Getting factor(0) Levels: in predicting NaiveBayes model
I relate to the last line in the example. I would like to build a NaiveBayes model per train$TN value. It means that for all the row that their train$TN = 4 I'll build the NB_TRAIN_model[[1]], for all rows train$TN = 9 I'll build the NB_TRAIN_model[[2]] etc. However, the model will have to be based on train$Solar.R, train$Wind, train$Temp, train$Month, train$Day and not on train$TN. So, I hope I excluded this value OK by using: Ozone ~ . -TN, data = x (see last line):
library(party)
library(e1071)
airq <- subset(airquality, !is.na(Ozone))
## split data to train and test
set.seed(123)
train_ind <- sample(seq_len(nrow(airq)), size = smp_size)
train <- airq[train_ind, ]
test <- airq[-train_ind, ]
ct <- ctree(Ozone ~ ., data = train, controls = ctree_control(maxsurrogate = 3))
train$TN<-factor (ct@where)
## Builds a NB model per each terminal node
NB_TRAIN_model<-lapply(split(train, train$TN), function(x) naiveBayes(Ozone ~ . -TN, data = x))
Now I want to predict the values on the test. I tried to use the model[[1]] over the first row:
> predict (NB_TRAIN_model[[1]],test[1,2:6],type = "class")
I get:
factor(0)
Levels:
r predict naivebayes
asked Nov 24 '18 at 18:05
AviAvi
1,0311632
|
show 2 more comments
I relate to the last line in the example. I would like to build a NaiveBayes model per train$TN value. It means that for all the row that their train$TN = 4 I'll build the NB_TRAIN_model[[1]], for all rows train$TN = 9 I'll build the NB_TRAIN_model[[2]] etc. However, the model will have to be based on train$Solar.R, train$Wind, train$Temp, train$Month, train$Day and not on train$TN. So, I hope I excluded this value OK by using: Ozone ~ . -TN, data = x (see last line):
library(party)
library(e1071)
airq <- subset(airquality, !is.na(Ozone))
## split data to train and test
set.seed(123)
train_ind <- sample(seq_len(nrow(airq)), size = smp_size)
train <- airq[train_ind, ]
test <- airq[-train_ind, ]
ct <- ctree(Ozone ~ ., data = train, controls = ctree_control(maxsurrogate = 3))
train$TN<-factor (ct@where)
## Builds a NB model per each terminal node
NB_TRAIN_model<-lapply(split(train, train$TN), function(x) naiveBayes(Ozone ~ . -TN, data = x))
Now I want to predict the values on the test. I tried to use the model[[1]] over the first row:
> predict (NB_TRAIN_model[[1]],test[1,2:6],type = "class")
I get:
factor(0)
Levels:
r predict naivebayes
asked Nov 24 '18 at 18:05
AviAvi
1,0311632
what package is naiveBayes from please? (also smp_size is not defined)
– user20650
Nov 24 '18 at 18:44
I use package: e1071
– Avi
Nov 24 '18 at 18:47
Thanks. Should the outcome not be discrete?
– user20650
Nov 24 '18 at 18:51
Yes. I think U R right. I changed the line: NB_TRAIN_model<-lapply(split(train, train$TN), function(x) naiveBayes(as.factor(Ozone) ~ . -TN, data = x)) to factor. Since NB can't be continuous and Ozone is continuous value. Pitty I had no error message for this.
– Avi
Nov 24 '18 at 18:56
I think naiveBayes automatically coerces the outcome to discrete so using factor would not change it. But I think the thing to notice is that the probability tables are largely undefined -- lots of the st. deviations are NA; as there is only one value of the predictor within each class of the outcome.
– user20650
Nov 24 '18 at 19:39
|
show 2 more comments
I relate to the last line in the example. I would like to build a NaiveBayes model per train$TN value. It means that for all the row that their train$TN = 4 I'll build the NB_TRAIN_model[[1]], for all rows train$TN = 9 I'll build the NB_TRAIN_model[[2]] etc. However, the model will have to be based on train$Solar.R, train$Wind, train$Temp, train$Month, train$Day and not on train$TN. So, I hope I excluded this value OK by using: Ozone ~ . -TN, data = x (see last line):
library(party)
library(e1071)
airq <- subset(airquality, !is.na(Ozone))
## split data to train and test
set.seed(123)
train_ind <- sample(seq_len(nrow(airq)), size = smp_size)
train <- airq[train_ind, ]
test <- airq[-train_ind, ]
ct <- ctree(Ozone ~ ., data = train, controls = ctree_control(maxsurrogate = 3))
train$TN<-factor (ct@where)
## Builds a NB model per each terminal node
NB_TRAIN_model<-lapply(split(train, train$TN), function(x) naiveBayes(Ozone ~ . -TN, data = x))
Now I want to predict the values on the test. I tried to use the model[[1]] over the first row:
> predict (NB_TRAIN_model[[1]],test[1,2:6],type = "class")
I get:
factor(0)
Levels:
r predict naivebayes
asked Nov 24 '18 at 18:05
AviAvi
1,0311632
I relate to the last line in the example. I would like to build a NaiveBayes model per train$TN value. It means that for all the row that their train$TN = 4 I'll build the NB_TRAIN_model[[1]], for all rows train$TN = 9 I'll build the NB_TRAIN_model[[2]] etc. However, the model will have to be based on train$Solar.R, train$Wind, train$Temp, train$Month, train$Day and not on train$TN. So, I hope I excluded this value OK by using: Ozone ~ . -TN, data = x (see last line):
library(party)
library(e1071)
airq <- subset(airquality, !is.na(Ozone))
## split data to train and test
set.seed(123)
train_ind <- sample(seq_len(nrow(airq)), size = smp_size)
train <- airq[train_ind, ]
test <- airq[-train_ind, ]
ct <- ctree(Ozone ~ ., data = train, controls = ctree_control(maxsurrogate = 3))
train$TN<-factor (ct@where)
## Builds a NB model per each terminal node
NB_TRAIN_model<-lapply(split(train, train$TN), function(x) naiveBayes(Ozone ~ . -TN, data = x))
Now I want to predict the values on the test. I tried to use the model[[1]] over the first row:
> predict (NB_TRAIN_model[[1]],test[1,2:6],type = "class")
I get:
factor(0)
Levels:
r predict naivebayes
r predict naivebayes
asked Nov 24 '18 at 18:05
AviAvi
1,0311632
asked Nov 24 '18 at 18:05
AviAvi
1,0311632
edited Nov 24 '18 at 18:47
Avi
asked Nov 24 '18 at 18:05
AviAvi
1,0311632
asked Nov 24 '18 at 18:05
AviAvi
1,0311632
asked Nov 24 '18 at 18:05
AviAvi
1,0311632
1,0311632
what package is naiveBayes from please? (also smp_size is not defined)
– user20650
Nov 24 '18 at 18:44
I use package: e1071
– Avi
Nov 24 '18 at 18:47
Thanks. Should the outcome not be discrete?
