generated from LufsX/Challenge-kNN
This commit is contained in:
+5
-6
@@ -1,4 +1,3 @@
|
|||||||
|
|
||||||
import numpy as np
|
import numpy as np
|
||||||
|
|
||||||
"""
|
"""
|
||||||
@@ -7,9 +6,9 @@ qin
|
|||||||
id = "202210423206"
|
id = "202210423206"
|
||||||
name = "詹宇豪"
|
name = "詹宇豪"
|
||||||
|
|
||||||
def classify0(inX, dataSet, labels, k=3):
|
def classify0(inX, dataSet, labels, k=1):
|
||||||
"""
|
"""
|
||||||
KNN 分类算法。
|
KNN 分类算法(使用曼哈顿距离)。
|
||||||
Args:
|
Args:
|
||||||
- inX (numpy array): 输入待分类的样本。
|
- inX (numpy array): 输入待分类的样本。
|
||||||
- dataSet (numpy array): 训练数据集。
|
- dataSet (numpy array): 训练数据集。
|
||||||
@@ -18,8 +17,8 @@ def classify0(inX, dataSet, labels, k=3):
|
|||||||
Returns:
|
Returns:
|
||||||
- int: 预测的分类标签。
|
- int: 预测的分类标签。
|
||||||
"""
|
"""
|
||||||
# 使用广播机制计算欧氏距离,提高效率
|
# 曼哈顿距离计算
|
||||||
distances = np.linalg.norm(dataSet - inX, axis=1)
|
distances = np.sum(np.abs(dataSet - inX), axis=1)
|
||||||
|
|
||||||
# 按距离从小到大排序并获取对应的索引
|
# 按距离从小到大排序并获取对应的索引
|
||||||
sorted_indices = np.argsort(distances)
|
sorted_indices = np.argsort(distances)
|
||||||
@@ -67,5 +66,5 @@ if __name__ == "__main__":
|
|||||||
|
|
||||||
# 测试 classify0 函数
|
# 测试 classify0 函数
|
||||||
test_sample = np.array([65915, 3.868359, 0.128078])
|
test_sample = np.array([65915, 3.868359, 0.128078])
|
||||||
result = classify0(test_sample, train_data, train_labels, k=3)
|
result = classify0(test_sample, train_data, train_labels, k=1)
|
||||||
print("Predicted label:", result)
|
print("Predicted label:", result)
|
||||||
Reference in New Issue
Block a user