Error when trying to run the code

[fatimavrojas]

Hi there!, I´m tryng to run the code for the NYC data and getting this error:

--epochs 1 --device cpu --mode train
Train Epoch: 1 [2530/2531 Loss: 671.671570
Total training time: 23.70315432548523 seconds
Saving model to ./results/model_DG_new_york.pt ...
Computing the CPC on test set, loc2cpc_numerator ...
Traceback (most recent call last):
File "main.py", line 261, in
evaluate()
File "main.py", line 173, in evaluate
cpc_df = cpc_from_num(edf, oa2tile, o2d2flow)
File "main.py", line 166, in cpc_from_num
edf['tile'] = edf['locID'].apply(lambda x: oa2tile[x])
File "/home/fatima/.conda/envs/deepgravity/lib/python3.7/site-packages/pandas/core/series.py", line 4357, in apply
return SeriesApply(self, func, convert_dtype, args, kwargs).apply()
File "/home/fatima/.conda/envs/deepgravity/lib/python3.7/site-packages/pandas/core/apply.py", line 1043, in apply
return self.apply_standard()
File "/home/fatima/.conda/envs/deepgravity/lib/python3.7/site-packages/pandas/core/apply.py", line 1101, in apply_standard
convert=self.convert_dtype,
File "pandas/_libs/lib.pyx", line 2859, in pandas._libs.lib.map_infer
File "main.py", line 166, in
edf['tile'] = edf['locID'].apply(lambda x: oa2tile[x])
KeyError: 1

It seems the network is trained and saved properly, but something arise after it.
Thanks in advance,
Fatima.

[MassimilianoLuca]

Dear fatimavrojas,
we have just pushed a new version of the code and we solved this problem. Please let us know if the problem persists