pca图像压缩python_python 原始相素特征和Pca压缩重建进行图像识别 识别性能可视化...

import pandas as pd

import numpy as np

digits_train = pd.read_csv('../Datasets/Breast-Cancer/optdigits.tra', header=None)

digits_test = pd.read_csv('../Datasets/Breast-Cancer/optdigits.tes', header=None)

x_digits = digits_train[np.arange(64)]

y_digits = digits_train[64]

X_train = x_digits.dropna(how='any')

y_train = y_digits.dropna(how='any')

x_digits_test = digits_test[np.arange(64)]

y_digits_test = digits_test[64]

X_test = x_digits_test.dropna(how='any')

y_test = y_digits_test.dropna(how='any')

print(X_train)

print(y_train)

from sklearn.svm import LinearSVC

svc = LinearSVC()

svc.fit(X_train,y_train)

y_predict = svc.predict(X_test)

from sklearn.decomposition import PCA

estimator = PCA(n_components=20)

pca_X_train = estimator.fit_transform(X_train)

pca_X_test = estimator.transform(X_test)

pca_svc = LinearSVC()

pca_svc.fit(pca_X_train,y_train)

pca_y_predict = pca_svc.predict(pca_X_test)

target_namearray = []

from sklearn.metrics import classification_report

print('The accuracy of linesvm is',svc.score(X_test,y_test))

print(classification_report(y_test,y_predict,target_names = np.arange(10).astype(str)))

from matplotlib import pyplot as plt

def show_values(pc, fmt="%.2f", **kw):

'''

Heatmap with text in e