sklearn.cluster聚类算法:K-means和DBSCAN 学习笔记

首先放两个好玩的网页,动态可视化展示K-means和DBSCAN

K-mean https://www.naftaliharris.com/blog/visualizing-k-means-clustering/DBSCAN https://www.naftaliharris.com/blog/visualizing-dbscan-clustering/ import pandas as pd beer=pd.read_csv('data.txt',sep=' ') X = beer[['calories', 'sodium', 'alcohol', 'cost']] from sklearn.cluster import KMeans km = KMeans(n_clusters = 3).fit(X) km2 =KMeans(n_clusters = 2).fit(X) print(km.labels_) print(km2.labels_) beer['cluster'] = km.labels_ beer['cluster2'] =km2.labels_ beer.sort_values('cluster')

# 画图 from pandas.plotting import scatter_matrix %matplotlib inline cluster_centers = km.cluster_centers_ cluster2_centers=km2.cluster_centers_ centers = beer.groupby('cluster').mean().reset_index() centers2=beer.groupby('cluster2').mean().reset_index() import matplotlib.pyplot as plt plt.rcParams['font.size'] = 14 import numpy as np colors = np.array(['red','green','blue','yellow']) plt.figure(figsize=(8,6)) plt.scatter(beer['calories'], beer['alcohol'], c = colors[beer['cluster']]) plt.scatter(centers.calories, centers.alcohol, linewidths=3, marker='+', s=500, c='black') plt.scatter(centers2.calories,centers2.alcohol,linewidths=3, marker='^',s=100,c='gray',alpha=0.8) plt.xlabel('Calories') plt.ylabel('Alcohol') plt.show()

scatter_matrix(beer[['calories','sodium','alcohol','cost']],s=80,alpha=0.8, c=colors[beer['cluster']],figsize=(10,10)) plt.suptitle('With 3 centroids initialized',fontsize=18) plt.subplots_adjust(top=0.92) plt.show()

scatter_matrix(beer[['calories','sodium','alcohol','cost']], s=100, alpha=0.8, c = colors[beer['cluster2']], figsize=(10,10)) plt.suptitle('With 2 centrorids initialized', fontsize=18) plt.subplots_adjust(top=0.92)

数据预处理后看聚类效果

# 数据预处理:标准化 from sklearn.preprocessing import StandardScaler scaler = StandardScaler() X_scaled = scaler.fit_transform(X) km = KMeans(n_clusters = 2).fit(X_scaled) beer['scaled_cluster'] = km.labels_ beer.sort_values('scaled_cluster') pd.plotting.scatter_matrix(X,c=colors[beer.scaled_cluster],alpha=0.8,figsize=(10,10),s=120) plt.show()

从上图可看出此次数据标准化后聚类效果并不如原始数据.

聚类评估:轮廓系数(Silhouette Coefficient)

si接近1，则说明样本i聚类合理 si接近-1，则说明样本i更应该分类到另外的簇 若si 近似为0，则说明样本i在两个簇的边界上。

from sklearn import metrics score_scaled = metrics.silhouette_score(X, beer.scaled_cluster) score = metrics.silhouette_score(X, beer.cluster) score2= metrics.silhouette_score(X, beer.cluster2) print(score_scaled, score, score2)

0.5562170983766765 0.6731775046455796 0.6917656034079486

scores = [] for k in range(2,20): labels = KMeans(n_clusters = k).fit(X).labels_ score = metrics.silhouette_score(X, labels) scores.append(score) plt.figure(figsize = (10, 6)) plt.plot(list(range(2,20)), scores, 'bo-') plt.grid() plt.xlabel('Number of Clusters Initialized') plt.ylabel('Sihouette Score')

DBSCAN clustering

from sklearn.cluster import DBSCAN db = DBSCAN(eps=10, min_samples=2).fit(X) labels = db.labels_ beer['cluster_db'] = labels beer.sort_values('cluster_db') pd.plotting.scatter_matrix(X, c=colors[beer.cluster_db], figsize=(10,10), s=100) plt.show()

scores = [] for s in range(2, 10): labels = DBSCAN(eps = 10, min_samples = s).fit(X).labels_ score = metrics.silhouette_score(X, labels) scores.append(score) plt.figure(figsize = (8, 6)) plt.plot(list(range(2,10)), scores, 'r*-') plt.grid() plt.xlabel('Number of min_samples') plt.ylabel('Sihouette Score')