Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

feat: added ds for robyn_response() #600

Merged
merged 94 commits into from
Feb 28, 2023
Merged

feat: added ds for robyn_response() #600

merged 94 commits into from
Feb 28, 2023

Conversation

laresbernardo
Copy link
Collaborator

No description provided.

gufengzhou and others added 15 commits November 3, 2022 00:22
@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Jan 10, 2023
@laresbernardo laresbernardo self-assigned this Jan 13, 2023
@laresbernardo laresbernardo changed the title feat: added ds for robyn_response single date feat: added ds for robyn_response() Jan 16, 2023
gufengzhou
gufengzhou reviewed Jan 17, 2023
View reviewed changes
R/R/response.R Outdated Show resolved Hide resolved
laresbernardo and others added 27 commits February 16, 2023 09:10
@laresbernardo
fix: formating when spend = 0 (ROAS inf) and p2's factors
5f9ba79
@laresbernardo
fix: deprecate "max_response_expected_spend" scenario
a35bbe9
@laresbernardo
fix: p1 labs are back!
bf335c5
@laresbernardo
feat: enable flexible date_range input for allocator
afdaf59
@laresbernardo
fix: 0 errors ✔ | 0 warnings ✔ | 0 notes ✔
f5608c5
@laresbernardo
fix: print typo
cd17d2d
@laresbernardo
fix: normalize colour pallete (regardless of their scale-metric)
adc410c
@gufengzhou
recode: aligned model roi_mean with allocator initial roas
9c2aa5c 
- Need to reconsider mean_response calculation: for historical mean_response, maybe no need to simulate historical spend with mean spend?
- Need to include fx_objective in robyn_response to have clearer response process
- align difference between using dates vector or last_n in date_range in robyn_response
@gufengzhou
recode: align initial roas in allocator with roi_mean from model
318c18f 
- to-do: in model onepager, remove total roi from share plot, remove mean from error plot, add total_roi and mean_roi to error plot
@gufengzhou
recode: return correct mean_response
d2e8013 
- added carryover area to onepager response curve plot
@laresbernardo
fix: codefactor warnings
fbe85b8
@laresbernardo
Merge branch 'main' into ds-for-robyn_response
c84b5c5
@laresbernardo
docs: update wordings and styler apply
828c0f8
@laresbernardo
fix: carryover when no spend and get rid of sim curves with no spend
7627085
@laresbernardo
fix: NaN values_norm -> 0
ab46981
@laresbernardo
recode: change default date_range to 1 month worth of data + Viz labels
0c4ea60
@gufengzhou
feat: total_budget for allocator
87b1635 
- adapted initial spend calculation for allocator
- added total budget as simulation]
- to-do: need to re-assess if current initial spend makes sense (maybe come back to histSpendWindowUnitTotal? how to interpret 0 raw spend but has response from adstock?)
@laresbernardo
fix: fixed allocator print + added use case
2b7e15c
@gufengzhou
fix: zero spend period now also being allocated
4649d41
@laresbernardo
feat: inform user when budget is topped
aa47a29 
fix: enable contrains to 0 to remove media var
@laresbernardo
fix: order of constr mods before check
10035dc
@laresbernardo
feat: add total budget to caption + styler
692d8f5
@gufengzhou
feat: added mROAS / mCPA for better understanding of allocation
c93d739
@gufengzhou
recode: adapted caption and data
798a876
@gufengzhou
recode: adapted demo
61fed62
@laresbernardo
docs: updated to 3.10.0
ca5e985
@laresbernardo
fix: codefactor issues
13955b6
@laresbernardo laresbernardo merged commit d152ad3 into main Feb 28, 2023
@laresbernardo
Copy link
Collaborator Author

Summary:

  • Feat: all new one-pager for robyn_allocator() showing initial, bounded and less-bounded scenarios, using last month's worth of data by default. Relevant changes from previous versions: initial spend is now mean of date range selected, not non-zero mean anymore + deprecated "max_response_expected_spend" scenario + carryover information is now provided in the curves + inform user when budget is topped and can't be fully allocated + added mROAS / mCPA for better understanding of allocation.
  • Feat: robyn_response() now requires date or date range for adstocking (last period by default) and accepts single or multiple values to return different use cases and scenarios.
  • Feat: new transform_adstock() exported wrapper function.
  • Feat: added NRMSE validation on test set.
  • Feat: added prophet monthly component.
  • Fix: added correct solID for fixed hyperparameters (not 1_1_1).
  • Recode: reduced the size of xDecompVec on OutputCollect to only pareto-front models.
  • Recode: got rid of "ggcorrplot" and "rPref" package dependencies.
  • Docs: added blueprint link to demo.R.

Co-authored: @gufengzhou @laresbernardo

@laresbernardo laresbernardo deleted the ds-for-robyn_response branch March 7, 2023 15:09
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@gufengzhou gufengzhou gufengzhou left review comments

Assignees

@laresbernardo laresbernardo

Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@laresbernardo @gufengzhou @facebook-github-bot