|
Hi,
I'm trying to use predict within the by function but I do not succeed.
I have the data frame before_database.frame which contains different subsets (identified by their serial numbers). These I want to fit separately and receive the prediction of a value from the fit.
For a subset alone I'm able to do it but I don't know how to do it in combination with by.
Single set:
before_database.frame<- read.table("APD_data.txt",
header = TRUE,
sep = "",
dec="."
)
Single_APD.frame<- before_database.frame[before_database.frame$Serial_number==912009913, ]
fit<- lm(Voltage ~ poly(Amplification,2), data=Single_APD.frame)
New_Amp_Single_APD.frame<- data.frame(Amplification=150)
predict(fit, New_Amp_Single_APD.frame)
Now I would like to this for all subsets and I think it should be somehow like follows:
Read data:
before_database.frame<- read.table(
"APD_data.txt",
header = TRUE,
sep = "",
dec="."
)
Group and fit:
grouped.frame<- do.call(
'rbind',
by(before_database.frame, before_database.frame$Serial_number,
function(d) (
fit<- lm(Amplification ~ Voltage, data = d)
New_Amp_Single_APD.frame<- data.frame(Amplification=150),
predict(fit, New_Amp_Single_APD.frame)
)
)
Thank you in advance!
|