python如何实现mean-shift聚类算法-创新互联

这篇文章主要讲解了python如何实现mean-shift聚类算法，内容清晰明了，对此有兴趣的小伙伴可以学习一下，相信大家阅读完之后会有帮助。

本文实例为大家分享了python实现mean-shift聚类算法的具体代码，供大家参考，具体内容如下

1、新建MeanShift.py文件

import numpy as np

# 定义 预先设定 的阈值
STOP_THRESHOLD = 1e-4
CLUSTER_THRESHOLD = 1e-1


# 定义度量函数
def distance(a, b):
 return np.linalg.norm(np.array(a) - np.array(b))


# 定义高斯核函数
def gaussian_kernel(distance, bandwidth):
 return (1 / (bandwidth * np.sqrt(2 * np.pi))) * np.exp(-0.5 * ((distance / bandwidth)) ** 2)


# mean_shift类
class mean_shift(object):
 def __init__(self, kernel=gaussian_kernel):
  self.kernel = kernel

 def fit(self, points, kernel_bandwidth):

  shift_points = np.array(points)
  shifting = [True] * points.shape[0]

  while True:
   max_dist = 0
   for i in range(0, len(shift_points)):
    if not shifting[i]:
     continue
    p_shift_init = shift_points[i].copy()
    shift_points[i] = self._shift_point(shift_points[i], points, kernel_bandwidth)
    dist = distance(shift_points[i], p_shift_init)
    max_dist = max(max_dist, dist)
    shifting[i] = dist > STOP_THRESHOLD

   if(max_dist < STOP_THRESHOLD):
    break
  cluster_ids = self._cluster_points(shift_points.tolist())
  return shift_points, cluster_ids

 def _shift_point(self, point, points, kernel_bandwidth):
  shift_x = 0.0
  shift_y = 0.0
  scale = 0.0
  for p in points:
   dist = distance(point, p)
   weight = self.kernel(dist, kernel_bandwidth)
   shift_x += p[0] * weight
   shift_y += p[1] * weight
   scale += weight
  shift_x = shift_x / scale
  shift_y = shift_y / scale
  return [shift_x, shift_y]

 def _cluster_points(self, points):
  cluster_ids = []
  cluster_idx = 0
  cluster_centers = []

  for i, point in enumerate(points):
   if(len(cluster_ids) == 0):
    cluster_ids.append(cluster_idx)
    cluster_centers.append(point)
    cluster_idx += 1
   else:
    for center in cluster_centers:
     dist = distance(point, center)
     if(dist < CLUSTER_THRESHOLD):
      cluster_ids.append(cluster_centers.index(center))
    if(len(cluster_ids) < i + 1):
     cluster_ids.append(cluster_idx)
     cluster_centers.append(point)
     cluster_idx += 1
  return cluster_ids