From a53439dc964440776a8ceff0160734748798f103 Mon Sep 17 00:00:00 2001
From: cy <939601402@qq.com>
Date: Tue, 1 Oct 2024 19:29:51 +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 | 47 +++++++++++++++++++++++++++++++++++++----------
 1 file changed, 37 insertions(+), 10 deletions(-)

diff --git a/function.py b/function.py
index 2ce8f6f..7e1efe0 100644
--- a/function.py
+++ b/function.py
@@ -23,8 +23,8 @@ 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 = "202210423117"
+name = "程悦"
 
 
 """
@@ -38,7 +38,7 @@ name = "test_name"
 
 
 # 这里写自己的代码实现
-def classify0(inX, dataSet, labels, k=""):
+def classify0(inX, dataSet, labels, k=3):
     """
     KNN 分类算法。
 
@@ -52,6 +52,20 @@ def classify0(inX, dataSet, labels, k=""):
     - int: 预测的分类标签。
     """
 
+    # 计算输入样本与训练集中每个样本的欧几里得距离  
+    distances = [np.sqrt(np.sum((x_train - inX) ** 2)) for x_train in dataSet]  
+      
+    # 按距离排序并选择前k个最小的距离  
+    k_indices = np.argsort(distances)[:k]  
+    k_nearest_labels = [labels[i] for i in k_indices]  
+      
+    # 计算多数标签  
+    from collections import Counter  
+    label_counts = Counter(k_nearest_labels)  
+    most_common_label = label_counts.most_common(1)[0][0]  
+      
+    return most_common_label  
+
 
 def load_data(file_path):
     """
@@ -64,10 +78,23 @@ def load_data(file_path):
 
 
 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))
+    # 以下代码可用于测试，可自行随意修改  
+    train_file = "datingTrainSet2.tsv"  
+    test_file = "datingTestSet2.tsv"  
+  
+    train_data, train_labels = load_data(train_file)  
+    test_data, test_labels = load_data(test_file)  
+  
+    # 测试 classify0 函数  
+    test_sample = test_data[0]  # 使用测试集中的第一个样本进行测试  
+    predicted_label = classify0(test_sample, train_data, train_labels)  
+    print(f"Predicted label: {predicted_label}, Actual label: {test_labels[0]}")  
+  
+    # 你也可以遍历整个测试集来评估分类器的性能  
+    correct_count = 0  
+    for i in range(len(test_data)):  
+        predicted_label = classify0(test_data[i], train_data, train_labels)  
+        if predicted_label == test_labels[i]:  
+            correct_count += 1  
+    accuracy = correct_count / len(test_data)  
+    print(f"Accuracy: {accuracy * 100:.2f}%")