sklearn笔记：DBSCAN

1 基本使用方法

sklearn.cluster.DBSCAN(
    eps=0.5, 
    *, 
    min_samples=5, 
    metric='euclidean', 
    metric_params=None, 
    algorithm='auto', 
    leaf_size=30, 
    p=None, 
    n_jobs=None)

2 主要参数介绍

eps	邻域半径
Min_samples	最少点数目

3 属性

core_sample_indices_	核心点的index
components_	核心点的复制
labels_	每个样本的类别label，noise是-1

 4 举例

4.1 简单的例子

from sklearn.cluster import DBSCAN
import numpy as np
X = np.array([[1, 2], [2, 2], [2, 3],
               [8, 7], [8, 8], [25, 80]])
clustering = DBSCAN(eps=3, min_samples=2).fit(X)
clustering.labels_
#array([ 0,  0,  0,  1,  1, -1], dtype=int64)

4.2 带可视化的例子

4.2.1 数据集

from sklearn.datasets import make_blobs
from sklearn.preprocessing import StandardScaler

centers = [[1, 1], [-1, -1], [1, -1]]
X, labels_true = make_blobs(
    n_samples=750, centers=centers, cluster_std=0.4, random_state=0
)

import matplotlib.pyplot as plt

plt.scatter(X[:, 0], X[:, 1])
plt.show()

 sklearn 笔记：make_blobs 生成聚类数据_random_state=3_UQI-LIUWJ的博客-CSDN博客

4.2.2 DBSCAN预测

import numpy as np
from sklearn.cluster import DBSCAN
from sklearn import metrics

db = DBSCAN(eps=0.3, min_samples=10).fit(X)
labels = db.labels_
#-1是noise


n_clusters_ = len(set(labels))-1
#不考虑noise的情况下，类别数量
n_noise_ = list(labels).count(-1)

print("Estimated number of clusters: %d" % n_clusters_)
print("Estimated number of noise points: %d" % n_noise_)
'''
Estimated number of clusters: 3
Estimated number of noise points: 22
'''

 4.2.3 可视化

unique_labels = set(labels)
core_samples_mask = np.zeros_like(labels, dtype=bool)
core_samples_mask[db.core_sample_indices_] = True
#表示样本是否是核心点的mask 向量

colors = ['black','red','green','blue']
for k, col in zip(unique_labels, colors):
    color=colors[k+1]

    class_member_mask = (labels == k)
    #哪些样本是类别k 的mask矩阵
    
    xy = X[class_member_mask & core_samples_mask]
    plt.scatter(
        xy[:, 0],
        xy[:, 1],
        s=40,
        c=color)
    
    xy = X[class_member_mask & ~core_samples_mask]
    plt.scatter(
        xy[:, 0],
        xy[:, 1],
        s=6,
        c=color)
    #核心点，非核心点分开画

plt.title(f"Estimated number of clusters: {n_clusters_}")
plt.show()