generated from LufsX/Experiment-kNN
138 lines
4.9 KiB
Python
138 lines
4.9 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。
|
|
"""
|
|
|
|
"""
|
|
请在这里填写学号和姓名，不填写即成绩无效。
|
|
"""
|
|
id = "202210423208"
|
|
name = "刘义天"
|
|
|
|
def classify(input_vector, dataSet, labels, k=3):
|
|
"""
|
|
使用kNN算法分类。
|
|
|
|
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。
|
|
"""
|
|
# 计算欧式距离
|
|
distances = np.linalg.norm(dataSet - input_vector, axis=1)
|
|
# 获取距离最小的k个样本的索引
|
|
nearest_indices = distances.argsort()[:k]
|
|
# 获取这k个样本的标签
|
|
nearest_labels = [labels[i] for i in nearest_indices]
|
|
# 统计每个标签的频率，选择出现频率最高的标签作为预测结果
|
|
most_common_label = Counter(nearest_labels).most_common(1)[0][0]
|
|
|
|
return most_common_label
|
|
|
|
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。
|
|
"""
|
|
labels = []
|
|
data_matrix = []
|
|
|
|
for file_name in os.listdir(directory):
|
|
if file_name.endswith('.txt'):
|
|
# 获取标签（文件名的第一个字符是标签）
|
|
label = int(file_name.split('_')[0])
|
|
labels.append(label)
|
|
|
|
# 读取文件内容并转换为1x1024的特征向量
|
|
file_path = os.path.join(directory, file_name)
|
|
with open(file_path, 'r') as f:
|
|
# 32x32的图像转化为1x1024的向量
|
|
image_vector = np.array([int(char) for line in f for char in line.strip()])
|
|
data_matrix.append(image_vector)
|
|
|
|
return np.array(data_matrix), np.array(labels)
|
|
|
|
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:
|
|
image_vector = np.array([int(char) for line in f for char in line.strip()])
|
|
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}")
|