Skip to content

[WIP] Generative regression (workflow, scores, cross validation, prediction type)#193

Open
kegl wants to merge 204 commits intomasterfrom
generative_regression_clean
Open

[WIP] Generative regression (workflow, scores, cross validation, prediction type)#193
kegl wants to merge 204 commits intomasterfrom
generative_regression_clean

Conversation

@kegl
Copy link
Copy Markdown
Contributor

@kegl kegl commented Dec 2, 2019

No description provided.

@lgtm-com
Copy link
Copy Markdown

lgtm-com bot commented Dec 2, 2019

This pull request introduces 8 alerts when merging 7572151 into f48b024 - view on LGTM.com

new alerts:

  • 2 for Unused local variable
  • 2 for Unused import
  • 1 for Unnecessary pass
  • 1 for Explicit export is not defined
  • 1 for Nested loops with same variable
  • 1 for Unguarded next in generator

@lgtm-com
Copy link
Copy Markdown

lgtm-com bot commented Dec 2, 2019

This pull request introduces 8 alerts when merging 814b598 into f48b024 - view on LGTM.com

new alerts:

  • 2 for Unused local variable
  • 2 for Unused import
  • 1 for Unnecessary pass
  • 1 for Explicit export is not defined
  • 1 for Nested loops with same variable
  • 1 for Unguarded next in generator

@lgtm-com
Copy link
Copy Markdown

lgtm-com bot commented Dec 3, 2019

This pull request introduces 7 alerts when merging 7c68e92 into 0d837ef - view on LGTM.com

new alerts:

  • 2 for Unused import
  • 1 for Unnecessary pass
  • 1 for Unused local variable
  • 1 for Explicit export is not defined
  • 1 for Nested loops with same variable
  • 1 for Unguarded next in generator

@lgtm-com
Copy link
Copy Markdown

lgtm-com bot commented Dec 11, 2019

This pull request introduces 7 alerts when merging 5860913 into c1b4273 - view on LGTM.com

new alerts:

  • 2 for Unused import
  • 1 for Unnecessary pass
  • 1 for Unused local variable
  • 1 for Explicit export is not defined
  • 1 for Nested loops with same variable
  • 1 for Unguarded next in generator

@codecov
Copy link
Copy Markdown

codecov bot commented Dec 12, 2019 •
edited
Loading

Codecov Report

Merging #193 (ea0853c) into master (212720f) will decrease coverage by 0.90%.
The diff coverage is 79.33%.

❗ Current head ea0853c differs from pull request most recent head 2b9e240. Consider uploading reports for the commit 2b9e240 to get more accurate results
Impacted file tree graph

@@            Coverage Diff             @@
##           master     #193      +/-   ##
==========================================
- Coverage   83.05%   82.15%   -0.91%     
==========================================
  Files         137      154      +17     
  Lines        4704     5794    +1090     
==========================================
+ Hits         3907     4760     +853     
- Misses        797     1034     +237
Impacted Files Coverage Δ
rampwf/utils/cli/blend.py 0.00% <0.00%> (-70.97%) ⬇️
rampwf/workflows/el_nino.py 29.16% <33.33%> (ø)
rampwf/cvs/time_series.py 33.07% <36.89%> (+16.40%) ⬆️
rampwf/prediction_types/base.py 81.81% <50.00%> (-5.28%) ⬇️
rampwf/utils/cli/testing.py 62.50% <50.00%> (ø)
rampwf/utils/generative_regression.py 61.73% <61.73%> (ø)
rampwf/workflows/generative_regressor.py 67.11% <67.11%> (ø)
rampwf/score_types/r2.py 72.72% <72.72%> (ø)
rampwf/utils/cli/show.py 76.40% <73.33%> (ø)
rampwf/workflows/ts_feature_extractor.py 81.39% <79.16%> (+64.72%) ⬆️
... and 79 more

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 212720f...2b9e240. Read the comment docs.

@lgtm-com
Copy link
Copy Markdown

lgtm-com bot commented Dec 18, 2019

This pull request introduces 8 alerts when merging 5f68f90 into c1b4273 - view on LGTM.com

new alerts:

  • 2 for Unused local variable
  • 2 for Unused import
  • 1 for Unnecessary pass
  • 1 for Explicit export is not defined
  • 1 for Nested loops with same variable
  • 1 for Unguarded next in generator

@albertcthomas albertcthomas force-pushed the generative_regression_clean branch from 0acbf72 to d77df0a Compare December 26, 2019 19:13
@lgtm-com
Copy link
Copy Markdown

lgtm-com bot commented Dec 26, 2019

This pull request introduces 7 alerts when merging d77df0a into c1b4273 - view on LGTM.com

new alerts:

  • 2 for Unused local variable
  • 1 for Unnecessary pass
  • 1 for Unused import
  • 1 for Explicit export is not defined
  • 1 for Nested loops with same variable
  • 1 for Unguarded next in generator

@lgtm-com
Copy link
Copy Markdown

lgtm-com bot commented Jan 13, 2020

This pull request introduces 7 alerts when merging 9bc6578 into c1b4273 - view on LGTM.com

new alerts:

  • 2 for Unused local variable
  • 1 for Unnecessary pass
  • 1 for Unused import
  • 1 for Explicit export is not defined
  • 1 for Nested loops with same variable
  • 1 for Unguarded next in generator

kegl and others added 20 commits September 7, 2020 17:25
@kegl
Decoupled cv (#243)
87d6510 
* passing fold to workflow.test_submission

