Releases | Open Source Science

Robyn - v3.12.0 [GitHub R]

What's Changed

Exposure fitting, curve calibration & reach and frequency allocator (https://github.com/facebookexperimental/Robyn/pull/1132) * feat: enable exposure fitting - Exposures (Imp/GRP etc) will be prioritised over spend for parent model fitting - Deprecate function fitspendexposure, incl. Michaelis Menten. Nonlinear fitting between spend and exposure wasn't improving fitting significantly. Instead, future curve calibration feature will aim to improve curve identification. - Use cpe (cost per exposure) as ratio for spend to exposure translation. use cpe_window to scale the whole dataset in order to obtain the right spend scale for modeling period. - remove minpack.lm / nlsLM dependency - update exposure plot

feat: The curve calibrator - robyn_calibrate
Simulate cumulative R&F dataset with frequency bucket
add beta coef besides alpha and gamma to nevergrad hyperparameter to improve curve fit
plot with freq_bucket as well as onepager per trial
add dfcurvereach_freq as dummy dataset
create robyn_calibrate that consumes curve input and outputs hyperparameter ranges as input.
Rename previous internal robyncalibrate function as liftcalibration
early stop convergence with while loop
update documentation
prototype: reach and frequency allocator This is the proof of concept of a R&F allocator that includes
Simulated R&F data
The R&F hill params are estimated using a multiplicative equation with Nevergrad
visualisation of surface
R&F allocator with nlopt
constrain validation
update: checks, input, transformation & website
simplify various check functions
adapt model.R, incl. reset run_transformations params to have clearer overview of params needed. simplify transformation.R by removing unnecessary checks
In model.R & pareto.R: remove decompSpendDist from both scripts to reduce memory leak. Use xDecompAgg subsets instead
In transformation.R & response.R: unify transformation namings in runtransformation and robynresponse
In response.R: remove exposure extrapolation because it's already done in robyn_input. Also add inflexion point to output.
In plots.R: fix onepager saturation plot issues
In pareto.R: rewrite rundtresp() as response_wrapper and align transformation logic & naming.
In pareto: Replace foreach response loop with lapply for simplicity.
In pareto.R: Simplify plot data generation process, esp for saturation curve plot, actual vs predicted plot & immediate vs carryover plot.
In pareto.R: Remove redundancy in xDecompVecCollect -> remove type rawMedia, rawSpend, predictedExposure, saturatedMedia & saturatedSpendReversed. Only keep adstockedMedia & decompMedia for response curve plotting.
add setdefaulthyppar for easier testing
website update for all above changes

Contributors

@gufengzhou, @laresbernardo

Full Changelog: https://github.com/facebookexperimental/Robyn/compare/v3.11.0...v3.12.0

- Jupyter Notebook
Published by gufengzhou about 1 year ago

Robyn - v3.11.1 [CRAN]

What's Changed

fix: one-pager decomp labels and warning by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/1011

- Jupyter Notebook
Published by laresbernardo over 1 year ago

Robyn - v3.11.0 [CRAN]

