kmeans算法实现代码

以下是KMeans算法的Python实现代码：

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.randint(0, len(data) - 1)])

        for i in range(self.max_iterations):
            clusters = {}
            for j in range(self.k):
                clusters[j] = []

            for point in data:
                distances = [np.linalg.norm(point - centroid) for centroid in self.centroids]
                cluster_index = distances.index(min(distances))
                clusters[cluster_index].append(point)

            prev_centroids = self.centroids.copy()

            for cluster_index in clusters:
                self.centroids[cluster_index] = np.average(clusters[cluster_index], axis=0)

            optimized = True
            for j in range(self.k):
                original_centroid = prev_centroids[j]
                current_centroid = self.centroids[j]
                if np.sum((current_centroid - original_centroid) / original_centroid * 100.0) > 0.001:
                    optimized = False

            if optimized:
                break

    def predict(self, data):
        distances = [np.linalg.norm(data - centroid) for centroid in self.centroids]
        cluster_index = distances.index(min(distances))
        return cluster_index

其中，`fit`方法用于训练模型，`predict`方法用于预测数据的类别。