PCA特征脸

# -*- coding: UTF-8 -*-
import numpy as np
import matplotlib.pyplot as plt
import seaborn
from sklearn.datasets import fetch_lfw_people
from sklearn.decomposition import PCA
seaborn.set()

faces = fetch_lfw_people(min_faces_per_person=60)
print(faces.target_names)
print(faces.images.shape)  # 1348张图片，62*47矩阵供显示
print(faces.data.shape)  # 1348张图，每张图2914特征维度
pca = PCA(150)  # 随机前150个主成分
pca.fit(faces.data)
fig, axes = plt.subplots(3, 8, figsize=(9, 4), subplot_kw={'xticks': [], 'yticks': []},
                         gridspec_kw=dict(hspace=0.1, wspace=0.1))
for i, ax in enumerate(axes.flat):
    ax.imshow(pca.components_[i].reshape(62, 47), cmap='bone')  # 展示每个特诊维度的综合画像
print('pca.components_:\n', pca.components_.shape)  # 150个特征，2914张照片
fig2 = plt.figure()
plt.plot(np.cumsum(pca.explained_variance_ratio_))
plt.xlabel('number of components')
plt.ylabel('cumulative explained variance')

pca = PCA(150).fit(faces.data)
components = pca.transform(faces.data)
projected = pca.inverse_transform(components)
fig, ax = plt.subplots(2, 10, figsize=(10, 2.5),
                       subplot_kw={'xticks': [], 'yticks': []},
                       gridspec_kw=dict(hspace=0.1, wspace=0.1))
for i in range(10):
    ax[0, i].imshow(faces.data[i].reshape(62, 47), cmap='binary_r')
    ax[1, i].imshow(projected[i].reshape(62, 47), cmap='binary_r')
ax[0, 0].set_ylabel('full-dim\ninput')
ax[1, 0].set_ylabel('150-dim\nreconstruction')
plt.show()