advanced PR noe besson

numpy_questions.py

@@ -37,11 +37,19 @@ 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
-
+    max_value = X[i, j]
+    for row in range(X.shape[0]):
+        for col in range(X.shape[1]):
+            if X[row, col] > max_value:
+                max_value = X[row, col]
+                i, j = row, col
     return i, j
 
 
@@ -62,6 +70,7 @@ 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
+    k = np.arange(1, n_terms + 1)
+    return 2 * np.prod(4 * k**2 / (4 * k**2 - 1))

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.
+
+    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.
-
-        And describe parameters
+        """Fit the classifier by storing the training data.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The training samples.
+        y : ndarray of shape (n_samples,)
+            The target labels.
+
+        Returns
+        -------
+        self : OneNearestNeighbor
+            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_train_ = X
+        self.y_train_ = y
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """Predict the class of each sample in X.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The samples to classify.
 
-        And describe parameters
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            The predicted 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
+        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."
+            )
+
+        dists = np.sum(
+            (X[:, np.newaxis, :] - self.X_train_[np.newaxis, :, :]) ** 2,
+            axis=2,
         )
-
-        # XXX fix
+        nearest = np.argmin(dists, axis=1)
+        y_pred = self.y_train_[nearest]
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Return the accuracy on the given data.
+
+        Parameters
+        ----------
+        X : ndarray of shape(n_samples, n_features)
+            The test samples
+        y : ndarray of shape (n_samples,)
+            The true labels
+
+        Returns
+        -------
+        score : float
+            Fraction of correctly classified samples.
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
-
-        # XXX fix
-        return y_pred.sum()
+        return np.mean(y_pred == y)