获取不同k值下kNN的confusion_matrix与classification_report报错求助

问题场景 #

尝试为一系列k值的KNN模型生成混淆矩阵和分类报告，编写的代码如下：

confusion_matrix = {}
classification_report = {}
neighbors = np.arange(5, 20)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,
random_state=42, stratify=y)
for neighbor in neighbors:    
    # Set up a KNN Classifier
    knn = KNeighborsClassifier(n_neighbors=neighbor)    
    # Fit the model
    knn.fit(X_train, y_train) 
     # Compute 
    y_pred= knn.predict(X_test) 
    confusion_matrix[neighbor] = confusion_matrix(y_test,y_pred)
    classification_report[neighbor] = classification_report(y_test,y_pred)

print(confusion_matrix(y_test,y_pred))
print(classification_report(y_test,y_pred))

运行后触发如下错误：

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
/var/folders/92/5m7b39tj1j5g7s50bvjdxglc0000gp/T/ipykernel_12129/985428575.py in <module>
     13      # Compute
     14     y_pred= knn.predict(X_test)
---> 15     confusion_matrix[neighbor] = confusion_matrix(y_test,y_pred)
     16     classification_report[neighbor] = classification_report(y_test,y_pred)
     17 

TypeError: 'dict' object is not callable

错误原因 #

你将存储结果的字典命名为confusion_matrix和classification_report，这两个名字与sklearn库中生成混淆矩阵、分类报告的同名函数完全一致。第一次执行循环时，字典会覆盖原有的函数引用，后续再尝试调用confusion_matrix(y_test,y_pred)时，实际是在调用一个字典对象，因此触发"dict不可调用"的TypeError。

修改后的代码 #

将存储结果的字典重命名为不冲突的名称，比如cm_dict和cr_dict，同时调整最后打印逻辑以输出所有k值的结果：

# 重命名字典，避免与sklearn函数名冲突
cm_dict = {}
cr_dict = {}
neighbors = np.arange(5, 20)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,
random_state=42, stratify=y)

for neighbor in neighbors:    
    knn = KNeighborsClassifier(n_neighbors=neighbor)    
    knn.fit(X_train, y_train) 
    y_pred = knn.predict(X_test) 
    # 调用sklearn的原函数，结果存入重命名后的字典
    cm_dict[neighbor] = confusion_matrix(y_test, y_pred)
    cr_dict[neighbor] = classification_report(y_test, y_pred)

# 遍历输出所有k值对应的结果
for k in neighbors:
    print(f"=== k={k} 的结果 ===")
    print("混淆矩阵：")
    print(cm_dict[k])
    print("分类报告：")
    print(cr_dict[k])

关键修改点 #

• 避免变量名与库函数名重名：把confusion_matrix、classification_report这两个字典改成cm_dict、cr_dict，确保后续能正常调用sklearn的原函数
• 调整输出逻辑：遍历字典打印每个k值对应的结果，而不是仅打印最后一次循环的结果

内容的提问来源于stack exchange，提问作者sam muti