基于鸢尾花数据集的四种聚类算法(kmeans,层次聚类,DBSCAN,FCM)和学习向量量化对比

基于鸢尾花数据集的四种聚类算法(kmeans,层次聚类,DBSCAN,FCM)和学习向量量化对比

注:下面的代码可能需要做一点参数调整,才得到所有我的运行结果。

kmeans算法:

python 复制代码
import matplotlib.pyplot as plt # 导入matplotlib的库
import numpy as np # 导入numpy的包
from sklearn import datasets #导入数据集
from sklearn.decomposition import PCA # PCA主成分分析类
from sklearn.metrics import silhouette_score
from sklearn.metrics import calinski_harabasz_score
from sklearn.metrics import davies_bouldin_score
iris = datasets.load_iris() #加载iris数据集
X = iris.data #加载特征数据
# Y = iris.target #加载标签数据
#绘制数据分布图
y = iris.target
X = iris.data
#X.shape
#调用PCA
pca = PCA(n_components=2) # 降到2维
pca = pca.fit(X) #拟合模型
X_dr = pca.transform(X) #获取新矩阵 (降维后的)
#X_dr



#也可以fit_transform一步到位
#X_dr = PCA(2).fit_transform(X)


#plt.figure()
#plt.scatter(X_dr[y==0, 0], X_dr[y==0, 1], c="red", label=iris.target_names[0]) 
#plt.scatter(X_dr[y==1, 0], X_dr[y==1, 1], c="black", label=iris.target_names[1])
#plt.scatter(X_dr[y==2, 0], X_dr[y==2, 1], c="orange", label=iris.target_names[2])
#plt.legend()
#plt.title('PCA of IRIS dataset')
#plt.show()


print("===K-means聚类===")
from sklearn.cluster import KMeans # 引入KMeans模块


estimator = KMeans(n_clusters=3).fit(X)  # 构造聚类器
label_pred = estimator.labels_  # 获取聚类标签

# 评估指标列表  
silhouette_avg_scores = []  
  
Calinski_Harabasz_scores = []  
Davies_Bouldin_scores = []  
# 遍历不同的n_clusters值  
for n_clusters in range(2, 11):  
    kmeans = KMeans(n_clusters=n_clusters)  
    kmeans.fit(X)  
    labels = kmeans.labels_  
    silhouette_avg = silhouette_score(X, kmeans.labels_)  
    print(silhouette_avg)
# 2. Calinski-Harabasz指数
    calinski_haraba=calinski_harabasz_score(X, kmeans.labels_)
    print(calinski_haraba)
 
    # 3. DB指数(Davies-Bouldin Index)
    davies_bouldin=davies_bouldin_score(X, kmeans.labels_)
    Davies_Bouldin_scores.append(davies_bouldin)
    Calinski_Harabasz_scores.append(calinski_haraba)
    silhouette_avg_scores.append(silhouette_avg)  
  
# 绘制图形  
plt.plot(range(2, 11), silhouette_avg_scores, marker='o', label='Silhouette Coefficient')  

plt.title('Silhouette Coefficient for Different n_clusters-kmeans')  
plt.xlabel('Number of clusters (n_clusters)')  
plt.ylabel('Silhouette Coefficient')  
plt.legend()
plt.show()
 
plt.plot(range(2, 11), Calinski_Harabasz_scores, marker='o', label=' Calinski-Harabasz')  
plt.title(' Calinski-Harabaszfor Different n_clusters-kmeans')  
plt.xlabel('Number of clusters (n_clusters)')  
plt.ylabel('Calinski Harabasz')  
plt.legend()
plt.show()

  
plt.plot(range(2, 11), Davies_Bouldin_scores, marker='o', label='Davies-Bouldin Index')  
plt.title('Davies-Bouldin Index for Different n_clusters-kmeans')  
plt.xlabel('Number of clusters (n_clusters)')  
plt.ylabel('Davies-Bouldin Index')  
plt.legend()
plt.show()

运行结果如下:

DBSCAN:

python 复制代码
import matplotlib.pyplot as plt # 导入matplotlib的库
import numpy as np # 导入numpy的包
from sklearn import datasets #导入数据集
from sklearn.decomposition import PCA # PCA主成分分析类
from sklearn.metrics import silhouette_score
from sklearn.metrics import calinski_harabasz_score
from sklearn.metrics import davies_bouldin_score

from sklearn.cluster import DBSCAN # 引入DBSCAN模块

iris = datasets.load_iris() #加载iris数据集
X = iris.data #加载特征数据
# Y = iris.target #加载标签数据
#绘制数据分布图
y = iris.target
X = iris.data
#X.shape
##调用PCA
#pca = PCA(n_components=2) # 降到2维
#pca = pca.fit(X) #拟合模型
#X_dr = pca.transform(X) #获取新矩阵 (降维后的)
##X_dr



