How does mtry affect the speed of randomForest when tuning with cross validation in R?
1
I tried to tune my randomForest model with codes below:
trControl=trainControl(method="cv",number=10)
tuneGrid = expand.grid(mtry=1:5)
And then I used
train(model,data=data,method="rf",ntree=500,trControl=trControl,tuneGrid=tuneGrid)
to find for the best mtry
It took about 3 hours to finish
However, when I changed expand.grid(mtry=1:5) to expand.grid(mtry=1:8), the codes did not finish in more than 9 hours. I want to ask how does the parameter mtry affect the speed of tuning randomForest. Or in other words, what exactly does the parameter mtry do in the tuning process?
r random-forest cross-validation r-caret
edited Nov 13 '18 at 4:31
alistaire
31.7k43764
asked Nov 13 '18 at 3:43
SanguisSanguis
113
add a comment |
1
I tried to tune my randomForest model with codes below:
trControl=trainControl(method="cv",number=10)
tuneGrid = expand.grid(mtry=1:5)
And then I used
train(model,data=data,method="rf",ntree=500,trControl=trControl,tuneGrid=tuneGrid)
to find for the best mtry
It took about 3 hours to finish
However, when I changed expand.grid(mtry=1:5) to expand.grid(mtry=1:8), the codes did not finish in more than 9 hours. I want to ask how does the parameter mtry affect the speed of tuning randomForest. Or in other words, what exactly does the parameter mtry do in the tuning process?
r random-forest cross-validation r-caret
edited Nov 13 '18 at 4:31
alistaire
31.7k43764
asked Nov 13 '18 at 3:43
SanguisSanguis
113
4
@12b345b6b78 No,ntreeis the number of trees built.mtryis the number of features tried out at each split to find the most significant. Fewer options to test will make the model run faster, but usually you care more about a metric like accuracy or RMSE more than run time, somtryis optimized accordingly.
– alistaire
Nov 13 '18 at 4:30
You might want to use method = "ranger". This will use the randomForest from the ranger package and will speed up your code significantly.
– phiver
Nov 13 '18 at 12:18
@phiver, Hi, thanks for your advice. I tried to use method = "ranger' but it returns error that says "something is wrong, all the rmse are missing". But the same error did not occur when using method = "rf"
– Sanguis
Nov 13 '18 at 15:07
add a comment |
1
1
1
I tried to tune my randomForest model with codes below:
trControl=trainControl(method="cv",number=10)
tuneGrid = expand.grid(mtry=1:5)
And then I used
train(model,data=data,method="rf",ntree=500,trControl=trControl,tuneGrid=tuneGrid)
to find for the best mtry
It took about 3 hours to finish
However, when I changed expand.grid(mtry=1:5) to expand.grid(mtry=1:8), the codes did not finish in more than 9 hours. I want to ask how does the parameter mtry affect the speed of tuning randomForest. Or in other words, what exactly does the parameter mtry do in the tuning process?
r random-forest cross-validation r-caret
edited Nov 13 '18 at 4:31
alistaire
31.7k43764
asked Nov 13 '18 at 3:43
SanguisSanguis
113
I tried to tune my randomForest model with codes below:
trControl=trainControl(method="cv",number=10)
tuneGrid = expand.grid(mtry=1:5)
And then I used
train(model,data=data,method="rf",ntree=500,trControl=trControl,tuneGrid=tuneGrid)
to find for the best mtry
It took about 3 hours to finish
However, when I changed expand.grid(mtry=1:5) to expand.grid(mtry=1:8), the codes did not finish in more than 9 hours. I want to ask how does the parameter mtry affect the speed of tuning randomForest. Or in other words, what exactly does the parameter mtry do in the tuning process?
r random-forest cross-validation r-caret
r random-forest cross-validation r-caret
edited Nov 13 '18 at 4:31
alistaire
31.7k43764
asked Nov 13 '18 at 3:43
SanguisSanguis
113
edited Nov 13 '18 at 4:31
alistaire
31.7k43764
asked Nov 13 '18 at 3:43
SanguisSanguis
113
edited Nov 13 '18 at 4:31
alistaire
31.7k43764
edited Nov 13 '18 at 4:31
alistaire
31.7k43764
edited Nov 13 '18 at 4:31
alistaire
31.7k43764
31.7k43764
asked Nov 13 '18 at 3:43
SanguisSanguis
113
asked Nov 13 '18 at 3:43
SanguisSanguis
113
asked Nov 13 '18 at 3:43
SanguisSanguis
113
113
4
@12b345b6b78 No,ntreeis the number of trees built.mtryis the number of features tried out at each split to find the most significant. Fewer options to test will make the model run faster, but usually you care more about a metric like accuracy or RMSE more than run time, somtryis optimized accordingly.
