# 导入必要的库和模块
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 joblib
from tqdm import tqdm

# 加载手写数字数据集
digits = datasets.load_digits()

# 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(digits.data, digits.target, test_size=0.2, random_state=42)

# 初始化变量以存储最佳准确率，相应的k值和最佳knn模型
best_accuracy = 0
best_k = 0
best_knn_model = None

# 初始化一个列表以存储每个k值的准确率
accuracies = []

# 尝试从1到40的k值
for k in tqdm(range(1, 41), desc="Training KNN models"):
    # 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)

    # 保存最佳准确率，k值和knn模型
    if accuracy > best_accuracy:
        best_accuracy = accuracy
        best_k = k
        best_knn_model = knn

    # 将准确率添加到列表中
    accuracies.append(accuracy)

# 绘制准确率与K值的关系图
plt.figure(figsize=(10, 6))
plt.plot(range(1, 41), accuracies, linestyle='-', color='b')  # 移除了 marker 参数
plt.axvline(x=best_k, color='r', linestyle='-', label=f'Best K={best_k}')
plt.scatter([best_k], [best_accuracy], color='red')  # 添加交点的标记
plt.text(best_k, best_accuracy, f'(k={best_k}, Accuracy={best_accuracy:.2f})')
plt.xlabel('K Value')
plt.ylabel('Accuracy')
plt.title('KNN Accuracy for Different K Values')
plt.legend()
plt.grid(True)
plt.savefig('accuracy_plot.pdf')
plt.show()
# 将最佳KNN模型保存到二进制文件
joblib.dump(best_knn_model, 'best_knn_model.pkl')

# 打印最佳准确率和相应的k值
print(f"最佳的准确率为: {best_accuracy:.2f}")
print(f"对应的k值为: {best_k}")