自定义多输入原始错误返回“TypeError: issubclass() arg 1 must be a class”

如何解决自定义多输入原始错误返回“TypeError: issubclass() arg 1 must be a class”

我正在使用 Featuretools 库来尝试生成涉及客户交易的自定义功能。我测试了该函数并返回了答案，所以我不确定为什么会出现此错误。

我尝试使用以下链接： https://featuretools.alteryx.com/en/stable/getting_started/primitives.html

谢谢！

from featuretools.primitives import make_agg_primitive

from featuretools.variable_types import DatetimeTimeIndex,Numeric,Categorical

def test_fun(categorical,datetimeindex):
    
    x = pd.DataFrame({'store_name': categorical,'session_start_time': datetimeindex})

    x_mode = list(x['store_name'].mode())[0]

    x = x[x['store_name'] == x_mode]

    y = x.session_start_time.diff().fillna(pd.timedelta(seconds=0))/np.timedelta64(1,'s')    
   
    return y.median()


Test_Fun = make_agg_primitive(function = test_fun,input_types = [Categorical,DatetimeTimeIndex],return_type = [Numeric])
      
fm,fd = ft.dfs(
    entityset = es,target_entity = 'customers',agg_primitives = [Test_Fun],cutoff_time = lt,cutoff_time_in_index = True,include_cutoff_time = False,verbose = True,)

导致以下错误

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-492-358f980bb6b0> in <module>
     20                                 return_type = [Numeric])
     21 
---> 22 fm,fd = ft.dfs(
     23     entityset = es,24     target_entity = 'customers',~\Anaconda3\lib\site-packages\featuretools\utils\entry_point.py in function_wrapper(*args,**kwargs)
     38                     ep.on_error(error=e,39                                 runtime=runtime)
---> 40                 raise e
     41 
     42             # send return value

~\Anaconda3\lib\site-packages\featuretools\utils\entry_point.py in function_wrapper(*args,**kwargs)
     30                 # call function
     31                 start = time.time()
---> 32                 return_value = func(*args,**kwargs)
     33                 runtime = time.time() - start
     34             except Exception as e:

~\Anaconda3\lib\site-packages\featuretools\synthesis\dfs.py in dfs(entities,relationships,entityset,target_entity,cutoff_time,instance_ids,agg_primitives,trans_primitives,groupby_trans_primitives,allowed_paths,max_depth,ignore_entities,ignore_variables,primitive_options,seed_features,drop_contains,drop_exact,where_primitives,max_features,cutoff_time_in_index,save_progress,features_only,training_window,approximate,chunk_size,n_jobs,dask_kwargs,verbose,return_variable_types,progress_callback,include_cutoff_time)
    259                                       seed_features=seed_features)
    260 
--> 261     features = dfs_object.build_features(
    262         verbose=verbose,return_variable_types=return_variable_types)
    263 

~\Anaconda3\lib\site-packages\featuretools\synthesis\deep_feature_synthesis.py in build_features(self,verbose)
    287             assert isinstance(return_variable_types,list),msg
    288 
--> 289         self._run_dfs(self.es[self.target_entity_id],RelationshipPath([]),290                       all_features,max_depth=self.max_depth)
    291 

~\Anaconda3\lib\site-packages\featuretools\synthesis\deep_feature_synthesis.py in _run_dfs(self,entity,relationship_path,all_features,max_depth)
    412         """
    413 
--> 414         self._build_transform_features(all_features,max_depth=max_depth)
    415 
    416         """

~\Anaconda3\lib\site-packages\featuretools\synthesis\deep_feature_synthesis.py in _build_transform_features(self,require_direct_input)
    576                 input_types = input_types[0]
    577 
--> 578             matching_inputs = self._get_matching_inputs(all_features,579                                                         entity,580                                                         new_max_depth,~\Anaconda3\lib\site-packages\featuretools\synthesis\deep_feature_synthesis.py in _get_matching_inputs(self,input_types,primitive,require_direct_input,feature_filter)
    793                              primitive,require_direct_input=False,794                              feature_filter=None):
--> 795         features = self._features_by_type(all_features=all_features,796                                           entity=entity,797                                           max_depth=max_depth,~\Anaconda3\lib\site-packages\featuretools\synthesis\deep_feature_synthesis.py in _features_by_type(self,variable_type)
    768             if (variable_type == variable_types.PandasTypes._all or
    769                     f.variable_type == variable_type or
--> 770                     any(issubclass(f.variable_type,vt) for vt in variable_type)):
    771                 if max_depth is None or f.get_depth(stop_at=self.seed_features) <= max_depth:
    772                     selected_features.append(f)

~\Anaconda3\lib\site-packages\featuretools\synthesis\deep_feature_synthesis.py in <genexpr>(.0)
    768             if (variable_type == variable_types.PandasTypes._all or
    769                     f.variable_type == variable_type or
--> 770                     any(issubclass(f.variable_type,vt) for vt in variable_type)):
    771                 if max_depth is None or f.get_depth(stop_at=self.seed_features) <= max_depth:
    772                     selected_features.append(f)

TypeError: issubclass() arg 1 must be a class

解决方法

我想我明白了。如果有更好的方法，请告诉我！

我不知道为什么文档中的方法不起作用（它使用函数而不是类并且没有提到类）。

我能够利用这个问题的解决方案来解决问题：

How to get an item's group mean but exclude the item itself?

from featuretools.primitives import AggregationPrimitive

class Test_Fun(AggregationPrimitive):
    
    name = "test_fun"
    input_types = [Categorical,DatetimeTimeIndex]
    return_type = Numeric
    stack_on_self = False
    
    def get_function(self):
        
        def mean_excluding_value(categorical,datetimeindex):
            
            x = pd.DataFrame({'store_name': categorical,'session_start_time': datetimeindex})
            x_mode = list(x['store_name'].mode())[0]
            x = x[x['store_name'] == x_mode]
            y = x.session_start_time.diff().fillna(pd.Timedelta(seconds=0))/np.timedelta64(1,'s')    
   
            return y.median()

        return mean_excluding_value

     
fm,fd = ft.dfs(
    entityset = es,target_entity = 'customers',agg_primitives = [Test_Fun],cutoff_time = lt,cutoff_time_in_index = True,include_cutoff_time = False,verbose = True,)

,

在这部分代码中：

Test_Fun = make_agg_primitive(function = test_fun,input_types = [Categorical,DatetimeTimeIndex],return_type = [Numeric])

return_type 应该设置为 Numeric 而不是 [Numeric]

此代码对我有用：

Test_Fun = make_agg_primitive(function = test_fun,return_type = Numeric)