主成分分析代码(手写数字识别)

导入模块

import time
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.decomposition import PCA
from sklearn.neighbors import KNeighborsClassifier
%matplotlib inline
font = FontProperties(fname='/Library/Fonts/Heiti.ttc')

数据预处理

# 导入手写识别数字数据集
digits = datasets.load_digits()
X = digits.data
y = digits.target

X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=1)

KNN训练数据

knn = KNeighborsClassifier()
knn.fit(X_train, y_train)

KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
           metric_params=None, n_jobs=None, n_neighbors=5, p=2,
           weights='uniform')

准确度

knn.score(X_train, y_train)

0.9866369710467706

降维(2维)

pca = PCA(n_components=2)

pca.fit(X_train)
X_train_reduction = pca.transform(X_train)
X_test_reduction = pca.transform(X_test)

KNN训练数据