tiphaineBERTHOU_assignment

numpy_questions.py

@@ -37,11 +37,11 @@ def max_index(X):
         If the input is not a numpy array or
         if the shape is not 2D.
     """
-    i = 0
-    j = 0
-
-    # TODO
-
+    if not isinstance(X, np.ndarray):
+        raise ValueError("The input must be a numpy array.")
+    if X.ndim != 2:
+        raise ValueError("The input must be a 2D array.")
+    i, j = np.unravel_index(np.argmax(X), X.shape)
     return i, j
 
 
@@ -64,4 +64,8 @@ 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
+    n = np.arange(1, n_terms + 1)
+    terms = 4 * n**2 / (4 * n**2 - 1)
+    return 2 * np.prod(terms)

sklearn_questions.py

@@ -30,46 +30,79 @@
 
 
 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 classifier by storing the training data.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+                Training sample.
+        y : ndarray of shape(n_samples)
+                Target labels of the training sample.
+        Returns
+        -------
+        Fitted classifier.
         """
         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_train_ = X
+        self.y_train_ = y
         return self
 
     def predict(self, X):
-        """Write docstring.
-
-        And describe parameters
+        """Predict the class of each sample using nearest neighbor classifier.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+                Testing sample to classify.
+        Returns
+        ----------
+        y_pred : ndarray of shape (n_samples)
+            The classes predicted for each sample
         """
         check_is_fitted(self)
+
         X = check_array(X)
+        X = validate_data(self, X, reset=False)
+        # reset = False: reads n_features_in_ from the estimator
+        # and comapres it with the number of features in the new X
+
         y_pred = np.full(
             shape=len(X), fill_value=self.classes_[0],
             dtype=self.classes_.dtype
         )
 
-        # XXX fix
+        for i, x in enumerate(X):
+            distances = np.linalg.norm(self.X_train_ - x, axis=1)
+            y_pred[i] = self.y_train_[np.argmin(distances)]
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Compute the accuracy of the classifier.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+                Testing sample.
+        y : ndarray of shape(n_samples)
+                Labels of the testing sample.
+
+        Returns
+        ----------
+        score : float
+            Fraction of samples correctly classified
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
 
-        # XXX fix
+        y_pred = (y_pred == y) / len(y)
         return y_pred.sum()