|
|
ad99efedd7
|
saving work
|
2022-06-24 13:21:21 +01:00 |
|
|
|
3514e1b4ba
|
added run_7030_LOOP.py to loop through the resampling data and get processed output
|
2022-06-23 21:29:54 +01:00 |
|
|
|
1d3190899d
|
added ProcessMultModelsCl.py that processes the output for multiple models
|
2022-06-23 21:27:13 +01:00 |
|
|
|
4fe62c072b
|
added metadata output for running multiple models
|
2022-06-23 21:25:00 +01:00 |
|
|
|
5dea35f97c
|
aaded scripts for FS including test call, etc
|
2022-06-23 14:53:01 +01:00 |
|
|
|
8fe0048328
|
saving work
|
2022-06-23 14:52:27 +01:00 |
|
|
|
0350784d52
|
changed blind_test_input_df to blind_test_df in MultModelsCl
|
2022-06-22 16:42:04 +01:00 |
|
|
|
bc12dbd7c2
|
added run_7030.py that runs as cmd for all gene targets and sampling methods and outputs a single csv
|
2022-06-21 20:37:53 +01:00 |
|
|
|
5b0ccdfec4
|
added ml_data_fg.py
|
2022-06-21 18:21:41 +01:00 |
|
|
|
11ef627150
|
removed _dissected files and renamed them to _fg
|
2022-06-21 18:20:22 +01:00 |
|
|
|
fe0986aa28
|
adde script to run ml baseline models orig version with feature groups
|
2022-06-21 18:17:56 +01:00 |
|
|
|
137f19a285
|
saving work
|
2022-06-21 18:12:31 +01:00 |
|
|
|
7b378ca6f3
|
adding formatting to get all output from ML for feature grpups starting with genomics
|
2022-06-21 14:08:12 +01:00 |
|
|
|
cadaed2ba7
|
ML logs
|
2022-06-20 21:55:47 +01:00 |
|
|
|
4c5afa614f
|
python scripts for original analysis with logs
|
2022-06-20 21:54:48 +01:00 |
|
|
|
8d8fc03f72
|
added test script to test dissected model
|
2022-06-20 21:53:15 +01:00 |
|
|
|
e68a153883
|
working on dissected model, testing diff feature groups
|
2022-06-20 21:51:07 +01:00 |
|
|
|
135efcee41
|
added option to add confusion matrix and target numbers in the mult function
|
2022-06-20 17:08:22 +01:00 |
|
|
|
905327bf4e
|
script to run models based on group of features
|
2022-06-20 14:59:02 +01:00 |
|
|
|
4ab99dcbd2
|
saving work for yesterday where uq runs were repeated
|
2022-06-20 14:57:11 +01:00 |
|
|
|
efeaf52cde
|
added ml runs for complete data with _cd_ in filenames reflecting this
|
2022-06-18 19:36:33 +01:00 |
|
|
|
9bc26c1947
|
slight formatting for existing scripts
|
2022-06-18 19:35:49 +01:00 |
|
|
|
a53fce5455
|
added notes for running ml scripts
|
2022-06-18 14:45:48 +01:00 |
|
|
|
e176d018cb
|
added log files for these ml runs
|
2022-06-18 14:44:02 +01:00 |
|
|
|
5bd8ba33f7
|
added scripts for reverse training
|
2022-06-18 14:43:35 +01:00 |
|
|
|
d85415daf8
|
added scripts for scaling law split
|
2022-06-18 14:42:46 +01:00 |
|
|
|
4037641dfa
|
added data and ml scripts for 8020 splits
|
2022-06-18 14:42:02 +01:00 |
|
|
|
2e50a555a0
|
minor formatting consistency for 7030 scripts
|
2022-06-18 14:41:05 +01:00 |
|
|
|
e05e4e2e38
|
added script for running 7030 split
|
2022-06-17 18:28:26 +01:00 |
|
|
|
91e868736c
|
changed dir to allow ml script to import functions
|
2022-06-17 18:27:20 +01:00 |
|
|
|
e6d3692445
|
changed dir for reading func in pnca_config.py
|
2022-06-17 16:37:07 +01:00 |
|
|
|
96d4e61dca
|
added baseline config files for running v2 ml analysis
|
2022-06-17 14:14:26 +01:00 |
|
|
|
05dd9698c4
|
added aa_index data for running ml
|
2022-06-17 13:41:25 +01:00 |
|
|
|
39ccd6cdf4
|
initial adding of ml scripts for baseline models
|
2022-06-17 13:40:09 +01:00 |
|
|
|
f355846dae
|
added active site indication for merged_dfs in count_vars_ML.R and also added 'gene_name' in combining_dfs.py
|
2022-06-15 18:36:28 +01:00 |
|
|
|
1204f1faba
|
added scripts and files to make AA index work for all drug targets, add header to the aa index output and fetch the aa index headers
|
2022-06-15 11:24:07 +01:00 |
|
|
|
03321c261e
|
working new_aa.sh
|
2022-06-13 22:05:41 +01:00 |
|
|
|
c4ae6d2412
|
improved aa script
|
2022-06-13 21:48:44 +01:00 |
|
|
|
2307a19d86
|
added example bash cmds
|
2022-06-13 21:22:49 +01:00 |
|
|
|
40c4d382f4
|
added eg to run aaindex from a diff dir
|
2022-06-13 21:15:12 +01:00 |
|
|
|
bd7d01c7e6
|
various aa_index_scripts
|
2022-06-13 09:42:48 +01:00 |
|
|
|
0c316e4a41
|
renamed aa_index folder to aa_index_scripts
|
2022-05-30 02:24:54 +01:00 |
|
|
|
650d357afc
|
reran to output merged_df3 and merged_df2 csvs from count_vars.ML
|
2022-05-29 03:10:51 +01:00 |
|
|
|
f41cd0082e
|
moved mmcsm_provean_ed_combine_CHECKS.py to scratch for when I need ED data for merging
|
2022-05-25 23:45:01 +01:00 |
|
|
|
1baf7fa9f0
|
lf
|
2022-05-25 23:44:13 +01:00 |
|
|
|
8e65d75b58
|
added checks before comnining provean and mmcsm_lig
|
2022-05-25 08:51:37 +01:00 |
|
|
|
a2bcc3a732
|
added mmcsm_lig and provean dfs merges in comnining_df.py
|
2022-05-25 08:50:33 +01:00 |
|
|
|
d8041fb494
|
added count_vars_ML.R to check numbers for revised counts
|
2022-05-05 19:32:34 +01:00 |
|
|
|
39566ceadd
|
lineage labels gsub now redundant in combining_dfs_plotting.R
|
2022-05-05 19:31:00 +01:00 |
|
|
|
d61d11e020
|
Merge branch 'master' of https://git.tunstall.in/tanu/LSHTM_analysis
|
2022-05-05 13:36:03 +01:00 |
|
