Assignment submission - Francois Andreani

numpy_questions.py

@@ -40,7 +40,16 @@ def max_index(X):
     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 array")
+
+    flat_index = np.argmax(X)
+    i, j = np.unravel_index(flat_index, X.shape)
+
+    i, j = int(i), int(j)
 
     return i, j
 
@@ -64,4 +73,11 @@ def wallis_product(n_terms):
     """
     # 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 1.0
+
+    product = 1.0
+    for n in range(1, n_terms + 1):
+        product *= (4 * n * n) / (4 * n * n - 1)
+
+    return 2 * product

sklearn_questions.py

@@ -6,7 +6,7 @@
 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`,
+number of samples correctly 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`.
@@ -20,55 +20,98 @@
 `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):
+    """OneNearestNeighbor classifier.
+
+    This classifier predicts the class of a sample based on the class of
+    its nearest neighbor in the training set, using Euclidean distance.
+    """
 
     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 : OneNearestNeighbor
+            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
+        # Store training data
+        self.X_ = X
+        self.y_ = y
+
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """Predict class labels for given samples.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Samples for which to predict labels.
 
-        And describe parameters
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            Predicted class label for each sample.
         """
         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
+        # Check number of features against what was seen in fit
+        if X.shape[1] != self.n_features_in_:
+            raise ValueError(
+                f"X has {X.shape[1]} features, but {self.__class__.__name__} "
+                f"is expecting {self.n_features_in_} features as input"
+            )
+
+        # Compute squared Euclidean distances to all training samples
+        diff = X[:, np.newaxis, :] - self.X_[np.newaxis, :, :]
+        distances = np.sum(diff ** 2, axis=2)
+
+        # Index of nearest neighbor for each sample
+        nearest_idx = np.argmin(distances, axis=1)
+
+        # Predicted labels
+        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 float(np.mean(y_pred == y))