# TODO: 导入必要的库和模块

# TODO: 加载数字数据集

# TODO: 将数据集划分为训练集和测试集

# TODO: 初始化变量以存储最佳准确率，相应的k值和最佳knn模型

# TODO: 初始化一个列表以存储每个k值的准确率

# TODO: 尝试从1到40的k值，对于每个k值，训练knn模型，保存最佳准确率，k值和knn模型

# TODO: 将最佳KNN模型保存到二进制文件

# TODO: 打印最佳准确率和相应的k值
import numpy as np  
import matplotlib.pyplot as plt  
from sklearn import datasets  
from sklearn.model_selection import train_test_split  
from sklearn.neighbors import KNeighborsClassifier  
from sklearn.metrics import accuracy_score  
import pickle  
from tqdm import tqdm  
  
# 加载手写数字数据集  
digits = datasets.load_digits()  
X = digits.data  
y = digits.target  
  
# 将数据集划分为训练集和测试集  
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)  
  
# 初始化变量  
best_accuracy = 0  
best_k = 0  
best_knn_model = None  
accuracies = []  
  
# 尝试从1到40的k值  
for k in tqdm(range(1, 41)):  
    # 训练knn模型  
    knn = KNeighborsClassifier(n_neighbors=k)  
    knn.fit(X_train, y_train)  
    # 预测测试集  
    y_pred = knn.predict(X_test)  
    # 计算准确率  
    accuracy = accuracy_score(y_test, y_pred)  
    # 保存准确率和模型  
    accuracies.append(accuracy)  
    if accuracy > best_accuracy:  
        best_accuracy = accuracy  
        best_k = k  
        best_knn_model = knn  
  
# 将最佳KNN模型保存到二进制文件  
with open('best_knn_model.pkl', 'wb') as f:  
    pickle.dump(best_knn_model, f)  
  
# 绘制准确率变化图  
plt.figure(figsize=(10, 6))  
plt.plot(range(1, 41), accuracies, marker='o')  
plt.title('Accuracy vs. K value')  
plt.xlabel('K')  
plt.ylabel('Accuracy')  
plt.axvline(x=best_k, color='r', linestyle='--')  
plt.text(best_k, best_accuracy, f'Best k={best_k}, Accuracy={best_accuracy:.2f}', fontsize=12, color='red')  
plt.grid(True)  
plt.savefig('accuracy_plot.pdf')  
  
# 打印最佳准确率和相应的k值  
print(f"Best K: {best_k}, Best Accuracy: {best_accuracy:.2f}")