Nickhartmann_assignment

numpy_questions.py

@@ -37,10 +37,17 @@ 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.")
 
-    # TODO
+    if X.ndim != 2:
+        raise ValueError("Input must be a 2D array.")
+
+    # Find the flat index of the maximum
+    flat_idx = np.argmax(X)
+
+    # Convert the flat index back to 2D indices
+    i, j = np.unravel_index(flat_idx, X.shape)
 
     return i, j
 
@@ -62,6 +69,13 @@ 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:
+        return 1.0
+
+    k = np.arange(1, n_terms + 1, dtype=float)
+    terms = (4 * k * k) / (4 * k * k - 1)
+
+    # Product converges to pi / 2, so multiply by 2
+    pi_approx = 2 * np.prod(terms)
+
+    return float(pi_approx)

sklearn_questions.py

@@ -22,53 +22,68 @@
 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.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.
+
+    This classifier implements the 1-nearest neighbor rule using the
+    Euclidean distance to find, for each sample, the closest point in the
+    training set and predict its class label.
+    """
 
     def __init__(self):  # noqa: D107
         pass
 
     def fit(self, X, y):
-        """Write docstring.
-
-        And describe parameters
-        """
+        """Fit the OneNearestNeighbor classifier."""
         X, y = check_X_y(X, y)
         check_classification_targets(y)
+
         self.classes_ = np.unique(y)
+        self.X_ = X
+        self.y_ = y
+
+        # Required for sklearn compatibility
         self.n_features_in_ = X.shape[1]
 
-        # XXX fix
         return self
 
     def predict(self, X):
-        """Write docstring.
-
-        And describe parameters
-        """
+        """Predict class labels for samples in X."""
         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
-        return y_pred
+        # Manually enforce n_features_in_ check (older sklearn versions do not)
+        if X.shape[1] != self.n_features_in_:
+            raise ValueError(
+                f"X has {X.shape[1]} features, but {type(self).__name__} "
+                f"is expecting {self.n_features_in_} features as input"
+            )
+
+        # Compute Euclidean distances
+        diff = X[:, np.newaxis, :] - self.X_[np.newaxis, :, :]
+        distances = np.linalg.norm(diff, axis=2)
+        nearest_idx = np.argmin(distances, axis=1)
+
+        return self.y_[nearest_idx]
 
     def score(self, X, y):
-        """Write docstring.
+        """Return the mean accuracy on the given test data and labels."""
+        X = check_array(X)
 
-        And describe parameters
-        """
-        X, y = check_X_y(X, y)
-        y_pred = self.predict(X)
+        if X.shape[1] != self.n_features_in_:
+            raise ValueError(
+                f"X has {X.shape[1]} features, but {type(self).__name__} "
+                f"is expecting {self.n_features_in_} features as input"
+            )
 
-        # XXX fix
-        return y_pred.sum()
+        y_pred = self.predict(X)
+        return float(np.mean(y_pred == y))