這是I/O

以下是代碼：

import matplotlib.pyplot as plt

import pandas as pd

import numpy as np

def findDistance(x, y):

return np.sqrt(np.sum(np.power(x-y, 2)))

def findPoints(data, k):

m, n = np.shape(data)

points = np.mat(np.zeros((k, n)))

for i in range(n):

min = np.min(data[:, i])

I = float(np.max(data[:, i]) - min)

points[:, i] = min + I * np.random.rand(k, 1)

return points

def kMeans(data, k):

m, n = np.shape(data)

cluster = np.mat(np.zeros((m, 2)))

points = findPoints(data, k)

flag = True

while flag:

flag = False

for i in range(m):

minDistance = np.inf

minIndex = -1

for j in range(k):

distance = findDistance(points[j, :], data[i, :])

if distance < minDistance:

minDistance = distance

minIndex = j

if cluster[i, 0] != minIndex:

flag = True

cluster[i, :] = minIndex, minDistance**2

for p in range(k):

pts = data[np.nonzero(cluster[:, 0].A == p)[0]]

points[p, :] = np.mean(pts, axis=0)

return points, cluster

if __name__ == '__main__':

data = pd.read_csv("E:\\result.csv")

data = pd.DataFrame({'x': data['value'], 'y': data['price']})

data = data.to_numpy()

k = 2

a, b = kMeans(data, k)

fig = plt.figure(figsize=(10, 10), dpi=100)

ax = fig.add_subplot(111)

ax.set_xlabel("$value$")

ax.set_xticks(range(0, 250000, 25000))

ax.set_ylabel("$price$")

ax.set_yticks(range(0, 85000, 5000))

ax.set_title('K-means')

for i in range(k):

pts = data[np.nonzero(b[:, 0].A == i)[0], :]

ax.scatter(np.matrix(data[:, 0]).A[0], np.matrix(data[:, 1]).A[0], marker='o', s=90, color='b', alpha=0.2)

ax.scatter(a[:, 0].flatten().A[0], a[:, 1].flatten().A[0], marker='*', s=900, color='r', alpha=0.9)

plt.show()

END

總結

以上是生活随笔為你收集整理的python实现kmean算法_K-means聚类算法的Python实现,Kmeans的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。