更新 function.py

function.py

@@ -58,8 +58,6 @@ def load_data(file_path):
     return features, labels
 
 
-import numpy as np
-
 def classify0(inX, dataSet, labels, k=3):
     """
     KNN 分类算法。
@@ -85,29 +83,29 @@ def classify0(inX, dataSet, labels, k=3):
     else:
         return -1
 
-
 if __name__ == "__main__":
+    # 加载数据
     def load_data(file_path):
         data = np.loadtxt(file_path, delimiter="\t")
         features = data[:, :-1]
         labels = data[:, -1].astype(int)
         return features, labels
 
+    train_file_path = "datingTrainSet2.tsv"
+    test_file_path = "datingTestSet2.tsv"
+
+    train_features, train_labels = load_data(train_file_path)
+    test_features, test_labels = load_data(test_file_path)
+
+    # 归一化特征
     def normalize(features):
         min_vals = features.min(axis=0)
         max_vals = features.max(axis=0)
         ranges = max_vals - min_vals
         normalized = (features - min_vals) / ranges
-        normalized[ranges == 0] = 0  # Prevent division by zero
+        normalized[ranges == 0] = 0  # 防止除以零
         return normalized
 
-    train_file_path = "datingTrainSet2.tsv"
-    train_features, train_labels = load_data(train_file_path)
-    
-    test_file_path = "datingTestSet2.tsv"
-    test_features, test_labels = load_data(test_file_path)
-    
-    # Normalize features
     train_features = normalize(train_features)
     test_features = normalize(test_features)
 
@@ -121,3 +119,13 @@ if __name__ == "__main__":
 
     accuracy = correct_count / len(test_features)
     print(f"Accuracy: {accuracy:.2f}")
+    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)
+        if predict_label == -1:
+            continue
+        correct_count += (predict_label == test_labels[i])
+
+    accuracy = correct_count / len(test_features)
+    print(f"Accuracy: {accuracy:.2f}")