Saved model.pkl file is not trained

[svkadhikary]

Sir, I want to point out one significant point about the saved model.pkl file.
In the utils.py file, we never returned the best model object itself, just the score.

mlproject/src/utils.py

Line 50 in 6d24fc7

return report

And then in model_trainer.py we sort the best max score and then initialize a totally new model based on the name of the highest score model. And in the save_object we are actually saving the newly initialized model which is untrained.

mlproject/src/components/model_trainer.py

Line 98 in 6d24fc7

best_model = models[best_model_name]

What's strange is how it gave a prediction.
Mine didn't and I had to edit the code.
https://github.com/svkadhikary/student_perfomance/blob/45ba9818eb3ab7fb681da7c70d425ed0c70fc0a0/src/utils.py#L66
https://github.com/svkadhikary/student_perfomance/blob/45ba9818eb3ab7fb681da7c70d425ed0c70fc0a0/src/components/model_trainer.py#L100

[Swam80]

Hey,

The model is trained with the best parameters in utils.py itself. See where model.set_params(**gs.best_params_) is done. It sets the parameters to all the model objects one by one and then we do fit, which means it has trained.
I hope you got your point cleared since its been two weeks now.