更新 function.py

function.py

@@ -44,38 +44,61 @@ name = "李燕如"
 # 这里写自己的代码实现
 import numpy as np
 
-def classify0(inX, dataSet, labels, k=3):
+def classify0(inX, dataSet, labels, k=5):
-    # 数据标准化
+    """
-    dataSet = (dataSet - np.mean(dataSet, axis=0)) / np.std(dataSet, axis=0)
+    KNN 分类算法。
-    inX = (inX - np.mean(dataSet, axis=0)) / np.std(dataSet, axis=0)
 
-    # 计算距离
+    Args:
-    distances = np.sqrt(np.sum((dataSet - inX) ** 2, axis=1))
+    - 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): kNN 算法参数，默认值为 5。
 
-    # 获取k个最近邻的索引
+    Returns:
-    k_indices = np.argsort(distances)[:k]
+    - int: 预测的分类标签。
+    """
+    # 计算待分类样本与训练集中每个样本的欧氏距离
+    diffMat = np.tile(inX, (dataSet.shape[0], 1)) - dataSet
+    sqDiffMat = diffMat**2
+    sqDistances = sqDiffMat.sum(axis=1)
+    distances = sqDistances**0.5
     
-    # 获取这些样本对应的标签
+    # 对距离进行排序，获取距离最近的 k 个样本的索引
-    k_nearest_labels = labels[k_indices]
+    sortedDistIndices = distances.argsort()
     
-    # 投票决定分类
+    # 提取距离最近的 k 个样本的标签
-    result = {}
+    classCount = {}
-    for label in k_nearest_labels:
+    for i in range(k):
-        if label in result:
+        voteIlabel = labels[sortedDistIndices[i]]
-            result[label] += 1
+        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
-        else:
-            result[label] = 1
     
-    # 返回出现次数最多的类别
+    # 根据出现次数最多的标签来预测待分类样本的标签
-    return max(result, key=result.get)
+    sortedClassCount = sorted(classCount.items(), key=lambda x: x[1], reverse=True)
+    return sortedClassCount[0][0]
 
 def load_data(file_path):
+    """
+    加载 TSV 格式数据文件，并进行标准化处理。
+    """
     data = np.loadtxt(file_path, delimiter="\t")
     features = data[:, :-1]
     labels = data[:, -1].astype(int)
+    
+    # 标准化特征
+    features = (features - np.mean(features, axis=0)) / np.std(features, axis=0)
+    
     return features, labels
 
 if __name__ == "__main__":
     train_file = "datingTrainSet2.tsv"
     train_data, train_labels = load_data(train_file)
-    print(classify0([65915, 3.868359, 0.128078], train_data, train_labels))
+    test_file = "datingTestSet2.tsv"
+    test_data, test_labels = load_data(test_file)
+    
+    # 测试 KNN 分类器
+    correct_count = 0
+    for i in range(test_data.shape[0]):
+        if classify0(test_data[i], train_data, train_labels) == test_labels[i]:
+            correct_count += 1
+    
+    print(f"Accuracy: {correct_count / test_data.shape[0] * 100:.2f}%")