– user20650
Nov 24 '18 at 18:51
Yes. I think U R right. I changed the line: NB_TRAIN_model<-lapply(split(train, train$TN), function(x) naiveBayes(as.factor(Ozone) ~ . -TN, data = x)) to factor. Since NB can't be continuous and Ozone is continuous value. Pitty I had no error message for this.
– Avi
Nov 24 '18 at 18:56
I think naiveBayes automatically coerces the outcome to discrete so using factor would not change it. But I think the thing to notice is that the probability tables are largely undefined -- lots of the st. deviations are NA; as there is only one value of the predictor within each class of the outcome.
– user20650
Nov 24 '18 at 19:39
|
show 2 more comments
what package is naiveBayes from please? (also smp_size is not defined)
– user20650
Nov 24 '18 at 18:44
I use package: e1071
– Avi
Nov 24 '18 at 18:47
Thanks. Should the outcome not be discrete?
– user20650
Nov 24 '18 at 18:51
Yes. I think U R right. I changed the line: NB_TRAIN_model<-lapply(split(train, train$TN), function(x) naiveBayes(as.factor(Ozone) ~ . -TN, data = x)) to factor. Since NB can't be continuous and Ozone is continuous value. Pitty I had no error message for this.
– Avi
Nov 24 '18 at 18:56
I think naiveBayes automatically coerces the outcome to discrete so using factor would not change it. But I think the thing to notice is that the probability tables are largely undefined -- lots of the st. deviations are NA; as there is only one value of the predictor within each class of the outcome.
– user20650
Nov 24 '18 at 19:39
what package is naiveBayes from please? (also smp_size is not defined)
– user20650
Nov 24 '18 at 18:44
what package is naiveBayes from please? (also smp_size is not defined)
– user20650
Nov 24 '18 at 18:44
I use package: e1071
– Avi
Nov 24 '18 at 18:47
I use package: e1071
– Avi
Nov 24 '18 at 18:47
Thanks. Should the outcome not be discrete?
– user20650
Nov 24 '18 at 18:51
Thanks. Should the outcome not be discrete?
– user20650
Nov 24 '18 at 18:51
Yes. I think U R right. I changed the line: NB_TRAIN_model<-lapply(split(train, train$TN), function(x) naiveBayes(as.factor(Ozone) ~ . -TN, data = x)) to factor. Since NB can't be continuous and Ozone is continuous value. Pitty I had no error message for this.
– Avi
Nov 24 '18 at 18:56
Yes. I think U R right. I changed the line: NB_TRAIN_model<-lapply(split(train, train$TN), function(x) naiveBayes(as.factor(Ozone) ~ . -TN, data = x)) to factor. Since NB can't be continuous and Ozone is continuous value. Pitty I had no error message for this.
– Avi
Nov 24 '18 at 18:56
I think naiveBayes automatically coerces the outcome to discrete so using factor would not change it. But I think the thing to notice is that the probability tables are largely undefined -- lots of the st. deviations are NA; as there is only one value of the predictor within each class of the outcome.
– user20650
Nov 24 '18 at 19:39
I think naiveBayes automatically coerces the outcome to discrete so using factor would not change it. But I think the thing to notice is that the probability tables are largely undefined -- lots of the st. deviations are NA; as there is only one value of the predictor within each class of the outcome.
– user20650
Nov 24 '18 at 19:39
|
show 2 more comments
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
});
}
});
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%2f53460997%2fgetting-factor0-levels-in-predicting-naivebayes-model%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
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.
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%2f53460997%2fgetting-factor0-levels-in-predicting-naivebayes-model%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
what package is naiveBayes from please? (also smp_size is not defined)
– user20650
Nov 24 '18 at 18:44
I use package: e1071
– Avi
Nov 24 '18 at 18:47
Thanks. Should the outcome not be discrete?
– user20650
Nov 24 '18 at 18:51
Yes. I think U R right. I changed the line: NB_TRAIN_model<-lapply(split(train, train$TN), function(x) naiveBayes(as.factor(Ozone) ~ . -TN, data = x)) to factor. Since NB can't be continuous and Ozone is continuous value. Pitty I had no error message for this.
– Avi
Nov 24 '18 at 18:56
I think naiveBayes automatically coerces the outcome to discrete so using factor would not change it. But I think the thing to notice is that the probability tables are largely undefined -- lots of the st. deviations are NA; as there is only one value of the predictor within each class of the outcome.
– user20650
Nov 24 '18 at 19:39