更新 function.py

function.py

@@ -42,8 +42,9 @@ name = "章程鸿"
 # 这里写自己的代码实现
 import numpy as np
 from collections import Counter
+from sklearn.preprocessing import MinMaxScaler
 
-def classify0(inX, dataSet, labels, k=2):
+def classify0(inX, dataSet, labels, k=3):
     """
     KNN 分类算法。
 
@@ -55,6 +56,7 @@ def classify0(inX, dataSet, labels, k=2):
 
     Returns: 
     - int: 预测的分类标签。
+    
     """
     # 计算距离
     diffMat = inX - dataSet
@@ -64,26 +66,46 @@ def classify0(inX, dataSet, labels, k=2):
     
     # 排序并选取前k个最小距离
     sortedDistIndices = distances.argsort()
-    classCount = {}
-
-    for i in range(k):
-        voteIlabel = labels[sortedDistIndices[i]]
-        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
+    classCount = Counter(labels[sortedDistIndices[:k]])
     
     # 返回出现频率最高的类别
-    sortedClassCount = sorted(classCount.items(), key=lambda x: x[1], reverse=True)
-    return sortedClassCount[0][0]
+    return classCount.most_common(1)[0][0]
 
+def load_data(file_path):
+    """
+    加载 TSV 格式数据文件。
+    """
+    data = np.loadtxt(file_path, delimiter="\t")
+    features = data[:, :-1]
+    labels = data[:, -1].astype(int)
+    return features, labels
 
+def preprocess_data(features):
+    """
+    特征预处理，包括归一化。
+    """
+    scaler = MinMaxScaler()
+    normalized_features = scaler.fit_transform(features)
+    return normalized_features
 
 if __name__ == "__main__":
-    # 以下代码可用于测试，可自行随意修改
     train_file = "datingTrainSet2.tsv"
     
     train_data, train_labels = load_data(train_file)
+    train_data_normalized = preprocess_data(train_data)
 
-    # 测试数据点
-    test_point = np.array([65915, 3.868359, 0.128078])
-    predicted_label = classify0(test_point, train_data, train_labels)
-    print("预测的分类标签是:", predicted_label)
+    # 选择几个有代表性的测试数据点
+    test_points = [
+        [26052, 1.441871, 0.805124],  # 实际标签是 1
+        [38344, 1.669788, 0.134296],  # 实际标签是 1
+        [28488, 10.528555, 1.304844], # 实际标签是 3
+        [22620, 5.297865, 0.638306],  # 实际标签是 2
+        [28567, 9.968648, 0.731232],  # 实际标签是 3
+        [41611, 0.230453, 1.151996]   # 实际标签是 1
+    ]
+    
+    for point in test_points:
+        normalized_point = preprocess_data(np.array([point]))[0]
+        predicted_label = classify0(normalized_point, train_data_normalized, train_labels)
+        print(f"测试数据 {point} 预测标签: {predicted_label}")