Python Forum

Can any one help me on this , unable to determince the reason behind the error while performing RFM analysis.

rfm= data_filtered.groupby('ProductID').agg({'Transaction Time': lambda date: (PRESENT - date.max()).days,
                                        'RetailStore': lambda num: len(num),
                                        'Cost': lambda price: price.sum()})

HELP NEEDED!!

Error:TypeError                                 Traceback (most recent call last)
~\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in aggregate(self, func_or_funcs, *args, **kwargs)
   3494             try:
-> 3495                 return self._python_agg_general(func_or_funcs, *args, **kwargs)
   3496             except Exception:

~\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in _python_agg_general(self, func, *args, **kwargs)
   1073         if len(output) == 0:
-> 1074             return self._python_apply_general(f)
   1075 

~\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in _python_apply_general(self, f)
    935         keys, values, mutated = self.grouper.apply(f, self._selected_obj,
--> 936                                                    self.axis)
    937 
~\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in apply(self, f, data, axis)
   2272             group_axes = _get_axes(group)
-> 2273             res = f(group)
   2274             if not _is_indexed_like(res, group_axes):

~\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in <lambda>(x)
   1061         func = self._is_builtin_func(func)
-> 1062         f = lambda x: func(x, *args, **kwargs)
   1063 

<ipython-input-30-c2dd1078948c> in <lambda>(date)
----> 1 rfm= data_filtered.groupby('ProductID').agg({'Transaction Time': lambda date: (PRESENT - date.max()).days,
      2                                         'RetailStore': lambda num: len(num),
      3                                         'Cost': lambda price: price.sum()})

TypeError: unsupported operand type(s) for -: 'datetime.datetime' and 'str'

During handling of the above exception, another exception occurred:

TypeError                                 Traceback (most recent call last)
<ipython-input-30-c2dd1078948c> in <module>
      1 rfm= data_filtered.groupby('ProductID').agg({'Transaction Time': lambda date: (PRESENT - date.max()).days,
      2                                         'RetailStore': lambda num: len(num),
----> 3                                         'Cost': lambda price: price.sum()})

~\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in aggregate(self, arg, *args, **kwargs)
   4654         axis=''))
   4655     def aggregate(self, arg, *args, **kwargs):
-> 4656         return super(DataFrameGroupBy, self).aggregate(arg, *args, **kwargs)
   4657 
   4658     agg = aggregate

~\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in aggregate(self, arg, *args, **kwargs)
   4085 
   4086         _level = kwargs.pop('_level', None)
-> 4087         result, how = self._aggregate(arg, _level=_level, *args, **kwargs)
   4088         if how is None:
   4089             return result

~\Anaconda3\lib\site-packages\pandas\core\base.py in _aggregate(self, arg, *args, **kwargs)
    488 
    489                 try:
--> 490                     result = _agg(arg, _agg_1dim)
    491                 except SpecificationError:
    492 

~\Anaconda3\lib\site-packages\pandas\core\base.py in _agg(arg, func)
    439                 result = compat.OrderedDict()
    440                 for fname, agg_how in compat.iteritems(arg):
--> 441                     result[fname] = func(fname, agg_how)
    442                 return result
    443 

~\Anaconda3\lib\site-packages\pandas\core\base.py in _agg_1dim(name, how, subset)
    422                     raise SpecificationError("nested dictionary is ambiguous "
    423                                              "in aggregation")
--> 424                 return colg.aggregate(how, _level=(_level or 0) + 1)
    425 
    426             def _agg_2dim(name, how):

~\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in aggregate(self, func_or_funcs, *args, **kwargs)
   3495                 return self._python_agg_general(func_or_funcs, *args, **kwargs)
   3496             except Exception:
-> 3497                 result = self._aggregate_named(func_or_funcs, *args, **kwargs)
   3498 
   3499             index = Index(sorted(result), name=self.grouper.names[0])

~\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in _aggregate_named(self, func, *args, **kwargs)
   3623         for name, group in self:
   3624             group.name = name
-> 3625             output = func(group, *args, **kwargs)
   3626             if isinstance(output, (Series, Index, np.ndarray)):
   3627                 raise Exception('Must produce aggregated value')

<ipython-input-30-c2dd1078948c> in <lambda>(date)
----> 1 rfm= data_filtered.groupby('ProductID').agg({'Transaction Time': lambda date: (PRESENT - date.max()).days,
      2                                         'RetailStore': lambda num: len(num),
      3                                         'Cost': lambda price: price.sum()})

TypeError: unsupported operand type(s) for -: 'datetime.datetime' and 'str'

check your data - you have str values where you expect to have numbers

findbikash

findbikash

buran