import numpy as np
import os

# KNN分类算法
def classify(input_vector, dataSet, labels, k=3, distance_metric='euclidean', weighted=False):
    """
    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 参数，默认为3。
    - distance_metric (str): 距离度量方法，默认为'euclidean'。可选'manhattan', 'mahalanobis'。
    - weighted (bool): 是否使用加权KNN。默认为False。

    Returns:
    - int: 预测的分类标签。
    """
    
    if distance_metric == 'euclidean':
        distances = np.linalg.norm(dataSet - input_vector, axis=1)
    elif distance_metric == 'manhattan':
        distances = np.sum(np.abs(dataSet - input_vector), axis=1)
    elif distance_metric == 'mahalanobis':
        cov_matrix = np.cov(dataSet.T)
        inv_cov_matrix = np.linalg.inv(cov_matrix)
        delta = dataSet - input_vector
        distances = np.sqrt(np.einsum('ij,jk,ik->i', delta, inv_cov_matrix, delta))
    else:
        raise ValueError("Unsupported distance metric")

    nearest_neighbors_indices = distances.argsort()[:k]
    nearest_labels = np.array(labels)[nearest_neighbors_indices]

    if weighted:
        weights = 1 / (distances[nearest_neighbors_indices] + 1e-5)  # 防止除0错误
        weighted_votes = np.bincount(nearest_labels, weights=weights)
        predicted_label = weighted_votes.argmax()
    else:
        predicted_label = np.bincount(nearest_labels).argmax()

    return predicted_label

# 从文件夹加载数据
def load_dataset(directory):
    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)
    return np.array(data_list), np.array(labels)

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

# 测试代码
if __name__ == "__main__":
    train_data, train_labels = load_dataset("trainingDigits")
    test_data = (
        "00000000000000110000000000000000"
        "00000000000011111000000000000000"
        # ... 中间数据省略 ...
        "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, k=5, distance_metric='manhattan', weighted=True)
    print(f"预测的标签: {predicted_label}")