_max = X[i, j]
+                max_i, max_j = i, j
+
+    return max_i, max_j
 
 
 def wallis_product(n_terms):
@@ -62,6 +73,12 @@ 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
+
+    product = 1.0
+    for i in range(1, n_terms + 1):
+        term = (4 * i**2) / (4 * i**2 - 1)
+        product *= term
+
+    return 2 * product

sklearn_questions.py

@@ -28,47 +28,98 @@
 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.
+        """Fit the OneNearestNeighbor classifier.
 
-        And describe parameters
+        This stores the training data so that predictions can be made
+        by looking for the closest training sample to each new point.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training input samples.
+
+        y : array-like of shape (n_samples,)
+            Target labels for each training sample.
+
+        Returns
+        -------
+        self : OneNearestNeighbor
+            The fitted classifier.
         """
         X, y = check_X_y(X, y)
         check_classification_targets(y)
+
+        self.X_ = X
+        self.y_ = y
         self.classes_ = np.unique(y)
         self.n_features_in_ = X.shape[1]
 
-        # XXX fix
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """Predict class labels for the given samples.
 
-        And describe parameters
+        For each sample in X, the predicted label is the label of the
+        closest training sample (in Euclidean distance).
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Input samples to classify.
+
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            Predicted class labels.
         """
         check_is_fitted(self)
         X = check_array(X)
-        y_pred = np.full(
-            shape=len(X), fill_value=self.classes_[0],
-            dtype=self.classes_.dtype
-        )
 
-        # XXX fix
+        if X.shape[1] != self.n_features_in_:
+            raise ValueError(
+                f"X has {X.shape[1]} features, but "
+                f"{self.__class__.__name__} is expecting "
+                f"{self.n_features_in_} features as input"
+            )
+
+        n_samples = X.shape[0]
+        y_pred = np.empty(n_samples, dtype=self.y_.dtype)
+
+        for i in range(n_samples):
+            x = X[i]
+            dists = np.linalg.norm(self.X_ - x, axis=1)
+            nn_idx = np.argmin(dists)
+            y_pred[i] = self.y_[nn_idx]
+
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
+        """Compute accuracy of the classifier on the given test data.
+
+        The accuracy is the proportion of correctly classified samples.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Test input samples.
+
+        y : array-like of shape (n_samples,)
+            True labels for X.
 
-        And describe parameters
+        Returns
+        -------
+        score : float
+            Mean accuracy of predictions on X compared to y.
         """
         X, y = check_X_y(X, y)
-        y_pred = self.predict(X)
+        check_is_fitted(self)
 
-        # XXX fix
-        return y_pred.sum()
+        y_pred = self.predict(X)
+        return np.mean(y_pred == y)