#也可以fit_transform一步到位
#X_dr = PCA(2).fit_transform(X)


#plt.figure()
#plt.scatter(X_dr[y==0, 0], X_dr[y==0, 1], c="red", label=iris.target_names[0]) 
#plt.scatter(X_dr[y==1, 0], X_dr[y==1, 1], c="black", label=iris.target_names[1])
#plt.scatter(X_dr[y==2, 0], X_dr[y==2, 1], c="orange", label=iris.target_names[2])
#plt.legend()
#plt.title('PCA of IRIS dataset')
#plt.show()


print("===DBSCAN聚类===")
from sklearn.cluster import KMeans # 引入KMeans模块


estimator = KMeans(n_clusters=3).fit(X)  # 构造聚类器
label_pred = estimator.labels_  # 获取聚类标签

# 评估指标列表  
silhouette_avg_scores = []  
  
Calinski_Harabasz_scores = []  
Davies_Bouldin_scores = []  
# 遍历不同的n_clusters值  
for n_clusters in range(2, 11):  
    dbscan = DBSCAN(eps=0.4, min_samples=n_clusters).fit(X) #导入DBSCAN模块进行训练,在一个邻域的半径内min_samples数的邻域eps被认为是一个簇。请记住,初始点包含在min_samples中。
    label_pred = dbscan.labels_ # labels为每个数据的簇标签,不在任何"高密度"集群中的"noisy"样本返回-1
    silhouette_avg = silhouette_score(X, dbscan.labels_)  
    print(silhouette_avg)

  
 
# 2. Calinski-Harabasz指数
   
    calinski_haraba=calinski_harabasz_score(X, dbscan.labels_)
    print(calinski_haraba)
 
    # 3. DB指数(Davies-Bouldin Index)
    davies_bouldin=davies_bouldin_score(X, dbscan.labels_)
    Davies_Bouldin_scores.append(davies_bouldin)
    Calinski_Harabasz_scores.append(calinski_haraba)
    silhouette_avg_scores.append(silhouette_avg)  
  
# 绘制图形  
plt.plot(range(2, 11), silhouette_avg_scores, marker='o', label='Silhouette Coefficient')  

plt.title('Silhouette Coefficient for Different min_samples-DBSCAN-eps=0.4')  
plt.xlabel('Number of min_samples (min_samples)')  
plt.ylabel('Silhouette Coefficient')  
plt.legend()
plt.show()
 
plt.plot(range(2, 11), Calinski_Harabasz_scores, marker='o', label=' Calinski-Harabasz')  
plt.title('Calinski-Harabasz for Different min_samples-DBSCAN-eps=0.4')  
plt.xlabel('Number of min_samples (min_samples)')  
plt.ylabel('Calinski Harabasz')  
plt.legend()
plt.show()

  
plt.plot(range(2, 11), Davies_Bouldin_scores, marker='o', label='Davies-Bouldin Index')  
plt.title('Davies-Bouldin Index for Different min_samples-DBSCAN-eps=0.4')  
plt.xlabel('Number of min_samples (min_samples)')  
plt.ylabel('Davies-Bouldin Index')  
plt.legend()
plt.show()



# 评估指标列表  
silhouette_avg_scores = []  
  
Calinski_Harabasz_scores = []  
Davies_Bouldin_scores = []  

xindex= [0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,1,1.1,1.2,1.4,1.6]
for s in xindex:  
    print(s)
    dbscan = DBSCAN(eps=s, min_samples=3).fit(X) #导入DBSCAN模块进行训练,在一个邻域的半径内min_samples数的邻域eps被认为是一个簇。请记住,初始点包含在min_samples中。
    label_pred = dbscan.labels_ # labels为每个数据的簇标签,不在任何"高密度"集群中的"noisy"样本返回-1
    silhouette_avg = silhouette_score(X, dbscan.labels_)  
    print(silhouette_avg)

  
 
# 2. Calinski-Harabasz指数
   
    calinski_haraba=calinski_harabasz_score(X, dbscan.labels_)
    print(calinski_haraba)
 
    # 3. DB指数(Davies-Bouldin Index)
    davies_bouldin=davies_bouldin_score(X, dbscan.labels_)
    Davies_Bouldin_scores.append(davies_bouldin)
    Calinski_Harabasz_scores.append(calinski_haraba)
    silhouette_avg_scores.append(silhouette_avg)  
  
