#3-5-3DBSCAN具有噪声的基于密度空间聚类
import mglearn
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from numpy.core.umath_tests import inner1d
from mpl_toolkits.mplot3d import Axes3D,axes3d
from scipy.cluster.hierarchy import dendrogram,ward
from sklearn.cluster import KMeans,AgglomerativeClustering,DBSCAN
from sklearn.datasets import load_breast_cancer,make_moons,make_circles,make_blobs
from sklearn.datasets import load_iris,fetch_lfw_people,load_digits
from sklearn.decomposition import NMF,PCA
from sklearn.ensemble import RandomForestClassifier,GradientBoostingClassifier
from sklearn.svm import SVC,LinearSVC
from sklearn.neighbors import KNeighborsClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.manifold import TSNE
from sklearn.tree import DecisionTreeClassifier
from sklearn.preprocessing import MinMaxScaler,StandardScaler
x,y = make_blobs(random_state=0,n_samples=12)
dbscan = DBSCAN()
clusters = dbscan.fit_predict(x)
print('cluster memberships:{}'.format(clusters))
cluster memberships:[-1 -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 -1]
mglearn.plots.plot_dbscan()
min_samples: 2 eps: 1.000000 cluster: [-1 0 0 -1 0 -1 1 1 0 1 -1 -1]
min_samples: 2 eps: 1.500000 cluster: [0 1 1 1 1 0 2 2 1 2 2 0]
min_samples: 2 eps: 2.000000 cluster: [0 1 1 1 1 0 0 0 1 0 0 0]
min_samples: 2 eps: 3.000000 cluster: [0 0 0 0 0 0 0 0 0 0 0 0]
min_samples: 3 eps: 1.000000 cluster: [-1 0 0 -1 0 -1 1 1 0 1 -1 -1]
min_samples: 3 eps: 1.500000 cluster: [0 1 1 1 1 0 2 2 1 2 2 0]
min_samples: 3 eps: 2.000000 cluster: [0 1 1 1 1 0 0 0 1 0 0 0]
min_samples: 3 eps: 3.000000 cluster: [0 0 0 0 0 0 0 0 0 0 0 0]
min_samples: 5 eps: 1.000000 cluster: [-1 -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 -1]
min_samples: 5 eps: 1.500000 cluster: [-1 0 0 0 0 -1 -1 -1 0 -1 -1 -1]
min_samples: 5 eps: 2.000000 cluster: [-1 0 0 0 0 -1 -1 -1 0 -1 -1 -1]
min_samples: 5 eps: 3.000000 cluster: [0 0 0 0 0 0 0 0 0 0 0 0]
x,y = make_moons(random_state=0,n_samples=200,noise=0.05)
scaler = StandardScaler()
scaler.fit(x)
x_scaled = scaler.transform(x)
dbscan = DBSCAN(eps=0.5)
clusters = dbscan.fit_predict(x_scaled)
plt.scatter(x_scaled[:,0],x_scaled[:,1],c=clusters,cmap=mglearn.cm2,s=60)
plt.xlabel('feature 0')
plt.ylabel('feature 1')
