# function.py
import numpy as np
from numpy.linalg import inv, det
from scipy.stats import mode
"""
挑战说明:
- 自行编写实现 KNN 分类算法。
- 输入: 待分类的样本 inX, 训练数据集 dataSet, 训练集对应的标签 labels。
- 输出: 预测的分类标签。

注意事项:
- 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。
- 在 function.py 中实现 KNN 分类算法。
- 自动评测脚本仅会加载 classify0 函数，请勿修改函数名。
- 训练集在本目录下的 datingTrainSet2.tsv 中。
- 评测数据集在本目录下的 datingTestSet2.tsv 中。

挑战环境:
- Ubuntu 22.04.04 LTS
- Python 3.10.12
"""


"""
请在这里填写学号和姓名，不填写即成绩无效。
"""
id = "202210423226"
name = "潘宇豪"


"""
参数说明:
- inX (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。
返回值:
- int: 预测的分类标签。
"""


def classify0(inX, dataSet, labels, k):
    """
    KNN classification using Mahalanobis distance for fast computation.
    inX: The input sample to classify
    dataSet: The training data
    labels: The corresponding labels for the training data
    k: The number of nearest neighbors to consider
    """
    # Calculate covariance matrix and its inverse from the dataset
    cov_matrix = np.cov(dataSet.T)
    inv_cov_matrix = inv(cov_matrix)
    
    # Compute the Mahalanobis distance between inX and all points in the dataset
    diff = dataSet - inX
    distances = np.sqrt(np.sum(np.dot(diff, inv_cov_matrix) * diff, axis=1))
    
    # Sort by distance and return the indices of the k nearest neighbors
    sorted_indices = np.argsort(distances)
    
    # Get the labels of the k nearest neighbors
    k_nearest_labels = [labels[i] for i in sorted_indices[:k]]
    
    # Return the most common label among the k nearest neighbors
    most_common_label = Counter(k_nearest_labels).most_common(1)[0][0]
    
    return most_common_label
 
def load_data(file_path):
    """
    加载TSV格式的数据文件。

    参数:
    - file_path (str): 数据文件的路径。

    返回值:
    - tuple: 包含特征数组和标签数组的元组。
    """
    features = []
    labels = []

    with open(file_path, "r") as file:
        for line in file:
            values = line.strip().split("\t")
            features.append([float(x) for x in values[:-1]])
            labels.append(int(values[-1]))

    return np.array(features), np.array(labels)



if __name__ == "__main__":
    train_file = "datingTrainSet2.tsv"
    train_data, train_labels = load_data(train_file)
    # 使用一个测试样本进行测试
    test_result = classify0([65915, 3.868359, 0.128078], train_data, train_labels, k=3)
    print("预测结果:", test_result)