# 绘制图形  
plt.plot(xindex, silhouette_avg_scores, marker='o', label='Silhouette Coefficient')  

plt.title('Silhouette Coefficient for Different min_samples-DBSCAN- min_samples=3')  
plt.xlabel('eps')  
plt.ylabel('Silhouette Coefficient')  
plt.legend()
plt.show()
 
plt.plot(xindex, Calinski_Harabasz_scores, marker='o', label=' Calinski-Harabasz')  
plt.title('Calinski-Harabasz for Different min_samples-DBSCAN- min_samples=3')  
plt.xlabel('eps')  
plt.ylabel('Calinski Harabasz')  
plt.legend()
plt.show()

  
plt.plot(xindex, Davies_Bouldin_scores, marker='o', label='Davies-Bouldin Index')  
plt.title('Davies-Bouldin Index for Different min_samples-DBSCAN- min_samples=3')  
plt.xlabel('eps')  
plt.ylabel('Davies-Bouldin Index')  
plt.legend()
plt.show()

运行结果:

层次聚类:

python 复制代码
import matplotlib.pyplot as plt # 导入matplotlib的库
import numpy as np # 导入numpy的包
from sklearn import datasets #导入数据集
from sklearn.decomposition import PCA # PCA主成分分析类
from sklearn.metrics import silhouette_score
from sklearn.metrics import calinski_harabasz_score
from sklearn.metrics import davies_bouldin_score

from sklearn.cluster import AgglomerativeClustering
iris = datasets.load_iris() #加载iris数据集
X = iris.data #加载特征数据
# Y = iris.target #加载标签数据
#绘制数据分布图
y = iris.target
X = iris.data
#X.shape
#调用PCA
pca = PCA(n_components=2) # 降到2维
pca = pca.fit(X) #拟合模型
X_dr = pca.transform(X) #获取新矩阵 (降维后的)
#X_dr



#也可以fit_transform一步到位
#X_dr = PCA(2).fit_transform(X)


#plt.figure()
#plt.scatter(X_dr[y==0, 0], X_dr[y==0, 1], c="red", label=iris.target_names[0]) 
#plt.scatter(X_dr[y==1, 0], X_dr[y==1, 1], c="black", label=iris.target_names[1])
#plt.scatter(X_dr[y==2, 0], X_dr[y==2, 1], c="orange", label=iris.target_names[2])
#plt.legend()
#plt.title('PCA of IRIS dataset')
#plt.show()


print("===K-means聚类===")
from sklearn.cluster import KMeans # 引入KMeans模块


estimator = KMeans(n_clusters=3).fit(X)  # 构造聚类器
label_pred = estimator.labels_  # 获取聚类标签

# 评估指标列表  
silhouette_avg_scores = []  
  
Calinski_Harabasz_scores = []  
Davies_Bouldin_scores = []  
# 遍历不同的n_clusters值  
for n_clusters in range(2, 11):  
    agg = AgglomerativeClustering( n_clusters=n_clusters)
    agg.fit(X)  
    labels = agg.labels_  
    silhouette_avg = silhouette_score(X, agg.labels_)  
# 2. Calinski-Harabasz指数
    calinski_haraba=calinski_harabasz_score(X, agg.labels_)
 
    # 3. DB指数(Davies-Bouldin Index)
    davies_bouldin=davies_bouldin_score(X, agg.labels_)
    Davies_Bouldin_scores.append(davies_bouldin)
    Calinski_Harabasz_scores.append(calinski_haraba)
    silhouette_avg_scores.append(silhouette_avg)  
  
# 绘制图形  
plt.plot(range(2, 11), silhouette_avg_scores, marker='o', label='Silhouette Coefficient')  

plt.title('Silhouette Coefficient for Different n_clusters-AgglomerativeClustering')  
plt.xlabel('Number of clusters (n_clusters)')  
plt.ylabel('Silhouette Coefficient')  
plt.legend()
plt.show()
 
plt.plot(range(2, 11), Calinski_Harabasz_scores, marker='o', label=' Calinski-Harabasz')  
plt.title(' Calinski-Harabaszfor Different n_clusters-AgglomerativeClustering')  
plt.xlabel('Number of clusters (n_clusters)')  
plt.ylabel('Calinski Harabasz')  
plt.legend()
plt.show()

  
plt.plot(range(2, 11), Davies_Bouldin_scores, marker='o', label='Davies-Bouldin Index')  
plt.title('Davies-Bouldin Index for Different n_clusters-AgglomerativeClustering')  
plt.xlabel('Number of clusters (n_clusters)')  
plt.ylabel('Davies-Bouldin Index')  
plt.legend()
plt.show()

