generated from LufsX/Experiment-kNN
169 lines
5.6 KiB
Python
169 lines
5.6 KiB
Python
# 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 = "202210423209"
|
|
name = "万子玉"
|
|
|
|
|
|
"""
|
|
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
|
|
def mahalanobis_distance(x, mean, inv_covmat):
|
|
delta = x - mean
|
|
m_dist = np.sqrt(np.dot(np.dot(delta, inv_covmat), delta.T))
|
|
return m_dist
|
|
|
|
def classify(input_vector, dataSet, labels, k=2):
|
|
"""
|
|
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 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**。
|
|
|
|
Returns:
|
|
- int: 预测的分类标签。
|
|
"""
|
|
mean = np.mean(dataSet, axis=0)
|
|
covmat = np.cov(dataSet, rowvar=0)
|
|
inv_covmat = np.linalg.inv(covmat)
|
|
|
|
dists = [mahalanobis_distance(input_vector, mean, inv_covmat)]
|
|
|
|
for data in dataSet:
|
|
dists.append(mahalanobis_distance(data, mean, inv_covmat))
|
|
|
|
k_indices = np.argsort(dists)[:k]
|
|
k_nearest_labels = [labels[i] for i in k_indices]
|
|
|
|
if not k_nearest_labels:
|
|
raise ValueError("No neighbors found; possible causes: k is too small or all distances are the same.")
|
|
|
|
most_common = Counter(k_nearest_labels).most_common(1)
|
|
|
|
if most_common:
|
|
return most_common[0][0]
|
|
else:
|
|
return None
|
|
|
|
|
|
# 这里也写自己的代码实现
|
|
def load_dataset(directory):
|
|
"""
|
|
从文件夹中加载数据，若不自行正确实现，则无法通过评测，**不记录成绩**。
|
|
|
|
Args:
|
|
- directory (str): 数据文件夹路径。
|
|
|
|
Returns:
|
|
- np.array: 特征数据。
|
|
- np.array: 标签数据。
|
|
"""
|
|
data_list = []
|
|
label_list = []
|
|
for root, dirs, files in os.walk(directory):
|
|
for file in files:
|
|
file_path = os.path.join(root, file)
|
|
vector = img_to_vector(file_path)
|
|
data_list.append(vector)
|
|
label_list.append(int(file.split('_')[0]))
|
|
return np.array(data_list), np.array(label_list)
|
|
|
|
|
|
# 这里还写自己的代码实现
|
|
def img_to_vector(filename):
|
|
"""
|
|
将二值图像转换为向量。
|
|
该部分应为 load_dataset 函数的辅助子函数，可单独在这里实现，也可直接集成至 load_dataset 函数中。
|
|
|
|
Args:
|
|
- filename (str): 图像文件路径。
|
|
|
|
Returns:
|
|
- np.array: 二值图像向量。
|
|
"""
|
|
with open(filename, 'r') as f:
|
|
lines = f.readlines()
|
|
vector = np.array([int(char) for line in lines for char in line.strip() if char.isdigit()])
|
|
return vector.reshape(1, -1)
|
|
|
|
if __name__ == "__main__":
|
|
# 以下代码可用于测试，可自行随意修改
|
|
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}") |