From f6a583863c5a1eb723a5b09e8d7cce62e631218e Mon Sep 17 00:00:00 2001
From: yuhaopan <1159526601@qq.com>
Date: Tue, 15 Oct 2024 20:29:54 +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 | 39 ++++++++++++++++++++++-----------------
 1 file changed, 22 insertions(+), 17 deletions(-)

diff --git a/function.py b/function.py
index 05fac37..0f205a1 100644
--- a/function.py
+++ b/function.py
@@ -38,30 +38,35 @@ name = "潘宇豪"
 """
 
 
-def classify0(inX, dataSet, labels, k):
+def classify0(inX, dataSet, labels, k=4):
     """
-    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
+    KNN 分类算法，使用马氏距离，并避免显式循环。
+
+    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。
     """
-    # Calculate covariance matrix and its inverse from the dataset
-    cov_matrix = np.cov(dataSet.T)
+    # 计算训练数据集的协方差矩阵和它的逆矩阵
+    cov_matrix = np.cov(dataSet, rowvar=False)
     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))
+    # 计算马氏距离
+    diffMat = dataSet - inX
+    distances = np.sqrt(np.sum(np.dot(diffMat, inv_cov_matrix) * diffMat, axis=1))
     
-    # Sort by distance and return the indices of the k nearest neighbors
-    sorted_indices = np.argsort(distances)
+    # 对距离进行排序并找到最近的k个邻居
+    sortedDistIndices = np.argsort(distances)[:k]  # 直接选择前k个最近的索引
     
-    # Get the labels of the k nearest neighbors
-    k_nearest_labels = [labels[i] for i in sorted_indices[:k]]
+    # 获取这k个邻居的标签
+    k_nearest_labels = labels[sortedDistIndices]
     
-    # Return the most common label among the k nearest neighbors
-    most_common_label = Counter(k_nearest_labels).most_common(1)[0][0]
+    # 使用np.bincount计算每个标签的出现次数，并返回出现次数最多的标签
+    most_common_label = np.bincount(k_nearest_labels).argmax()
     
     return most_common_label