运行结果:

FCM算法:

代码:

python 复制代码
import matplotlib.pyplot as plt # 导入matplotlib的库
import numpy as np # 导入numpy的包
from sklearn import datasets #导入数据集
from sklearn.decomposition import PCA # PCA主成分分析类
from sklearn.metrics import silhouette_score
from sklearn.metrics import calinski_harabasz_score
from sklearn.metrics import davies_bouldin_score
from sklearn.cluster import FeatureAgglomeration
from sklearn.cluster import AgglomerativeClustering
iris = datasets.load_iris() #加载iris数据集
X = iris.data #加载特征数据
# Y = iris.target #加载标签数据
#绘制数据分布图
y = iris.target
X = iris.data
#X.shape
#调用PCA
pca = PCA(n_components=2) # 降到2维
pca = pca.fit(X) #拟合模型
X_dr = pca.transform(X) #获取新矩阵 (降维后的)
#X_dr



#也可以fit_transform一步到位
#X_dr = PCA(2).fit_transform(X)


#plt.figure()
#plt.scatter(X_dr[y==0, 0], X_dr[y==0, 1], c="red", label=iris.target_names[0]) 
#plt.scatter(X_dr[y==1, 0], X_dr[y==1, 1], c="black", label=iris.target_names[1])
#plt.scatter(X_dr[y==2, 0], X_dr[y==2, 1], c="orange", label=iris.target_names[2])
#plt.legend()
#plt.title('PCA of IRIS dataset')
#plt.show()


print("===K-means聚类===")
from sklearn.cluster import KMeans # 引入KMeans模块
def FCM(X, c_clusters=3, m=2, eps=10):
    membership_mat = np.random.random((len(X), c_clusters))   # 生成随机二维数组shape(150,3),随机初始化隶属矩阵
    # 这一步的操作是为了使Xi的隶属度总和为1
    membership_mat = np.divide(membership_mat, np.sum(membership_mat, axis=1)[:, np.newaxis])

    while True:
        working_membership_mat = membership_mat ** m   # shape->(150,3)
        # 根据公式计算聚类中心点Centroids.shape->(3,4)
        Centroids = np.divide(np.dot(working_membership_mat.T, X), np.sum(working_membership_mat.T, axis=1)[:, np.newaxis])

        # 该矩阵保存所有实点到每个聚类中心的欧式距离
        n_c_distance_mat = np.zeros((len(X), c_clusters)) # shape->(150,3)
        for i, x in enumerate(X):
            for j, c in enumerate(Centroids):
                n_c_distance_mat[i][j] = np.linalg.norm(x-c, 2)   # 计算l2范数(欧氏距离)

        new_membership_mat = np.zeros((len(X), c_clusters))

        # 根据公式计算模糊矩阵U
        for i, x in enumerate(X):
            for j, c in enumerate(Centroids):
                new_membership_mat[i][j] = 1. / np.sum((n_c_distance_mat[i][j] / n_c_distance_mat[i]) ** (2 / (m-1)))
        if np.sum(abs(new_membership_mat - membership_mat)) < eps:
            break
        membership_mat = new_membership_mat
    return np.argmax(new_membership_mat, axis=1)



# 评估指标列表  
silhouette_avg_scores = []  
  
Calinski_Harabasz_scores = []  
Davies_Bouldin_scores = []  
# 遍历不同的n_clusters值  
for n_clusters in range(2, 11):  
    print(n_clusters)
    fcm =FCM(X, c_clusters=n_clusters)
  
    print(len(fcm ))
    silhouette_avg = silhouette_score(X, fcm)  
    print(silhouette_avg)
# 2. Calinski-Harabasz指数
    calinski_haraba=calinski_harabasz_score(X, fcm)
    print(calinski_haraba)
 
    # 3. DB指数(Davies-Bouldin Index)
    davies_bouldin=davies_bouldin_score(X,fcm)
    Davies_Bouldin_scores.append(davies_bouldin)
    Calinski_Harabasz_scores.append(calinski_haraba)
    silhouette_avg_scores.append(silhouette_avg)  
  
