Comments (6)
So this is a bit tricky and I also realised that some models returned different names. It seems to happen with both multilevel models and models with contrasts, as the underlying projections have names for the contrasts.
I think your solution can partially solve the issue in some models but we still have the thing of fixing the group names, as in your example we recover my_group.(Intercept)
and so on while we ideally want (Intercept | my_group)
, etc. I'll reply in your PR with this in case you want to address that as well?
from projpred.
I also thought about keeping the old column names style (from x$solution_terms
, but re-ordered), but I have two other issues that I wanted to submit afterwards and whose fixes make sense with this new style of column names. I'll create PRs for those two new issues and then it might be easier to discuss the naming of the columns.
Thanks for the hint concerning contrasts. I will have to see whether my proposed fix has to be adapted for contrasts.
from projpred.
from projpred.
Yes, the same holds for my two other issues.
from projpred.
I also thought about keeping the old column names style (from
x$solution_terms
, but re-ordered), but I have two other issues that I wanted to submit afterwards and whose fixes make sense with this new style of column names. I'll create PRs for those two new issues and then it might be easier to discuss the naming of the columns.
Here are these two new PRs: #74 and #75.
from projpred.
Fixed by merged PR #75.
from projpred.
Related Issues (20)
- `d_test` with nontrivial offsets
- Binomial family with > 1 trials: `mu` and `y` in `get_stat()` don't match HOT 2
- cv_varsel error in development version HOT 3
- search_terms argument in cv_varsel not working properly HOT 2
- Fixing certain terms to be included in all submodels in cv_varsel in a high dimensional setting HOT 5
- Problem with projpred for a simple brms model HOT 1
- `datafit`s: `type = "diff"` and `type = "diff.se"` HOT 1
- Adding bernoulli() to extend_family() HOT 2
- Projection for discrete exponential dispersion (DED) families HOT 5
- Unexpected behaviour when incompatible full formulas included in search_terms argument HOT 2
- Projpred “inherits(formula, “formula”) is not TRUE” HOT 2
- error in installation in Mac OS M2 HOT 3
- Inconsistency in reference model formula between GAMs and GAMMs
- Add post-selection inference to latent-projection vignette
- WISH: future_plan = NULL to support currently set future backend plan HOT 3
- Please undo any changes in future::plan() to what it was before HOT 3
- Recent CRAN failures HOT 1
- Use observation weights in `proj_predict()`
- L1 search and `I()` terms
- Model fit with custom distribution family? HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from projpred.