OLIVER SMITH PR LAB

numpy_questions.py

@@ -37,12 +37,25 @@ def max_index(X):
         If the input is not a numpy array or
         if the shape is not 2D.
     """
+    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, but got shape: {}"
+                         .format(X.shape))
+
     i = 0
     j = 0
+    num_rows, num_cols = X.shape
 
-    # TODO
+    max = 0
+    for i in range(num_cols):
+        for j in range(num_rows):
+            if X[i][j] > max:
+                max = X[i][j]
+                res = (i, j)
 
-    return i, j
+    return res
 
 
 def wallis_product(n_terms):
@@ -64,4 +77,11 @@ 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
+    res = 1
+    for i in range(1, n_terms+1):
+        res *= (4 * i**2) / (4 * i**2 - 1)
+
+    return res * 2

sklearn_questions.py

@@ -28,47 +28,98 @@
 from sklearn.utils.multiclass import check_classification_targets
 
 
-class OneNearestNeighbor(BaseEstimator, ClassifierMixin):
-    "OneNearestNeighbor classifier."
+class OneNearestNeighbor(ClassifierMixin, BaseEstimator):
+    """OneNearestNeighbor classifier.
+
+    This classifier implements the 1-nearest neighbor algorithm, which
+    classifies a new data point based on the class of its closest neighbor
+    in the training set. Proximity is measured using Euclidean distance.
+    """
 
     def __init__(self):  # noqa: D107
         pass
 
     def fit(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Train the 1-nearest neighbor classifier.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data, where n_samples is the number of samples and
+            n_features is the number of features.
+        y : array-like of shape (n_samples,)
+            Target values.
+
+        Returns
+        -------
+        self : object
+            Returns self.
         """
         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_train_ = X
+        self.y_train_ = y
         return self
 
     def predict(self, X):
-        """Write docstring.
-
-        And describe parameters
+        """Predict the class labels for the provided data.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Test samples, where n_samples is the number of samples and
+            n_features is the number of features.
+
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            Class labels for each data sample.
         """
-        check_is_fitted(self)
+        check_is_fitted(self, ['X_train_', 'y_train_'])
         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
         )
+        for i, x in enumerate(X):
+            # Calculate distances to all training points
+            distances = np.sqrt(np.sum((self.X_train_ - x)**2, axis=1))
+
+            # Find the index of the minimum distance
+            nearest_idx = np.argmin(distances)
+
+            # Assign the class of the nearest neighbor
+            y_pred[i] = self.y_train_[nearest_idx]
 
-        # XXX fix
         return y_pred
 
     def score(self, X, y):
-        """Write docstring.
-
-        And describe parameters
+        """Return the accuracy on the given test data and labels.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Test samples, where n_samples is the number of samples and
+            n_features is the number of features.
+        y : array-like of shape (n_samples,)
+            True labels for X.
+
+        Returns
+        -------
+        score : float
+            Accuracy of the classifier, which is the fraction of correctly
+            classified samples.
         """
         X, y = check_X_y(X, y)
         y_pred = self.predict(X)
 
         # XXX fix
-        return y_pred.sum()
+        return np.mean(y_pred == y)