python手写kmeans算法

kmean聚类是最基础和常见的算法，工程上使用比较常见，spark, sklearn都有实现，本文手写实现kmeans

#!/usr/bin/python
import sys
import random
import math

def create_rand_points(max_x, max_y, count):
    """Create count points (0-x), (0-y).

    """
    points = []
    for i in range(0, count):
        x = random.randint(0, max_x)
        y = random.randint(0, max_y)
        points.append([x,y])
    return points

def get_start_k_points(points, k):
    """Get k start points.

    """
    if k > len(points):
        return None
    random.shuffle(points)
    return points[0:k]

def get_nearest_point_index(point, central_points):
    """
    """
    min_dis = 2000000000
    index = 0
    for i in range(0, len(central_points)):
        dis = 0.0
        for j in range(0, len(point)):
            dis += (point[j]-central_points[i][j]) * (point[j]-central_points[i][j])
        if math