What's Changed

Add objective weights by @gufengzhou in https://github.com/facebookexperimental/Robyn/pull/826
build(deps): bump @babel/traverse from 7.21.5 to 7.23.2 in /website by @dependabot in https://github.com/facebookexperimental/Robyn/pull/842
feat: check and fix allsoljson & new pareto_df parameters inputs by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/843
feat + fix: bundle fixes and improvements on json files by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/852
fix: compatibility with legacy files on robyn_recreate() by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/865
Fix #850 & #838 by @michellegrushkometa in https://github.com/facebookexperimental/Robyn/pull/864
Robyn api by @yu-ya-tanaka in https://github.com/facebookexperimental/Robyn/pull/863
fix: crashed cut() when monthly data by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/868
fix: when all values on a column are negative crash by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/871
fix: winsorize errors with na.rm = TRUE #872 + InputCollect print when no prophet by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/875
Bundle of small fixes and feats by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/882
fix: foreach seed for reproducibility + dtsimulatedweekly dataset by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/907
Robyn api update notebook and endpoint by @yu-ya-tanaka in https://github.com/facebookexperimental/Robyn/pull/912
fix: avoid overwriting csv when scenario changes by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/913
fix: intercept param in outputs + ts_validation plot for convergence by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/917
build(deps): bump follow-redirects from 1.15.3 to 1.15.4 in /website by @dependabot in https://github.com/facebookexperimental/Robyn/pull/899
feat: enable baselinelevel param for decompplot() + let NULL solID when single model available +docs: update robyn_response() examples by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/923
docs: clarify objective_weights order by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/929
feat: add clusters information to one-pagers, fix metric notes, reduce texts sizes, no ng check to recreate + fix: RNG warning by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/928
feat: keep custom exported data from JSON when recreating model & use raw_data if available + update docs by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/930
fix: mediaVecCollect's organic vars weren't being multiplied by coef values + InputCollect print when no prophet country set by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/936
fix: One or both dimensions exceed the maximum (50000px) error #874 by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/939
build(deps): bump follow-redirects from 1.15.4 to 1.15.6 in /website by @dependabot in https://github.com/facebookexperimental/Robyn/pull/941
build(deps): bump webpack-dev-middleware from 5.3.3 to 5.3.4 in /website by @dependabot in https://github.com/facebookexperimental/Robyn/pull/943
build(deps): bump express from 4.18.2 to 4.19.2 in /website by @dependabot in https://github.com/facebookexperimental/Robyn/pull/947
fix: target = 1 error and better constraints check by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/942
Fixed error when ts_validation is false. by @yu-ya-tanaka in https://github.com/facebookexperimental/Robyn/pull/965
bl01: refresh fixes and improvements + others by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/969
build(deps): bump braces from 3.0.2 to 3.0.3 in /website by @dependabot in https://github.com/facebookexperimental/Robyn/pull/997
fix: refresh hyps check + use data available in json + refresh hyps + upper constraints fix when higher than mean by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/974
build(deps): bump ws from 7.5.9 to 7.5.10 in /website by @dependabot in https://github.com/facebookexperimental/Robyn/pull/999
docs: CRAN 3.11.0 by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/1001

New Contributors

@yu-ya-tanaka made their first contribution in https://github.com/facebookexperimental/Robyn/pull/863

Full Changelog: https://github.com/facebookexperimental/Robyn/compare/v3.10.5...v3.11.0

- Jupyter Notebook
Published by laresbernardo over 1 year ago

Robyn - v3.10.5: Objective function weight, Meta MMM API beta, website tab "Features" revamp, bug fixes

Feat: New arg objective_weights in robyn_run() to allow manual tuning of weights for objective functions (NRMSE, DECOMP.RSSD, MAPE.LIFT). Default weight is even weights c(1,1,1). Note: This is experimental and there's no guidance on how weights biases modelling. Commit here
Feat: Meta MMM API connector demo, a beta script. Commit here
Doc: Updated and revamped the website "features" tab, also reorganised the navigation. see here

Full Changelog: https://github.com/facebookexperimental/Robyn/compare/v3.10.3...v3.10.5

- Jupyter Notebook
Published by gufengzhou over 2 years ago

Robyn - v3.10.3: Objects size reduction, RSSD penalty for 0 effect media

More details on Facebook's Robyn Community post

Feat: Reduced object sizes up to 88% #687
Feat: RSSD penalty for 0 media effects media (parameter) #680
Feat: Always constraint prophet coefficients to 0-1 #686
Feat: Windsorized NRMSE on multi-objective optimization plots [1/500 default threshold] to avoid extreme skewness #693
Feat: New intercept parameter passed to glmnet() #722
Fix: Return meaningful error when, after filtering by modeling window, a variable has no variance #619
Fix: Removed negative carryover outputs for Weibull PDF adstock #706
Fix: Correctly pass plot_folder input on robyn_refresh() #708

Full Changelog: https://github.com/facebookexperimental/Robyn/compare/v3.10.2...v3.10.3

- Jupyter Notebook
Published by laresbernardo almost 3 years ago

Robyn - v3.10.2: Refresh model selection and small bugs

Fix: when running robyn_refresh(), select the refresh model by error_score value correctly #674
Fix: pass penalty.factor when dropping intercept too
Fix: when importing holidays data, force date values as dates #663 by @richin13
Docs: update several documentations across functions and site

