From 3a4694497efb1dcb2a1b9c9283d78720515f7413 Mon Sep 17 00:00:00 2001
From: 202210423104 <1961532386@qq.com>
Date: Wed, 16 Oct 2024 21:58:42 +0800
Subject: [PATCH] =?UTF-8?q?=E4=B8=8A=E4=BC=A0=E6=96=87=E4=BB=B6=E8=87=B3?=
 =?UTF-8?q?=20/?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 function.py | 43 +++++++++++++------------------------------
 1 file changed, 13 insertions(+), 30 deletions(-)

diff --git a/function.py b/function.py
index cbe0062..a7eb05f 100644
--- a/function.py
+++ b/function.py
@@ -2,63 +2,46 @@
 import numpy as np
 from collections import Counter
 
-
 id = "202210423104"
 name = "张钦诚"
 
-
-
-def classify0(inX, dataSet, labels, k=3):
-
-    # 转换输入样本为numpy数组
+def classify0(inX, dataSet, labels, k=5):
     inX = np.array(inX)
-
-    # 计算欧氏距离
-    # 使用广播计算所有训练样本与输入样本的距离
-    distances = np.linalg.norm(dataSet - inX, axis=1)
-
-    # 获取距离最小的k个样本的索引
-    nearest_indices = distances.argsort()[:k]
-
-    # 获取这k个样本的标签
+    distances = np.sum((dataSet - inX) ** 2, axis=1)
+    nearest_indices = np.argpartition(distances, k)[:k]
     nearest_labels = labels[nearest_indices]
-
-    # 统计出现次数最多的标签
     label_count = Counter(nearest_labels)
-
-    # 返回出现次数最多的标签
     return label_count.most_common(1)[0][0]
 
-
 def load_data(file_path):
-
     data = np.loadtxt(file_path, delimiter="\t")
     features = data[:, :-1]
     labels = data[:, -1].astype(int)
     return features, labels
 
+def standardize(train_data, test_data):
+    mean = np.mean(train_data, axis=0)
+    std = np.std(train_data, axis=0)
+    std[std == 0] = 1
+    train_standardized = (train_data - mean) / std
+    test_standardized = (test_data - mean) / std
+    return train_standardized, test_standardized
 
 if __name__ == "__main__":
-    # 以下代码可用于测试，可自行随意修改
-
     train_file = "datingTrainSet2.tsv"
     test_file = "datingTestSet2.tsv"
 
-    # 加载训练数据
     train_data, train_labels = load_data(train_file)
-
-    # 加载测试数据
     test_data, test_labels = load_data(test_file)
 
-    # 测试样本
+    train_data, test_data = standardize(train_data, test_data)
+
     test_sample = [65915, 3.868359, 0.128078]
+    test_sample = (np.array(test_sample) - np.mean(train_data, axis=0)) / np.std(train_data, axis=0)
 
-    # 预测标签
     predicted_label = classify0(test_sample, train_data, train_labels)
-
     print(f"预测的分类标签: {predicted_label}")
 
-    # 计算准确率
     predictions = np.array([classify0(sample, train_data, train_labels) for sample in test_data])
     accuracy = np.mean(predictions == test_labels) * 100
     print(f"准确率: {accuracy:.2f}%")