I’m trying to train the TPOT XGBoost out of the box classification model. One of the environment variables is train_time which is set by default to 2 minutes. I’ve tried changing this when starting the pipeline, however I get the following error:
Traceback (most recent call last):
File “/usr/local/lib/python3.6/site-packages/tpot/base.py”, line 711, in fit
File “/usr/local/lib/python3.6/site-packages/tpot/gp_deap.py”, line 227, in eaMuPlusLambda
population[:] = toolbox.evaluate(population)
File “/usr/local/lib/python3.6/site-packages/tpot/base.py”, line 1287, in _evaluate_individuals
File “/usr/local/lib/python3.6/site-packages/tpot/base.py”, line 1205, in _stop_by_max_time_mins
if total_mins_elapsed >= self.max_time_mins:
TypeError: ‘>=’ not supported between instances of ‘float’ and ‘str’
There is obviously a mismatch of variable type here, however it looks like its an issue with the maximum training time that I’ve set (from what I can tell).
Is there a way that I need to set the variable as a float or something else that I’m missing?