diff --git a/.DS_Store b/.DS_Store
new file mode 100644
index 00000000..e9d4ff11
Binary files /dev/null and b/.DS_Store differ
diff --git a/github-assignment b/github-assignment
new file mode 160000
index 00000000..769c2dd0
--- /dev/null
+++ b/github-assignment
@@ -0,0 +1 @@
+Subproject commit 769c2dd03019961072c98a6b9802aef4e14cfa67
diff --git a/numpy_questions.py b/numpy_questions.py
index 21fcec4b..c16ec3dd 100644
--- a/numpy_questions.py
+++ b/numpy_questions.py
@@ -37,10 +37,15 @@ 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("X must be a numpy array.")
+    if X.ndim != 2:
+        raise ValueError("X must be a 2D array.")
     i = 0
     j = 0
 
-    # TODO
+    flat_index = np.argmax(X)
+    i, j = np.unravel_index(flat_index, X.shape)
 
     return i, j
 
@@ -62,6 +67,12 @@ 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 n in range(1, n_terms + 1):
+        product *= (4 * n**2) / (4 * n**2 - 1)
+
+    pi = 2 * product
+    return pi
diff --git a/sklearn_questions.py b/sklearn_questions.py
index f65038c6..b8370f2a 100644
--- a/sklearn_questions.py
+++ b/sklearn_questions.py
@@ -29,46 +29,91 @@
 
 
 class OneNearestNeighbor(BaseEstimator, ClassifierMixin):
-    "OneNearestNeighbor classifier."
+    """One Nearest Neighbor classifier.
 
-    def __init__(self):  # noqa: D107
+    This classifier predicts the label of the closest training sample
+    using the Euclidean distance.
+    """
+
+    def __init__(self):
+        """Initialize the OneNearestNeighbor classifier."""
         pass
 
     def fit(self, X, y):
-        """Write docstring.
+        """Fit the classifier.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data.
+
+        y : array-like of shape (n_samples,)
+            Class labels.
 
-        And describe parameters
+        Returns
+        -------
+        self : object
+            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 the closest label for each sample.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Input samples.
 
-        And describe parameters
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            Predicted class labels.
         """
-        check_is_fitted(self)
+        check_is_fitted(self, ["X_", "y_", "n_features_in_"])
         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(
+                "X has {} features, but OneNearestNeighbor was fitted with "
+                "{} features.".format(X.shape[1], self.n_features_in_)
+            )
+
+        n_samples = X.shape[0]
+        y_pred = np.empty(n_samples, dtype=self.y_.dtype)
+
+        for i in range(n_samples):
+            # Compute Euclidean distances to all training samples
+            distances = np.linalg.norm(self.X_ - X[i], axis=1)
+            nn_index = np.argmin(distances)
+            y_pred[i] = self.y_[nn_index]
+
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
+        """Return accuracy of the classifier.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Test samples.
 
-        And describe parameters
+        y : array-like of shape (n_samples,)
+            True labels.
+
+        Returns
+        -------
+        score : float
+            Accuracy (fraction 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)