Is it possible to fit a model to a vector outcome?
up vote
0
down vote
favorite
I have a data set with 60 features. 10 of these features are target variables in 1/0 format.
Using caret and e.g. random forest I could fit 10 separate models on each of the 10 target features.
My question is, is it possible to fit a model to a vector?
Suppose for the e.g. 1st observation the ten target variables are c(1,1,1,0,1,0,0,0,0,1)
. I could create a model for each where the outcome is either 0 or 1.
My question is, is there some way to fit a model on a vector of outcomes so that I only need to fit one model not 10?
r r-caret
add a comment |
up vote
0
down vote
favorite
I have a data set with 60 features. 10 of these features are target variables in 1/0 format.
Using caret and e.g. random forest I could fit 10 separate models on each of the 10 target features.
My question is, is it possible to fit a model to a vector?
Suppose for the e.g. 1st observation the ten target variables are c(1,1,1,0,1,0,0,0,0,1)
. I could create a model for each where the outcome is either 0 or 1.
My question is, is there some way to fit a model on a vector of outcomes so that I only need to fit one model not 10?
r r-caret
As I understand your sole aim is to make model fitting more concise, and to actually still fit 10 separate models, right? In that case, I guess the answer is negative asy
is supposed, when usingtrain
, to be "A numeric or factor vector containing the outcome for each sample.". If you wanted to do a kind of multivariate model, you could transform your vector into a factor. But in that case there would be some serious problems when the vector is long enough.
– Julius Vainora
Nov 7 at 0:13
2
Really a methodological question, but yes, you can have a matrix on hte LHS or regression functions.
– 42-
Nov 7 at 0:19
This is called multi-label classification. It can be done in mlr, take a look at this. I am not sure, but think it can not be done in caret.
– missuse
Nov 7 at 12:56
add a comment |
up vote
0
down vote
favorite
up vote
0
down vote
favorite
I have a data set with 60 features. 10 of these features are target variables in 1/0 format.
Using caret and e.g. random forest I could fit 10 separate models on each of the 10 target features.
My question is, is it possible to fit a model to a vector?
Suppose for the e.g. 1st observation the ten target variables are c(1,1,1,0,1,0,0,0,0,1)
. I could create a model for each where the outcome is either 0 or 1.
My question is, is there some way to fit a model on a vector of outcomes so that I only need to fit one model not 10?
r r-caret
I have a data set with 60 features. 10 of these features are target variables in 1/0 format.
Using caret and e.g. random forest I could fit 10 separate models on each of the 10 target features.
My question is, is it possible to fit a model to a vector?
Suppose for the e.g. 1st observation the ten target variables are c(1,1,1,0,1,0,0,0,0,1)
. I could create a model for each where the outcome is either 0 or 1.
My question is, is there some way to fit a model on a vector of outcomes so that I only need to fit one model not 10?
r r-caret
r r-caret
asked Nov 6 at 23:54
Doug Fir
5,2222680147
5,2222680147
As I understand your sole aim is to make model fitting more concise, and to actually still fit 10 separate models, right? In that case, I guess the answer is negative asy
is supposed, when usingtrain
, to be "A numeric or factor vector containing the outcome for each sample.". If you wanted to do a kind of multivariate model, you could transform your vector into a factor. But in that case there would be some serious problems when the vector is long enough.
– Julius Vainora
Nov 7 at 0:13
2
Really a methodological question, but yes, you can have a matrix on hte LHS or regression functions.
– 42-
Nov 7 at 0:19
This is called multi-label classification. It can be done in mlr, take a look at this. I am not sure, but think it can not be done in caret.
– missuse
Nov 7 at 12:56
add a comment |
As I understand your sole aim is to make model fitting more concise, and to actually still fit 10 separate models, right? In that case, I guess the answer is negative asy
is supposed, when usingtrain
, to be "A numeric or factor vector containing the outcome for each sample.". If you wanted to do a kind of multivariate model, you could transform your vector into a factor. But in that case there would be some serious problems when the vector is long enough.
