Julian Fix - assignment partB

numpy_questions.py

@@ -37,10 +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
+    if not isinstance(X, np.ndarray):
+        raise ValueError("Input must be a numpy array.")
+    if X.ndim != 2:
+        raise ValueError(f"Input array must be 2D, not {X.ndim} dimensions.")
 
-    # TODO
+    index = np.argmax(X)
+    (i, j) = np.unravel_index(index, X.shape)
 
     return i, j
 
@@ -62,6 +65,15 @@ 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:
+        pi = 1.0
+
+    else:
+        product = 1.0
+        for n in range(1, n_terms + 1):
+            num = 4.0 * n ** 2
+            den = num - 1.0
+            product *= (num / den)
+        pi = 2.0 * product
+
+    return pi

sklearn_questions.py

@@ -1,23 +1,9 @@
-"""Assignment - making a sklearn estimator.
-
-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.
+"""
+Implementation of a One-Nearest Neighbor classifier.
+
+Implementation of a One-Nearest Neighbor classifier adhering to
+the scikit-learn estimator interface.
+
 """
 import numpy as np
 from sklearn.base import BaseEstimator
@@ -29,46 +15,89 @@
 
 
 class OneNearestNeighbor(BaseEstimator, ClassifierMixin):
-    "OneNearestNeighbor classifier."
+    """One-Nearest-Neighbor classifier.
+
+    This classifier predicts the class of a sample by finding the
+    closest sample in the training data (using Euclidean distance)
+    and assigning its class.
+    """
 
     def __init__(self):  # noqa: D107
+        """Initialize the OneNearestNeighbor classifier."""
         pass
 
     def fit(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Fit the One-Nearest-Neighbor classifier.
+
+        This method stores the training data (X and y) to be used
+        during prediction.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data.
+        y : array-like of shape (n_samples,)
+            Target values.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
         """
         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 the class labels for provided data.
 
-        And describe parameters
+        For each sample in X, finds the closest training sample
+        (using Euclidean distance) and returns its label.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Test samples.
+
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            Predicted class 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
-        )
 
-        # XXX fix
+        y_pred = np.empty(shape=len(X), dtype=self.y_.dtype)
+
+        for i, x_test in enumerate(X):
+            sq_distances = np.sum((self.X_ - x_test)**2, axis=1)
+            nearest_index = np.argmin(sq_distances)
+            y_pred[i] = self.y_[nearest_index]
+
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Return the mean accuracy on the given test data and labels.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Test samples.
+        y : array-like of shape (n_samples,)
+            True labels for X.
+
+        Returns
+        -------
+        score : float
+            Mean accuracy of self.predict(X) wrt. y.
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
 
-        # XXX fix
-        return y_pred.sum()
+        return np.mean(y_pred == y)