Merge branch 'quantum-kmeans-clustering' of https://github.com/RahulPatnaik/Python into quantum-kmeans-clustering

Author: RahulPatnaik

quantum/quantum_kmeans_clustering.py

@@ -4,23 +4,12 @@
 from sklearn.datasets import make_blobs
 from sklearn.preprocessing import MinMaxScaler
 
-def generate_data(n_samples: int = 100, n_features: int = 2, n_clusters: int = 2) -> tuple[np.ndarray, np.ndarray]:
-    """
-    Generates synthetic data using the make_blobs function and normalizes it.
-
-    :param n_samples: Number of samples to generate.
-    :param n_features: Number of features for each sample.
-    :param n_clusters: Number of clusters to generate.
-    :return: A tuple containing normalized data and labels.
 
-    >>> data, labels = generate_data(10, 2, 2)
-    >>> assert data.shape == (10, 2)
-    >>> assert len(labels) == 10
-    """
+def generate_data(n_samples=100, n_features=2, n_clusters=2):
     data, labels = make_blobs(n_samples=n_samples, centers=n_clusters, n_features=n_features, random_state=42)
     return MinMaxScaler().fit_transform(data), labels
 
-def quantum_distance(point1: np.ndarray, point2: np.ndarray) -> float:
+def quantum_distance(point1, point2):
     """
     Computes the quantum distance between two points.
 
@@ -59,51 +48,17 @@ def initialize_centroids(data: np.ndarray, k: int) -> np.ndarray:
     """
     return data[np.random.choice(len(data), k, replace=False)]
 
-def assign_clusters(data: np.ndarray, centroids: np.ndarray) -> list[list[np.ndarray]]:
-    """
-    Assigns data points to the nearest centroid.
-
-    :param data: The dataset to cluster.
-    :param centroids: The current centroids.
-    :return: A list of clusters, each containing points assigned to it.
-
-    >>> data = np.array([[1, 2], [3, 4], [5, 6]])
-    >>> centroids = np.array([[1, 2], [5, 6]])
-    >>> clusters = assign_clusters(data, centroids)
-    >>> assert len(clusters) == 2
-    """
+def assign_clusters(data, centroids):
     clusters = [[] for _ in range(len(centroids))]
     for point in data:
         closest = min(range(len(centroids)), key=lambda i: quantum_distance(point, centroids[i]))
         clusters[closest].append(point)
     return clusters
 
-def recompute_centroids(clusters: list[list[np.ndarray]]) -> np.ndarray:
-    """
-    Recomputes the centroids based on the assigned clusters.
-
-    :param clusters: A list of clusters, each containing points assigned to it.
-    :return: An array of newly computed centroids.
-
-    >>> clusters = [[np.array([1, 2]), np.array([1, 3])], [np.array([5, 6]), np.array([5, 7])]]
-    >>> centroids = recompute_centroids(clusters)
-    >>> assert centroids.shape == (2, 2)
-    """
+def recompute_centroids(clusters):
     return np.array([np.mean(cluster, axis=0) for cluster in clusters if cluster])
 
-def quantum_kmeans(data: np.ndarray, k: int, max_iters: int = 10) -> tuple[np.ndarray, list[list[np.ndarray]]]:
-    """
-    Applies the quantum k-means clustering algorithm.
-
-    :param data: The dataset to cluster.
-    :param k: The number of clusters.
-    :param max_iters: The maximum number of iterations.
-    :return: A tuple containing final centroids and clusters.
-
-    >>> data = np.array([[1, 2], [3, 4], [5, 6]])
-    >>> centroids, clusters = quantum_kmeans(data, 2)
-    >>> assert centroids.shape[0] == 2
-    """
+def quantum_kmeans(data, k, max_iters=10):
     centroids = initialize_centroids(data, k)
 
     for _ in range(max_iters):
@@ -138,4 +93,4 @@ def quantum_kmeans(data: np.ndarray, k: int, max_iters: int = 10) -> tuple[np.nd
 plt.tight_layout()
 plt.show()
 
-print(f"Final Centroids:\n{final_centroids}") 
+print(f"Final Centroids:\n{final_centroids}")