diff --git a/numpy_questions.py b/numpy_questions.py
index 21fcec4b..ce352311 100644
--- a/numpy_questions.py
+++ b/numpy_questions.py
@@ -40,9 +40,15 @@ def max_index(X):
     i = 0
     j = 0
 
-    # TODO
+    if not isinstance(X, np.ndarray):
+        raise ValueError("Error : input must be a numpy array.")
+    if X.ndim != 2:
+        raise ValueError("Error : input must be 2D.")
 
-    return i, j
+    index = np.argmax(X)            # index in the flattened array
+    i, j = np.unravel_index(index, X.shape)  # convert to (row, col)
+
+    return int(i), int(j)
 
 
 def wallis_product(n_terms):
@@ -62,6 +68,13 @@ 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 not isinstance(n_terms, (int, np.integer)) or n_terms < 0:
+        raise ValueError("Error : input must be a non negative integer.")
+
+    if n_terms == 0:
+        return 1
+
+    k = np.arange(1, n_terms + 1, dtype=float)
+    terms = (4.0 * k * k) / (4.0 * k * k - 1.0)
+    prod = np.prod(terms)
+    return float(2.0 * prod)
diff --git a/sklearn_questions.py b/sklearn_questions.py
index f65038c6..5cea98f3 100644
--- a/sklearn_questions.py
+++ b/sklearn_questions.py
@@ -28,47 +28,85 @@
 from sklearn.utils.multiclass import check_classification_targets
 
 
-class OneNearestNeighbor(BaseEstimator, ClassifierMixin):
-    "OneNearestNeighbor classifier."
+class OneNearestNeighbor(ClassifierMixin, BaseEstimator):
+    """One-nearest-neighbor classifier.
+
+    This estimator predicts the label of each input sample as the label of
+    the single closest training sample under the Euclidean distance.
+    """
 
     def __init__(self):  # noqa: D107
         pass
 
     def fit(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Fit the classifier.
+
+        The fitting process for OneNearestNeighbor only means storing
+        the training data, as it is a lazy learning algorithm.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data.
+        y : array-like of shape (n_samples,)
+            Target labels.
+        Returns
+        -------
+        self :
+        OneNearestNeighbor Fitted estimator.
         """
         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
+        self.n_features_in_ = X.shape[1]
+        self.classes_ = np.unique(y)
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """Predict class labels for the provided data.
+
+        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)
-        X = check_array(X)
-        y_pred = np.full(
-            shape=len(X), fill_value=self.classes_[0],
-            dtype=self.classes_.dtype
-        )
-
-        # XXX fix
+        check_is_fitted(self, attributes=("X_", "y_"))
+        X = self._validate_data(X, reset=False)
+        X_sq = np.sum(X ** 2, axis=1, keepdims=True)
+        Xt_sq = np.sum(self.X_ ** 2, axis=1, keepdims=True).T
+        dist_2 = X_sq + Xt_sq - 2 * (X @ self.X_.T)
+        nn_index = np.argmin(dist_2, axis=1)
+        y_pred = self.y_[nn_index]
+
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Return accuracy on the given test data and labels.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+        Test samples.
+        y : array-like of shape (n_samples,)
+        True labels.
+
+        Returns
+        -------
+        float
+        Accuracy of ``self.predict(X)`` vs ``y``.
         """
         X, y = check_X_y(X, y)
+        y = check_array(y, ensure_2d=False)
+        if y.shape[0] != X.shape[0]:
+            raise ValueError("X and y have incompatible shapes.")
+
         y_pred = self.predict(X)
 
-        # XXX fix
-        return y_pred.sum()
+        return float(np.mean(y_pred == y))
diff --git a/students.txt b/students.txt
index 393f42dd..d358425e 100644
--- a/students.txt
+++ b/students.txt
@@ -15,7 +15,7 @@ Burtin	Léo
 Chaabouni	Kenza     
 Chauhan	Bhavesh     
 Chou	Wei-Chieh X    
-Clot	Augustin     
+Clot	Augustin   X
 De Sauvan D'Aramon	Ithier     X
 Descazeaud	Lucien X   
 Despréaux	Maxime X    
@@ -27,7 +27,7 @@ Du	Jing
 El Bakouri	Samy     
 Enderwitz	Julius   X  
 Etienne	Romain X
-Finotti	Alice     
+Finotti	Alice  X   
 Fix	Julian     X
 Fouache D'Halloy Martin X  
 Franco--Tetu	Erwan  X 
@@ -42,7 +42,7 @@ Hartmann	Nick
 Heimann	Carl X   
 Hou	Litong  X   
 Hourquet	Augustin  X   
-Jacobacci	Giacomo     
+Jacobacci	Giacomo   X
 Jacquin De Margerie	Anatole     
 Jankovic	Nina    X 
 Kanaan	Julien     
@@ -51,16 +51,16 @@ Keum	Hae In     X
 Khaw	Tristan    X
 Khazzaka	Chloe     
 Korouhanba Khuman	Laikhuram  X   
-Lassus	Gabin     
+Lassus	Gabin X    
 Lau	Martin Alexander     X
 Le Bacon	Alexandre  X   
 Lefebvre	Félix     
 Levin	Nikolai X    
-Liard	Eléanor     
+Liard	Eléanor X     
 Liu	Guangyue    X 
-Liu	Yunxian     
+Liu	Yunxian     X
 Lucille	Maximilien X     
-Mahé	Blanche     
+Mahé	Blanche     X
 Martin	Justin     X
 Massias	Mathurin     
 Massoud	Alexandre.....X