[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Author: pre-commit-ci[bot]

machine_learning/k_medoids.py

@@ -23,18 +23,21 @@
 from matplotlib import pyplot as plt
 from sklearn.metrics import pairwise_distances
 
+
 def get_initial_medoids(data, k, seed=None):
     rng = np.random.default_rng(seed)
     n = data.shape[0]
     indices = rng.choice(n, k, replace=False)
     medoids = data[indices, :]
     return medoids
 
+
 def assign_clusters(data, medoids):
-    distances = pairwise_distances(data, medoids, metric='euclidean')
+    distances = pairwise_distances(data, medoids, metric="euclidean")
     cluster_assignment = np.argmin(distances, axis=1)
     return cluster_assignment
 
+
 def revise_medoids(data, k, cluster_assignment):
     new_medoids = []
     for i in range(k):
@@ -47,6 +50,7 @@ def revise_medoids(data, k, cluster_assignment):
         new_medoids.append(members[medoid_index])
     return np.array(new_medoids)
 
+
 def compute_heterogeneity(data, k, medoids, cluster_assignment):
     heterogeneity = 0.0
     for i in range(k):
@@ -57,14 +61,18 @@ def compute_heterogeneity(data, k, medoids, cluster_assignment):
         heterogeneity += np.sum(distances**2)
     return heterogeneity
 
+
 def kmedoids(data, k, initial_medoids, maxiter=100, verbose=False):
     medoids = initial_medoids.copy()
     prev_assignment = None
     for itr in range(maxiter):
         cluster_assignment = assign_clusters(data, medoids)
         medoids = revise_medoids(data, k, cluster_assignment)
 
-        if prev_assignment is not None and (prev_assignment == cluster_assignment).all():
+        if (
+            prev_assignment is not None
+            and (prev_assignment == cluster_assignment).all()
+        ):
             break
 
         if verbose and prev_assignment is not None:
@@ -75,21 +83,24 @@ def kmedoids(data, k, initial_medoids, maxiter=100, verbose=False):
 
     return medoids, cluster_assignment
 
+
 # Optional plotting
 def plot_clusters(data, medoids, cluster_assignment):
-    ax = plt.axes(projection='3d')
-    ax.scatter(data[:,0], data[:,1], data[:,2], c=cluster_assignment, cmap='viridis')
-    ax.scatter(medoids[:,0], medoids[:,1], medoids[:,2], c='red', s=100, marker='x')
+    ax = plt.axes(projection="3d")
+    ax.scatter(data[:, 0], data[:, 1], data[:, 2], c=cluster_assignment, cmap="viridis")
+    ax.scatter(medoids[:, 0], medoids[:, 1], medoids[:, 2], c="red", s=100, marker="x")
     ax.set_xlabel("X")
     ax.set_ylabel("Y")
     ax.set_zlabel("Z")
     ax.set_title("3D K-Medoids Clustering")
     plt.show()
 
+
 # Optional test
 if __name__ == "__main__":
     from sklearn import datasets
-    X = datasets.load_iris()['data']
+
+    X = datasets.load_iris()["data"]
     k = 3
     medoids = get_initial_medoids(X, k, seed=0)
     medoids, clusters = kmedoids(X, k, medoids, maxiter=50, verbose=True)

machine_learning/k_nearest_neighbours.py

@@ -54,7 +54,9 @@ def _calculate_distance(self, a: np.ndarray[float], b: np.ndarray[float]) -> flo
         elif self.distance_metric == "minkowski":
             return float(np.sum(np.abs(a - b) ** self.p) ** (1 / self.p))
         else:
-            raise ValueError("Invalid distance metric. Choose 'euclidean', 'manhattan', or 'minkowski'.")
+            raise ValueError(
+                "Invalid distance metric. Choose 'euclidean', 'manhattan', or 'minkowski'."
+            )
 
     def classify(self, pred_point: np.ndarray[float], k: int = 5) -> str:
         """
@@ -81,6 +83,7 @@ def classify(self, pred_point: np.ndarray[float], k: int = 5) -> str:
 
 if __name__ == "__main__":
     import doctest
+
     doctest.testmod()
 
     iris = datasets.load_iris()
@@ -102,4 +105,4 @@ def classify(self, pred_point: np.ndarray[float], k: int = 5) -> str:
 
     print("\nUsing Minkowski Distance (p=3):")
     classifier3 = KNN(X_train, y_train, iris_classes, distance_metric="minkowski", p=3)
-    print(classifier3.classify(iris_point, k=3))
+    print(classifier3.classify(iris_point, k=3))