"""
    -*- coding: utf-8 -*-
    @ Time     : 2021/8/15  22:19
    @ Author   : Raymond
    @ Email    : wanght2316@163.com
    @ Editor   : Pycharm
"""
from sklearn.datasets import load_digits
from sklearn.decomposition import PCA
import pandas as pd
import matplotlib.pyplot as plt

digits = load_digits()
print(digits.keys())
print("數(shù)據(jù)的形狀為: {}".format(digits['data'].shape))
# 構(gòu)建模型 - 降到10 d
pca = PCA(n_components=10)
pca.fit(digits.data)
projected=pca.fit_transform(digits.data)
print('降維后主成分的方差值為：',pca.explained_variance_)
print('降維后主成分的方差值占總方差的比例為：',pca.explained_variance_ratio_)
print('降維后最大方差的成分為：',pca.components_)
print('降維后主成分的個(gè)數(shù)為：',pca.n_components_)
print('original shape:',digits.data.shape)
print('transformed shape:',projected.shape)
s = pca.explained_variance_
c_s = pd.DataFrame({'b': s,'b_sum': s.cumsum() / s.sum()})
c_s['b_sum'].plot(style= '--ko',figsize= (10, 4))
plt.rcParams['font.sans-serif'] = ['SimHei']  # 指定默認(rèn)字體
plt.rcParams['axes.unicode_minus'] = False  # 解決保存圖像是負(fù)號(hào)'-'顯示為方塊的問(wèn)題
plt.axhline(0.85,  color= 'r',linestyle= '--')
plt.text(6, c_s['b_sum'].iloc[6]-0.08, '第7個(gè)成分累計(jì)貢獻(xiàn)率超過(guò)85%', color='b')
plt.title('PCA 各成分累計(jì)占比')
plt.grid()
plt.savefig('./PCA.jpg')
plt.show()