Ryan Balech — Part B PR

numpy_questions.py

@@ -37,11 +37,13 @@ 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 must be a numpy array.")
+    if X.ndim != 2:
+        raise ValueError("Input must be a 2D numpy array.")
 
+    flat_index = np.argmax(X)
+    i, j = np.unravel_index(flat_index, X.shape)
     return i, j
 
 
@@ -62,6 +64,12 @@ 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:
+        raise ValueError("n_terms must be non-negative.")
+    if n_terms == 0:
+        return 1.0
+
+    n = np.arange(1, n_terms + 1)
+    terms = (4 * n * n) / (4 * n * n - 1)
+    product = np.prod(terms)
+    return 2 * product

sklearn_questions.py

@@ -2,73 +2,98 @@
 
 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.
 """
 import numpy as np
-from sklearn.base import BaseEstimator
-from sklearn.base import ClassifierMixin
-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.base import BaseEstimator, ClassifierMixin
+from sklearn.utils.validation import check_X_y, check_array, check_is_fitted
 from sklearn.utils.multiclass import check_classification_targets
 
 
-class OneNearestNeighbor(BaseEstimator, ClassifierMixin):
-    "OneNearestNeighbor classifier."
+class OneNearestNeighbor(ClassifierMixin, BaseEstimator):
+    """One nearest neighbor classifier."""
 
     def __init__(self):  # noqa: D107
+        # no hyperparameters
         pass
 
     def fit(self, X, y):
-        """Write docstring.
+        """Fit the OneNearestNeighbor classifier.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training input samples.
+
+        y : array-like of shape (n_samples,)
+            Training class labels.
 
-        And describe parameters
+        Returns
+        -------
+        self : OneNearestNeighbor
+            The fitted classifier.
         """
         X, y = check_X_y(X, y)
         check_classification_targets(y)
+
         self.classes_ = np.unique(y)
+        self.X_ = X
+        self.y_ = y
         self.n_features_in_ = X.shape[1]
 
-        # XXX fix
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """Predict class labels for the provided samples.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Test samples.
 
-        And describe parameters
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            Predicted class labels.
         """
-        check_is_fitted(self)
+        check_is_fitted(self, attributes=["X_", "y_"])
         X = check_array(X)
-        y_pred = np.full(
-            shape=len(X), fill_value=self.classes_[0],
-            dtype=self.classes_.dtype
+
+        # Enforce consistency of number of features with training data
+        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"
+            )
+
+        # Compute Euclidean distances to all training points
+        # X shape: (n_test, n_features)
+        # self.X_ shape: (n_train, n_features)
+        distances = np.linalg.norm(
+            self.X_[np.newaxis, :, :] - X[:, np.newaxis, :],
+            axis=2,
         )
+        nearest_idx = np.argmin(distances, axis=1)
+        y_pred = self.y_[nearest_idx]
 
-        # XXX fix
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
+        """Return the accuracy of the classifier on the given test data.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Test samples.
 
-        And describe parameters
+        y : array-like of shape (n_samples,)
+            True class labels.
+
+        Returns
+        -------
+        score : float
+            Classification accuracy.
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
-
-        # XXX fix
-        return y_pred.sum()
+        return float(np.mean(y_pred == y))