generated from LufsX/Experiment-kNN
116 lines
3.6 KiB
Python
116 lines
3.6 KiB
Python
import numpy as np
|
|
import os
|
|
|
|
id = "202210218225"
|
|
name = "周水源"
|
|
|
|
def classify(input_vector, dataSet, labels, k=3):
|
|
"""
|
|
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，默认值为3。
|
|
|
|
Returns:
|
|
- int: 预测的分类标签。
|
|
"""
|
|
# 计算欧氏距离
|
|
distances = np.linalg.norm(dataSet - input_vector, axis=1)
|
|
# 获取距离最近的k个样本的索引
|
|
nearest_indices = distances.argsort()[:k]
|
|
# 获取这k个样本对应的标签
|
|
nearest_labels = labels[nearest_indices]
|
|
# 统计出现最多的标签
|
|
predicted_label = np.bincount(nearest_labels).argmax()
|
|
return predicted_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 = []
|
|
file_list = os.listdir(directory)
|
|
dataSet = np.zeros((len(file_list), 1024))
|
|
|
|
for i, filename in enumerate(file_list):
|
|
# 获取文件的标签，假设标签是文件名的第一个字符
|
|
label = int(filename.split('_')[0])
|
|
labels.append(label)
|
|
# 将图像转换为向量
|
|
dataSet[i, :] = img_to_vector(os.path.join(directory, filename))
|
|
|
|
return dataSet, np.array(labels)
|
|
|
|
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。
|
|
"""
|
|
img_vector = np.zeros((1, 1024))
|
|
with open(filename, 'r') as f:
|
|
for i in range(32): # 32x32图像
|
|
line = f.readline()
|
|
for j in range(32):
|
|
img_vector[0, 32 * i + j] = int(line[j])
|
|
return img_vector
|
|
|
|
if __name__ == "__main__":
|
|
# 测试
|
|
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}")
|