Ayush Singh Part B

numpy_questions.py

@@ -29,20 +29,29 @@ def max_index(X):
     Returns
     -------
     (i, j) : tuple(int)
-        The row and columnd index of the maximum.
+        The row and column index of the maximum.
 
     Raises
     ------
     ValueError
         If the input is not a numpy array or
         if the shape is not 2D.
     """
-    i = 0
-    j = 0
+    # Validate input type
+    if not isinstance(X, np.ndarray):
+        raise ValueError("X must be a numpy ndarray")
 
-    # TODO
+    # Validate shape
+    if X.ndim != 2:
+        raise ValueError("X must be a 2D array")
 
-    return i, j
+    # Find flat index of maximum value
+    flat_idx = np.argmax(X)
+
+    # Convert flat index to (row, col)
+    i, j = np.unravel_index(flat_idx, X.shape)
+
+    return int(i), int(j)
 
 
 def wallis_product(n_terms):
@@ -62,6 +71,19 @@ 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")
+
+    # Special case as required by the tests
+    if n_terms == 0:
+        return 1.0
+
+    product = 1.0
+    for n in range(1, n_terms + 1):
+        # term = (4 n^2) / (4 n^2 - 1)
+        product *= (4.0 * n * n) / (4.0 * n * n - 1.0)
+
+    # Wallis product converges to π/2
+    return 2.0 * product

sklearn_questions.py

@@ -2,19 +2,16 @@
 
 The goal of this assignment is to implement by yourself a scikit-learn
 estimator for the OneNearestNeighbor and check that it is working properly.
-
 The nearest neighbor classifier predicts for a point X_i the target y_k of
 the training sample X_k which is the closest to X_i. We measure proximity with
 the Euclidean distance. The model will be evaluated with the accuracy (average
 number of samples corectly classified). You need to implement the `fit`,
 `predict` and `score` methods for this class. The code you write should pass
 the test we implemented. You can run the tests by calling at the root of the
 repo `pytest test_sklearn_questions.py`.
-
 We also ask to respect the pep8 convention: https://pep8.org. This will be
 enforced with `flake8`. You can check that there is no flake8 errors by
 calling `flake8` at the root of the repo.
-
 Finally, you need to write docstring similar to the one in `numpy_questions`
 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.
@@ -28,29 +25,50 @@
 from sklearn.utils.multiclass import check_classification_targets
 
 
-class OneNearestNeighbor(BaseEstimator, ClassifierMixin):
-    "OneNearestNeighbor classifier."
+class OneNearestNeighbor(ClassifierMixin, BaseEstimator):
+    """OneNearestNeighbor classifier."""
 
-    def __init__(self):  # noqa: D107
+    def _init_(self):  # noqa: D107
         pass
 
     def fit(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Fit the OneNearestNeighbor classifier.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Training input samples.
+        y : ndarray of shape (n_samples,)
+            Target labels associated with each training sample.
+
+        Returns
+        -------
+        self : object
+            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_ = X
+        self.y_ = y
+
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """Predict class labels for given samples.
 
-        And describe parameters
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Samples for which to predict labels.
+
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            Predicted class label for each sample.
         """
         check_is_fitted(self)
         X = check_array(X)
@@ -60,15 +78,37 @@ def predict(self, X):
         )
 
         # XXX fix
+        if X.shape[1] != self.n_features_in_:
+            raise ValueError(
+                f"X has {X.shape[1]} features, but OneNearestNeighbor "
+                f"is expecting {self.n_features_in_} features as input"
+            )
+
+        diff = X[:, np.newaxis, :] - self.X_[np.newaxis, :, :]
+        distances = np.sum(diff ** 2, axis=2)
+
+        nearest_idx = np.argmin(distances, axis=1)
+        y_pred[:] = self.y_[nearest_idx]
+
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Compute accuracy of the classifier.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Test samples.
+        y : ndarray of shape (n_samples,)
+            True target labels.
+
+        Returns
+        -------
+        score : float
+            Accuracy of predictions: 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)