generated from LufsX/Experiment-kNN
zhangchenghong
208277f981
Gitea Actions Experiment Test / Experiment-Actions (push) Successful in 10s
178 lines
5.9 KiB
Python
178 lines
5.9 KiB
Python
# 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·"
|
|
|
|
|
|
"""
|
|
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。
|
|
"""
|
|
|
|
|
|
# 这里写自己的代码实现
|
|
import numpy as np
|
|
import os
|
|
from collections import Counter
|
|
|
|
def classify(input_vector, dataSet, labels, k=3):
|
|
"""
|
|
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 3。
|
|
|
|
返回:
|
|
- int: 预测的分类标签。
|
|
"""
|
|
# 计算马氏距离
|
|
mean_vector = np.mean(dataSet, axis=0)
|
|
cov_matrix = np.cov(dataSet.T)
|
|
inv_cov_matrix = np.linalg.inv(cov_matrix)
|
|
diff_vector = input_vector - dataSet
|
|
mahalanobis_distances = np.sqrt(np.einsum('ij,jk,ik->i', diff_vector, inv_cov_matrix, diff_vector.T))
|
|
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()
|
|
|
|
# 使用加权多数表决法
|
|
weighted_votes = {}
|
|
for label, weight in zip(k_nearest_labels, weights):
|
|
if label not in weighted_votes:
|
|
weighted_votes[label] = weight
|
|
else:
|
|
weighted_votes[label] += weight
|
|
|
|
return max(weighted_votes, key=weighted_votes.get)
|
|
|
|
def load_dataset(directory):
|
|
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（归一化）
|
|
min_value = np.min(feature_matrix)
|
|
max_value = np.max(feature_matrix)
|
|
feature_matrix = (feature_matrix - min_value) / (max_value - min_value)
|
|
|
|
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"
|
|
)
|
|
# 使用多数表决法的结果
|
|
predicted_label_majority = classify(
|
|
np.array([int(char) for char in test_data]).reshape(1, 1024),
|
|
train_data,
|
|
train_labels,
|
|
)
|
|
print(f"使用多数表决法预测的标签: {predicted_label_majority}")
|
|
|
|
# 使用加权多数表决法的结果
|
|
predicted_label_weighted = classify(
|
|
np.array([int(char) for char in test_data]).reshape(1, 1024),
|
|
train_data,
|
|
train_labels,
|
|
)
|
|
print(f"使用加权多数表决法预测的标签: {predicted_label_weighted}")
|
|
|
|
# 对比分析
|
|
if predicted_label_majority == predicted_label_weighted:
|
|
print("两种方法预测结果一致。")
|
|
else:
|
|
print("两种方法预测结果不同。")
|
|
|