generated from LufsX/Challenge-kNN
This commit is contained in:
+23
-3
@@ -25,8 +25,8 @@ import numpy as np
|
||||
"""
|
||||
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 = "202210423219"
|
||||
name = "李燕如"
|
||||
|
||||
|
||||
"""
|
||||
@@ -41,7 +41,7 @@ name = "test_name"
|
||||
|
||||
|
||||
# 这里写自己的代码实现
|
||||
def classify0(inX, dataSet, labels, k=0):
|
||||
def classify0(inX, dataSet, labels, k=3):
|
||||
"""
|
||||
KNN 分类算法。
|
||||
|
||||
@@ -54,6 +54,26 @@ def classify0(inX, dataSet, labels, k=0):
|
||||
Returns:
|
||||
- int: 预测的分类标签。
|
||||
"""
|
||||
# 计算待分类样本与训练集中每个样本的距离
|
||||
distances = np.sqrt(np.sum((dataSet - inX) ** 2, axis=1))
|
||||
|
||||
# 获取距离最近的 k 个样本的索引
|
||||
k_indices = np.argsort(distances)[:k]
|
||||
|
||||
# 获取这些样本对应的标签
|
||||
k_nearest_labels = labels[k_indices]
|
||||
|
||||
# 统计每个类别出现的次数
|
||||
count = {}
|
||||
for label in k_nearest_labels:
|
||||
if label in count.keys():
|
||||
count[label] += 1
|
||||
else:
|
||||
count[label] = 1
|
||||
|
||||
# 找到出现次数最多的类别
|
||||
sorted_count = sorted(count.items(), key=lambda x: x[1], reverse=True)
|
||||
return sorted_count[0][0]
|
||||
|
||||
|
||||
def load_data(file_path):
|
||||
|
||||
Reference in New Issue
Block a user