python实现mean-shift聚类算法
程序员文章站
2022-03-12 11:01:12
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s...
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
2、调用上述py文件
# -*- coding: utf-8 -*- """ created on tue oct 09 11:02:08 2018 @author: muli """ from sklearn.datasets.samples_generator import make_blobs import matplotlib.pyplot as plt import random import numpy as np import meanshift def colors(n): ret = [] for i in range(n): ret.append((random.uniform(0, 1), random.uniform(0, 1), random.uniform(0, 1))) return ret def main(): centers = [[-1, -1], [-1, 1], [1, -1], [1, 1]] x, _ = make_blobs(n_samples=300, centers=centers, cluster_std=0.4) mean_shifter = meanshift.mean_shift() _, mean_shift_result = mean_shifter.fit(x, kernel_bandwidth=0.5) np.set_printoptions(precision=3) print('input: {}'.format(x)) print('assined clusters: {}'.format(mean_shift_result)) color = colors(np.unique(mean_shift_result).size) for i in range(len(mean_shift_result)): plt.scatter(x[i, 0], x[i, 1], color = color[mean_shift_result[i]]) plt.show() if __name__ == '__main__': main()
结果如图所示:
参考
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持。