New Contributors

@richin13 made their first contribution in https://github.com/facebookexperimental/Robyn/pull/663

Full Changelog: https://github.com/facebookexperimental/Robyn/compare/v3.10.1...v3.10.2

- Jupyter Notebook
Published by laresbernardo almost 3 years ago

Robyn - v3.10.1 - New “Target Efficiency” scenario for budget allocator

More details in post: Hitting ROAS target using Robyn’s budget allocator

Feat: allocator's new scenario "target_efficiency" for ROAS/CPA target #648
Fix: inverted CPA in allocator viz table #640
Fix: re-enable experimental addpenaltyfactor feature
Fix: re-include spend from skipped channels #645

Full Changelog: https://github.com/facebookexperimental/Robyn/compare/v3.10.0...v3.10.1

- Jupyter Notebook
Published by laresbernardo almost 3 years ago

Robyn - v3.10.0: Allocator upgrade

More details in post: The convergence of marginal ROAS in the budget allocation in Robyn

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 "maxresponseexpected_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. And one step closer to the forecast functionality. #600
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: issue with differences on OutputCollect$OutputModels and OutputModels to produce ts_validation plot. #596
Fix: added correct solID for fixed hyperparameters (not 111).
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.

Full Changelog: https://github.com/facebookexperimental/Robyn/compare/v3.9.0...v3.10.0

- Jupyter Notebook
Published by laresbernardo almost 3 years ago

Robyn - v3.9.0: Time-series validation feature

Feat: new time series validation via time-series train/val/test dynamic splits and Adjusted R2 and NRMSE metrics reported for each group feature #545. We are adding an additional train_size hyperparameter to pick the size of the training size, which by default will iterate in the range of 0.5-0.8. Given it's a hyperparameter, you can change the range or fix the value manually. Turn on/off this feature using the ts_validation new parameter on robyn_run(); default is set to FALSE for now. This is an important step for the forecasting coming function.
Feat: new ts_validation() function to plot time-series validation and convergence results. Generated and exported by default when ts_validation = TRUE, and when export = TRUE, creating ts_validation_plot.png file.
Fix: updated Adjusted R2 calculation (get_rsq()) for time-series validation using same denominator.
Fix: results are not sorted by lowest errors now to keep iteration results actual order.
Feat: added prophet monthly component to enrich decomposition results #525
Fix: correct solID (not "111") for fixed hyperparameters recreated models.
Recode: reduced the size of xDecompVec on OutputCollect by keeping pareto-front models only.
Docs: changed standard inputs on demo.R file for modeling window to include more data (3 years by default).

New Contributors

@michellegrushkometa made their first contribution in https://github.com/facebookexperimental/Robyn/pull/559

Full Changelog: https://github.com/facebookexperimental/Robyn/compare/v3.8.2...v3.9.0

- Jupyter Notebook
Published by laresbernardo about 3 years ago

Robyn - v3.8.2: Memory friendly outputs, progress bars for Pareto-front models, bugs and docs

Feat: new status bars for Pareto-Front models per trial to provide information on calculation status
Feat: included carryover results into paretoaggregated.csv output and `OutputCollect$xDecompAgg$carryoverpct`
Feat: new error message shows which hyperparameters inputs are missing #543
Fix: substantially reduced the size of robyn_run() and robyn_outputs() results (around -80% compared with 3.8.1 version's size) by removing redundant and unused data from outputs #534
Fix: invalid argument type in check_factorvars() and issue recreating calibrated models #520
Fix: add_penalty_factor parameter now works correctly with JSON files and robyn_refresh() #543
Fix: correct hyper-parameters length for custom data #533
Fix: bug in RobynLearn when checking numerical data #532
Fix: removed .iData format for legacy demo .RData files
Fix: passing custom pareto_fronts input instead of "auto" now works as expected
Docs: updated released version on website, meta.com emails, update CRAN link on robyn_update()

Full Changelog: https://github.com/facebookexperimental/Robyn/compare/v3.8.0...v3.8.2

