From 8630be16533eea8827884e5b2c82b59e787d8100 Mon Sep 17 00:00:00 2001
From: meixiaodong <3081674342@qq.com>
Date: Tue, 22 Oct 2024 02:19:39 +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 | 59 +++++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 57 insertions(+), 2 deletions(-)

diff --git a/function.py b/function.py
index 2393b3b..183c427 100644
--- a/function.py
+++ b/function.py
@@ -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 = "202210423211"
+name = "梅晓东"
 
 
 """
@@ -54,6 +54,61 @@ def classify0(inX, dataSet, labels, k=0):
     Returns:
     - int: 预测的分类标签。
     """
+    # function.py
+import numpy as np
+import pandas as pd
+from collections import Counter
+
+# 确保填写自己的学号和姓名
+# 学号: YOUR_STUDENT_ID
+# 姓名: YOUR_NAME
+
+def classify(inx, dataset, labels, k=3):
+    """
+    使用kNN算法对输入样本进行分类。
+
+    :param inx: 要分类的输入样本（1D数组）
+    :param dataset: 训练数据集（2D数组）
+    :param labels: 训练集对应的标签（1D数组）
+    :param k: 最近邻居的数量
+    :return: 输入样本的预测标签
+    """
+    
+    # 将输入转换为numpy数组以便于操作
+    dataset = np.array(dataset)
+    labels = np.array(labels)
+    inx = np.array(inx)
+
+    # 计算输入样本与所有样本的距离
+    distances = np.linalg.norm(dataset - inx, axis=1)
+
+    # 获取最近k个邻居的索引
+    k_indices = np.argsort(distances)[:k]
+
+    # 获取这k个邻居的标签
+    k_nearest_labels = labels[k_indices]
+
+    # 使用多数投票确定预测标签
+    most_common = Counter(k_nearest_labels).most_common(1)
+    return most_common[0][0]
+
+# 测试代码示例（可选择性运行）
+if __name__ == "__main__":
+    # 加载训练数据集
+    train_data = pd.read_csv('datingTrainset2.tsv', sep='\t')
+    train_labels = train_data['label'].values  # 替换'label'为你的实际标签列名
+    train_features = train_data.drop('label', axis=1).values  # 删除标签列
+
+    # 加载测试数据集
+    test_data = pd.read_csv('datingTestset2.tsv', sep='\t')
+    test_labels = test_data['label'].values  # 替换'label'为你的实际标签列名
+    test_features = test_data.drop('label', axis=1).values  # 删除标签列
+
+    # 示例：对一个样本进行分类
+    sample = test_features[0]  # 使用测试集中第一个样本
+    predicted_label = classify(sample, train_features, train_labels, k=3)
+    print(f"Predicted label: {predicted_label}")
+
 
 
 def load_data(file_path):