DBSCAN聚类︱scikit-learn中一种基于密度的聚类方式

密度：空间中任意一点的密度是以该点为圆心，以EPS为半径的圆区域内包含的点数目
边界点：空间中某一点的密度，如果小于某一点给定的阈值minpts,则称为边界点
噪声点：不属于核心点，也不属于边界点的点，也就是密度为1的点

DBSCAN(eps=0.5, min_samples=5, metric='euclidean', algorithm='auto', leaf_size=30, p=None, n_jobs=1)

import numpy
import pandas
import matplotlib.pyplot as plt

#导入数据
data = pandas.read_csv("F:\\python 数据挖掘分析实战\\Data\\data (7).csv")

plt.scatter(
    data['x'], 
    data['y']
)

eps = 0.2;
MinPts = 5;

from sklearn.metrics.pairwise import euclidean_distances

ptses = []
dist = euclidean_distances(data)
for row in dist:
    #密度,空间中任意一点的密度是以该点为圆心、以 Eps 为半径的圆区域内包含的点数
    density = numpy.sum(row<eps)
    pts = 0;
    if density>MinPts:
        #核心点（Core Points）
        #空间中某一点的密度，如果大于某一给定阈值MinPts，则称该为核心点
        pts = 1
    elif density>1 :
        #边界点（Border Points）
        #空间中某一点的密度，如果小于某一给定阈值MinPts，则称该为边界点
        pts = 2
    else:
        #噪声点（Noise Points）
        #数据集中不属于核心点，也不属于边界点的点，也就是密度值为1的点
        pts = 0
    ptses.append(pts)

#把噪声点过滤掉，因为噪声点无法聚类，它们独自一类
corePoints = data[pandas.Series(ptses)!=0]

coreDist = euclidean_distances(corePoints)

#首先，把每个点的领域都作为一类
#邻域（Neighborhood）
#空间中任意一点的邻域是以该点为圆心、以 Eps 为半径的圆区域内包含的点集合
cluster = dict();
i = 0;
for row in coreDist: 
    cluster[i] = numpy.where(row<eps)[0]
    i = i + 1

#然后，将有交集的领域，都合并为新的领域
for i in range(len(cluster)):
    for j in range(len(cluster)):
        if len(set(cluster[j]) & set(cluster[i]))>0 and i!=j:
            cluster[i] = list(set(cluster[i]) | set(cluster[j]))
            cluster[j] = list();

#最后，找出独立（也就是没有交集）的领域，就是我们最后的聚类的结果了
result = dict();
j = 0
for i in range(len(cluster)):
  if len(cluster[i])>0:
    result[j] = cluster[i]
    j = j + 1

#找出每个点所在领域的序号，作为他们最后聚类的结果标记
for i in range(len(result)):
    for j in result[i]:
        data.at[j, 'type'] = i

plt.scatter(
    data['x'], 
    data['y'],
    c=data['type']
)

# DBSCAN clustering algorithm

print(__doc__)

import numpy as np

from sklearn.cluster import DBSCAN
from sklearn import metrics
from sklearn.datasets.samples_generator import make_blobs
from sklearn.preprocessing import StandardScaler

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

X = StandardScaler().fit_transform(X)


# Compute DBSCAN
db = DBSCAN(eps=0.1, min_samples=10).fit(X)
core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
core_samples_mask[db.core_sample_indices_] = True
labels = db.labels_

# Number of clusters in labels, ignoring noise if present.
n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)

print('Estimated number of clusters: %d' % n_clusters_)
print("Homogeneity: %0.3f" % metrics.homogeneity_score(labels_true, labels))
print("Completeness: %0.3f" % metrics.completeness_score(labels_true, labels))
print("V-measure: %0.3f" % metrics.v_measure_score(labels_true, labels))
print("Adjusted Rand Index: %0.3f"
      % metrics.adjusted_rand_score(labels_true, labels))
print("Adjusted Mutual Information: %0.3f"
      % metrics.adjusted_mutual_info_score(labels_true, labels))
print("Silhouette Coefficient: %0.3f"
      % metrics.silhouette_score(X, labels))


# 
import matplotlib.pyplot as plt

# Black removed and is used for noise instead.
unique_labels = set(labels)
colors = [plt.cm.Spectral(each)
          for each in np.linspace(0, 1, len(unique_labels))]
for k, col in zip(unique_labels, colors):
    if k == -1:
        # Black used for noise.
        col = [0, 0, 0, 1]

    class_member_mask = (labels == k)

    xy = X[class_member_mask & core_samples_mask]
    plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),
             markeredgecolor='k', markersize=14)

    xy = X[class_member_mask & ~core_samples_mask]
    plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),
             markeredgecolor='k', markersize=6)

plt.title('Estimated number of clusters: %d' % n_clusters_)
plt.show()