Commit graph

767 commits

Author SHA1 Message Date
c32005c99c adding other split types on ml_iterator 2022-07-27 15:58:15 +01:00
63c8876764 checking the splitTTS script to make sure other splits have been factored in 2022-07-27 15:52:20 +01:00
f4cab1fdfb fixed masking condition for ML training data for genes and wrote revised mask files out 2022-07-27 13:36:16 +01:00
0adf69f75a added model names sklearn 2022-07-16 15:35:42 +01:00
39e72b2dfb added all_estimators 2022-07-16 13:32:19 +01:00
a590354f15 saving work from panino 2022-07-12 10:14:06 +01:00
33e3b5a0a6 various bugs 2022-07-12 10:14:06 +01:00
6950c4b057 added reverse traininig as split type in SplitTTS.py 2022-07-11 20:03:06 +01:00
1965517681 added other split_type options i.e none and none with bts 2022-07-11 19:27:14 +01:00
ce730fbe57 uncommented 2022-07-10 13:29:01 +01:00
350be30f19 minor changes to run combined_model 2022-07-10 13:23:13 +01:00
057c98c2f1 updated rs 2022-07-10 13:04:51 +01:00
e37442efd2 updated ml_iterator function args 2022-07-10 13:03:14 +01:00
9594d0a328 uncommented models for logo 2022-07-10 12:53:51 +01:00
4d5b848471 iterator 2022-07-10 12:47:22 +01:00
01ff9d5be6 added instructions to run individual genes 2022-07-10 12:45:45 +01:00
3b4cfecc9f added target_count_numbers.py 2022-07-10 12:43:00 +01:00
de5c1270be added Mult_clfs_logo and Mult_clsf.py with consistency 2022-07-10 12:32:52 +01:00
06f2ce97b6 minor var name fix for MultClfs.py and ml_iterator 2022-07-09 11:02:37 +01:00
ef52fd7a94 saving before running 2022-07-09 10:59:26 +01:00
e07fa3bc05 rerunning ml_iteraror.py 2022-07-09 10:58:14 +01:00
8bde6f0640 minor var bame update in ml_iterator 2022-07-09 10:52:50 +01:00
8079dd7b6c reran to generate merged_df3 with correct dst for dst muts. modified combining_dfs_plotting.R 2022-07-08 21:33:57 +01:00
289c8913d0 added MultClds_SIMPLE.py to simplify my function to run without blind test 2022-07-08 13:54:49 +01:00
880ef46099 added CHECK_model 2022-07-08 13:53:44 +01:00
23799275a0 saving work from thinkpad 2022-07-08 13:53:17 +01:00
5577f5b195 fucking shit count vars 2022-07-07 20:27:03 +01:00
3e18193a36 added examples 2022-07-07 17:46:06 +01:00
f57f25f47a various changes to count_vars_ML.R 2022-07-07 12:33:20 +01:00
d14c3f9c4a adde dummy classifier 2022-07-07 12:28:58 +01:00
a15d801c2a tried pca 2022-07-05 23:05:37 +01:00
8d831f3613 added different scaling options 2022-07-05 22:47:13 +01:00
ebef0c7967 added test script to see one gene 2022-07-05 16:06:24 +01:00
79cb89a019 saving work 2022-07-05 16:06:03 +01:00
652cf4802e added MultClfs_fi to add FI scores for models, in development 2022-07-05 14:19:35 +01:00
53c229f480 added random state to split in function 2022-07-05 14:15:43 +01:00
e5f882841e added cm_datai.py to get data for cm model for running fs later 2022-07-02 16:57:41 +01:00
b2d0b827ad added cm run for logo_skf for actual data 2022-07-02 16:57:11 +01:00
9071a87056 fs: cut down the number of iterations 2022-07-02 11:12:39 +01:00
7ba838b493 redo unconfusion 2022-07-02 10:32:19 +01:00
a166a37c0e undo wrong rename 2022-07-02 10:31:55 +01:00
5a81511163 filename 2022-07-02 10:28:10 +01:00
dccd3c8eb2 multiple changes 2022-07-02 10:25:55 +01:00
2fda32901b change more hardcoded CPU counts to os.cpu_count() 2022-07-02 10:25:13 +01:00
b8653c6afe ML scripts: {'n_jobs': os.cpu_count() } 2022-07-02 10:22:07 +01:00
11af00f1db changed ml output dirs and ready to run fs 2022-07-01 21:40:14 +01:00
57348f1874 added log frile for cm run for complete data with skf 2022-07-01 20:38:34 +01:00
b7e1b51a31 added ml_iterator_fs.py 2022-07-01 20:38:08 +01:00
b5777a17c9 saving work 2022-07-01 20:37:41 +01:00
d812835713 added cm_logo_skf.py and placeholder for splits 2022-07-01 13:55:12 +01:00