本文共 3150 字，大约阅读时间需要 10 分钟。

K-Means????

K-Means ????

K-Means???????????????????????????????????????????????????????????????????????????????????????????

K-Means ?????

K-Means????????????????????

K-Means ?????

K-Means???????????????

K-Means ?????

Python ??????

# ??????
from copy import deepcopy
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
# ????
k = 3
# ?????????
X = np.random.random((200, 2)) * 10
# ??????????
C_x = np.random.choice(range(0, int(np.max(X[:, 0])), size=k, replace=False))
C_y = np.random.choice(range(0, int(np.max(X[:, 1])), size=k, replace=False))
C = np.array(list(zip(C_x, C_y)), dtype=np.float32)
# ????????
print("????????", C)
# ????????????
plt.scatter(X[:, 0], X[:, 1], c='#050505', s=7)
plt.scatter(C[:, 0], C[:, 1], marker='*', s=300, c='g')
plt.show()

??????

# ?????
C_old = np.zeros(C.shape)
clusters = np.zeros(len(X))
# ????????
def dist(a, b, ax=1):
    return np.linalg.norm(a - b, axis=ax)
# ???????????
error = dist(C, C_old, None)
while error != 0:
    # ???????
    for i in range(len(X)):
        distances = dist(X[i], C)
        clusters[i] = np.argmin(distances)
    
    # ????????
    C_old = deepcopy(C)
    
    # ??????
    for i in range(k):
        points = [X[j] for j in range(len(X)) if clusters[j] == i]
        C[i] = np.mean(points, axis=0)
    
    # ????
    error = dist(C, C_old, None)
    # ??????
    colors = ['r', 'g', 'b', 'y', 'c', 'm']
    fig, ax = plt.subplots()
    for i in range(k):
        points = np.array([X[j] for j in range(len(X)) if clusters[j] == i])
        ax.scatter(points[:, 0], points[:, 1], s=7, c=colors[i])
    ax.scatter(C[:, 0], C[:, 1], marker='*', s=200, c='#050505')
    plt.show()

K-Means ?????

1. ????

K-Means??????????????????????????????????????????????

2. ?????

??K-Means???????????????????????????????????????????????????????????????????????????????

K-Means ????????

1. K-Means vs Hard Clustering

K-Means?????????????????????????????????????????Soft Clustering????GMM?????????????????????

2. K-Means ????

K-Means ?????????

??????????????K-Means??????????????????????

img = imread('Tulips.jpg')
imshow(img)
show()

model = KMeans(n_clusters=3)
labels = model.fit_predict(pixel)

palette = model.cluster_centers
for i in range(len(pixel)):
    pixel_new[i, :] = palette[labels[i]]

imshow(pixel_new.reshape(img.shape[0], img.shape[1], 3))
show()

K-Means ?????

K-Means ??????

??K-Means?????????????????????????

??

K-Means??????????????????????????????????????????????????????????????????K-Means?????????