Part B: Bhavesh Chauhan

numpy_questions.py

@@ -37,20 +37,20 @@ 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("Input must be a 2D array.")
 
-    # TODO
+    flat_index = np.argmax(X)
+    i, j = np.unravel_index(flat_index, X.shape)
 
     return i, j
 
 
 def wallis_product(n_terms):
     """Implement the Wallis product to compute an approximation of pi.
 
-    See:
-    https://en.wikipedia.org/wiki/Wallis_product
-
     Parameters
     ----------
     n_terms : int
@@ -62,6 +62,11 @@ 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
+    product = 1.0
+
+    for k in range(1, n_terms + 1):
+        product *= (4 * k * k) / (4 * k * k - 1)
+
+    return 2 * product

sklearn_questions.py

@@ -20,55 +20,96 @@
 `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.utils.multiclass import check_classification_targets
 
+# Try importing validate_data from newer sklearn
+try:
+    from sklearn.utils.validation import validate_data
+except ImportError:
+    # Fallback validate_data for older sklearn versions (used on CI)
+    def validate_data(estimator, X, y=None, **kwargs):
+        """
+        Fallback implementation of validate_data for older sklearn versions.
+
+        Parameters
+        ----------
+        estimator : estimator instance
+            The estimator calling this function.
+        X : array-like
+            Input data.
+        y : array-like, optional
+            Target values.
+        kwargs : dict
+            Additional arguments (e.g., dtype, ensure_2d, reset).
+        """
+        # Remove unsupported kwargs for check_array/check_X_y
+        kwargs.pop("reset", None)
+
+        if y is not None:
+            X, y = check_X_y(X, y, **kwargs)
+            estimator.n_features_in_ = X.shape[1]
+            return X, y
+        else:
+            X_checked = check_array(X, **kwargs)
+            return X_checked
 
-class OneNearestNeighbor(BaseEstimator, ClassifierMixin):
-    "OneNearestNeighbor classifier."
+
+class OneNearestNeighbor(ClassifierMixin, BaseEstimator):
+    """OneNearestNeighbor classifier."""
 
     def __init__(self):  # noqa: D107
         pass
 
     def fit(self, X, y):
-        """Write docstring.
+        """Fit the OneNearestNeighbor classifier."""
+        # Validate input (numeric only)
+        X, y = check_X_y(X, y, dtype="numeric")
 
-        And describe parameters
-        """
-        X, y = check_X_y(X, y)
         check_classification_targets(y)
+
+        # Store training data
+        self.X_ = X
+        self.y_ = y
+
+        # Required sklearn attribute
         self.classes_ = np.unique(y)
+
+        # Required for compatibility with predict
         self.n_features_in_ = X.shape[1]
 
-        # XXX fix
         return self
 
     def predict(self, X):
-        """Write docstring.
-
-        And describe parameters
-        """
+        """Predict class labels using 1-nearest neighbor."""
         check_is_fitted(self)
-        X = check_array(X)
-        y_pred = np.full(
-            shape=len(X), fill_value=self.classes_[0],
-            dtype=self.classes_.dtype
+
+        # Validate input and check feature consistency
+        X = validate_data(
+            self, X,
+            dtype="numeric",
+            ensure_2d=True,
+            reset=False
         )
 
-        # XXX fix
+        n_test = X.shape[0]
+        y_pred = np.empty(n_test, dtype=self.y_.dtype)
+
+        for i in range(n_test):
+            distances = np.sum((self.X_ - X[i]) ** 2, axis=1)
+            nn_index = np.argmin(distances)
+            y_pred[i] = self.y_[nn_index]
+
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
-        """
-        X, y = check_X_y(X, y)
+        """Return mean accuracy."""
+        X, y = check_X_y(X, y, dtype="numeric")
         y_pred = self.predict(X)
-
-        # XXX fix
-        return y_pred.sum()
+        return np.mean(y_pred == y)