Closed pplonski closed 3 years ago
Hi @pplonski , I am new to contributing to open source projects. I want to contribute and solve this issue, any help from where I can start solving it would be great.
Hey @rushiv0609 ! Great to hear that you would like to contribute! :) BTW, how have you found this project?
The issue:
In all three steps, the model with random feature should be excluded. Give me a few minutes, I will find in the code where it should be.
@rushiv0609 some tips on how to start:
_perform_model_stacking()
method in base_automl.py
get_hill_climbing_params
in tuner/mljar_tuner.py
fileget_oof_matrix()
in ensemble.py
To check if model has inserted random feature:
if model.params["preprocessing"].get("add_random_feature", False):
print("there is random feature")
If you will need further help, please let me know. Happy to help!
Thanks a lot @pplonski . I was just browsing through good first issues tags and came across this project.
When I run AutoML.fit(), I get the following runtime error, I cannot find anywhere how to resolve this
* Step default_algorithms will try to check up to 3 models
Exception ignored in: <bound method Image.__del__ of <tkinter.PhotoImage object at 0x000002577A5FE3C8>>
Traceback (most recent call last):
File "D:\Python36\lib\tkinter\__init__.py", line 3507, in __del__
self.tk.call('image', 'delete', self.name)
RuntimeError: main thread is not in main loop
Exception ignored in: <bound method Image.__del__ of <tkinter.PhotoImage object at 0x000002577C962630>>
Traceback (most recent call last):
File "D:\Python36\lib\tkinter\__init__.py", line 3507, in __del__
self.tk.call('image', 'delete', self.name)
RuntimeError: main thread is not in main loop
Exception ignored in: <bound method Image.__del__ of <tkinter.PhotoImage object at 0x000002577C9626A0>>
Traceback (most recent call last):
File "D:\Python36\lib\tkinter\__init__.py", line 3507, in __del__
self.tk.call('image', 'delete', self.name)
RuntimeError: main thread is not in main loop
2020-09-26 07:24:15,387 concurrent.futures ERROR exception calling callback for <Future at 0x2570013f0f0 state=finished raised BrokenProcessPool>
joblib.externals.loky.process_executor._RemoteTraceback:
It is fixed in 0.10.3
Right now a model with random feature inserted (part of feature selection procedure) can be used for stacking - it shouldnt.