# 绘制图形  
plt.plot(range(2, 11), silhouette_avg_scores, marker='o', label='Silhouette Coefficient')  

plt.title('Silhouette Coefficient for Different n_clusters-FCM')  
plt.xlabel('Number of clusters (n_clusters)')  
plt.ylabel('Silhouette Coefficient')  
plt.legend()
plt.show()
 
plt.plot(range(2, 11), Calinski_Harabasz_scores, marker='o', label=' Calinski-Harabasz')  
plt.title(' Calinski-Harabaszfor Different n_clusters-FCM')  
plt.xlabel('Number of clusters (n_clusters)')  
plt.ylabel('Calinski Harabasz')  
plt.legend()
plt.show()

  
plt.plot(range(2, 11), Davies_Bouldin_scores, marker='o', label='Davies-Bouldin Index')  
plt.title('Davies-Bouldin Index for Different n_clusters-FCM')  
plt.xlabel('Number of clusters (n_clusters)')  
plt.ylabel('Davies-Bouldin Index')  
plt.legend()
plt.show()

lvp算法:

python 复制代码
import matplotlib.pyplot as plt # 导入matplotlib的库
import numpy as np # 导入numpy的包
from sklearn import datasets #导入数据集
from sklearn.decomposition import PCA # PCA主成分分析类
from sklearn.metrics import silhouette_score
from sklearn.metrics import calinski_harabasz_score
from sklearn.metrics import davies_bouldin_score
from sklearn.cluster import FeatureAgglomeration
from sklearn.cluster import AgglomerativeClustering

 
# 使用LVQ进行聚类
from sklearn_lvq import GlvqModel
 


iris = datasets.load_iris() #加载iris数据集
X = iris.data #加载特征数据
# Y = iris.target #加载标签数据
#绘制数据分布图
y = iris.target
X = iris.data
#X.shape
#调用PCA
pca = PCA(n_components=2) # 降到2维
pca = pca.fit(X) #拟合模型
X_dr = pca.transform(X) #获取新矩阵 (降维后的)
#X_dr



#也可以fit_transform一步到位
#X_dr = PCA(2).fit_transform(X)


#plt.figure()
#plt.scatter(X_dr[y==0, 0], X_dr[y==0, 1], c="red", label=iris.target_names[0]) 
#plt.scatter(X_dr[y==1, 0], X_dr[y==1, 1], c="black", label=iris.target_names[1])
#plt.scatter(X_dr[y==2, 0], X_dr[y==2, 1], c="orange", label=iris.target_names[2])
#plt.legend()
#plt.title('PCA of IRIS dataset')
#plt.show()
def FCM(X, c_clusters=3, m=2, eps=10):
    membership_mat = np.random.random((len(X), c_clusters))   # 生成随机二维数组shape(150,3),随机初始化隶属矩阵
    # 这一步的操作是为了使Xi的隶属度总和为1
    membership_mat = np.divide(membership_mat, np.sum(membership_mat, axis=1)[:, np.newaxis])

    while True:
        working_membership_mat = membership_mat ** m   # shape->(150,3)
        # 根据公式计算聚类中心点Centroids.shape->(3,4)
        Centroids = np.divide(np.dot(working_membership_mat.T, X), np.sum(working_membership_mat.T, axis=1)[:, np.newaxis])

        # 该矩阵保存所有实点到每个聚类中心的欧式距离
        n_c_distance_mat = np.zeros((len(X), c_clusters)) # shape->(150,3)
        for i, x in enumerate(X):
            for j, c in enumerate(Centroids):
                n_c_distance_mat[i][j] = np.linalg.norm(x-c, 2)   # 计算l2范数(欧氏距离)

        new_membership_mat = np.zeros((len(X), c_clusters))

        # 根据公式计算模糊矩阵U
        for i, x in enumerate(X):
            for j, c in enumerate(Centroids):
                new_membership_mat[i][j] = 1. / np.sum((n_c_distance_mat[i][j] / n_c_distance_mat[i]) ** (2 / (m-1)))
        if np.sum(abs(new_membership_mat - membership_mat)) < eps:
            break
        membership_mat = new_membership_mat
    return np.argmax(new_membership_mat, axis=1)



# 评估指标列表  
silhouette_avg_scores = []  
  
Calinski_Harabasz_scores = []  
Davies_Bouldin_scores = []  
from sklearn.datasets import make_blobs

# 遍历不同的n_clusters值  
for n_clusters in range(2, 11):  
    print(n_clusters)
    zX, y_true = make_blobs(n_samples=150, centers=n_clusters, cluster_std=0.6, random_state=0)
    lvq = GlvqModel()
    lvq.fit(X, y_true)
 
