From 7c35d69479e89ee36e020cd0dc34b51d1197fa6b Mon Sep 17 00:00:00 2001
From: zhangchenghong <1598349064@qq.com>
Date: Tue, 8 Oct 2024 17:15:57 +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 | 40 +++++++++++++++++++++++++++-------------
 1 file changed, 27 insertions(+), 13 deletions(-)

diff --git a/function.py b/function.py
index 878989d..d3c46d9 100644
--- a/function.py
+++ b/function.py
@@ -40,7 +40,10 @@ name = "章程鸿"
 
 
 # 这里写自己的代码实现
-def classify0(inX, dataSet, labels, k=0):
+import numpy as np
+from collections import Counter
+
+def classify0(inX, dataSet, labels, k=3):
     """
     KNN 分类算法。
 
@@ -48,28 +51,39 @@ def classify0(inX, dataSet, labels, k=0):
     - 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，请自行设置默认值，评测时仅会使用其默认值。
+    - k (int): KNN 算法参数，默认为3。
 
     Returns:
     - int: 预测的分类标签。
     """
+    # 计算距离
+    diffMat = inX - dataSet
+    sqDiffMat = diffMat ** 2
+    sqDistances = sqDiffMat.sum(axis=1)
+    distances = sqDistances ** 0.5
+    
+    # 排序并选取前k个最小距离
+    sortedDistIndices = distances.argsort()
+    classCount = {}
 
+    for i in range(k):
+        voteIlabel = labels[sortedDistIndices[i]]
+        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
+
+    # 返回出现频率最高的类别
+    sortedClassCount = sorted(classCount.items(), key=lambda x: x[1], reverse=True)
+    return sortedClassCount[0][0]
 
-def load_data(file_path):
-    """
-    加载 TSV 格式数据文件。
-    """
-    data = np.loadtxt(file_path, delimiter="\t")
-    features = data[:, :-1]
-    labels = data[:, -1].astype(int)
-    return features, labels
 
 
 if __name__ == "__main__":
     # 以下代码可用于测试，可自行随意修改
-
     train_file = "datingTrainSet2.tsv"
-
+    
     train_data, train_labels = load_data(train_file)
 
-    print(classify0([65915, 3.868359, 0.128078], train_data, train_labels))
+    # 测试数据点
+    test_point = np.array([65915, 3.868359, 0.128078])
+    predicted_label = classify0(test_point, train_data, train_labels)
+    print("预测的分类标签是:", predicted_label)
+