XGBoost Classifier - Githubissues

ijyliu / computer-vision-project

Using classical and neural image embeddings and finetuned end-to-end networks to achieve top-tier performance on a vehicle type classification task. Containerized and deployed model as a web app

https://cv-web-app-3m4f2rmfzq-uc.a.run.app/

0 stars 0 forks source link

XGBoost Classifier #40

Closed ijyliu closed 5 months ago

ijyliu commented 6 months ago

Input: all features train and test files. to construct X in the training run you should drop all string variables, and have 'Class', as the y variable. to construct X in the prediction run you should drop all string variables and there should not be a y

Output:

[x] joblib file of model.
[x] Excel file containing time to fit/train overall, train and validation accuracies.
[x] Pickle file of dictionaries of all hyperparameters searched and optimal hyperparameters
[x] Excel file of predictions - this should be all string columns in all features test + one column called classifier_name + '_Prediction'. Excel file of inference time.

ijyliu commented 5 months ago

@ashutoshtiwari13 to add back in multiple hyperparameters

@ijyliu to run

ijyliu commented 5 months ago

completed, good work @ashutoshtiwari13

ijyliu commented 5 months ago

@ashutoshtiwari13 just realized that the hyperparameter settings you changed to for xgboost didnt make it in time before the model was run

in the below, image, just now, i commented out the things you changed to and put what was actually run so the code is accurate

were you expecting the settings you had changed to (the settings that are commented out in the above) be substantially better or did they correct a serious error in the prior settings? if so, we can rerun. but otherwise, don't think its worth it

ijyliu commented 5 months ago

nevermind, switched back to the commented out settings again