基于Python——Kmeans聚类算法的实现

距离算法公式实现(calculate_distance_algorithm.py)：

import numpy as np
def manhattan_distance(x1, x2):
    """
    计算两点间的曼哈顿距离
    :param x1:(x1, y1)
    :param x2:(x2, y2)
    :return:返回两点之间的曼哈顿距离
    """
    result = np.abs(x1[0] - x2[0]) + np.abs(x1[1] - x1[1])
    return result
def chebyshev_distance(x1, x2):
    """
    计算两点间的切比雪夫距离
    :param x1:(x1, y1)
    :param x2:(x2, y2)
    :return:返回两点之间的切比雪夫距离
    """
    return np.max(np.abs(x1 - x2))
def euclid_distance(x1, x2):
    """
    计算两点间的欧式距离
    :param x1:(x1, y1)
    :param x2:(x2, y2)
    :return: 返回两点之间的欧式距离
    """
    return np.sqrt(np.sum((x1 - x2) ** 2))

聚类图片对象为：

聚类结果图像：

测试代码：

import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
import cv2 as cv
from K_means import KMeans
from calculate_distance_algorithm import manhattan_distance, chebyshev_distance, euclid_distance
def recreate_image(clusters, labels, w, h):
    """
    重新创建图像
    :param clusters: 聚类中心
    :param labels: 预测的种类集合
    :param w: 图像的宽
    :param h: 图像的高
    :return: 返回图像
    """
    d = clusters.shape[1]    # 构建图像 w：宽， h:高， d:聚类个数
    # print(clusters)
    image = np.zeros((w, h, d))
    label_idx = 0
    for i in range(w):
        for j in range(h):
            image[i][j] = clusters[labels[label_idx]]            # print(image[i][j])
            label_idx += 1
    return image
def get_data(data, k):
    """
    将对应的三维数组转换成 n*4维的矩阵，前3列是数据，最后一列是该类数据对应的样本标签值k
    :param data: 数据
    :param k: 标签
    :return: 转换好的n*4维数据
    """
    # 展开成n*3维
    data = data.reshape(-1, 3)
    # 生成颜色对应的标签
    data_label = np.ones((data.shape[0], 1))
    data_label *= k
    # 将标签列与数据合并
    return np.hstack((data, data_label))
if __name__ == '__main__':
 3/5   首页 上一页 1 2 3 4 5 下一页 尾页