Catboost：为什么多类分类在内部转换为回归/单类分类问题

如何解决Catboost：为什么多类分类在内部转换为回归/单类分类问题

在多类分类中使用自定义损失函数时，出现一个错误，即我的自定义目标函数没有calc_ders_range属性。但是，根据我在catboost的Telegram频道中的讨论，calc_ders_range用于单个分类/回归。即使我将自定义目标传递给CatBoostClassifier，我仍然困惑于以下错误。

我的代码： 输出标签为int64类型，其值从0到25代表26个类别。自Usage Examples的{​​{3}}样本中获取了自定义目标和准确性指标

class MyObjective(object):
    def calc_ders_multi(self,approx,target,weight):
        approx = np.array(approx) - max(approx)
        exp_approx = np.exp(approx)
        exp_sum = exp_approx.sum()
        grad = []
        hess = []
        for j in range(len(approx)):
            der1 = -exp_approx[j] / exp_sum
            if j == target:
                der1 += 1
            hess_row = []
            for j2 in range(len(approx)):
                der2 = exp_approx[j] * exp_approx[j2] / (exp_sum**2)
                if j2 == j:
                    der2 -= exp_approx[j] / exp_sum
                hess_row.append(der2 * weight)
                
            grad.append(der1 * weight)
            hess.append(hess_row)
            
        return (grad,hess)

class AccuracyMetric(object):
    def get_final_error(self,error,weight):
        return error / (weight + 1e-38)

    def is_max_optimal(self):
        return True

    def evaluate(self,approxes,weight):
        best_class = np.argmax(approxes,axis=0)
        
        accuracy_sum = 0
        weight_sum = 0 

        for i in range(len(target)):
            w = 1.0 if weight is None else weight[i]
            weight_sum += w
            accuracy_sum += w * (best_class[i] == target[i])

        return accuracy_sum,weight_sum

def get_pipeline(args):
    """Create a pipeline."""
    pipeline_feat1 = Pipeline([
        ('selector',ColumnSelector(cols='feat1',drop_axis=True)),('vec',TfidfVectorizer(tokenizer=word_tokenize)),])
    pipeline_feat2 = Pipeline([
        ('selector',ColumnSelector(cols='feat2',drop_axis=False)),('imputer',SimpleImputer(missing_values=np.nan,strategy="constant",fill_value=0,copy=False)),('ohe',OneHotEncoder(handle_unknown='ignore')),])
    pipeline_feat3 = Pipeline([
        ('selector',ColumnSelector(cols='feat3',])
    features = FeatureUnion([
        ('f1',pipeline_feat1),('f2',pipeline_feat2),('f3',pipeline_feat3),])

    steps = [
        ('features',features),('clf',CatBoostClassifier(task_type='CPU',iterations=5000,random_seed=0,loss_function=MyObjective(),eval_metric=AccuracyMetric(),verbose=100))
    ]
    train_pipeline = Pipeline(steps)

    params = {
        "features__f1__vec__max_features": args.f1_max_features,"features__f1__vec__ngram_range": (1,args.f1_max_ngram)
    }
    params = {k: v for k,v in params.items() if v is not None}

    train_pipeline.set_params(**params)
    return train_pipeline

# Train model.
pipeline = get_pipeline()
# Split train and test data.
X_train,X_val,y_train,y_val = train_test_split(df_train[['feat1','feat2','feat3']],df_train['label'],train_size=0.8,random_state=21)
model = pipeline.fit(X_train,y_train)

错误消息：

AttributeError                            Traceback (most recent call last)
_catboost.pyx in _catboost._ObjectiveCalcDersRange()

AttributeError: 'MyObjective' object has no attribute 'calc_ders_range'

During handling of the above exception,another exception occurred:

CatBoostError                             Traceback (most recent call last)
<ipython-input-12-ea20f154d788> in <module>
     10                                                     train_size=0.8,11                                                     random_state=21)
---> 12 model = pipeline.fit(X_train,y_train)
     13 

/opt/conda/lib/python3.7/site-packages/sklearn/pipeline.py in fit(self,X,y,**fit_params)
    333             if self._final_estimator != 'passthrough':
    334                 fit_params_last_step = fit_params_steps[self.steps[-1][0]]
--> 335                 self._final_estimator.fit(Xt,**fit_params_last_step)
    336 
    337         return self

/opt/conda/lib/python3.7/site-packages/catboost/core.py in fit(self,cat_features,text_features,embedding_features,sample_weight,baseline,use_best_model,eval_set,verbose,logging_level,plot,column_description,verbose_eval,metric_period,silent,early_stopping_rounds,save_snapshot,snapshot_file,snapshot_interval,init_model)
   4296         self._fit(X,None,4297                   eval_set,-> 4298                   silent,init_model)
   4299         return self
   4300 

/opt/conda/lib/python3.7/site-packages/catboost/core.py in _fit(self,pairs,group_id,group_weight,subgroup_id,pairs_weight,init_model)
   1807                 params,1808                 allow_clear_pool,-> 1809                 train_params["init_model"]
   1810             )
   1811 

/opt/conda/lib/python3.7/site-packages/catboost/core.py in _train(self,train_pool,test_pool,params,allow_clear_pool,init_model)
   1256 
   1257     def _train(self,init_model):
-> 1258         self._object._train(train_pool,init_model._object if init_model else None)
   1259         self._set_trained_model_attributes()
   1260 

_catboost.pyx in _catboost._CatBoost._train()

_catboost.pyx in _catboost._CatBoost._train()

CatBoostError: catboost/python-package/catboost/helpers.cpp:42: Traceback (most recent call last):
  File "_catboost.pyx",line 1345,in _catboost._ObjectiveCalcDersRange
AttributeError: 'MyObjective' object has no attribute 'calc_ders_range'