更新 function.py

function.py

@@ -41,6 +41,24 @@ name = "孔祥芷"
 
 # 这里写自己的代码实现
 
+def load_data(file_path):
+    """
+    加载 TSV 格式数据文件。
+
+    Args:
+    - file_path (str): 文件路径。
+
+    Returns:
+    - features (numpy array): 特征数据。
+    - labels (numpy array): 标签数据。
+    """
+    data = np.loadtxt(file_path, delimiter="\t")
+    features = data[:, :-1]
+    labels = data[:, -1].astype(int)
+    return features, labels
+
+
+
 def classify0(inX, dataSet, labels, k=3):
     """
     KNN 分类算法。
@@ -66,56 +84,32 @@ def classify0(inX, dataSet, labels, k=3):
     else:
         return -1
 
-def load_data(file_path):
-    """
-    加载 TSV 格式数据文件。
 
-    Args:
-    - file_path (str): 文件路径。
-
-    Returns:
-    - features (numpy array): 特征数据。
-    - labels (numpy array): 标签数据。
-    """
-    data = np.loadtxt(file_path, delimiter="\t")
-    features = data[:, :-1]
-    labels = data[:, -1].astype(int)
-    return features, labels
-
-def standardize(features):
-    mean = np.mean(features, axis=0)
-    std = np.std(features, axis=0)
-    standardized = (features - mean) / std
-    return standardized
+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  # 防止除以零
+    return normalized
 
 if __name__ == "__main__":
     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)
-    
-    # 特征标准化
-    train_features = standardize(train_features)
-    test_features = standardize(test_features)
-    
-    # 尝试不同的 K 值
-    best_k = 3
-    best_accuracy = 0.0
-    
-    for k in [1, 3, 5, 7, 9]:
-        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=k)
-            if predict_label == -1:
-                continue
-            correct_count += (predict_label == test_labels[i])
-        
-        accuracy = correct_count / len(test_features)
-        print(f"Accuracy with k={k}: {accuracy:.2f}")
-        if accuracy > best_accuracy:
-            best_accuracy = accuracy
-            best_k = k
-    
-    print(f"Best K: {best_k}, Best Accuracy: {best_accuracy:.2f}")
+
+    # 归一化特征
+    train_features = normalize(train_features)
+    test_features = normalize(test_features)
+
+    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}")