3-5-2凝聚聚類

#3-5-1K均值聚類
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
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

mglearn.plots.plot_agglomerative_algorithm()

x,y = make_blobs(random_state=1)
agg = AgglomerativeClustering(n_clusters=3)
assignment = agg.fit_predict(x)
mglearn.discrete_scatter(x[:,0],x[:,1],assignment)
plt.xlabel('feature 0')
plt.ylabel('feature 1')

mglearn.plots.plot_agglomerative()

x,y = make_blobs(random_state=0,n_samples=12)
linkage_array = ward(x)  #得出鏈接數組
dendrogram(linkage_array)  #距離得出樹狀圖
ax = plt.gca()
bounds = ax.get_xbound()
ax.plot(bounds,[7.25,7.25],'--',c='k')
ax.plot(bounds,[4,4],'--',c='k')
ax.text(bounds[1],7.25,' two clusters',va='center',fontdict={'size':15})
ax.text(bounds[1],4,' three clusters',va='center',fontdict={'size':15})
plt.xlabel('sample index')
plt.ylabel('cluster distance')