Implement numpy and sklearn assignment

numpy_questions.py

@@ -37,11 +37,12 @@ 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("Input is not a numpy array.")
+    if X.ndim != 2:
+        raise ValueError("Input is not a 2D array.")
+    flat_index = np.argmax(X)
+    i, j = np.unravel_index(flat_index, X.shape)
     return i, j
 
 
@@ -62,6 +63,16 @@ 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):
+        raise ValueError("n_terms must be an integer.")
+    if n_terms < 0:
+        raise ValueError("n_terms must be non-negative.")
+    if n_terms == 0:
+        pi = 1.0
+    else:
+        product_terms = np.arange(1, n_terms + 1)
+        numerator = 4 * (product_terms ** 2)
+        denominator = numerator - 1
+        pi = np.prod(numerator / denominator)*2
+
+    return pi

sklearn_questions.py

@@ -19,6 +19,7 @@
 for the methods you code and for the class. The docstring will be checked using
 `pydocstyle` that you can also call at the root of the repo.
 """
+
 import numpy as np
 from sklearn.base import BaseEstimator
 from sklearn.base import ClassifierMixin
@@ -28,47 +29,75 @@
 from sklearn.utils.multiclass import check_classification_targets
 
 
-class OneNearestNeighbor(BaseEstimator, ClassifierMixin):
-    "OneNearestNeighbor classifier."
+class OneNearestNeighbor(ClassifierMixin, BaseEstimator):
+    """One Nearest Neighbor classifier using Euclidean distance.
+
+    This classifier assigns to each input sample the label of its closest
+    training sample,
+    where closeness is measured using the Euclidean distance.
+    """
 
     def __init__(self):  # noqa: D107
         pass
 
     def fit(self, X, y):
-        """Write docstring.
+        """Fit the OneNearestNeighbor classifier from the training data.
 
-        And describe parameters
+        Parameters
+        X: ndarray of shape (n_samples, n_features) containing training data.
+        y: ndarray of shape (n_samples,).
+            It contains target labels corresponding to the training samples.
+
+        Returns
+        self : OneNearestNeighbor
+            The 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_ = X
+        self.y_ = y
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """Predict class labels for the input samples.
 
-        And describe parameters
+        Parameters
+        X: ndarray of shape (n_samples, n_features)
+        containing input samples for which predictions are requested.
+        It must contain the same number of features as the training data.
+
+        Returns
+        y_pred: ndarray of shape (n_samples,),
+        containing predicted class labels for each input sample.
         """
         check_is_fitted(self)
         X = check_array(X)
+        X = self._validate_data(X, reset=False)
         y_pred = np.full(
             shape=len(X), fill_value=self.classes_[0],
             dtype=self.classes_.dtype
         )
+        differences = (X[:, np.newaxis, :] - self.X_[np.newaxis, :, :])
+        distances = np.sqrt(np.sum(differences ** 2, axis=2))
+        nearest_indices = np.argmin(distances, axis=1)
+        y_pred = self.y_[nearest_indices]
 
-        # XXX fix
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
+        """Compute the accuracy of the classifier.
+
+        Parameters
+        X: ndarray of shape (n_samples, n_features) containing test samples.
+        y: array-like of shape (n_samples,)
+        containing true labels for the test samples.
 
-        And describe parameters
+        Returns
+        accuracy: The fraction of correctly classified samples.
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
-
-        # XXX fix
-        return y_pred.sum()
+        score = np.sum(y_pred == y)
+        return score / len(y)