generated from LufsX/Experiment-kNN
This commit is contained in:
+31
-5
@@ -1,4 +1,3 @@
|
||||
# function.py
|
||||
import numpy as np
|
||||
import os
|
||||
|
||||
@@ -21,12 +20,11 @@ import os
|
||||
- numpy: 2.1.1
|
||||
"""
|
||||
|
||||
|
||||
"""
|
||||
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 = "20221042303"
|
||||
name = "赵昊龙"
|
||||
|
||||
|
||||
"""
|
||||
@@ -41,7 +39,7 @@ name = "test_name"
|
||||
|
||||
|
||||
# 这里写自己的代码实现
|
||||
def classify(input_vector, dataSet, labels, k=0):
|
||||
def classify(input_vector, dataSet, labels, k=3):
|
||||
"""
|
||||
KNN 分类算法。
|
||||
|
||||
@@ -54,6 +52,22 @@ def classify(input_vector, dataSet, labels, k=0):
|
||||
Returns:
|
||||
- int: 预测的分类标签。
|
||||
"""
|
||||
# 计算输入向量与数据集中每个向量的欧式距离
|
||||
distances = []
|
||||
for i in range(dataSet.shape[0]):
|
||||
dist = np.sqrt(np.sum((input_vector - dataSet[i]) ** 2))
|
||||
distances.append((dist, labels[i]))
|
||||
|
||||
# 根据距离进行排序,取前k个最近邻
|
||||
distances.sort(key=lambda x: x[0])
|
||||
k_nearest_labels = [label for _, label in distances[:k]]
|
||||
|
||||
# 统计前k个最近邻中出现次数最多的标签
|
||||
from collections import Counter
|
||||
label_counts = Counter(k_nearest_labels)
|
||||
most_common_label = label_counts.most_common(1)[0][0]
|
||||
|
||||
return most_common_label
|
||||
|
||||
|
||||
# 这里也写自己的代码实现
|
||||
@@ -68,6 +82,17 @@ def load_dataset(directory):
|
||||
- np.array: 特征数据。
|
||||
- np.array: 标签数据。
|
||||
"""
|
||||
training_file_list = os.listdir(directory)
|
||||
training_matrix = []
|
||||
training_labels = []
|
||||
|
||||
for file in training_file_list:
|
||||
class_num = int(file.split('_')[0])
|
||||
vector = img_to_vector(os.path.join(directory, file))
|
||||
training_matrix.append(vector)
|
||||
training_labels.append(class_num)
|
||||
|
||||
return np.array(training_matrix), np.array(training_labels)
|
||||
|
||||
|
||||
# 这里还写自己的代码实现
|
||||
@@ -82,6 +107,7 @@ def img_to_vector(filename):
|
||||
Returns:
|
||||
- np.array: 二值图像向量。
|
||||
"""
|
||||
return np.array([int(pixel) for pixel in open(filename).read().split()])
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
Reference in New Issue
Block a user