Hugo Vandenbussche assignment

numpy_questions.py

@@ -40,7 +40,10 @@ def max_index(X):
     i = 0
     j = 0
 
-    # TODO
+    if not isinstance(X, np.ndarray) or X.ndim != 2:
+        raise ValueError('X is not an np.array or is not of dimension 2D.')
+
+    i, j = np.unravel_index(np.argmax(X), X.shape)
 
     return i, j
 
@@ -64,4 +67,11 @@ 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
+
+    n = np.arange(1, n_terms + 1)
+    product = np.prod((4 * n**2) / (4 * n**2 - 1))
+
+    return float(2 * product)

sklearn_questions.py

@@ -25,51 +25,87 @@
 from sklearn.utils.validation import check_X_y
 from sklearn.utils.validation import check_array
 from sklearn.utils.validation import check_is_fitted
-from sklearn.utils.validation import validate_data
 from sklearn.utils.multiclass import check_classification_targets
 
 
 class OneNearestNeighbor(ClassifierMixin, BaseEstimator):
-    "OneNearestNeighbor classifier."
+    """OneNearestNeighbor classifier."""
 
     def __init__(self):  # noqa: D107
         pass
 
     def fit(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Fit the model on the training set (X training data, y target value).
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The input samples.
+        y : ndarray of shape (n_samples,)
+                The target values.
+
+        Returns
+        -------
+        self : object
+            the 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_fit_ = X
+        self.y_fit_ = y
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """Predict the class label for each sample in X.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The input samples.
 
-        And describe parameters
+        Returns
+        --------
+        y_pred : ndarray of shape (n_samples,)
+            The predicted class labels
         """
         check_is_fitted(self)
         X = check_array(X)
+        if X.shape[1] != self.n_features_in_:
+            raise ValueError(
+                f"X has {X.shape[1]} features, but OneNearestNeighbor "
+                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
         )
 
-        # XXX fix
+        distances = np.linalg.norm(
+            X[:, np.newaxis, :] - self.X_fit_[np.newaxis, :, :], axis=2
+        )
+        nearestneighbor = np.argmin(distances, axis=1)
+        y_pred = self.y_fit_[nearestneighbor]
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Return the mean accuracy on the given test data and labels.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Test sample
+        y : ndarray of shape (n_samples,)
+            True labels of X
+
+        Returns
+        -------
+        score : float
+            Mean accuracy of predictions of X with respect to y
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
 
-        # XXX fix
-        return y_pred.sum()
+        return np.mean(y_pred == y)