# function.py
import numpy as np
import os
from collections import Counter

"""
实验说明:
- 自行编写实现数据加载与 kNN 的手写数字分类算法。
- 函数输入: 待分类的样本 input_vector, 训练数据集 dataSet, 训练集对应的标签 labels。
- 函数返回: 预测的分类标签。

注意事项:
- 在 function.py 中实现 kNN 分类算法。
- 可以自行导入其他库，需要在 requirements.txt 添加依赖，若未在 requirements.txt 中添加使用到的依赖，则无法自动评测，成绩为零。
- 自动评测脚本仅会加载 classify 和 load_data 函数，请勿修改函数名。
- 训练集和测试集需手动下载解压，并放入当前目录下。

测评环境:
- CPU: Intel Xeon(R) CPU E3-1231 v3 @ 3.40GHz
- OS: Ubuntu 22.04.4 LTS
- Python: 3.10.12
- numpy: 2.1.1
"""


"""
请在这里填写学号和姓名，不填写即成绩无效。
"""
id = "202210423222"
name = "邓龙树"


"""
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。
"""


# KNN 分类算法
def classify(input_vector, dataSet, labels, k=3):
    # 计算输入向量与训练集中每个样本的距离
    distances = [np.linalg.norm(input_vector - data) for data in dataSet]
    # 根据距离排序并获取前 k 个标签
    k_indices = np.argsort(distances)[:k]
    k_labels = [labels[index] for index in k_indices]
    # 对 k 个标签进行投票，返回出现次数最多的标签
    vote = Counter(k_labels).most_common(1)[0][0]
    return vote


# 从文件夹中加载数据
def load_dataset(directory):
    feature_list = []
    label_list = []
    for file in os.listdir(directory):
        file_path = os.path.join(directory, file)
        feature = img_to_vector(file_path)
        label = int(file.split('_')[0])
        feature_list.append(feature)
        label_list.append(label)
    return np.array(feature_list), np.array(label_list)


# 将二值图像转换为向量
def img_to_vector(filename):
    with open(filename, 'r') as f:
        return np.array([int(char) for char in f.read().strip()])


if __name__ == "__main__":
    #加载训练数据
    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"
    )
   # 将测试数据转换为向量
    test_vector = np.array([int(char) for char in test_data]).reshape(1, 1024)
    # 进行分类预测
    predicted_label = classify(test_vector, train_data, train_labels)
    print(f"预测的标签: {predicted_label}")