    # 可视化聚类结果
    fcm = lvq.predict(X)
   
  
    print(len(fcm ))
    silhouette_avg = silhouette_score(X, fcm)  
    print(silhouette_avg)
# 2. Calinski-Harabasz指数
    calinski_haraba=calinski_harabasz_score(X, fcm)
    print(calinski_haraba)
 
    # 3. DB指数(Davies-Bouldin Index)
    davies_bouldin=davies_bouldin_score(X,fcm)
    Davies_Bouldin_scores.append(davies_bouldin)
    Calinski_Harabasz_scores.append(calinski_haraba)
    silhouette_avg_scores.append(silhouette_avg)  
  
# 绘制图形  
plt.plot(range(2, 11), silhouette_avg_scores, marker='o', label='Silhouette Coefficient')  

plt.title('Silhouette Coefficient for Different n_clusters--lvp')  
plt.xlabel('Number of clusters (n_clusters)')  
plt.ylabel('Silhouette Coefficient')  
plt.legend()
plt.show()
 
plt.plot(range(2, 11), Calinski_Harabasz_scores, marker='o', label=' Calinski-Harabasz')  
plt.title(' Calinski-Harabaszfor Different n_clusters--lvp')  
plt.xlabel('Number of clusters (n_clusters)')  
plt.ylabel('Calinski Harabasz')  
plt.legend()
plt.show()

  
plt.plot(range(2, 11), Davies_Bouldin_scores, marker='o', label='Davies-Bouldin Index')  
plt.title('Davies-Bouldin Index for Different n_clusters-lvp')  
plt.xlabel('Number of clusters (n_clusters)')  
plt.ylabel('Davies-Bouldin Index')  
plt.legend()
plt.show()

最后我们还做了一个所有算法最优参数汇总的代码:

python 复制代码
import matplotlib.pyplot as plt # 导入matplotlib的库
import numpy as np # 导入numpy的包
from sklearn import datasets #导入数据集
from sklearn.decomposition import PCA # PCA主成分分析类
iris = datasets.load_iris() #加载iris数据集
X = iris.data #加载特征数据
# Y = iris.target #加载标签数据
#绘制数据分布图
y = iris.target
X = iris.data
#X.shape
#调用PCA
pca = PCA(n_components=2) # 降到2维
pca = pca.fit(X) #拟合模型
X_dr = pca.transform(X) #获取新矩阵 (降维后的)
#X_dr



#也可以fit_transform一步到位
X_dr = PCA(2).fit_transform(X)


plt.figure()
plt.scatter(X_dr[y==0, 0], X_dr[y==0, 1], c="red", label=iris.target_names[0]) 
plt.scatter(X_dr[y==1, 0], X_dr[y==1, 1], c="black", label=iris.target_names[1])
plt.scatter(X_dr[y==2, 0], X_dr[y==2, 1], c="orange", label=iris.target_names[2])
plt.legend()
plt.title('PCA of IRIS dataset')
plt.show()


print("===K-means聚类===")
from sklearn.cluster import KMeans # 引入KMeans模块
estimator = KMeans(n_clusters=3).fit(X)  # 构造聚类器
label_pred = estimator.labels_  # 获取聚类标签
#绘制k-means结果
x0 = X_dr[label_pred == 0]# 获取聚类标签等于0的话,则赋值给x0
x1 = X_dr[label_pred == 1]# 获取聚类标签等于1的话,则赋值给x1
x2 = X_dr[label_pred == 2]# 获取聚类标签等于2的话,则赋值给x2
plt.scatter(x0[:, 0], x0[:, 1], c="red", marker='o', label='label 0')#画label 0的散点图
plt.scatter(x1[:, 0], x1[:, 1], c="green", marker='*', label='label 1')#画label 1的散点图
plt.scatter(x2[:, 0], x2[:, 1], c="blue", marker='+', label='label 2')#画label 2的散点图
plt.xlabel('K-means')# 设置X轴的标签为K-means
# plt.legend(loc=2)# 设置图标在左上角
plt.title("kmeans+PCA")
plt.show()


x0 = X[label_pred == 0]# 获取聚类标签等于0的话,则赋值给x0
x1 = X[label_pred == 1]# 获取聚类标签等于1的话,则赋值给x1
x2 = X[label_pred == 2]# 获取聚类标签等于2的话,则赋值给x2
plt.scatter(x0[:, 0], x0[:, 1], c="red", marker='o', label='label 0')#画la

plt.scatter(x1[:, 0], x1[:, 1], c="green", marker='*', label='label 1')#画label 1的散点图
plt.scatter(x2[:, 0], x2[:, 1], c="blue", marker='+', label='label 2')#画label 2的散点图
plt.xlabel('K-means')# 设置X轴的标签为K-means
# plt.legend(loc=2)# 设置图标在左上角
plt.title("kmeans-features[0:2]")
plt.show()