- Jupyter Notebook
Published by laresbernardo over 3 years ago

Robyn - v3.8.0 - Bootstrapped CI, Immediate vs Carryover, Multi-channel calibration

Feat: Added in-cluster bootstrapped confidence intervals (CI) for ROAS and CPA. We treat each cluster of Pareto-optimal model candidates as a sample from a local optimum of the entire population. Default parameters can be customized manually with boot_n and sim_n arguments.
Feat: New robyn_calibrate() function that replaces previous un-exported function calibrate_mmm(). The new calibration method is able to separate immediate & carryover effects. When calibrating using experimental results, only the immediate response and its future carryover serve as a calibration target, as opposed to previously the total response. The historical response is excluded from calibration.
Feat: Enabled multi-channel calibration so we can use experiments that measured more than one channel with a single experiment to be used for calibration (i.e. incrementality experiment measured all fb but you had fb_brand and fb_perf as two separate media channels/variables).
Feat: Added 2 new plots into model one-pager: bootstrapped CI plot and immediate vs carryover response plot.
Feat: Changed default Pareto-fronts from 3 to ”auto" to pick the N that contains at least 100 models (threshold can be changed manually with min_candidates parameter).
Recode: improved CodeFactor's code quality score from C- to A
Feat: Additional CI outputs containing revamped plot and CSV file.
Feat: Enabled turning off parallel calculations when cores = 1.
Fix: Fixed few minor bugs and doumentations (#496, #506, #507, #515)

Full Changelog: https://github.com/facebookexperimental/Robyn/compare/v3.7.2...v3.8.0

- Jupyter Notebook
Published by gufengzhou over 3 years ago

Robyn - v3.7.2 - CRAN update, partial results, more reproducibility

Feat: wrap robyn_mmm() with a tryCatch() to return partial results if the function crashes after a certain time running and warns the user when this happens
Feat: auto-detect categorical variables (no need to set factor_vars parameter in robyn_inputs())
Feat: include R and Robyn's versions to JSON files and InputCollect for reproducibility
Feat: export/save raw data input for reproducibility (raw_data.csv file)
Feat: set Robyn::dt_prophet_holidays as default input on dt_holidays parameters
Fix: inverted counters in check_hyperparameters() message #474
Fix: force date format before binding rows in robyn_refresh() #480
Fix: check_context() was being skipped in some cases
Fix: when only 1 categorical value with 2 unique values crashed one-hot-encoding
Docs: updated templates for issues and pull requests

Full Changelog: https://github.com/facebookexperimental/Robyn/compare/v3.7.1...v3.7.2 Full Changelog since last CRAN update: https://github.com/facebookexperimental/Robyn/compare/v3.6.3...v3.7.2

- Jupyter Notebook
Published by laresbernardo over 3 years ago

Robyn - v3.7.1 - JSON import/export, reactivate spend exposure fitting Latest

Feat: new robyn_read() and robyn_write() functions to save and load Robyn models in a transparent, flexible, and cost-efficient way using JSON instead of RDS files (read more); also, new print methods for both objects containing the most relevant information
Feat: new robyn_recreate() to rebuild any model's InputCollect and OutputCollect objects based on their JSON files and data
Feat: reactivated spend exposure fitting and plotting #463
Feat: updated robyn_response() to receive numeric vectors #464
Feat: enabled calibration_input on robyn_refresh() to calibrate on the fly and more robust checks on data inputs
Feat added Robyn and R versions as the caption in one-pagers to help users debug
Feat: trimmed spend response curves on robyn_allocator() and robyn_onepagers() plots outputs
Fix: missed intercept calculation in fitted vs residual plot #462
Fix: when single categorical value had 2 levels it crashed the one-hot-encoding process
Fix: datasets with no categorical data crashed when using one-hot-encoding #419
Fix: no need to manually sort the dates before passing the data to robyn_inputs(). Ref: check_datevar() #448
Fix: fixed ggplot warnings on some plots (previously hidden with suppressWarnings)
Other: added badges with website and Facebook group in README files (see here), updated documentation and website, and more data checks on user inputs

New Contributors

@Tomobay made his first contribution #464

Full Changelog: https://github.com/facebookexperimental/Robyn/compare/v3.7.0...v3.7.1

