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

Add support to multinomial and Cox models #10

Closed
wants to merge 52 commits into from
Closed

Add support to multinomial and Cox models #10

wants to merge 52 commits into from

Conversation

linxihui
Copy link
Contributor

Here are the main changes:

  1. Add file Multinomial.jl: multi-class calssification
  2. Add file CoxNet.jl: Cox model for survival data
  3. Allow y to be string vector for logistic and multinomial classification
  4. Add to predict: key word argument outtype for link and probability outcome; predict for GLMNetCrossValidation using the best lambda
  5. Add plotting for elastic-net path, cross validation object
  6. Add coef, lambdamin for GLMNetCrossValidation type
  7. Add a classification example to README
  8. Add tests

@linxihui
add support for survival data
a71d478
@linxihui
add CV for coxnet
73a94b9
@linxihui
add coxDeviance
468f801
@linxihui
support for multi-class classification
bfcbd1d
@linxihui
replace tab by spaces
01841db
@linxihui
define GLMNetPathMultinomial as output
dff9e40
@linxihui
add another method for coxnet
d3b1615
@linxihui
code clean up
d79809a
@linxihui
add loss/deviance function
43279e8
@linxihui
code clean up
fcc1155
@linxihui
Add export CoxNet; change coxDeviance to CoxDeviance
aa7af09
@linxihui
add export; change GLMNetPathMultinomial to LogNetPath
2694ed3
@linxihui
change GLMNetCrossValidation.path to Any; include Multinomial, CoxNet
fcdbf14
@linxihui
big bug: x->X; mean/std does not reduce dim; add offsets to glmnetcv;…
2195fd1 
… define StringVector
@linxihui
fixed bug: x->X; define StringVector; fixed bug in CoxDeviance
aac5379
@linxihui
add offsets to glmnetcv
5a62436
@linxihui
add predict function on GLMNetCrossValidation object; code clean up
dcfe72c
@linxihui
add glmnet method on AbstractMatrix
3adf4a5
@linxihui
fixed bug in glmnetcv: pass weights/offsets to glmnet
383d05e
@linxihui
fixed bug in glmnetcv: pass weights/offsets to glmnet
3356d7a
@linxihui
fix bug in glmnetcv: no offsets for Normal family
14d3d98
@linxihui
add convenient function coef, lambdamin
449e663
@linxihui
add to predict: output type
14bbfe8
@linxihui
update for new functionality; added multiclass example
88a142b
@linxihui
in glmnetcv, change default weights from ones(legnth(y)) to ones(size…
4352ada 
…(X, 1)) as y can be matrix
@linxihui
add method glmentcv(Matrix, y::StringVector)
d3cd8e7
@linxihui
change outtype to be keyword parameter
52bab2f
@linxihui
fix typo
d339b5d
@linxihui
clean example
5648f49
@linxihui
glmnetcv: fixed bug on offsets when binomial; test passed
ae761b9
@linxihui
add test for multinomial and survival outcome
f1d0ec8
@linxihui
fixed bug in predict, ccall; add offsets to predict, loss and cv
1e23a5a
@linxihui
add keyword argument offset to predict, loss, glmnetcv; include plot.jl
c6a5902
@linxihui
add integerity checking on x, y; re-indent
1c00f36
@linxihui
fixed bug in predict, ccall; add offsets to predict, loss and cv
fa312cd
@linxihui
re-indent
f73ae64
@linxihui
import Gadfly function
a48e07e
@linxihui
replace DataFrames.rep by repmat
1e01a8d
@linxihui
load DataFrames
64c3361
@linxihui
explicitly import predict from DataFrame, which solves that problem t…
2a180fd 
…hat predict cannot be found when DataFrame is loaded after GLMNet
@linxihui
add coef method for Multinomial
5624014
@linxihui
more tests
f902852
@linxihui
fix bug, clean up, better test coverage
80d638b
@linxihui
update examples
b2b41e6
@linxihui
update examples
e0a9a50
@linxihui
update examples
f9e5ade
@linxihui
replaced PNG by SVG images
ee0f482
@linxihui
change links to svg images
344de80
@linxihui
Copy link
Contributor Author

linxihui commented Aug 4, 2015

@simonster
More functionality added, test passed and code coverage are not bad now. Can you merge and create a new tag? Thanks!

@maximsch2
Copy link

Is there something that is holding up this PR?

@simonster
Copy link
Member

Just me. I'll take a closer look in the next couple days.

@slundberg
Copy link

This might need merged before the sparse data support...

@linxihui linxihui mentioned this pull request May 15, 2017
Closed
@jeffwong
Copy link

jeffwong commented Jul 5, 2017

Would love to see cox support merged

@linxihui
Copy link
Contributor Author

@simonster Is there still people watching and maintaining this package? I feel that things are so lagging behind.

@ararslan
Copy link
Member

I don't think this package is actively maintained right now. For Cox proportional hazards models, see https://github.com/ararslan/Survival.jl.

@Marco-Congedo
Copy link

This is a nice package. Will someone taking it over and pushing it forward?

@dsweber2 dsweber2 mentioned this pull request Dec 2, 2020
Merged
@JackDunnNZ
Copy link
Collaborator

Revived and merged in #50

@JackDunnNZ JackDunnNZ closed this Dec 5, 2020
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.

None yet
8 participants
@linxihui @simonster @maximsch2 @slundberg @jeffwong @ararslan @Marco-Congedo @JackDunnNZ