请用python实现kmeans算法，不要用sci-kit learn

可以参考下面的代码：
# 导入基本库
import numpy as np

# 定义K-Means类
class KMeans:
# 初始化
def __init__(self, k=2, tol=0.001, max_iter=300):
self.k = k
self.tol = tol
self.max_iter = max_iter

# 训练模型
def fit(self,data):

self.centroids = {}

# 随机选择初始聚类中心
for i in range(self.k):
self.centroids[i] = data[i]

# 迭代更新聚类中心
for i in range(self.max_iter):
self.classifications = {}

# 将每个数据点分配到最近的聚类中心
for i in range(self.k):
self.classifications[i] = []
for featureset in data:
distances = [np.linalg.norm(featureset-self.centroids[centroid]) for centroid in self.centroids]
classification = distances.index(min(distances))
self.classifications[classification].append(featureset)

prev_centroids = dict(self.centroids)

# 更新聚类中心
for classification in self.classifications:
self.centroids[classification] = np.average(self.classifications[classification],axis=0)

# 检查更新是否足够小
optimized = True
for c in self.centroids:
original_centroid = prev_centroids[c]
current_centroid = self.centroids[c]
if np.sum((current_centroid-original_centroid)/original_centroid*100.0) > self.tol:
optimized = False

# 如果更新较小，则保存模型
if optimized:
break

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