人工智能——K-Means聚類算法及Python實現

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)  # 建立模型並進行聚類，設定 K=2
print("聚類中心坐標:",kmCluster.cluster_centers_)  # 返回每個聚類中心的坐標
print("分類結果:",kmCluster.labels_)  # 返回樣本集的分類結果
print("顯示預測判斷:",kmCluster.predict([[0, 0], [12, 3]]))  # 根據模型聚類結果進行預測判斷

聚類中心坐標: [[10.  2.]
 [ 1.  2.]]
分類結果: [1 1 1 0 0 0]
顯示預測判斷: [1 0]
 
Process finished with exit code 0

from sklearn.cluster import MiniBatchKMeans # 導入 .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("樣本集的分類結果:",mbkmCluster.labels_)  # 返回樣本集的分類結果
print("顯示判斷結果：樣本屬於哪個類別:",mbkmCluster.predict([[0,0], [4,5]]))  # 根據模型聚類結果進行預測判斷

聚類中心的坐標: [[ 2.55932203  1.76271186]
 [ 0.75862069 -0.20689655]
 [ 4.20588235  4.5       ]]
樣本集的分類結果: [0 0 1 0 0 2 2 1 0 0 2 1]
顯示判斷結果：樣本屬於哪個類別: [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():
    # 讀取數據文件
    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據
    # print(file.dtypes)  # 查看 df 各列的數據類型
    # print(file.shape)  # 查看 df 的行數和列數
    print(file.head())
 
    # 數據準備
    z_scaler = lambda x:(x-np.mean(x))/np.std(x)  # 定義數據標準化函數
    dfScaler = file[['D1','D2','D3','D4','D5','D6','D7','D8','D9','D10']].apply(z_scaler)  # 數據歸一化
    dfData = pd.concat([file[['地區']], dfScaler], axis=1)  # 列級別合並
    df = dfData.loc[:,['D1','D2','D3','D4','D5','D6','D7','D8','D9','D10']]  # 基於全部 10個特征聚類分析
    # df = dfData.loc[:,['D1','D2','D7','D8','D9','D10']]  # 降維後選取 6個特征聚類分析
    X = np.array(df)  # 準備 sklearn.cluster.KMeans 模型數據
    print("Shape of cluster data:", X.shape)
 
    # KMeans 聚類分析(sklearn.cluster.KMeans)
    nCluster = 4
    kmCluster = KMeans(n_clusters=nCluster).fit(X)  # 建立模型並進行聚類，設定 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果
 
    # 整理聚類結果(太棒啦！)
    listName = dfData['地區'].tolist()  # 將 dfData 的首列 '地區' 轉換為 list
    dictCluster = dict(zip(listName,kmCluster.labels_))  # 將 listName 與聚類結果關聯，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聚類分析結果(分為{}類):".format(nCluster))  # 返回樣本集的分類結果
    for k in range(nCluster):
        print("第 {} 類：{}".format(k, listCluster[k]))  # 顯示第 k 類的結果
 
    return
 
if __name__ == '__main__':
    main()

#*========================1. 建立工程，導入sklearn相關包======================================**
 
import numpy as np
from sklearn.cluster import KMeans
 
#*======================2. 加載數據，創建K-means算法實例，並進行訓練，獲得標簽====================**
 
def loadData(filePath):
    fr = open(filePath, 'r+')            #r+：讀寫打開一個文本文件
    lines = fr.readlines()           #.readlines() 一次讀取整個文件（類似於 .read() ) .readline() 每次隻讀.readlines() 慢得多。
    retData = []                     #retData：用來存儲城市的各項消費信息
    retCityName = []                 #retCityName：用來存儲城市名稱
    for line in lines:
        items = line.strip().split(",")
        retCityName.append(items[0])
        retData.append([float(items[i]) for i in range(1, len(items))])
    return retData, retCityName      #返回值：返回城市名稱，以及該城市的各項消費信息
 
def main():
    data, cityName = loadData('city.txt')    #1.利用loadData方法讀取數據
    km = KMeans(n_clusters=4)                #2.創建實例
    label = km.fit_predict(data)             #3.調用Kmeans（）fit_predict()方法進行計算
    expenses = np.sum(km.cluster_centers_, axis=1)
    # print(expenses)
    CityCluster = [[], [], [], []]          #將城市按label分成設定的簇
    for i in range(len(cityName)):
        CityCluster[label[i]].append(cityName[i])   #將每個簇的城市輸出
    for i in range(len(CityCluster)):              #將每個簇的平均花費輸出
        print("Expenses:%.2f" % expenses[i])
        print(CityCluster[i])
 
if __name__ == '__main__':
    main()
 
#*=============3. 輸出標簽，查看結果========================================**
 
#將城市按照消費水平n_clusters類，消費水平相近的城市聚集在一類中
#expense：聚類中心點的數值加和，也就是平均消費水平