WeiChieh-Chou PartB Submit

numpy_questions.py

@@ -19,49 +19,30 @@
 
 
 def max_index(X):
-    """Return the index of the maximum in a numpy array.
+    """Return the index of the maximum in a numpy array."""
+    # Check input type
+    if not isinstance(X, np.ndarray):
+        raise ValueError("Input must be a numpy array.")
 
-    Parameters
-    ----------
-    X : ndarray of shape (n_samples, n_features)
-        The input array.
+    # Check shape
+    if X.ndim != 2:
+        raise ValueError("Input must be a 2D array.")
 
-    Returns
-    -------
-    (i, j) : tuple(int)
-        The row and columnd index of the maximum.
-
-    Raises
-    ------
-    ValueError
-        If the input is not a numpy array or
-        if the shape is not 2D.
-    """
-    i = 0
-    j = 0
-
-    # TODO
+    # Find the index of maximum
+    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
+    """Compute an approximation of pi using the Wallis product."""
+    if n_terms == 0:
+        return 1.0  # by definition
 
-    Parameters
-    ----------
-    n_terms : int
-        Number of steps in the Wallis product. Note that `n_terms=0` will
-        consider the product to be `1`.
+    product = 1.0
+    for n in range(1, n_terms + 1):
+        term = (4 * n * n) / (4 * n * n - 1)
+        product *= term
 
-    Returns
-    -------
-    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.
+    return 2 * product

sklearn_questions.py

@@ -28,47 +28,90 @@
 from sklearn.utils.multiclass import check_classification_targets
 
 
-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.
 
-        And describe parameters
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data.
+
+        y : array-like of shape (n_samples,)
+            Class labels.
+
+        Returns
+        -------
+        self : object
+            Fitted estimator.
         """
+        # Validate X and y
         X, y = check_X_y(X, y)
         check_classification_targets(y)
+
+        # Store training data
+        self.X_train_ = X
+        self.y_train_ = y
+
+        # Required by sklearn API
         self.classes_ = np.unique(y)
         self.n_features_in_ = X.shape[1]
 
-        # XXX fix
         return self
 
     def predict(self, X):
-        """Write docstring.
+        """Predict class labels using nearest neighbor.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Input data.
 
-        And describe parameters
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            Predicted 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
-        return y_pred
+        # required by sklearn test: MUST match regex
+        if X.shape[1] != self.n_features_in_:
+            raise ValueError(
+                f"X has {X.shape[1]} features, but "
+                f"expects {self.n_features_in_} features as input"
+            )
+
+        y_pred = []
+
+        for x in X:
+            distances = np.linalg.norm(self.X_train_ - x, axis=1)
+            idx = np.argmin(distances)
+            y_pred.append(self.y_train_[idx])
+
+        return np.array(y_pred)
 
     def score(self, X, y):
-        """Write docstring.
+        """Compute accuracy score.
 
-        And describe parameters
+        Parameters
+        ----------
+        X : array-like
+            Input features.
+
+        y : array-like
+            True labels.
+
+        Returns
+        -------
+        accuracy : float
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
-
-        # XXX fix
-        return y_pred.sum()
+        return np.mean(y_pred == y)