– Julius Vainora
Nov 7 at 0:13
2
Really a methodological question, but yes, you can have a matrix on hte LHS or regression functions.
– 42-
Nov 7 at 0:19
This is called multi-label classification. It can be done in mlr, take a look at this. I am not sure, but think it can not be done in caret.
– missuse
Nov 7 at 12:56
As I understand your sole aim is to make model fitting more concise, and to actually still fit 10 separate models, right? In that case, I guess the answer is negative as
y
is supposed, when using train
, to be "A numeric or factor vector containing the outcome for each sample.". If you wanted to do a kind of multivariate model, you could transform your vector into a factor. But in that case there would be some serious problems when the vector is long enough.– Julius Vainora
Nov 7 at 0:13
As I understand your sole aim is to make model fitting more concise, and to actually still fit 10 separate models, right? In that case, I guess the answer is negative as
y
is supposed, when using train
, to be "A numeric or factor vector containing the outcome for each sample.". If you wanted to do a kind of multivariate model, you could transform your vector into a factor. But in that case there would be some serious problems when the vector is long enough.– Julius Vainora
Nov 7 at 0:13
2
2
Really a methodological question, but yes, you can have a matrix on hte LHS or regression functions.
– 42-
Nov 7 at 0:19
Really a methodological question, but yes, you can have a matrix on hte LHS or regression functions.
– 42-
Nov 7 at 0:19
This is called multi-label classification. It can be done in mlr, take a look at this. I am not sure, but think it can not be done in caret.
– missuse
Nov 7 at 12:56
This is called multi-label classification. It can be done in mlr, take a look at this. I am not sure, but think it can not be done in caret.
– missuse
Nov 7 at 12:56
add a comment |
1 Answer
1
active
oldest
votes
up vote
0
down vote
accepted
No, caret does not support multiple outputs. See e.g. here (https://github.com/topepo/caret/issues/466#issuecomment-317527852) where the author of caret confirms this.
add a comment |
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
up vote
0
down vote
accepted
No, caret does not support multiple outputs. See e.g. here (https://github.com/topepo/caret/issues/466#issuecomment-317527852) where the author of caret confirms this.
add a comment |
up vote
0
down vote
accepted
No, caret does not support multiple outputs. See e.g. here (https://github.com/topepo/caret/issues/466#issuecomment-317527852) where the author of caret confirms this.
add a comment |
up vote
0
down vote
accepted
up vote
0
down vote
accepted
No, caret does not support multiple outputs. See e.g. here (https://github.com/topepo/caret/issues/466#issuecomment-317527852) where the author of caret confirms this.
No, caret does not support multiple outputs. See e.g. here (https://github.com/topepo/caret/issues/466#issuecomment-317527852) where the author of caret confirms this.
answered Nov 11 at 8:40
Gertjan Verhoeven
496
496
add a comment |
add a comment |
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Some of your past answers have not been well-received, and you're in danger of being blocked from answering.
Please pay close attention to the following guidance:
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53181836%2fis-it-possible-to-fit-a-model-to-a-vector-outcome%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
As I understand your sole aim is to make model fitting more concise, and to actually still fit 10 separate models, right? In that case, I guess the answer is negative as
y
is supposed, when usingtrain
, to be "A numeric or factor vector containing the outcome for each sample.". If you wanted to do a kind of multivariate model, you could transform your vector into a factor. But in that case there would be some serious problems when the vector is long enough.– Julius Vainora
Nov 7 at 0:13
2
Really a methodological question, but yes, you can have a matrix on hte LHS or regression functions.
– 42-
Nov 7 at 0:19
This is called multi-label classification. It can be done in mlr, take a look at this. I am not sure, but think it can not be done in caret.
– missuse
Nov 7 at 12:56