更新 function.py

function.py

@@ -42,6 +42,8 @@ name = "章程鸿"
 # 这里写自己的代码实现
 import numpy as np
 from collections import Counter
+from sklearn.model_selection import GridSearchCV
+from sklearn.neighbors import KNeighborsClassifier
 
 def classify0(inX, dataSet, labels, k=1):
     """
@@ -116,10 +118,28 @@ if __name__ == "__main__":
     # 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)
 
+    # 定义KNN分类器
+    knn = KNeighborsClassifier()
+
+    # 定义要搜索的k值范围
+    param_grid = {'n_neighbors': list(range(1, 31))}
+
+    # 使用GridSearchCV进行网格搜索
+    grid_search = GridSearchCV(knn, param_grid, cv=10, scoring='accuracy')
+    grid_search.fit(train_data_normalized, train_labels)
+
+    # 获取最佳的k值
+    optimal_k = grid_search.best_params_['n_neighbors']
+    print("Optimal k:", optimal_k)
+
+    # 使用最佳k值进行预测
+    best_knn = KNeighborsClassifier(n_neighbors=optimal_k)
+    best_knn.fit(train_data_normalized, train_labels)
+
     # 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])
     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)
+    predicted_label = best_knn.predict([test_point_normalized])
+    print("预测的分类标签是:", predicted_label[0])