Optimize logistic regression plates 3, 3 prime, and 5 #28
Conversation
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
There was a problem hiding this comment.
Nice job! I'm requesting changes mostly due to what looked like a misalignment in file naming for a parquet export labeled as a .joblib. Once that's in place, please feel free to re-request a review. All other comments are up for your consideration. Please don't hesitate to let me know if you have any questions along the way.
1.train_models/log_reg_plates_3_3p_5_cp_norm_data/nbconverted/plate_3_3p_5_train_log_reg_scv.py
Show resolved
Hide resolved
1.train_models/log_reg_plates_3_3p_5_cp_norm_data/nbconverted/plate_3_3p_5_train_log_reg_scv.py
Show resolved
Hide resolved
1.train_models/log_reg_plates_3_3p_5_cp_norm_data/nbconverted/plate_3_3p_5_train_log_reg_scv.py
Show resolved
Hide resolved
1.train_models/log_reg_plates_3_3p_5_cp_norm_data/nbconverted/plate_3_3p_5_train_log_reg_scv.py
Outdated
Show resolved
Hide resolved
1.train_models/log_reg_plates_3_3p_5_cp_norm_data/nbconverted/plate_3_3p_5_train_log_reg_scv.py
Outdated
Show resolved
Hide resolved
1.train_models/log_reg_plates_3_3p_5_cp_norm_data/nbconverted/plate_3_3p_5_train_log_reg_scv.py
Outdated
Show resolved
Hide resolved
1.train_models/log_reg_plates_3_3p_5_cp_norm_data/nbconverted/plate_3_3p_5_train_log_reg_scv.py
Show resolved
Hide resolved
1.train_models/log_reg_plates_3_3p_5_cp_norm_data/nbconverted/plate_3_3p_5_train_log_reg_scv.py
Show resolved
Hide resolved
1.train_models/log_reg_plates_3_3p_5_cp_norm_data/nbconverted/plate_3_3p_5_train_log_reg_scv.py
Show resolved
Hide resolved
1.train_models/log_reg_plates_3_3p_5_cp_norm_data/nbconverted/plate_3_3p_5_train_log_reg_scv.py
Show resolved
Hide resolved
|
Hey @d33bs, actually, I may add something to this pr, so could you wait to provide a re-review? |
|
Thanks @MattsonCam! I'll wait for your go-ahead here on a re-review. |
Thanks for waiting @d33bs, it's ready now! |
1.train_models/log_reg_plates_3_3p_5_cp_norm_data/nbconverted/plate_3_3p_5_train_log_reg_scv.py
Outdated
Show resolved
Hide resolved
1.train_models/log_reg_plates_3_3p_5_cp_norm_data/nbconverted/plate_3_3p_5_train_log_reg_scv.py
Show resolved
Hide resolved
1.train_models/log_reg_plates_3_3p_5_cp_norm_data/nbconverted/plate_3_3p_5_train_log_reg_scv.py
Show resolved
Hide resolved
|
Thanks @d33bs, merging now! |
In this pr, a random search of the regularization parameter is performed using data from plates 3, 3 prime, and 5. The final model is then trained on all of the cross-validated data and saved. The folds and data splits used for optimization were also saved for later evaluation of training and validation data. Please let me know if you have any suggestions.