# function.py import numpy as np import os """ 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 = "202210423215" name = "章程鸿·" import numpy as np import os from collections import Counter def classify(input_vector, dataSet, labels, k=2): """ 使用 KNN 算法对输入样本进行分类。 参数: - input_vector (numpy array): 输入待分类的样本(1xN)。 - dataSet (numpy array): 训练数据集(MxN)。 - labels (list or numpy array): 训练集对应的标签。 - k (int): kNN 算法参数,默认值为 2。 返回: - int: 预测的分类标签。 """ # 计算马氏距离 centered_dataSet = dataSet - np.mean(dataSet, axis=0) centered_input_vector = input_vector - np.mean(dataSet, axis=0) cov_matrix = np.cov(centered_dataSet.T) if np.linalg.det(cov_matrix) == 0: raise ValueError("协方差矩阵不可逆") inv_cov_matrix = np.linalg.inv(cov_matrix) mahalanobis_distances = np.sqrt(np.sum(centered_input_vector.dot(inv_cov_matrix) * centered_input_vector, axis=1)) sorted_indices = mahalanobis_distances.argsort() k_nearest_distances = mahalanobis_distances[sorted_indices[:k]] k_nearest_labels = labels[sorted_indices[:k]] # 计算权重(距离的倒数) weights = 1 / k_nearest_distances # 归一化权重 weights /= weights.sum() # 计算加权投票 weighted_votes = np.zeros((10,)) for label, weight in zip(k_nearest_labels, weights): weighted_votes[label] += weight return np.argmax(weighted_votes) def load_dataset(directory): """ 加载数据集中的图像,并将其转换为特征向量和标签。 参数: - directory (str): 数据文件夹路径。 返回: - np.array: 特征数据(Mx1024)。 - np.array: 标签数据(Mx1)。 """ feature_list = [] label_list = [] for file in os.listdir(directory): file_path = os.path.join(directory, file) feature_vector = img_to_vector(file_path) feature_list.append(feature_vector) label_list.append(int(file.split('_')[0])) feature_matrix = np.array(feature_list) label_array = np.array(label_list) # 特征缩放 feature_matrix = feature_matrix / 255.0 return feature_matrix, label_array 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。 """ vector = np.zeros((1024,)) with open(filename) as file: for i, line in enumerate(file): vector[i * 32:i * 32 + 32] = np.array([int(char) for char in line.strip()]) return vector if __name__ == "__main__": 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" ) predicted_label = classify( np.array([int(char) for char in test_data]).reshape(1, 1024), train_data, train_labels, ) print(f"预测的标签: {predicted_label}")