- Jupyter Notebook
Published by laresbernardo over 3 years ago

Robyn - v3.7.0 - Total recoding, UX feats, and combined errors fix

Relevant changes on v3.7.0:

Recode: got rid of data.table dependency for r2py wrapper and removed all globalVariables associated noise
Recode: all code is now clean and formatted under the tidyverse code style for better code reading and standardization
Feat: trimmed functionality for response curves on one-pagers outputs to have coherent ranges plotted
Feat: enabled channels removal on robyn_allocator() by setting their constraints to 0 #411
Feat: when manually selecting refresh models in robyn_refresh(), re-ask user until valid solID is provided, instead of crashing
Feat: new plot and improved print methods for robyn_refresh() outputs
Feat: include time units used in adstock plots for clarity
Feat: enabled organic media variables to be calibrated (no spend)
Fix: when best model based on minimum combined errors was tied with other models, inconsistent outputs (one-pagers / clustering). Standardized combined errors methodology with new errors_scores() function, especially normalizing errors before filtering models. The largest the "error_score", the better the model's performance #428
Fix: show blue dots on top of grey dots in Pareto plots #420
Fix: positive/negative colour palette on waterfall plot when all values are positive
Fix: set prophet's print as disabled when prophet_vars input is NULL (off)
Docs: added CRAN, site, and FB group badges on README files
Docs: several typos and documentation updates

Full Changelog: https://github.com/facebookexperimental/Robyn/compare/v3.6.3...v3.7.0

- Jupyter Notebook
Published by laresbernardo over 3 years ago

Robyn - v3.6.3 - CRAN version, site revamp, more inputs flexibility

Relevant changes on v3.6.3:

CRAN: First Robyn version available via CRAN. From now on, install CRAN's for stable version, GitHub's for dev version.
Docs: Site revamp #372, documentation updates and demo enrichment
Feat: Added version_prompt parameter to robyn_refresh() #375
Feat: Added new calibration checks to ensure quality experiments usage
Feat: New date_min and date_max parameters on robyn_allocator() to pick non-0 means window
Feat: New robyn_update() function
Feat: More checks and warnings included to push users to follow best practices.
Refactor: Changed 1 to 3 Pareto fronts as default to enrich robyn_clusters() results
Refactor: Changed default thresholds on robyn_converge() to be more flexible
Fix: Several bugs squashed

New Contributors

@mast4461 made their first contribution in https://github.com/facebookexperimental/Robyn/pull/362
@JustStas made their first contribution in https://github.com/facebookexperimental/Robyn/pull/375

Full Changelog: https://github.com/facebookexperimental/Robyn/compare/v3.6.2...v3.6.3

- Jupyter Notebook
Published by laresbernardo almost 4 years ago

Robyn - v3.6.2: Allocation and plot improvements, new warnings, bugs fixed

Relevant changes on v3.6.2:

Viz: removed redundant information on plots and standardized styles and contents on all visualizations.
Feat: new date_min and date_max parameters on robyn_allocator() to pick specific date range to consider mean spend values (user request).
Feat: new plot methods for robyn_allocator() and robyn_save() outputs, and print method for robyn_inputs() with and without hyperparameters.
Feat: provide recommendations on calibration inputs depending on the experiments' confidence, spending, and KPI measured (#307).
Feat: warn and avoid weekly trend input when data granularity is larger than "week".
Fix: issues on several robyn_allocator() specific cases (#349, #344, #345), especially when some coefficients were 0.
Fix: bug with Weibull adstock scenario (#353).
Docs: fixed some typos, updated, and standardized internal documentation.