#密度聚类之DBSCAN算法
print("===DBSCAN聚类===")
from sklearn.cluster import DBSCAN # 引入DBSCAN模块
dbscan = DBSCAN(eps=1.0, min_samples=3).fit(X) #导入DBSCAN模块进行训练,在一个邻域的半径内min_samples数的邻域eps被认为是一个簇。请记住,初始点包含在min_samples中。
label_pred = dbscan.labels_ # labels为每个数据的簇标签,不在任何"高密度"集群中的"noisy"样本返回-1

x0 = X[label_pred == 0] # 获取聚类标签等于0的话,则赋值给x0
x1 = X[label_pred == 1] # 获取聚类标签等于1的话,则赋值给x1
x2 = X[label_pred == 2] # 获取聚类标签等于2的话,则赋值给x2
plt.scatter(x0[:, 0], x0[:, 1], c="red", marker='o', label='label0') # 画label 0的散点图
plt.scatter(x1[:, 0], x1[:, 1], c="green", marker='*', label='label1') # 画label 1的散点图
plt.scatter(x2[:, 0], x2[:, 1], c="blue", marker='+', label='label2') # 画label 2的散点图
plt.xlabel('DBSCAN')# 设置X轴的标签为DBSCAN
plt.legend(loc=2)# 设置图标在左上角
plt.title("DBSCAN-features[0:2]")
plt.show()



x0 = X_dr[label_pred == 0]# 获取聚类标签等于0的话,则赋值给x0
x1 = X_dr[label_pred == 1]# 获取聚类标签等于1的话,则赋值给x1
x2 = X_dr[label_pred == 2]# 获取聚类标签等于2的话,则赋值给x2
plt.scatter(x0[:, 0], x0[:, 1], c="red", marker='o', label='label 0')#画label 0的散点图
plt.scatter(x1[:, 0], x1[:, 1], c="green", marker='*', label='label 1')#画label 1的散点图
plt.scatter(x2[:, 0], x2[:, 1], c="blue", marker='+', label='label 2')#画label 2的散点图
plt.xlabel('DBSCAN')# 设置X轴的标签为K-means
# plt.legend(loc=2)# 设置图标在左上角
plt.title("DBSCAN+PCA")
plt.show()
from sklearn_lvq import GlvqModel

import numpy as np
from matplotlib import pyplot as plt
from scipy.cluster.hierarchy import dendrogram
from scipy.cluster.hierarchy import linkage, dendrogram
def getLinkageMat(model):
    children = model.children_
    cs = np.zeros(len(children))
    N = len(model.labels_)
    for i,child in enumerate(children):
        count = 0
        for idx in child:
            count += 1 if idx < N else cs[idx - N]
        cs[i] = count
    return np.column_stack([children, model.distances_, cs])

from sklearn.cluster import AgglomerativeClustering
from sklearn.datasets import make_blobs

model = AgglomerativeClustering( n_clusters=3)

model = model.fit(X)

label_pred = model.labels_ # labels为每个数据的簇标签,不在任何"高密度"集群中的"noisy"样本返回-1

Z = linkage(X, method='ward', metric='euclidean')
p = dendrogram(Z, 0)
plt.show()



x0 = X_dr[label_pred == 0]# 获取聚类标签等于0的话,则赋值给x0
x1 = X_dr[label_pred == 1]# 获取聚类标签等于1的话,则赋值给x1
x2 = X_dr[label_pred == 2]# 获取聚类标签等于2的话,则赋值给x2
plt.scatter(x0[:, 0], x0[:, 1], c="red", marker='o', label='label 0')#画label 0的散点图
plt.scatter(x1[:, 0], x1[:, 1], c="green", marker='*', label='label 1')#画label 1的散点图
plt.scatter(x2[:, 0], x2[:, 1], c="blue", marker='+', label='label 2')#画label 2的散点图
plt.xlabel('AgglomerativeClustering')# 设置X轴的标签为K-means
# plt.legend(loc=2)# 设置图标在左上角
plt.title("AgglomerativeClustering+PCA")
plt.show()

def FCM(X, c_clusters=3, m=2, eps=10):
    membership_mat = np.random.random((len(X), c_clusters))   # 生成随机二维数组shape(150,3),随机初始化隶属矩阵
    # 这一步的操作是为了使Xi的隶属度总和为1
    membership_mat = np.divide(membership_mat, np.sum(membership_mat, axis=1)[:, np.newaxis])

    while True:
        working_membership_mat = membership_mat ** m   # shape->(150,3)
        # 根据公式计算聚类中心点Centroids.shape->(3,4)
        Centroids = np.divide(np.dot(working_membership_mat.T, X), np.sum(working_membership_mat.T, axis=1)[:, np.newaxis])

