import numpy as np
import os
import time

def classify(input_vector, dataSet, labels, k=4):
    """
    KNN 分类算法。

    Args:
    - input_vector (numpy array): 输入待分类的样本。
    - dataSet (numpy array): 训练数据集。
    - labels (list or numpy array): 训练集对应的标签。
    - k (int): kNN 算法参数，默认值为 4。

    Returns:
    - int: 预测的分类标签。
    """
    # 计算输入向量与数据集中每个向量的欧式距离
    diffMat = np.tile(input_vector, (dataSet.shape[0], 1)) - dataSet
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances**0.5
    # 获取距离最近的 k 个样本的索引
    sortedDistIndices = distances.argsort()
    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndices[i]]
        # 统计每个类别的出现次数
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
    # 返回出现次数最多的类别
    sortedClassCount = sorted(classCount.items(), key=lambda x: x[1], reverse=True)
    return sortedClassCount[0][0]

def load_dataset(directory):
    """
    从文件夹中加载数据。

    Args:
    - directory (str): 数据文件夹路径。

    Returns:
    - np.array: 特征数据。
    - np.array: 标签数据。
    """
    fileList = os.listdir(directory)
    m = len(fileList)
    dataSet = np.zeros((m, 1024))  # 28*28的二值图像数据
    labels = []
    for i in range(m):
        filename = fileList[i]
        filePath = os.path.join(directory, filename)
        vector = img_to_vector(filePath)
        dataSet[i, :] = vector
        # 假设文件名的格式为 "label_number.txt"
        label = int(filename.split('_')[0])
        labels.append(label)
    return dataSet, np.array(labels)

def img_to_vector(filename):
    """
    将二值图像转换为向量。

    Args:
    - filename (str): 图像文件路径。

    Returns:
    - np.array: 二值图像向量。
    """
    returnVect = np.zeros((1, 1024))
    with open(filename, 'r') as file:
        lines = file.readlines()
        n = 0
        for line in lines:
            # 去除每行末尾的换行符
            line = line.strip()
            for i in range(len(line)):
                returnVect[0, n] = int(line[i])
                n = n + 1
                if n >= 1024:
                    break
            if n >= 1024:
                break
    return returnVect

if __name__ == "__main__":
    # 加载训练数据集
    train_data, train_labels = load_dataset("trainingDigits")
    
    # 测试数据
    test_data = (
        "00000000000000110000000000000000"
        "00000000000011111000000000000000"
        "00000000000011111100000000000000"
        "00000000001111111110000000000000"
        "00000000001111111110000000000000"
        "00000000001111111100000000000000"
        "00000000011111111000000000000000"
        "00000000111111111000000000000000"
        "00000000111111110000000000000000"
        "00000000111111110000000000000000"
        "00000000111111110000000000000000"
        "00000000111111110000000000000000"
        "00000000111111100000000000000000"
        "00000001111111100000000000000000"
        "00000001111111100000000000000000"
        "00000001111111100000000000000000"
        "00000001111111111111000000000000"
        "00000001111111111111111000000000"
        "00000001111111111111111100000000"
        "00000011111111111111111110000000"
        "00000011111111111111111110000000"
        "00000001111111111111111110000000"
        "00000001111111111111111110000000"
        "00000000111111111100111111100000"
        "00000000111111111000111111100000"
        "00000000011111111001111111100000"
        "00000000011111111111111111000000"
        "00000000001111111111111111000000"
        "00000000000111111111111111000000"
        "00000000000011111111111100000000"
        "00000000000001111111110000000000"
        "00000000000000000111100000000000"
    )
    test_data_vector = np.array([int(char) for char in test_data]).reshape(1, 1024)
    
    # 使用k=4进行分类
    start_time = time.time()
    predicted_label = classify(test_data_vector, train_data, train_labels, k=4)
    end_time = time.time()
    print(f"k = 4, 预测的标签: {predicted_label}, 执行时间: {end_time - start_time:.2f} 秒")