generated from LufsX/Experiment-kNN
This commit is contained in:
+63
-80
@@ -25,8 +25,8 @@ import os
|
||||
"""
|
||||
请在这里填写学号和姓名，不填写即成绩无效。
|
||||
"""
|
||||
id = "202210423xxx"
|
||||
name = "test_name"
|
||||
id = "202210423210"
|
||||
name = "陈宇杰"
|
||||
|
||||
|
||||
"""
|
||||
@@ -40,92 +40,75 @@ name = "test_name"
|
||||
"""
|
||||
|
||||
|
||||
# 这里写自己的代码实现
|
||||
def classify(input_vector, dataSet, labels, k=0):
|
||||
"""
|
||||
KNN 分类算法。
|
||||
import numpy as np
|
||||
import os
|
||||
from collections import Counter
|
||||
|
||||
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**。
|
||||
# 加载数据的函数
|
||||
def load_data(directory):
|
||||
file_list = os.listdir(directory)
|
||||
data_matrix = []
|
||||
labels = []
|
||||
|
||||
for file_name in file_list:
|
||||
file_path = os.path.join(directory, file_name)
|
||||
# 读取txt文件并将其转化为向量
|
||||
vector = img_to_vector(file_path)
|
||||
data_matrix.append(vector)
|
||||
# 假设文件名格式为：{数字}_某些字符.txt，提取数字作为标签
|
||||
label = int(file_name.split('_')[0])
|
||||
labels.append(label)
|
||||
|
||||
return np.array(data_matrix), np.array(labels)
|
||||
|
||||
Returns:
|
||||
- int: 预测的分类标签。
|
||||
"""
|
||||
# 将32x32的二值图像转换为1x1024的向量
|
||||
def img_to_vector(file_path):
|
||||
vector = np.zeros((1, 1024))
|
||||
with open(file_path, 'r') as f:
|
||||
lines = f.readlines()
|
||||
for i in range(32):
|
||||
for j in range(32):
|
||||
vector[0, 32 * i + j] = int(lines[i][j])
|
||||
return vector
|
||||
|
||||
# kNN 分类函数
|
||||
def classify(input_vector, dataSet, labels, k=3):
|
||||
# 计算欧氏距离
|
||||
distances = np.linalg.norm(dataSet - input_vector, axis=1)
|
||||
# 获取距离最近的k个样本的标签
|
||||
nearest_neighbors = np.argsort(distances)[:k]
|
||||
nearest_labels = labels[nearest_neighbors]
|
||||
|
||||
# 确保 nearest_labels 是一维的，转换为 Python 列表
|
||||
nearest_labels = nearest_labels.flatten().tolist()
|
||||
|
||||
# 投票，返回出现次数最多的标签
|
||||
most_common = Counter(nearest_labels).most_common(1)
|
||||
return most_common[0][0]
|
||||
|
||||
# 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**。
|
||||
# 实验主程序
|
||||
def main():
|
||||
# 加载训练集和测试集
|
||||
training_data, training_labels = load_data('trainingdigits')
|
||||
test_data, test_labels = load_data('testdigits')
|
||||
|
||||
Args:
|
||||
- directory (str): 数据文件夹路径。
|
||||
# 测试 kNN 算法
|
||||
total_tests = len(test_data)
|
||||
correct_predictions = 0
|
||||
|
||||
Returns:
|
||||
- np.array: 特征数据。
|
||||
- np.array: 标签数据。
|
||||
"""
|
||||
for i in range(total_tests):
|
||||
test_sample = test_data[i]
|
||||
prediction = classify(test_sample, training_data, training_labels, k=3)
|
||||
actual_label = test_labels[i]
|
||||
|
||||
print(f"测试样本 {i+1}: 预测值 = {prediction}, 实际值 = {actual_label}")
|
||||
|
||||
# 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。
|
||||
if prediction == actual_label:
|
||||
correct_predictions += 1
|
||||
|
||||
Args:
|
||||
- filename (str): 图像文件路径。
|
||||
accuracy = correct_predictions / total_tests * 100
|
||||
print(f"\n分类精度: {accuracy:.2f}%")
|
||||
|
||||
Returns:
|
||||
- np.array: 二值图像向量。
|
||||
"""
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
|
||||
|
||||
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}")
|
||||
|
||||
Reference in New Issue
Block a user