        # 该矩阵保存所有实点到每个聚类中心的欧式距离
        n_c_distance_mat = np.zeros((len(X), c_clusters)) # shape->(150,3)
        for i, x in enumerate(X):
            for j, c in enumerate(Centroids):
                n_c_distance_mat[i][j] = np.linalg.norm(x-c, 2)   # 计算l2范数(欧氏距离)

        new_membership_mat = np.zeros((len(X), c_clusters))

        # 根据公式计算模糊矩阵U
        for i, x in enumerate(X):
            for j, c in enumerate(Centroids):
                new_membership_mat[i][j] = 1. / np.sum((n_c_distance_mat[i][j] / n_c_distance_mat[i]) ** (2 / (m-1)))
        if np.sum(abs(new_membership_mat - membership_mat)) < eps:
            break
        membership_mat = new_membership_mat
    return np.argmax(new_membership_mat, axis=1)

fcm =FCM(X, c_clusters=3)


x0 = X_dr[fcm == 0]# 获取聚类标签等于0的话,则赋值给x0
x1 = X_dr[fcm == 1]# 获取聚类标签等于1的话,则赋值给x1
x2 = X_dr[fcm == 2]# 获取聚类标签等于2的话,则赋值给x2
plt.scatter(x0[:, 0], x0[:, 1], c="red", marker='o', label='label 0')#画label 0的散点图
plt.scatter(x1[:, 0], x1[:, 1], c="green", marker='*', label='label 1')#画label 1的散点图
plt.scatter(x2[:, 0], x2[:, 1], c="blue", marker='+', label='label 2')#画label 2的散点图
plt.xlabel('FCM')# 设置X轴的标签为K-means
# plt.legend(loc=2)# 设置图标在左上角
plt.title("FCM+PCA")
plt.show()

zX, y_true = make_blobs(n_samples=150, centers=2, cluster_std=0.6, random_state=0)
lvq = GlvqModel()
lvq.fit(X, y)
 
    # 可视化聚类结果
lvqp = lvq.predict(X)




x0 = X_dr[lvqp == 0]# 获取聚类标签等于0的话,则赋值给x0
x1 = X_dr[lvqp == 1]# 获取聚类标签等于1的话,则赋值给x1
x2 = X_dr[lvqp == 2]# 获取聚类标签等于2的话,则赋值给x2
plt.scatter(x0[:, 0], x0[:, 1], c="red", marker='o', label='label 0')#画label 0的散点图
plt.scatter(x1[:, 0], x1[:, 1], c="green", marker='*', label='label 1')#画label 1的散点图
plt.scatter(x2[:, 0], x2[:, 1], c="blue", marker='+', label='label 2')#画label 2的散点图
plt.xlabel('lvq')# 设置X轴的标签为K-means
# plt.legend(loc=2)# 设置图标在左上角
plt.title("lvq+PCA")
plt.show()

运行结果:





相关推荐
q567315234 分钟前
在 Bash 中获取 Python 模块变量列
开发语言·python·bash
是萝卜干呀5 分钟前
Backend - Python 爬取网页数据并保存在Excel文件中
python·excel·table·xlwt·爬取网页数据
代码欢乐豆6 分钟前
数据采集之selenium模拟登录
python·selenium·测试工具
喵~来学编程啦13 分钟前
【论文精读】LPT: Long-tailed prompt tuning for image classification
人工智能·深度学习·机器学习·计算机视觉·论文笔记
狂奔solar41 分钟前
yelp数据集上识别潜在的热门商家
开发语言·python
Tassel_YUE42 分钟前
网络自动化04:python实现ACL匹配信息(主机与主机信息)
网络·python·自动化
聪明的墨菲特i1 小时前
Python爬虫学习
爬虫·python·学习
Chef_Chen2 小时前
从0开始学习机器学习--Day13--神经网络如何处理复杂非线性函数
神经网络·学习·机器学习
Troc_wangpeng2 小时前
R language 关于二维平面直角坐标系的制作
开发语言·机器学习
努力的家伙是不讨厌的2 小时前
解析json导出csv或者直接入库
开发语言·python·json