Jacobelli assignment

numpy_questions.py

@@ -42,6 +42,16 @@ def max_index(X):
 
     # TODO
 
+    if not isinstance(X, np.ndarray):
+        raise ValueError("The input is not a numpy array.")
+    if X.ndim != 2:
+        raise ValueError("The shape is not 2D")
+
+    for a in range(X.shape[0]):
+        for b in range(X.shape[1]):
+            if X[a, b] > X[i, j]:
+                i, j = a, b
+
     return i, j
 
 
@@ -64,4 +74,13 @@ 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
+
+    product = 1
+    for i in range(1, n_terms + 1):
+        four_n_squared = 4 * i * i
+        product *= four_n_squared / (four_n_squared - 1)
+
+    return 2 * product

sklearn_questions.py

@@ -25,33 +25,56 @@
 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.
+
+    Predict for each sample the target of the closest training sample,
+    using the Euclidean distance.
+    """
 
     def __init__(self):  # noqa: D107
         pass
 
     def fit(self, X, y):
-        """Write docstring.
+        """Store the training data to fit the classifier.
+
+        Parameters
+        ----------
+        X = ndarray of shape (n_samples, n_features)
+        The training sample, input array.
+
+        y = ndarray of shape (n_samples,)
+        The training target, input array.
 
-        And describe parameters
+        Returns
+        -------
+        self : OneNearestNeighbor
         """
         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.
+        """Predict the target of each sample.
+
+        Parameters
+        ----------
+        X = ndarray of shape (n_samples, n_features)
+        The training sample, input array.
+
+        Returns
+        -------
+        y_pred : nd array of shape (n_samples, )
+        The target of the closest training sample for each sample.
 
-        And describe parameters
         """
         check_is_fitted(self)
         X = check_array(X)
@@ -61,15 +84,37 @@ def predict(self, X):
         )
 
         # 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"
+            )
+        for i, x in enumerate(X):
+            distances = np.sum((self.X_train_ - x) ** 2, axis=1)
+            y_pred[i] = self.y_train_[np.argmin(distances)]
+
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
+        """Compute the accuracy of the model.
+
+        Parameters
+        ----------
+        X = ndarray of shape (n_samples, n_features)
+        The training sample, input array.
+
+        y = ndarray of shape (n_samples,)
+        The training target, input array.
 
-        And describe parameters
+        Returns
+        -------
+        score : float
+        The fraction of the samples correctly classified
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
 
         # XXX fix
-        return y_pred.sum()
+        return np.mean(y_pred == y)