generated from LufsX/Experiment-kNN
153 lines
5.2 KiB
Python
153 lines
5.2 KiB
Python
# function.py
|
|
import numpy as np
|
|
import os
|
|
from scipy.spatial.distance import mahalanobis
|
|
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 = "202210423111"
|
|
name = "李劲"
|
|
|
|
|
|
"""
|
|
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 classify(input_vector, dataSet, labels, k=1):
|
|
"""
|
|
KNN 分类算法，使用马氏距离。
|
|
"""
|
|
# 计算协方差矩阵及其逆
|
|
cov_matrix = np.cov(dataSet.T)
|
|
inv_cov_matrix = np.linalg.inv(cov_matrix)
|
|
|
|
# 计算马氏距离
|
|
distances = [mahalanobis(input_vector, point, inv_cov_matrix) for point in dataSet]
|
|
|
|
# 获取距离最近的 k 个样本的索引
|
|
k_indices = np.argsort(distances)[:k]
|
|
|
|
# 获取最近邻样本的标签
|
|
k_nearest_labels = [labels[i] for i in k_indices]
|
|
|
|
# 找出出现次数最多的标签
|
|
most_common = Counter(k_nearest_labels).most_common(1)[0][0]
|
|
|
|
return most_common
|
|
|
|
def load_dataset(directory):
|
|
"""
|
|
从文件夹中加载数据。
|
|
"""
|
|
features = []
|
|
labels = []
|
|
|
|
# 遍历文件夹中的所有文件
|
|
for filename in os.listdir(directory):
|
|
if filename.endswith(".txt"): # 假设文件是 .txt 格式
|
|
filepath = os.path.join(directory, filename)
|
|
|
|
try:
|
|
# 假设文件名格式为 "数字_编号.txt"
|
|
label = int(filename.split('_')[0])
|
|
|
|
# 加载文件中的二进制数据并转换为 1D 向量
|
|
image_vector = img_to_vector(filepath)
|
|
|
|
features.append(image_vector)
|
|
labels.append(label)
|
|
except Exception as e:
|
|
print(f"Error processing file {filepath}: {e}")
|
|
|
|
return np.array(features), np.array(labels)
|
|
|
|
def img_to_vector(filename):
|
|
"""
|
|
将二值图像转换为向量。
|
|
"""
|
|
try:
|
|
with open(filename) as file:
|
|
lines = file.readlines()
|
|
image_vector = np.array([int(char) for line in lines for char in line.strip()])
|
|
except Exception as e:
|
|
print(f"Error reading file {filename}: {e}")
|
|
image_vector = np.zeros(expected_vector_length) # 假设有一个预期的向量长度
|
|
# 或者可以抛出一个异常，根据需求决定
|
|
|
|
return image_vector
|
|
|
|
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}")
|