Commits log

Fix jde 20211209 by @jeffedwards in https://github.com/facebookexperimental/Robyn/pull/234
Added a couple file to run the code with actual data by @jeffedwards in https://github.com/facebookexperimental/Robyn/pull/235
Jde 20211209 general and troubleshoot by @jeffedwards in https://github.com/facebookexperimental/Robyn/pull/236
quick updates by @jeffedwards in https://github.com/facebookexperimental/Robyn/pull/237
quick updates by @jeffedwards in https://github.com/facebookexperimental/Robyn/pull/238
Updated for fix object to work. Updating check conditions to work by @jeffedwards in https://github.com/facebookexperimental/Robyn/pull/254
build(deps): bump follow-redirects from 1.14.7 to 1.14.8 in /website by @dependabot in https://github.com/facebookexperimental/Robyn/pull/302
Fix by @jeffedwards in https://github.com/facebookexperimental/Robyn/pull/303
Revert "Fix" by @jeffedwards in https://github.com/facebookexperimental/Robyn/pull/304
Updated with master branch. Created new Robyn file by @jeffedwards in https://github.com/facebookexperimental/Robyn/pull/305
PR v3.6.0 by @gufengzhou in https://github.com/facebookexperimental/Robyn/pull/314
build(deps): bump url-parse from 1.5.3 to 1.5.7 in /website by @dependabot in https://github.com/facebookexperimental/Robyn/pull/311
build(deps): bump prismjs from 1.25.0 to 1.27.0 in /website by @dependabot in https://github.com/facebookexperimental/Robyn/pull/326
build(deps): bump url-parse from 1.5.7 to 1.5.10 in /website by @dependabot in https://github.com/facebookexperimental/Robyn/pull/327
Weibull testfix by @kyletgoldberg in https://github.com/facebookexperimental/Robyn/pull/355
Fix log message "Using custom prophet parameters" by @andrey-legayev in https://github.com/facebookexperimental/Robyn/pull/356
build(deps): bump minimist from 1.2.5 to 1.2.6 in /website by @dependabot in https://github.com/facebookexperimental/Robyn/pull/357
Allocation and plots improvements. Version 3.6.2 by @laresbernardo in https://github.com/facebookexperimental/Robyn/pull/361

New Contributors

@kyletgoldberg made their first contribution in https://github.com/facebookexperimental/Robyn/pull/355

Full Changelog: https://github.com/facebookexperimental/Robyn/compare/v3.6.0...v3.6.2

- Jupyter Notebook
Published by laresbernardo almost 4 years ago

Robyn - v3.6.0 - Add new hyperparameter, new convergence metric, improved response function, prints and better allocation stability

What's New in v3.6.0

New hyperparameter "lambda" finds MOO-optimal lambda and thus removes the need of manual lambda selection.
New optional hyperparameter penalty.factor that further extends hyperparameter spaces and thus potentially better fit.
New optimisation convergence rules & plots for each objective function showing if set iterations have converged or not (NRMSE, DECOMP.RSSD, and MAPE if calibrated)
Improved response function now also returns the response for exposure metrics (response on imps, GRP, newsletter sendings, etc) and plots. Note that argument names and output class has changed. See updated demo.R for more details.
More budget allocation stability by defaulting fitting media variables from paid_media_vars to paid_media_spends. Spend exposure fitting with Michaelis Menten function will only serve robyn_response() function output and plotting. robyn_allocator() now only relies on direct spend - response transformation.
Default beta coefficient signs: positive for paid & organic media and unconstrained for the rest. Users can still set signs manually.
New print methods for robyn_inputs(), robyn_run(), robyn_outputs(), and robyn_allocator() outputs to enable visibility on each step's results and objects content.

Full Changelog: https://github.com/facebookexperimental/Robyn/compare/v3.5.1...v3.6.0

- Jupyter Notebook
Published by gufengzhou about 4 years ago

Robyn - v3.5.0 - Add clustering method for model selection and split robyn_run()

What's New in v3.5.0

New robyn_clusters() function to reduce the number of models to select from after Pareto front solutions are picked
Auto-select K clusters given a minimum WSS variance on robyn_clusters()
Split robyn_run() functionalities into robyn_outputs() for more control over modelings results and exporting process
Enabled custom prophet inputs to be used in modeling and refreshing models
Enabled users to use all outputs without the need of exporting results (Shiny devs)
New hyper_limits() helper function with permitted hyper-parameters limits
New quiet mode to reduce prints and messages, few recoding, and overall improvements

Full Changelog: https://github.com/facebookexperimental/Robyn/compare/v3.4.8...v3.5.0

- Jupyter Notebook
Published by laresbernardo about 4 years ago