更新 function.py

function.py

@@ -1,5 +1,7 @@
 # function.py
 import numpy as np
+from collections import Counter
+from scipy.spatial import distance
 
 """
 挑战说明:
@@ -52,19 +54,18 @@ def classify0(inX, dataSet, labels, k=3):
     - int: 预测的分类标签。
     """
 
-    # 计算输入样本与训练集中每个样本的欧几里得距离  
+    # 计算输入样本与训练集中每个样本的欧几里得距离
-    distances = [np.sqrt(np.sum((x_train - inX) ** 2)) for x_train in dataSet]  
+    distances = distance.cdist(dataSet, [inX], metric='euclidean').flatten()
-      
+
-    # 按距离排序并选择前k个最小的距离  
+    # 按距离排序并选择前k个最小的距离
-    k_indices = np.argsort(distances)[:k]  
+    k_indices = np.argsort(distances)[:k]
-    k_nearest_labels = [labels[i] for i in k_indices]  
+    k_nearest_labels = [labels[i] for i in k_indices]
-      
+
-    # 计算多数标签  
+    # 计算多数标签
-    from collections import Counter  
+    label_counts = Counter(k_nearest_labels)
-    label_counts = Counter(k_nearest_labels)  
+    most_common_label = label_counts.most_common(1)[0][0]
-    most_common_label = label_counts.most_common(1)[0][0]  
+
-      
+    return most_common_label 
-    return most_common_label  
 
 
 def load_data(file_path):
@@ -78,23 +79,23 @@ def load_data(file_path):
 
 
 if __name__ == "__main__":
-    # 以下代码可用于测试，可自行随意修改  
+    # 以下代码可用于测试，可自行随意修改
-    train_file = "datingTrainSet2.tsv"  
+    train_file = "datingTrainSet2.tsv"
-    test_file = "datingTestSet2.tsv"  
+    test_file = "datingTestSet2.tsv"
-  
+
-    train_data, train_labels = load_data(train_file)  
+    train_data, train_labels = load_data(train_file)
-    test_data, test_labels = load_data(test_file)  
+    test_data, test_labels = load_data(test_file)
-  
+
-    # 测试 classify0 函数  
+    # 测试 classify0 函数
-    test_sample = test_data[0]  # 使用测试集中的第一个样本进行测试  
+    test_sample = test_data[0]  # 使用测试集中的第一个样本进行测试
-    predicted_label = classify0(test_sample, train_data, train_labels)  
+    predicted_label = classify0(test_sample, train_data, train_labels)
-    print(f"Predicted label: {predicted_label}, Actual label: {test_labels[0]}")  
+    print(f"Predicted label: {predicted_label}, Actual label: {test_labels[0]}")
-  
+
-    # 你也可以遍历整个测试集来评估分类器的性能  
+    # 遍历整个测试集来评估分类器的性能
-    correct_count = 0  
+    correct_count = 0
-    for i in range(len(test_data)):  
+    for i in range(len(test_data)):
-        predicted_label = classify0(test_data[i], train_data, train_labels)  
+        predicted_label = classify0(test_data[i], train_data, train_labels)
-        if predicted_label == test_labels[i]:  
+        if predicted_label == test_labels[i]:
-            correct_count += 1  
+            correct_count += 1
-    accuracy = correct_count / len(test_data)  
+    accuracy = correct_count / len(test_data)
     print(f"Accuracy: {accuracy * 100:.2f}%")