|
|
e16e82e673
|
added ml numbers from run for multiple models for pnca without fs and started a file for fs
|
2022-05-20 08:11:53 +01:00 |
|
|
|
c1d27f5a92
|
added UQ_LR_FS.py scrip for LR feature selection. SO far this is manual. cannot get it to be part of pipeline
|
2022-05-20 08:10:44 +01:00 |
|
|
|
37bda41f44
|
added and ran hyperparam script for all different classifiers, but couldn't successfully run the feature selection and hyperparam together
|
2022-05-20 08:09:24 +01:00 |
|
|
|
74af5ef890
|
moved UQ_RF older verison to earlier_versions dir
|
2022-05-19 08:32:33 +01:00 |
|
|
|
8b0f69bbd9
|
added pratice and feature selection scripts for LR and hyperparam for all classification models as separate scripts in uq_ml_models
|
2022-05-19 08:31:16 +01:00 |
|
|
|
fa0f5e5b39
|
saving work with scripts for feature selection
|
2022-05-19 08:30:18 +01:00 |
|
|
|
a9dc3c43e5
|
added UQ_practice.py
|
2022-05-19 02:38:01 +01:00 |
|
|
|
ee163d3978
|
added UQ scripts to do hyperparam ML models
|
2022-05-19 02:37:00 +01:00 |
|
|
|
4dbc90ad44
|
modified ml params and models
|
2022-05-19 02:35:50 +01:00 |
|
|
|
3ed7840f60
|
added UQ import and ml call scripts
|
2022-05-16 08:06:56 +01:00 |
|
|
|
66ebb1a30a
|
saving work before adding uq stuff
|
2022-05-16 08:05:41 +01:00 |
|
|
|
5fe2dc47cd
|
added files and saving work
|
2022-05-05 19:44:19 +01:00 |
|
|
|
409caaf0bc
|
added lineage and af count accounting for corrupt data
|
2022-04-08 17:00:57 +01:00 |
|
|
|
28d0d68413
|
added distinct lin count for each mutation
|
2022-04-07 18:47:53 +01:00 |
|
|
|
67d9e6160a
|
added logoplot_example.R and ga_customers.csv
|
2022-04-05 14:52:08 +01:00 |
|
|
|
c647773520
|
saving work
|
2022-04-05 14:51:21 +01:00 |
|
|
|
6a9d23ec8f
|
added sample test data for processing to get correct annotations
|
2022-03-24 17:42:02 +00:00 |
|
|
|
005efb1e0e
|
updated NOTES to reflect importance of eg 5 in unsup_v1.py
|
2022-03-23 16:25:27 +00:00 |
|
|
|
89a0c3a58a
|
added tutorial examples and my data workthrough examplesin unsup_v1.py
|
2022-03-23 16:23:18 +00:00 |
|
|
|
ad5ebad7f8
|
renamed hyperparams to gscv
|
2022-03-22 11:08:20 +00:00 |
|
|
|
a82358dbb4
|
renamed practice_cv2 to cross_validate_vs_loopity_loop
|
2022-03-22 11:03:51 +00:00 |
|
|
|
0c4f1e1e5f
|
added all classification algorithms params for gridsearch
|
2022-03-21 13:51:20 +00:00 |
|
|
|
d012542435
|
added NOTES to indicate which scripts are important
|
2022-03-18 17:56:26 +00:00 |
|
|
|
ffd3ce6ee3
|
added intra_model_gscv.py that tell me within each model which hyperparasm are best, allows me to choose the models with the best hyperparams to then compare 'INTER' model
|
2022-03-18 17:52:06 +00:00 |
|
|
|
d3b6fe13a6
|
added grid_search_vs_base_estimator.py to compare results from baseestimator and gridsearch manual
|
2022-03-18 17:51:38 +00:00 |
|
|
|
b27bfa4a96
|
added names and links for classification algo
|
2022-03-18 17:50:49 +00:00 |
|
|
|
824c2f041c
|
saving work
|
2022-03-18 17:50:24 +00:00 |
|
|
|
ab1508e9fb
|
added testing_lazypredict that runs 30 ML models in one go
|
2022-03-17 18:20:50 +00:00 |
|
|
|
de05652ef6
|
added scripts for playing base_estimator
|
2022-03-17 18:20:19 +00:00 |
|
|
|
5138036d8b
|
playing with gridsearchCV and base estimator
|
2022-03-17 18:19:43 +00:00 |
|
|
|
458a933d73
|
added proof of concept checks to make sure loopity loop is equivalent to cross_validate with stratified Kfold passed as a cv param
|
2022-03-17 18:18:43 +00:00 |
|
|
|
d0c329a1d9
|
modified loopity and multclass3 to have skf_cv as a parameters for cv
|
2022-03-17 18:17:58 +00:00 |
|
|
|
97620c1bb0
|
added practice and base_estimator for all the confusion in my head
|
2022-03-16 10:12:59 +00:00 |
|
|
|
e28a296d98
|
saving work
|
2022-03-16 10:11:13 +00:00 |
|
|
|
a1631ea54b
|
added loopity loop function call to extract mean values for each model's metric from nested dict (2/3 levels)
|
2022-03-14 18:46:59 +00:00 |
|
|
|
29306e77ee
|
added exmaples and practice run for imbalanced data sets
|
2022-03-14 18:43:29 +00:00 |
|
|
|
1016430ae0
|
added copy to imports
|
2022-03-14 18:43:02 +00:00 |
|
|
|
160053d361
|
loopity_loop_CALL
|
2022-03-14 18:36:23 +00:00 |
|
|
|
7aead2d4f4
|
added loopity_loop to run multiple models with stratified k-fold, got stuck in infinite loops and nested dicts
|
2022-03-14 10:36:19 +00:00 |
|
|
|
69d0c1b557
|
dict
|
2022-03-10 19:20:02 +00:00 |
|
|
|
d733b980ba
|
added MultClassPipe3.py that runs multiple classification models on stratified K-fold data
|
2022-03-09 18:36:47 +00:00 |
|
|
|
1bfb35c30c
|
trying Stratified Kfold split on running multiple pipelines
|
2022-03-09 18:35:54 +00:00 |
|
|
|
bb8f6f70ba
|
added prelim run for pnca all models with on-hot encoder multi model pipeline
|
2022-03-07 18:27:58 +00:00 |
|
|
|
dd8fd5b8ac
|
added MultClassPipe2.py that has one hot encoder included
|
2022-03-07 18:27:29 +00:00 |
|
|
|
b637ebc6d2
|
saving work
|
2022-03-07 18:27:07 +00:00 |
|
|
|
564e72fc2d
|
added MultClassPipe2 that has one hot encoder step to the pipeline
|
2022-03-07 17:36:48 +00:00 |
|
|
|
f5dcf29e25
|
added my_data9.py trying models with num and cat features
|
2022-03-07 15:32:34 +00:00 |
|
|
|
3bf63c522c
|
trying one_hot encoder for categ vars, which was sucessful but not rfecv
|
2022-03-06 14:49:51 +00:00 |
|
|
|
6160d943f5
|
made var names more meaniningful
|
2022-03-06 14:49:32 +00:00 |
|
|
|
e2b997badf
|
trying feature selection for classification logistic algorithm on 3 types of target
|
2022-03-05 15:13:43 +00:00 |
|