* passing fold indices to Prediction init instead of indexing in util.submission.run_submission_on_cv_fold

* getting rid of passing valid_indexes to scores

* getting rid of valid_indexes in score_type.score_function

* flake

* functional data flow in doc

* training script in doc

* docstring minor

* Add test protocol to README

* Update README.rst

Co-authored-by: Balazs Kegl <b00497701@china.huawei.com>
@kegl
Update README.rst
7fbae01
@kegl
Update .travis.yml
b7cdedd
@kegl
adding --data-label (#245)
864906d 
* adding --data-label

* flake8

* albert's comments

* Update .travis.yml

* data_label default None
@kegl
Fixing ramp-leaderboard (#247)
f9b1939 
* adding data-label to ramp-show leaderboard; more syntax in --help

* fixing --bagged, adding more examples in help

* making a ramp-blend command

* removing old command line interface

* flake8

* fixing init

* command line option to change the blending metrics
@albertcthomas
Merge branch 'master' into advanced
3eadb4d
@albertcthomas
add condition in circle push_doc (#253)
96f6efb
@albertcthomas
add install instruction for advanved
45cce46
@albertcthomas
Merge branch 'master' into advanced
1676d9d
@gabriel-hurtado @kegl
hyperopt fix (#257)
ec8835e 
Co-authored-by: Gabriel Hurtado <gabriel.j.hurtado@gmail.com>

Co-authored-by: Balazs Kegl <balazs.kegl@gmail.com>
@gabriel-hurtado @albertcthomas
Modefied ramp for generative wf
85a533f
@gabriel-hurtado @albertcthomas
Added tests for new prediction type, generative regression
23a68c8
@gabriel-hurtado @albertcthomas
Cleaned a bit
19e0122
@gabriel-hurtado @albertcthomas
Renamed log likelihood for generation
7c20ac5
@gabriel-hurtado @albertcthomas
Probabilities are normalized and bins are checked, test is included
174ba01
@gabriel-hurtado @albertcthomas
convert all the nb to n
64c6bf6
@gabriel-hurtado @albertcthomas
Started ensembling code
53865c1
@gabriel-hurtado @albertcthomas
Loss could be negative
534af70
@gabriel-hurtado @albertcthomas
Now different generative regressor wf can have their ow different num…
b45630b 
…ber of bins
@gabriel-hurtado @albertcthomas
Added an optio for multi target generative regressors
ad5c5d2
@lgtm-com
Copy link
Copy Markdown

lgtm-com bot commented Mar 5, 2021

This pull request introduces 1 alert when merging c00e178 into 74686f7 - view on LGTM.com

new alerts:

  • 1 for Unguarded next in generator

@lgtm-com
Copy link
Copy Markdown

lgtm-com bot commented Mar 5, 2021

This pull request introduces 1 alert when merging ea0853c into 74686f7 - view on LGTM.com

new alerts:

  • 1 for Unguarded next in generator

kegl and others added 3 commits April 8, 2021 15:11
@kegl @albertcthomas @gabriel-hurtado
refactoring time series cv
2580c2b 
Co-authored-by: Albert Thomas <albertthomas88@gmail.com>
Co-authored-by: Gabriel Hurtado <gabriel.j.hurtado@gmail.com>
@albertcthomas
vectorization
8acfdee
@albertcthomas
Merge branch 'master' into generative_regression
3d853f1
@albertcthomas albertcthomas changed the base branch from advanced to master July 5, 2021 14:52
albertcthomas and others added 20 commits July 5, 2021 16:55
@albertcthomas
fix duplicate entry points after merge
b0c2091
@albertcthomas
Merge branch 'vectorized_env' into generative_regression
fbe9243
@albertcthomas
temp fix for sampling when n_burn_in > 1
f71c380
@albertcthomas
inside episode cv + refactoring
80b4075
@albertcthomas
no need of temp fix anymore in ts_fe_gen_reg
3b11aff
@albertcthomas
revert "temp fix for sampling when n_burn_in > 1"
f6fc8fa
@albertcthomas
add error message when using rw sample method with more than 1 sample
8bfa83e
@albertcthomas
Merge branch 'generative_regression' into inside_episode_cv
c82bdf2
@albertcthomas
add error message when using rw sample method with more than 1 sample
2b9e240
@albertcthomas
Merge branch 'generative_regression' into inside_episode_cv
756079d
@albertcthomas
add RollingInsideEpisode cv for learning curves
aac1614
@albertcthomas
Merge branch 'master' into generative_regression
21226a4
@albertcthomas
clean comments
60f34c9
@albertcthomas
Merge branch 'inside_episode_cv' into generative_regression
1357d69
@albertcthomas
clean one comment
b214e8d
@abenechehab
merged with master and resolved conflicts
4ee80d7
@kegl @albertcthomas
alphabetic order
8185d78
@gonzalezJohnas @albertcthomas
numpy based generative regressor and feature extractor workflow
8ea6c44 
Co-authored-by: Albert Thomas <albertthomas88@gmail.com>
@albertcthomas
partial training for generative regressors
217330c
@kegl
save retrain results when --save-output is True
180db08
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

5 participants

@kegl @albertcthomas @gabriel-hurtado @abenechehab @gonzalezJohnas