Alexandre Le Bacon assignment: numpy + sklearn solutions

numpy_questions.py

@@ -40,7 +40,12 @@ def max_index(X):
     i = 0
     j = 0
 
-    # TODO
+    if not isinstance(X, np.ndarray):
+        raise ValueError("X must be a numpy ndarray.")
+    if X.ndim != 2:
+        raise ValueError("X must be a 2D array.")
+    flat_index = np.argmax(X)
+    i, j = np.unravel_index(flat_index, X.shape)
 
     return i, j
 
@@ -64,4 +69,13 @@ 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:
+        raise ValueError("The number of terms must be positive")
+    if n_terms == 0:
+        return 1.0
+    n = np.arange(1, n_terms+1, dtype=float)
+    terms = 4*n**2/(4*n**2-1)
+    product = np.prod(terms)
+    pi_approx = 2*product
+    return pi_approx

sklearn_questions.py

@@ -20,55 +20,105 @@
 `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_is_fitted, check_array
 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
         pass
 
     def fit(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Fit the OneNearestNeighbor classifier.
+
+        This method stores the training data X and y inside the estimator
+        so that predictions can be made based on the nearest neighbor rule.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Training data.
+        y : ndarray of shape (n_samples,)
+            Target labels corresponding to X.
+
+        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 the given samples.
+
+        For each sample in X, this method finds the closest training sample
+        stored during ``fit`` using the Euclidean distance, and returns its
+        corresponding label.
 
-        And describe parameters
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Input samples for which to predict class labels.
+
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            Predicted class labels for each sample in X.
         """
         check_is_fitted(self)
         X = check_array(X)
+
+        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."
+            )
+
         y_pred = np.full(
-            shape=len(X), fill_value=self.classes_[0],
-            dtype=self.classes_.dtype
+            shape=len(X),
+            fill_value=self.classes_[0],
+            dtype=self.classes_.dtype,
         )
 
-        # XXX fix
+        for idx, x_i in enumerate(X):
+            diff = self.X_ - x_i
+            distances = np.sqrt(np.sum(diff**2, axis=1))
+            nearest = np.argmin(distances)
+            y_pred[idx] = self.y_[nearest]
+
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Compute the accuracy of the classifier.
+
+        This method compares the predicted labels for X with the true labels y
+        and returns the proportion of correctly classified samples.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Test samples.
+        y : ndarray of shape (n_samples,)
+            True labels for X.
+
+        Returns
+        -------
+        accuracy : float
+            Mean accuracy of the classifier on the given test data.
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
-
-        # XXX fix
-        return y_pred.sum()
+        correct = y_pred == y
+        accuracy = np.mean(correct)
+        return accuracy