聚类分析应用案例（K-means、层次聚类、DBSCAN）

K-means：该算法假设每个簇由具有连续特征的相似点构成，可以用相似的质心（平均值）和中心点来表示。应对密集、球状数据集时有着更为突出的效果。

# K-means
from sklearn.datasets import make_blobs

# 生成数据集
X, y = make_blobs(n_samples=150,
                  n_features=2,
                  centers=3,
                  cluster_std=0.5,
                  shuffle=True,
                  random_state=0)
# 绘制数据集
import matplotlib.pyplot as plt
plt.scatter(X[:, 0],
            X[:, 1],
            c='white',
            marker='o',
            edgecolor='black',
            s=50)
plt.grid()
plt.tight_layout()
plt.show()

from sklearn.cluster import KMeans

#训练与预测
km = KMeans(n_clusters=3,
            init='random',
            n_init=10,
            max_iter=300,
            tol=1e-04,
            random_state=0)
y_km = km.fit_predict(X)

# 可视化
plt.scatter(X[y_km == 0, 0],
            X[y_km == 0, 1],
            s=50, c='lightgreen',
            marker='s', edgecolor='black',
            label='Cluster 1')
plt.scatter(X[y_km == 1, 0],
            X[y_km == 1, 1],
            s=50, c='orange',
            marker='o', edgecolor='black',
            label='Cluster 2')
plt.scatter(X[y_km == 2, 0],
            X[y_km == 2, 1],
            s=50, c='lightblue',
            marker='v', edgecolor='black',
            label='Cluster 3')
plt.scatter(km.cluster_centers_[:, 0],
            km.cluster_centers_[:, 1],
            s=250, marker='*',
            c='red', edgecolor='black',
            label='Centroids')
plt.legend(scatterpoints=1)
plt.grid()
plt.tight_layout()
plt.show()

层次聚类 Hierarchical Clustering：通过绘制树状图，将聚类过程进行可视化；不需要预先指定簇的个数，在一些无法预先获悉样本分布特点的数据上具有明显优势。

#hierarchical
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from scipy.cluster.hierarchy import linkage

#dataSet
np.random.seed(123)
variables = ['X', 'Y', 'Z']
labels = ['ID_0', 'ID_1', 'ID_2', 'ID_3', 'ID_4']
X = np.random.random_sample([5, 3]) * 10
df = pd.DataFrame(X, columns=variables, index=labels)

from scipy.spatial.distance import pdist, squareform

row_dist = pd.DataFrame(squareform(pdist(df, metric='euclidean')), columns=labels, index=labels)

row_clusters = linkage(pdist(df, metric='euclidean'), method='complete')
pd.DataFrame(row_clusters,
             columns=['row label 1',
                      'row label 2',
                      'distance',
                      'no. of items in clust.'],
             index=['cluster %d' % (i + 1) for i in range(row_clusters.shape[0])])

from scipy.cluster.hierarchy import dendrogram
row_dendr = dendrogram(row_clusters, labels=labels)
plt.tight_layout()
plt.ylabel('Euclidean distance')
plt.show()

密度聚类DBSCAN：用密度取代数据的相似性，按照数据样本点的发布密度差异，将样本点密度足够大的区域联结在一起，以期能够发现任意形状的簇。不需要预设聚类个数，也不需要手动选择聚类层级。

# DBSCAN
from sklearn.datasets import make_moons
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans, AgglomerativeClustering

# dataSet
X, y = make_moons(n_samples=200,
                  noise=0.05,
                  random_state=0)
plt.scatter(X[:, 0], X[:, 1])
plt.tight_layout()
plt.show()

 三种聚类结果展示：

# K-means
f, (ax1, ax2) = plt.subplots(1, 2, figsize=(8, 3))
km = KMeans(n_clusters=2, random_state=0)
y_km = km.fit_predict(X)
ax1.scatter(X[y_km == 0, 0],
            X[y_km == 0, 1],
            c='lightblue',
            edgecolor='black',
            marker='o',
            s=40,
            label='cluster 1')
ax1.scatter(X[y_km == 1, 0],
            X[y_km == 1, 1],
            c='red',
            edgecolor='black',
            marker='s',
            s=40,
            label='cluster 2')
ax1.set_title('K-means clustering')

# hierarchical
ac = AgglomerativeClustering(n_clusters=2, metric='euclidean', linkage='complete')
y_ac = ac.fit_predict(X)

ax2.scatter(X[y_ac == 0, 0],
            X[y_ac == 0, 1],
            c='lightblue',
            edgecolor='black',
            marker='o',
            s=40,
            label='Cluster 1')
ax2.scatter(X[y_ac == 1, 0],
            X[y_ac == 1, 1],
            c='red',
            edgecolor='black',
            marker='s',
            s=40,
            label='Cluster 2')
ax2.set_title('Agglomerative clustering')
plt.legend()
plt.tight_layout()
plt.show()

# DBSCAN
from sklearn.cluster import DBSCAN

db = DBSCAN(eps=0.2,
            min_samples=5,
            metric='euclidean')
y_db = db.fit_predict(X)
plt.scatter(X[y_db == 0, 0],
            X[y_db == 0, 1],
            c='lightblue',
            edgecolor='black',
            marker='o',
            s=40,
            label='Cluster 1')
plt.scatter(X[y_db == 1, 0],
            X[y_db == 1, 1],
            c='red',
            edgecolor='black',
            marker='s',
            s=40,
            label='Cluster 2')
plt.legend()
plt.tight_layout()
plt.show()