Repeat {
for i = 1 to m
c(i) := index (form 1 to K) of cluster centroid closest to x(i)
for k = 1 to K
μk := average (mean) of points assigned to cluster k
}

from sklearn.cluster import KMeans ?# 導(dǎo)入 sklearn.cluster.KMeans 類
import numpy as np
?
X = np.array([[1,2], [1,4], [1,0], [10,2], [10,4], [10,0]])
kmCluster = KMeans(n_clusters=2).fit(X) ?# 建立模型并進行聚類，設(shè)定 K=2
print("聚類中心坐標:",kmCluster.cluster_centers_) ?# 返回每個聚類中心的坐標
print("分類結(jié)果:",kmCluster.labels_) ?# 返回樣本集的分類結(jié)果
print("顯示預(yù)測判斷:",kmCluster.predict([[0, 0], [12, 3]])) ?# 根據(jù)模型聚類結(jié)果進行預(yù)測判斷

聚類中心坐標: [[10. ?2.]
?[ 1. ?2.]]
分類結(jié)果: [1 1 1 0 0 0]
顯示預(yù)測判斷: [1 0]
?
Process finished with exit code 0

from sklearn.cluster import MiniBatchKMeans # 導(dǎo)入 .MiniBatchKMeans 類
import numpy as np
X = np.array([[1,2], [1,4], [1,0], [4,2], [4,0], [4,4],
? ? ? ? ? ? ? [4,5], [0,1], [2,2],[3,2], [5,5], [1,-1]])
# fit on the whole data
mbkmCluster = MiniBatchKMeans(n_clusters=3,batch_size=6,max_iter=10).fit(X)
print("聚類中心的坐標:",mbkmCluster.cluster_centers_) # 返回每個聚類中心的坐標
print("樣本集的分類結(jié)果:",mbkmCluster.labels_) ?# 返回樣本集的分類結(jié)果
print("顯示判斷結(jié)果：樣本屬于哪個類別:",mbkmCluster.predict([[0,0], [4,5]])) ?# 根據(jù)模型聚類結(jié)果進行預(yù)測判斷

聚類中心的坐標: [[ 2.55932203 ?1.76271186]
?[ 0.75862069 -0.20689655]
?[ 4.20588235 ?4.5 ? ? ? ]]
樣本集的分類結(jié)果: [0 0 1 0 0 2 2 1 0 0 2 1]
顯示判斷結(jié)果：樣本屬于哪個類別: [1 2]
?
Process finished with exit code 0

from sklearn.cluster import kmeans_plusplus
from sklearn.datasets import make_blobs
import matplotlib.pyplot as plt
?
# Generate sample data
n_samples = 4000
n_components = 4
?
X, y_true = make_blobs(
? ? n_samples=n_samples, centers=n_components, cluster_std=0.60, random_state=0
)
X = X[:, ::-1]
?
# Calculate seeds from kmeans++
centers_init, indices = kmeans_plusplus(X, n_clusters=4, random_state=0)
?
# Plot init seeds along side sample data
plt.figure(1)
colors = ["#4EACC5", "#FF9C34", "#4E9A06", "m"]
?
for k, col in enumerate(colors):
? ? cluster_data = y_true == k
? ? plt.scatter(X[cluster_data, 0], X[cluster_data, 1], c=col, marker=".", s=10)
?
plt.scatter(centers_init[:, 0], centers_init[:, 1], c="b", s=50)
plt.title("K-Means++ Initialization")
plt.xticks([])
plt.yticks([])
plt.show()

# ?-*- coding: utf-8 -*-
import numpy as np
import pandas as pd
from sklearn.cluster import KMeans, MiniBatchKMeans
?
def main():
? ? # 讀取數(shù)據(jù)文件
? ? file = pd.read_excel('K-Means.xlsx', header=0) ?# 首行為標題行
? ? file = file.dropna() ?# 刪除含有缺失值的數(shù)據(jù)
? ? # print(file.dtypes) ?# 查看 df 各列的數(shù)據(jù)類型
? ? # print(file.shape) ?# 查看 df 的行數(shù)和列數(shù)
? ? print(file.head())
?
? ? # 數(shù)據(jù)準備
? ? z_scaler = lambda x:(x-np.mean(x))/np.std(x) ?# 定義數(shù)據(jù)標準化函數(shù)
? ? dfScaler = file[['D1','D2','D3','D4','D5','D6','D7','D8','D9','D10']].apply(z_scaler) ?# 數(shù)據(jù)歸一化
? ? dfData = pd.concat([file[['地區(qū)']], dfScaler], axis=1) ?# 列級別合并
? ? df = dfData.loc[:,['D1','D2','D3','D4','D5','D6','D7','D8','D9','D10']] ?# 基于全部 10個特征聚類分析
? ? # df = dfData.loc[:,['D1','D2','D7','D8','D9','D10']] ?# 降維后選取 6個特征聚類分析
? ? X = np.array(df) ?# 準備 sklearn.cluster.KMeans 模型數(shù)據(jù)
? ? print("Shape of cluster data:", X.shape)
?
? ? # KMeans 聚類分析(sklearn.cluster.KMeans)
? ? nCluster = 4
? ? kmCluster = KMeans(n_clusters=nCluster).fit(X) ?# 建立模型并進行聚類，設(shè)定 K=4
? ? print("Cluster centers:\n", kmCluster.cluster_centers_) ?# 返回每個聚類中心的坐標
? ? print("Cluster results:\n", kmCluster.labels_) ?# 返回樣本集的分類結(jié)果
?
? ? # 整理聚類結(jié)果(太棒啦！)
? ? listName = dfData['地區(qū)'].tolist() ?# 將 dfData 的首列 '地區(qū)' 轉(zhuǎn)換為 list
? ? dictCluster = dict(zip(listName,kmCluster.labels_)) ?# 將 listName 與聚類結(jié)果關(guān)聯(lián)，組成字典
? ? listCluster = [[] for k in range(nCluster)]
? ? for v in range(0, len(dictCluster)):
? ? ? ? k = list(dictCluster.values())[v] ?# 第v個城市的分類是 k
? ? ? ? listCluster[k].append(list(dictCluster.keys())[v]) ?# 將第v個城市添加到 第k類
? ? print("\n聚類分析結(jié)果(分為{}類):".format(nCluster)) ?# 返回樣本集的分類結(jié)果
? ? for k in range(nCluster):
? ? ? ? print("第 {} 類：{}".format(k, listCluster[k])) ?# 顯示第 k 類的結(jié)果
?
? ? return
?
if __name__ == '__main__':
? ? main()