Calling a stored model within the predict() function

[Jim_S]

Hi all,

First of all, I'm a novice R user (less that a week), so perhaps my code isn't very efficient.

Using the MBoost package I created a model:

model <- gamboost(fpfm,data=SampleClusterData,baselearner="bbs") # Creating a model
save(model,file="model.RData") # Saving a model


After this, during a new R session, I want to deploy this model:

setwd("Q:/Program Files/R/library/mboost/data")
NewData <- read.table("NewData.txt",header=TRUE,sep=",") #Calling a new data set
setwd("Q:/Program Files/R/library/mboost")
model <- load("model.rdata") # Loading the model

This won't work. When I check the content of the 'model' object, the only screen output I see is :

"model
[1]model"

...and that the actual file size from 'model.rdata' is exactly 4,100 kb (is this a limit?!)


Then I try to call this model object with the predict() function:

CRPredict <- predict(model, newdata= NewData) # Make the predictions

This results in the following error message:

"Error in UseMethod("predict") : no applicable method for "predict"  "

Is there a correct way to store and call a model or is it only possible to create & deploy a model during the same R session?

Thanks!

Jim

[Jim_S]

No replies yet...
Is my problem explanation unclear?

Please let me know, thanks!

Jim

[Gabor Grothendieck]

Read the last line of every message to r-help.

On Sat, Apr 26, 2008 at 7:14 PM, Jim_S <virtualreal@...> wrote:

>
> Hi all,
>
> First of all, I'm a novice R user (less that a week), so perhaps my code
> isn't very efficient.
>
> Using the MBoost package I created a model using the following command and
> saved it to a file for later use:
>
> model <- gamboost(fpfm,data=SampleClusterData,baselearner="bbs") # Creating
> a model
> save(model,file="model.RData") # Saving a model
>
>
> After this, during a new R session, I want to deploy this model:
>
> setwd("Q:/Program Files/R/library/mboost/data")
> NewData <- read.table("NewData.txt",header=TRUE,sep=,",") #Calling a new
> data set
> setwd("Q:/Program Files/R/library/mboost")
> model <- load("model.rdata") # Loading the model
>
> This won't work. When I check the content of the 'model' object, the only
> screen output I see is :
>
> "model
> [1]model"
>
> ...and that the actual file size from 'model.rdata' is exactly 4,100 kb (is
> this a limit?!)
>
>
> Then I try to call this model object with the predict() function:
>
> CRPredict <- predict(model, newdata= SampleClusterData) # Make the
> predictions
>
> This results in the following error message:
>
> "Error in UseMethod("predict") : no applicable method for "predict"  "
>
> Is the a correct way to store and call a model or is it only possible to
> create & deploy a model during the same R session?
>
> Thanks!
>
> Jim
>
>
>
> --
> View this message in context: http://www.nabble.com/Calling-a-stored-model-within-the-predict%28%29-function-tp16918111p16918111.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> R-help@... mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

______________________________________________
R-help@... mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

[Jim_S]

After a short discussion I decided to post my compete code and data set. I hope this makes sense.

Thanks,

Jim



# READ DATA
# =========
SampleCluster.txt
setwd("C:/Program Files/R/library/mboost/data")
SampleClusterData <- read.table("SampleCluster.txt",header=TRUE,sep=",")
indep <- names(SampleClusterData) [-98]# INPUTS

# GENERATE FORMULA
# ===============
modelformula <- as.formula(paste("CR ~",paste(indep,collapse="+")))

# CREATE MODEL
# ===========
setwd("C:/Program Files/R/library/mboost")
library(mboost)

# Additive Model for same Variables
# =========================
model <- gamboost(modelformula,data=SampleClusterData,baselearner="bbs")

# STORE AND CALL MODEL FILE
# ======================
save(model,file="model.RData") # STORE MODEL
# ...
# New R-Session
setwd("C:/Program Files/R/library/mboost")
model <- load("model.rdata")


# PREDICT WITH A STORED MODEL OBJECT
# ==============================
Prediction <- predict(model, newdata= SampleClusterData)

# WRITE PREDICTION TO FILE
# =====================
write.table(Prediction,file="C:/Prediction.txt")

[Prof Brian Ripley]

Please read ?load more carefully.

Also, don't send multiple copies and completely ignore the posting guide
-- people who do reduce dramatically their chances of getting a reply.


On Sun, 27 Apr 2008, Jim_S wrote:

> After a short discussion I decided to post my compete code and data set. I
> hope this makes sence.
>
> Thanks,
>
> Jim
>
>
>
> # READ DATA
> # =========
> http://www.nabble.com/file/p16923910/SampleCluster.txt SampleCluster.txt
> setwd("C:/Program Files/R/library/mboost/data")
> SampleClusterData <- read.table("SampleCluster.txt",header=TRUE,sep=",")
> indep <- names(SampleClusterData) [-98]# INPUTS
>
> # GENERATE FORMULA
> # ===============
> modelformula <- as.formula(paste("CR ~",paste(indep,collapse="+")))
>
> # CREATE MODEL
> # ===========
> setwd("C:/Program Files/R/library/mboost")
> library(mboost)
>
> # Additive Model for same Variables
> # =========================
> model <- gamboost(modelformula,data=SampleClusterData,baselearner="bbs")
>
> # STORE AND CALL MODEL FILE
> # ======================
> save(model,file="model.RData") # STORE MODEL
> # ...
> # New R-Session
> setwd("C:/Program Files/R/library/mboost")
> model <- load("model.rdata")
>
>
> # PREDICT WITH A STORED MODEL OBJECT
> # ==============================
> Prediction <- predict(model, newdata= SampleClusterData)
>
> # WRITE PREDICTION TO FILE
> # =====================
> write.table(Prediction,file="C:/Prediction.txt")
>
>
>
> --
> View this message in context: http://www.nabble.com/Calling-a-stored-model-within-the-predict%28%29-function-tp16918111p16923910.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> R-help@... mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

--
Brian D. Ripley,                  ripley@...
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  [phone] (self)
1 South Parks Road,                     [phone] (PA)
Oxford OX1 3TG, UK                Fax:  [phone]

______________________________________________
R-help@... mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.