1.数据加载
'''
Documents:PCA,NMF,KMeans
Author:杨 景
Time:2018.1.15
'''
from sklearn.decomposition import NMF
from sklearn.decomposition import PCA
from sklearn.cluster import KMeans
from sklearn.datasets import fetch_lfw_people
from sklearn.model_selection import train_test_split
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
people=fetch_lfw_people(min_faces_per_person=20,resize=0.7)
image_shape=people.images[0].shape
mask=np.zeros(people.target.shape,dtype=np.bool)
for target in np.unique(people.target):
mask[np.where(people.target==target)[0][:50]]=1
X_people=people.data[mask]
y_people=people.target[mask]
X_people=X_people/255
X_train,X_test,y_train,y_test=train_test_split(X_people,y_people,stratify=y_people,random_state=0)
2.train
nmf=NMF(n_components=100,random_state=0)
nmf.fit(X_train)
pca=PCA(n_components=100,random_state=0)
pca.fit(X_train)
kmeans=KMeans(n_clusters=100,random_state=0)
kmeans.fit(X_train)
X_reconstructed_pca=pca.inverse_transform(pca.transform(X_test))
X_reconstructed_kmeans=kmeans.cluster_centers_[kmeans.predict(X_test)]
X_reconstructed_nmf=np.dot(nmf.transform(X_test),nmf.components_)
fig,axes=plt.subplots(3,5,figsize=(8,8),subplot_kw={'xticks':(),'yticks':()})
fig.suptitle('Extract Components')
for ax,comp_kmeans,comp_pca,comp_nmf in zip(axes.T,kmeans.cluster_centers_,pca.components_,nmf.components_):
ax[0].imshow(comp_kmeans.reshape(image_shape))
ax[1].imshow(comp_pca.reshape(image_shape),cmap='viridis')
ax[2].imshow(comp_nmf.reshape(image_shape))
axes[0,0].set_ylabel('kmeans')
axes[1,0].set_ylabel('pca')
axes[2,0].set_ylabel('nmf')
plt.show()
