更新 function.py

function.py

@@ -42,21 +42,10 @@ name = "章程鸿"
 # 这里写自己的代码实现
 import numpy as np
 from collections import Counter
-from sklearn.preprocessing import MinMaxScaler
 
 def classify0(inX, dataSet, labels, k=3):
     """
     KNN 分类算法。
-
-    Args:
-    - inX (numpy array): 输入待分类的样本。
-    - dataSet (numpy array): 训练数据集。
-    - labels (list or numpy array): 训练集对应的标签。
-    - k (int): KNN 算法参数，默认为3。
-
-    Returns: 
-    - int: 预测的分类标签。
-    
     """
     # 计算距离
     diffMat = inX - dataSet
@@ -80,19 +69,23 @@ def load_data(file_path):
     labels = data[:, -1].astype(int)
     return features, labels
 
-def preprocess_data(features):
+def normalize_features(features):
     """
     特征预处理，包括归一化。
     """
-    scaler = MinMaxScaler()
+    min_vals = features.min(axis=0)
-    normalized_features = scaler.fit_transform(features)
+    max_vals = features.max(axis=0)
-    return normalized_features
+    ranges = max_vals - min_vals
+    m = features.shape[0]
+    norm_features = features - np.tile(min_vals, (m, 1))
+    norm_features = norm_features / np.tile(ranges, (m, 1))
+    return norm_features
 
 if __name__ == "__main__":
     train_file = "datingTrainSet2.tsv"
     
     train_data, train_labels = load_data(train_file)
-    train_data_normalized = preprocess_data(train_data)
+    train_data_normalized = normalize_features(train_data)
 
     # 选择几个有代表性的测试数据点
     test_points = [
@@ -105,7 +98,6 @@ if __name__ == "__main__":
     ]
     
     for point in test_points:
-        normalized_point = preprocess_data(np.array([point]))[0]
+        normalized_point = normalize_features(np.array([point]))[0]
         predicted_label = classify0(normalized_point, train_data_normalized, train_labels)
         print(f"测试数据 {point} 预测标签: {predicted_label}")
-