From c426ae568391dcd00d016e42dff07cc3cbf9d05e Mon Sep 17 00:00:00 2001
From: anye <513317375@qq.com>
Date: Thu, 17 Oct 2024 16:26:03 +0800
Subject: [PATCH] =?UTF-8?q?=E6=9B=B4=E6=96=B0=20function.py?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 function.py | 32 ++++++++++++++------------------
 1 file changed, 14 insertions(+), 18 deletions(-)

diff --git a/function.py b/function.py
index bedbf8e..1eb8a81 100644
--- a/function.py
+++ b/function.py
@@ -1,3 +1,4 @@
+python
 import numpy as np
 
 """
@@ -6,28 +7,26 @@ qin
 id = "202210423206"
 name = "詹宇豪"
 
-def classify0(inX, dataSet, labels, k=1):
+def classify0(inX, dataSet, labels, k=3):
     """
     KNN 分类算法。
-
     Args:
     - inX (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。
     """
-    # 计算输入样本与训练数据集中每个样本的欧氏距离
-    distances = np.sqrt(((dataSet - inX) ** 2).sum(axis=1))
+    # 使用广播机制计算欧氏距离，提高效率
+    distances = np.linalg.norm(dataSet - inX, axis=1)
     
     # 按距离从小到大排序并获取对应的索引
-    sorted_indices = distances.argsort()
-
-    # 选择距离最近的k个样本
+    sorted_indices = np.argsort(distances)
+    
+    # 选择距离最近的k个样本的标签
     top_k_labels = labels[sorted_indices[:k]]
-
+    
     # 统计k个样本中出现最多的类别
     predicted_label = np.bincount(top_k_labels).argmax()
 
@@ -36,15 +35,13 @@ def classify0(inX, dataSet, labels, k=1):
 def normalize_data(data):
     """
     对数据进行归一化处理，将每个特征缩放到 [0, 1] 范围。
-
     Args:
     - data (numpy array): 待归一化的数据集。
-
     Returns:
     - numpy array: 归一化后的数据集。
     """
-    min_vals = data.min(0)  # 每一列的最小值
-    max_vals = data.max(0)  # 每一列的最大值
+    min_vals = data.min(axis=0)  # 每一列的最小值
+    max_vals = data.max(axis=0)  # 每一列的最大值
     ranges = max_vals - min_vals  # 每一列的取值范围
     norm_data = (data - min_vals) / ranges  # 归一化公式
     return norm_data, ranges, min_vals
@@ -64,12 +61,11 @@ def load_data(file_path):
 
 
 if __name__ == "__main__":
-    # 测试代码，可以修改以便调试
-    train_file = "datingTrainSet2.tsv"
-
     # 加载训练数据
+    train_file = "datingTrainSet2.tsv"
     train_data, train_labels = load_data(train_file)
-
+    
     # 测试 classify0 函数
-    result = classify0(np.array([65915, 3.868359, 0.128078]), train_data, train_labels)
+    test_sample = np.array([65915, 3.868359, 0.128078])
+    result = classify0(test_sample, train_data, train_labels, k=3)
     print("Predicted label:", result)
\ No newline at end of file