Lesson 3 IMDB example : KeyError: 'unsup'

[zhangjiekui]

data_clas = (TextList.from_folder(path, vocab=data_lm.vocab)
#grab all the text files in path
.split_by_folder(valid='test')
#split by train and valid folder (that only keeps 'train' and 'test' so no need to filter)
.label_from_folder(classes=['neg', 'pos'])
.filter_missing_y() #the error is the same even comments this line
#label them all with their folders
.databunch(bs=bs))

data_clas.save('tmp_clas')

KeyError Traceback (most recent call last)
/usr/anaconda/envs/pytorch10/lib/python3.7/site-packages/fastai/data_block.py in process_one(self, item)
277 def process_one(self,item):
--> 278 try: return self.c2i[item] if item is not None else None
279 except:

KeyError: 'unsup'

...
exception: Your validation data contains a label that isn't present in the training set, please fix your data.

[dinhju]

had the same issue and „fixed” it by moving the unsup out of the data folder.

[zhangjiekui]

yes , bug I think it's a bug. maybe some filters are needed!

i had tried"label_from_folder(classes=['neg', 'pos'])" ----> "label_from_folder()"
at least this line runs correctly

[agarnitin86]

My train and test set has proper distribution with number of samples in each class much greater than 5 still i am getting same error

[jph00]

It sounds like you might have the wrong dataset. Please ask on the forum if you're still stuck.