更新 function.py

function.py

@@ -25,8 +25,8 @@ import numpy as np
 """
 请在这里填写学号和姓名，不填写即成绩无效。
 """
-id = "202210423xxx"
+id = "202210423109"
-name = "test_name"
+name = "孔祥芷"
 
 
 """
@@ -53,23 +53,45 @@ def classify0(inX, dataSet, labels, k=0):
     Returns:
     - int: 预测的分类标签。
     """
+    dists = np.sqrt(((dataSet - inX) ** 2).sum(axis=1))
+    sorted_index = np.argsort(dists)
+    class_count = {}
+    for i in range(k):
+        vote_label = labels[sorted_index[i]]
+        if vote_label not in class_count.keys():
+            class_count[vote_label] = 1
+        else:
+            class_count[vote_label] += 1
+    sorted_class_count = sorted(class_count.items(), key=lambda item: item[1], reverse=True)
+    return sorted_class_count[0][0]
+
 
 
 def load_data(file_path):
-    """
+    
-    加载 TSV 格式数据文件。
+    #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
 
 
+
+
 if __name__ == "__main__":
     # 以下代码可用于测试，可自行随意修改
-
+    train_file_path = "datingTrainSet2.tsv"
-    train_file = "datingTrainSet2.tsv"
+    train_features, train_labels = load_data(train_file_path)
-
+    
-    train_data, train_labels = load_data(train_file)
+    test_file_path = "datingTestSet2.tsv"
-
+    test_features, test_labels = load_data(test_file_path)
-    print(classify0([65915, 3.868359, 0.128078], train_data, train_labels))
+    
+    correct_count = 0
+    for i in range(len(test_features)):
+        test_feature = test_features[i].reshape(1, -1)
+        predict_label = classify0(test_feature, train_features, train_labels, k=3)
+        correct_count += (predict_label == test_labels[i])
+    
+    accuracy = correct_count / len(test_features)
+    print(f"Accuracy: {accuracy:.2f}")