import numpy as np
import os
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KDTree

"""
请在这里填写学号和姓名，不填写即成绩无效。
"""
id = "202210423213"
name = "熊浩燃"

"""
参数说明:
- 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，请自行设置默认值，评测时仅会使用其默认值，不修改默认值将无法通过评测，成绩为零。
返回值:
- int: 预测的分类标签。
"""


def classify(input_vector, dataSet, labels, k=1, distance_metric='euclidean', weighted=True):
    """
    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 k=1。
    - distance_metric (str): 距离度量方法，默认欧氏距离。
    - weighted (bool): 是否使用加权投票机制，默认加权。
    
    Returns:
    - int: 预测的分类标签。
    """
    
    if distance_metric == 'euclidean':
        # 欧氏距离
        distances = np.linalg.norm(dataSet - input_vector, axis=1)
    elif distance_metric == 'manhattan':
        # 曼哈顿距离
        distances = np.sum(np.abs(dataSet - input_vector), axis=1)

    # 使用KD树加速最近邻查找
    tree = KDTree(dataSet)
    dist, indices = tree.query(input_vector.reshape(1, -1), k=k)
    
    nearest_labels = np.array(labels)[indices[0]]
    
    if weighted:
        # 使用距离的倒数作为权重
        weights = 1 / (dist[0] + 1e-5)  # 避免除以0
        label_weights = {}
        
        for i, label in enumerate(nearest_labels):
            label_weights[label] = label_weights.get(label, 0) + weights[i]
        
        # 返回加权得分最高的标签
        predicted_label = max(label_weights, key=label_weights.get)
    else:
        # 直接使用多数投票
        predicted_label = np.bincount(nearest_labels).argmax()

    return predicted_label


def load_dataset(directory):
    """
    从文件夹中加载数据，若不自行正确实现，则无法通过评测，不记录成绩。
    
    Args:
    - directory (str): 数据文件夹路径。
    
    Returns:
    - np.array: 标准化后的特征数据。
    - np.array: 标签数据。
    """
    labels = []
    data_list = []
    
    for filename in os.listdir(directory):
        if filename.endswith(".txt"):  # 确保读取的是 txt 文件
            label = int(filename.split('_')[0])
            labels.append(label)
            vector = img_to_vector(os.path.join(directory, filename))
            data_list.append(vector)
    
    data_array = np.array(data_list)
    
    # 标准化数据
    scaler = StandardScaler()
    scaled_data = scaler.fit_transform(data_array)
    
    return scaled_data, np.array(labels)


def img_to_vector(filename):
    """
    将二值图像转换为向量。该部分应为 load_dataset 函数的辅助子函数，可单独在这里实现，也可直接集成至 load_dataset 函数中。
    
    Args:
    - filename (str): 图像文件路径。
    
    Returns:
    - np.array: 二值图像向量。
    """
    with open(filename, 'r') as f:  # 确保使用文本模式读取
        lines = f.readlines()
    
    vector = np.zeros((1024,), dtype=int)  # 将其改为 (1024,) 的一维数组
    
    for i in range(32):
        for j in range(32):
            vector[32 * i + j] = int(lines[i][j])
    
    return vector


if __name__ == "__main__":
    # 测试代码
    train_data, train_labels = load_dataset("trainingDigits")

    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_vector = np.array([int(char) for char in test_data]).reshape(1, 1024)
    
    predicted_label = classify(test_vector, train_data, train_labels)
    print(f"预测的标签: {predicted_label}")