更新 function.py

function.py

@@ -83,25 +83,11 @@ def classify0(inX, dataSet, labels, k=3):
     else:
         return -1
 
-def load_data(file_path):
-    data = np.loadtxt(file_path, delimiter="\t")
-    features = data[:, :-1]
-    labels = data[:, -1].astype(int)
-    return features, labels
-
-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  # 防止除以零的情况
-    return normalized
 
 if __name__ == "__main__":
+    # 假设 load_data 和 normalize 函数已经定义
     train_features, train_labels = load_data("datingTrainSet2.tsv")
     test_features, test_labels = load_data("datingTestSet2.tsv")
-
-    # 在这里进行归一化处理
     train_features = normalize(train_features)
     test_features = normalize(test_features)
 
@@ -124,11 +110,3 @@ if __name__ == "__main__":
             best_k = k
 
     print(f"Best K: {best_k}, Best Accuracy: {best_accuracy:.2f}")
-
-        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}")