# 导入必要的工具包
import pandas as pd
from sklearn.decomposition import PCA
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.model_selection import cross_val_score
# %%
# 读取训练数据和测试数据
train = pd.read_csv('./data/MNIST_train.csv')
test = pd.read_csv('./data/MNIST_test.csv')
y_train = train.label.values
X_train = train.drop("label", axis=1).values
X_test = test.values
# %%
# 将像素值[0,255] --> [0,1]
X_train = X_train / 255.0
X_test = X_test / 255.0
## PCA降维
pca = PCA(n_components=0.95, svd_solver='full')
pca.fit(X_train)
# 在训练集和测试集降维
X_train_pca = pca.transform(X_train)
X_test_pca = pca.transform(X_test)
## LDA分类器
lda = LinearDiscriminantAnalysis()
lda.fit(X_train_pca, y_train)
# %%
# 用在降维后的全体训练数据集上训练的模型对测试集进行测试
y_predict = lda.predict(X_test_pca)
## 交叉验证, 评估模型性能
loss = cross_val_score(lda, X_train_pca, y_train, cv=5)
print('accuracy of each fold is: ', loss)
print('cv accuracy is:', loss.mean())
