From 337f3294a3138bafa52748df7647285300fb3aad Mon Sep 17 00:00:00 2001
From: yuhaopan <1159526601@qq.com>
Date: Tue, 15 Oct 2024 20:24:06 +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 | 60 +++++++++++++++++++++--------------------------------
 1 file changed, 24 insertions(+), 36 deletions(-)

diff --git a/function.py b/function.py
index fadf833..05fac37 100644
--- a/function.py
+++ b/function.py
@@ -38,44 +38,32 @@ name = "潘宇豪"
 """
 
 
-# 这里写自己的代码实现
-def classify0(inX, dataSet, labels, ,k_values = [3,4,5,6,7,8,9]):
+def classify0(inX, dataSet, labels, k):
     """
-    KNN 分类算法。
-
-    参数:
-    - 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): 使用的邻居数量。
-
-    返回值:
-    - int: 预测的分类标签。
+    KNN classification using Mahalanobis distance for fast computation.
+    inX: The input sample to classify
+    dataSet: The training data
+    labels: The corresponding labels for the training data
+    k: The number of nearest neighbors to consider
     """
-
-    def mahalanobis_distance(inX, data, cov_inv):
-        diff = inX - data
-        return np.sqrt(np.dot(np.dot(diff, cov_inv), diff.T))
-
-    mean = np.mean(dataSet, axis=0)
-    cov_inv = inv(np.cov(dataSet, rowvar=False))
-
-    # 计算所有k值的预测
-    predictions = []
-    for k in k_values:
-        distances = [mahalanobis_distance(inX, data, cov_inv) for data in dataSet]
-        sortedDistIndices = np.argsort(distances)
-        classCount = {}
-        for i in range(k):
-            voteIlabel = labels[sortedDistIndices[i]]
-            classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
-        
-        sortedClassCount = sorted(classCount.items(), key=lambda item: item[1], reverse=True)
-        predictions.append(sortedClassCount[0][0])
-
-    # 多数投票机制
-    final_prediction, _ = mode(predictions)
-    return final_prediction.mode[0]
+    # Calculate covariance matrix and its inverse from the dataset
+    cov_matrix = np.cov(dataSet.T)
+    inv_cov_matrix = inv(cov_matrix)
+    
+    # Compute the Mahalanobis distance between inX and all points in the dataset
+    diff = dataSet - inX
+    distances = np.sqrt(np.sum(np.dot(diff, inv_cov_matrix) * diff, axis=1))
+    
+    # Sort by distance and return the indices of the k nearest neighbors
+    sorted_indices = np.argsort(distances)
+    
+    # Get the labels of the k nearest neighbors
+    k_nearest_labels = [labels[i] for i in sorted_indices[:k]]
+    
+    # Return the most common label among the k nearest neighbors
+    most_common_label = Counter(k_nearest_labels).most_common(1)[0][0]
+    
+    return most_common_label
  
 def load_data(file_path):
     """