EM算法之GMM聚类

以下为GMM聚类程序

import pandas as pd

import matplotlib.pyplot as plt

import numpy as np

data=pd.read_csv('Fremont.csv',index_col='Date',parse_dates=True)

print(data.head())

data.plot()

plt.show()

data.resample('w').sum().plot()#以周为时间统计

data.resample('D').sum().rolling(365).sum().plot()

plt.show()

##按照时间为统计

data.groupby(data.index.time).mean().plot()

plt.xticks(rotation=45)

plt.show()

data.columns=['West','East']

data['Total']=data['West']+data['East']

pivoted=data.pivot_table('Total',index=data.index.time,columns=data.index.date)

pivoted.iloc[:5,:5]

print(pivoted.iloc[:5,:5])

pivoted.plot(legend=False,alpha=0.01)

plt.xticks(rotation=45)

plt.show()

print(pivoted.shape)

X=pivoted.fillna(0).T.values

print(X.shape)

from sklearn.decomposition import PCA

X2 =PCA(2).fit_transform(X)

print(X2.shape)

plt.scatter(X2[:,0],X2[:,1])

plt.show()

from sklearn.mixture import GaussianMixture

gmm =GaussianMixture (2)

gmm.fit(X)

# labels= gmm.predict_proba(X)

# print(labels)

labels=gmm.predict(X)

print(labels)

plt.scatter(X2[:,0],X2[:,1],c=labels,cmap='rainbow')

plt.show()

from sklearn.datasets.samples_generator import make_blobs

X,y_true =make_blobs(n_samples=800,centers=4,random_state=11)

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

plt.show()

from sklearn.cluster import KMeans

KMeans =KMeans(n_clusters=4)

KMeans.fit(X)

y_Kmeans=KMeans.predict(X)

plt.scatter(X[:,0],X[:,1],c=y_Kmeans,s=50,cmap='viridis')

centers=KMeans.cluster_centers_

plt.show()

from sklearn.mixture import GaussianMixture

gmm =GaussianMixture(n_components=4).fit(X)

labels=gmm.predict(X)

print(labels)

plt.scatter(X[:,0],X[:,1],c=labels,s=40,cmap='viridis')

plt.show()

　　

运行结果