Kmeans聚类算法代码

好的，以下是Kmeans聚类算法的Python代码：

import numpy as np

class KMeans:
    def __init__(self, k=2, max_iterations=500):
        self.k = k
        self.max_iterations = max_iterations

    def fit(self, data):
        self.centroids = []
        for i in range(self.k):
            self.centroids.append(data[np.random.choice(range(len(data)))])
        
        for i in range(self.max_iterations):
            clusters = [[] for _ in range(self.k)]
            
            for point in data:
                distances = [np.linalg.norm(point - centroid) for centroid in self.centroids]
                cluster_index = np.argmin(distances)
                clusters[cluster_index].append(point)
            
            prev_centroids = self.centroids.copy()
            
            for i in range(self.k):
                if clusters[i]:
                    self.centroids[i] = np.mean(clusters[i], axis=0)

            if prev_centroids == self.centroids:
                break

    def predict(self, data):
        predictions = []
        for point in data:
            distances = [np.linalg.norm(point - centroid) for centroid in self.centroids]
            cluster_index = np.argmin(distances)
            predictions.append(cluster_index)
        return predictions

使用示例：

import matplotlib.pyplot as plt
from sklearn.datasets import make_blobs

X, y = make_blobs(n_samples=300, centers=4, cluster_std=0.60, random_state=0)

kmeans = KMeans(k=4)
kmeans.fit(X)

predictions = kmeans.predict(X)

plt.scatter(X[:, 0], X[:, 1], c=predictions, cmap='viridis')
plt.scatter(kmeans.centroids[:, 0], kmeans.centroids[:, 1], marker='*', s=300, c='black')
plt.show()

该代码使用KMeans算法对样本数据进行聚类，并将结果可视化展示出来。