From 446f9fc29cf7be23e866dcb0050af10dd698d9fd Mon Sep 17 00:00:00 2001
From: cy <939601402@qq.com>
Date: Tue, 1 Oct 2024 20:35:34 +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 | 26 ++++++++++++--------------
 1 file changed, 12 insertions(+), 14 deletions(-)

diff --git a/function.py b/function.py
index 9297b5f..06141c5 100644
--- a/function.py
+++ b/function.py
@@ -41,7 +41,7 @@ name = "程悦"
 
 
 # 这里写自己的代码实现
-def classify0(inX, dataSet, labels, k=9):
+def classify0(inX, dataSet, labels, k=3):
     """
     KNN 分类算法。
 
@@ -54,22 +54,20 @@ def classify0(inX, dataSet, labels, k=9):
     Returns:
     - int: 预测的分类标签。
     """
-    # 计算协方差矩阵并求逆矩阵
-    cov_matrix = np.cov(dataSet, rowvar=False)
-    inv_cov_matrix = np.linalg.inv(cov_matrix)
+    
 
-    # 计算输入样本与训练集样本的马氏距离
-    distances = [distance.mahalanobis(inX, data_point, inv_cov_matrix) for data_point in dataSet]
+    # 计算输入样本与训练集中每个样本的欧几里得距离
+    distances = distance.cdist(dataSet, [inX], metric='euclidean').flatten()
 
-    # 按距离排序并选择前 k 个最近的邻居
+    # 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]
 
-    # 统计最近邻居中最多的标签
+    # 计算多数标签
     label_counts = Counter(k_nearest_labels)
     most_common_label = label_counts.most_common(1)[0][0]
 
-    return most_common_label
+    return most_common_label 
 
 
 def load_data(file_path):
@@ -90,10 +88,10 @@ if __name__ == "__main__":
     train_data, train_labels = load_data(train_file)
     test_data, test_labels = load_data(test_file)
 
-    # # 特征缩放
-    # scaler = StandardScaler()
-    # train_data = scaler.fit_transform(train_data)
-    # test_data = scaler.transform(test_data)
+    # 特征缩放
+    scaler = StandardScaler()
+    train_data = scaler.fit_transform(train_data)
+    test_data = scaler.transform(test_data)
 
     # 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
@@ -107,4 +105,4 @@ if __name__ == "__main__":
         if predicted_label == test_labels[i]:
             correct_count += 1
     accuracy = correct_count / len(test_data)
-    print(f"Accuracy: {accuracy * 100:.2f}%")
+    print(f"Accuracy: {accuracy * 100:.2f}%")
\ No newline at end of file