– alistaire
Nov 13 '18 at 4:30
You might want to use method = "ranger". This will use the randomForest from the ranger package and will speed up your code significantly.
– phiver
Nov 13 '18 at 12:18
@phiver, Hi, thanks for your advice. I tried to use method = "ranger' but it returns error that says "something is wrong, all the rmse are missing". But the same error did not occur when using method = "rf"
– Sanguis
Nov 13 '18 at 15:07
add a comment |
4
@12b345b6b78 No,ntreeis the number of trees built.mtryis the number of features tried out at each split to find the most significant. Fewer options to test will make the model run faster, but usually you care more about a metric like accuracy or RMSE more than run time, somtryis optimized accordingly.
– alistaire
Nov 13 '18 at 4:30
You might want to use method = "ranger". This will use the randomForest from the ranger package and will speed up your code significantly.
– phiver
Nov 13 '18 at 12:18
@phiver, Hi, thanks for your advice. I tried to use method = "ranger' but it returns error that says "something is wrong, all the rmse are missing". But the same error did not occur when using method = "rf"
– Sanguis
Nov 13 '18 at 15:07
4
4
@12b345b6b78 No,
ntree is the number of trees built. mtry is the number of features tried out at each split to find the most significant. Fewer options to test will make the model run faster, but usually you care more about a metric like accuracy or RMSE more than run time, so mtry is optimized accordingly.– alistaire
Nov 13 '18 at 4:30
@12b345b6b78 No,
ntree is the number of trees built. mtry is the number of features tried out at each split to find the most significant. Fewer options to test will make the model run faster, but usually you care more about a metric like accuracy or RMSE more than run time, so mtry is optimized accordingly.– alistaire
Nov 13 '18 at 4:30
You might want to use method = "ranger". This will use the randomForest from the ranger package and will speed up your code significantly.
– phiver
Nov 13 '18 at 12:18
You might want to use method = "ranger". This will use the randomForest from the ranger package and will speed up your code significantly.
– phiver
Nov 13 '18 at 12:18
@phiver, Hi, thanks for your advice. I tried to use method = "ranger' but it returns error that says "something is wrong, all the rmse are missing". But the same error did not occur when using method = "rf"
– Sanguis
Nov 13 '18 at 15:07
@phiver, Hi, thanks for your advice. I tried to use method = "ranger' but it returns error that says "something is wrong, all the rmse are missing". But the same error did not occur when using method = "rf"
– Sanguis
Nov 13 '18 at 15:07
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function ()
StackExchange.using("externalEditor", function ()
StackExchange.using("snippets", function ()
StackExchange.snippets.init();
);
);
, "code-snippets");
StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "1"
;
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function()
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled)
StackExchange.using("snippets", function()
createEditor();
);
else
createEditor();
);
function createEditor()
StackExchange.prepareEditor(
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader:
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
,
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);
);
draft saved
draft discarded
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%2f53273470%2fhow-does-mtry-affect-the-speed-of-randomforest-when-tuning-with-cross-validation%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
draft saved
draft discarded
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.
draft saved
draft discarded
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%2f53273470%2fhow-does-mtry-affect-the-speed-of-randomforest-when-tuning-with-cross-validation%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
4
@12b345b6b78 No,
ntreeis the number of trees built.mtryis the number of features tried out at each split to find the most significant. Fewer options to test will make the model run faster, but usually you care more about a metric like accuracy or RMSE more than run time, somtryis optimized accordingly.– alistaire
Nov 13 '18 at 4:30
You might want to use method = "ranger". This will use the randomForest from the ranger package and will speed up your code significantly.
– phiver
Nov 13 '18 at 12:18
@phiver, Hi, thanks for your advice. I tried to use method = "ranger' but it returns error that says "something is wrong, all the rmse are missing". But the same error did not occur when using method = "rf"
– Sanguis
Nov 13 '18 at 15:07