更新 function.py

function.py

@@ -85,13 +85,41 @@ def load_data(file_path):
     labels = data[:, -1].astype(int)
     return features, labels
 
+def normalize_min_max(data):
+    """
+    对数据进行最小-最大缩放归一化。
+
+    Args:
+    - data (numpy array): 待归一化的数据。
+
+    Returns:
+    - numpy array: 归一化后的数据。
+    - numpy array: 最小值。
+    - numpy array: 最大值。
+    """
+    min_vals = data.min(0)
+    max_vals = data.max(0)
+    ranges = max_vals - min_vals
+    # 避免除以零的情况
+    ranges[ranges == 0.0] = 1.0
+    m = data.shape[0]
+    norm_data = (data - min_vals) / ranges
+    return norm_data, min_vals, max_vals
+
 if __name__ == "__main__":
     # 以下代码可用于测试，可自行随意修改
     train_file = "datingTrainSet2.tsv"
     
+    # 加载训练数据
     train_data, train_labels = load_data(train_file)
 
-    # 测试数据点
+    # 归一化训练数据，并获取最小值和最大值
+    train_data_normalized, min_vals, max_vals = normalize_min_max(train_data)
+
+    # 测试数据点也需要用同样的方式归一化
     test_point = np.array([65915, 3.868359, 0.128078])
-    predicted_label = classify0(test_point, train_data, train_labels)
+    test_point_normalized = (test_point - min_vals) / (max_vals - min_vals)
+
+    # 使用归一化后的数据进行预测
+    predicted_label = classify0(test_point_normalized, train_data_normalized, train_labels)
     print("预测的分类标签是:", predicted_label)