更新 function.py

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.
+    KNN 分类算法，使用马氏距离，并避免显式循环。
-    inX: The input sample to classify
+
-    dataSet: The training data
+    参数:
-    labels: The corresponding labels for the training data
+    - inX (numpy array): 输入待分类的样本。
-    k: The number of nearest neighbors to consider
+    - 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
+    # 计算训练数据集的协方差矩阵和它的逆矩阵
-    cov_matrix = np.cov(dataSet.T)
+    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
+    # 计算马氏距离
-    diff = dataSet - inX
+    diffMat = dataSet - inX
-    distances = np.sqrt(np.sum(np.dot(diff, inv_cov_matrix) * diff, axis=1))
+    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
+    # 对距离进行排序并找到最近的k个邻居
-    sorted_indices = np.argsort(distances)
+    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
+    # 获取这k个邻居的标签
-    k_nearest_labels = [labels[i] for i in sorted_indices[:k]]
+    k_nearest_labels = labels[sortedDistIndices]
     
-    # Return the most common label among the k nearest neighbors
+    # 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 = Counter(k_nearest_labels).most_common(1)[0][0]
+    most_common_label = np.bincount(k_nearest_labels).argmax()
     
     return most_common_label