Robyn is an experimental, AI/ML-powered and open sourced Marketing Mix Modeling (MMM) package from Meta Marketing Science. Our mission is to democratise modeling knowledge, inspire the industry through innovation, reduce human bias in the modeling process & build a strong open source marketing science community.
As titled, This PR integrates the pareto and clustering with visualizers one pager.
Added the utils function to map the pareto results after clustering
Added a private method in pareto_visualizer to get the baseline variables
fixed minor edge cases which weren't working for bootstrap graph
changed solID to snake case sol_id
PENDING and Observations from testing:
I saw the actual vs predicted in R is generating some vertical lines which represent something,
Adstock graph, bootstrap, and spend share vs effect share and has a simple sorting that needs to be done on the Y axis if you look (doesn’t have to match R but should be consistent for readability sake for users),
The x axis for all the response curves is really large compared to R which makes the graph look incorrect but I know its not
Fitted vs Residual graph looks incorrect in terms of the red line being drawn and the shaded area needs to tighter
The Response Decomponsition Waterfall graph should have the numbers closer to teh actual blue line, right now they are floating all over lol but the data and graph definitely looks correct
As titled, This PR integrates the pareto and clustering with visualizers one pager.
Added the utils function to map the pareto results after clustering Added a private method in pareto_visualizer to get the baseline variables fixed minor edge cases which weren't working for bootstrap graph changed solID to snake case sol_id
PENDING and Observations from testing: