更新 function.py

function.py

@@ -2,6 +2,7 @@
 import numpy as np
 from collections import Counter
 from scipy.spatial import distance
+# from sklearn.preprocessing import StandardScaler
 
 """
 挑战说明:
@@ -71,7 +72,6 @@ def classify0(inX, dataSet, labels, k=9):
     return most_common_label
 
 
-
 def load_data(file_path):
     """
     加载 TSV 格式数据文件。
@@ -81,13 +81,20 @@ def load_data(file_path):
     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 = "datingTrainSet2.tsv"
     test_file = "datingTestSet2.tsv"
 
     train_data, train_labels = load_data(train_file)
     test_data, test_labels = load_data(test_file)
 
+    # # 特征缩放
+    # scaler = StandardScaler()
+    # train_data = scaler.fit_transform(train_data)
+    # test_data = scaler.transform(test_data)
+
     # 测试 classify0 函数
     test_sample = test_data[0]  # 使用测试集中的第一个样本进行测试
     predicted_label = classify0(test_sample, train_data, train_labels)
@@ -101,4 +108,3 @@ if __name__ == "__main__":
             correct_count += 1
     accuracy = correct_count / len(test_data)
     print(f"Accuracy: {accuracy * 100:.2f}%")
-