Code-Review.md

@@ -261,7 +261,7 @@ Password: 001303
 - [x] Prepare O3 scripts for the real events and produce preliminary set of results.
 
 
-## 20 August 2021
+## 13 August 2021
 - JR Tested the installation and added fix an issue of cloning. The installation seems to work fine.
 
 - We went through the preliminary results of O3 event pairs. Notebook [here](https://git.ligo.org/srashti.goyal/lensid-ml-o3/-/blob/master/O3_ML/ML_pred_O3.ipynb).
@@ -276,21 +276,15 @@ Password: 001303
 
 - [x] Make new repo for real events analysis.
 
-- [ ] fix whitening procedure for simulated events.. investigate for real events too.
+- [x] fix whitening procedure for simulated events.. investigate for real events too.
 
 - [x] Present/Update the lensing group about the preliminary results.
 
 - [x] Move the analysis to CIT cluster, where GPU is available and is not too busy. 
 
-- [ ] Reproduce all the results there and retrain the densenets with the help of Hari.
 
-- [ ] restrict training set to low masses, retraining Q transform classifier, see model loss; comparison to the high mass case.
-
-- [ ] increase training set size, check convergence.
 
-- [ ] Prepare injection set for super-sub pairs. Lensed and Unlensed.
-
-## 13 August 2021
+## 20 August 2021
 
 - We discussed about packaging of the pipeline, and the git issue which Deep created. (here)[https://git.ligo.org/srashti.goyal/strong-lensing-ml/-/issues/1].
 
@@ -298,12 +292,41 @@ Password: 001303
 
 ### Action items:
 
-- [ ] Investigate extreme events in the test set for the BLU & ML, by seeing their QTs and skymaps to understand the independent behaviour of ML & BLU.
+- [x] Investigate extreme events in the test set for the BLU & ML, by seeing their QTs and skymaps to understand the independent behaviour of ML & BLU.
 
 - [x] Use entry points as mentioned (here)[https://git.ligo.org/srashti.goyal/strong-lensing-ml/-/issues/1].
 
+
+- [x] Create new repo for the package and package data, and probably move this review page also over there.
+
+## 24 & 27 August 2021
+
+- Deep suggested to include unit test with the code. 
+
+- JR and Srashti discussed the events list for O3b lensing paper, seeing the (document)[https://docs.google.com/spreadsheets/d/1rV-b2HE2mGxrxRl9-rdEunLsp9f5S5sMhD5EauI1-nE/edit?usp=sharing] prepared by Justin.
+
+- The whitening procedure is fixed for injections, the low frequency cut(flow) in psd generation was the problem. Notebook (here)[https://git.ligo.org/srashti.goyal/lensid/-/blob/master/review/whitening_investigations.ipynb].
+
+- We discussed the events which have low ML FPP but high BLU FPP and vice versa, for the test set, by seeing the qtransforms and bayestar + PE skymaps for them. Notebook (here)[https://git.ligo.org/srashti.goyal/lensid/-/blob/master/review/ML_blu_FPPs_inj_pars_investigate.ipynb]
+
+- J.R. thinks that the pipeline is almost ready for the code review and sign-off can happen within a week or two. 
+
+- For super-sub analysis the code will not change hence we can just include it is the result review or keep it for later.
+
+### Action items:
+
+- [ ] Prepare the pipeline to get the first set of results with the accepted event list. CIT, retrain etc., update event list. 
+
+- [ ] Convert training/testing notebooks to scripts format wherever possible.
+
 - [ ] Think about integrating with igwn-py37.
 
 - [ ] Try out the installation on igwn-py38.
 
-- [x] Create new repo for the package and package data, and probably move this review page also over there.
\ No newline at end of file
+- [ ] Reproduce all the results on CIT and retrain the densenets with the help of Hari.
+
+- [ ] retrain densenets using whitened QTs, wider qrange etc, XGB with QTs with missing data etc.
+
+- [ ] increase training set size, check convergence.
+
+- [ ] Prepare injection set for super-sub pairs. Lensed and Unlensed.
\ No newline at end of file