Currently trying to create a tabular model with all categorical variables predicting a boolean. My data is in an identical format to Rossman going in, but having an issue with the label_from_df method.
Here’s the error:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-15-d1d1aaded1de> in <module>
1 data = (TabularList.from_df(df, path=PATH, cat_names=cat_names, procs=procs)
2 .random_split_by_pct()
----> 3 .label_from_df(cols=dep_var)
4 .add_test(test)
5 .databunch())
/opt/conda/envs/fastai/lib/python3.6/site-packages/fastai/data_block.py in _inner(*args, **kwargs)
432 self.valid = fv(*args, **kwargs)
433 self.__class__ = LabelLists
--> 434 self.process()
435 return self
436 return _inner
/opt/conda/envs/fastai/lib/python3.6/site-packages/fastai/data_block.py in process(self)
482 "Process the inner datasets."
483 xp,yp = self.get_processors()
--> 484 for ds,n in zip(self.lists, ['train','valid','test']): ds.process(xp, yp, name=n)
485 #progress_bar clear the outputs so in some case warnings issued during processing disappear.
486 for ds in self.lists:
/opt/conda/envs/fastai/lib/python3.6/site-packages/fastai/data_block.py in process(self, xp, yp, name)
656 p.warns = []
657 self.x,self.y = self.x[~filt],self.y[~filt]
--> 658 self.x.process(xp)
659 return self
660
/opt/conda/envs/fastai/lib/python3.6/site-packages/fastai/data_block.py in process(self, processor)
71 if processor is not None: self.processor = processor
72 self.processor = listify(self.processor)
---> 73 for p in self.processor: p.process(self)
74 return self
75
/opt/conda/envs/fastai/lib/python3.6/site-packages/fastai/tabular/data.py in process(self, ds)
72 ds.codes = np.stack([c.cat.codes.values for n,c in ds.xtra[ds.cat_names].items()], 1).astype(np.int64) + 1
73 self.classes = ds.classes = OrderedDict({n:np.concatenate([['#na#'],c.cat.categories.values])
---> 74 for n,c in ds.xtra[ds.cat_names].items()})
75 cat_cols = list(ds.xtra[ds.cat_names].columns.values)
76 else: ds.codes,ds.classes,self.classes,cat_cols = None,None,None,[]
/opt/conda/envs/fastai/lib/python3.6/site-packages/fastai/tabular/data.py in <dictcomp>(.0)
72 ds.codes = np.stack([c.cat.codes.values for n,c in ds.xtra[ds.cat_names].items()], 1).astype(np.int64) + 1
73 self.classes = ds.classes = OrderedDict({n:np.concatenate([['#na#'],c.cat.categories.values])
---> 74 for n,c in ds.xtra[ds.cat_names].items()})
75 cat_cols = list(ds.xtra[ds.cat_names].columns.values)
76 else: ds.codes,ds.classes,self.classes,cat_cols = None,None,None,[]
TypeError: invalid type promotion
Would love any insight into what’s going on in the source code here:
if len(ds.cat_names) != 0:
ds.codes = np.stack([c.cat.codes.values for n,c in ds.inner_df[ds.cat_names].items()], 1).astype(np.int64) + 1
self.classes = ds.classes = OrderedDict({n:np.concatenate([['#na#'],c.cat.categories.values])
for n,c in ds.inner_df[ds.cat_names].items()})
cat_cols = list(ds.inner_df[ds.cat_names].columns.values)