Joris,
Thank you, I have corrected my mistakes. I very much appreciate your time
and patience.
All my best,
Cobbler.
--
View this message in context:
http://r.789695.n4.nabble.com/Linear-Discriminant-Analysis-in-R-tp2231922p2240547.html
Sent from the R help mailing list archive at Nabble.com.
I checked your data. Now I have to get some sense out of your code. You do :
G <- vowel_features[15]
cvc_lda <- lda(G~ vowel_features[15], data=mask_features,
na.action="na.omit", CV=TRUE)
Firstly, as I suspected, you need to select a column by using
vowel_features[,15] . Mind the comma! Essentia
Hi Janis,
As you have suggested below is the output for the following:
test.vowel <- vowel_features[,1:10]
test.mask <- mask_features[,1:10]
dput(test.vowel)
dput(test.mask)
--- NOTE: outputs are limited
>>test_vowel first 12 columns are all zero (total of 26 columns)
V1 V2 V3
It's not your questions, Cobbler, but could you PLEASE just do what we asked
for?
Copy-paste the following in R and copy-paste ALL output you get in your next
mail.
test.vowel <- vowel_features[,1:10]
test.mask <- mask_features[,1:10]
dput(test.vowel)
dput(test.mask)
I don't know whether your vow
Thanks for being patient with me.
I guess my problem is with understand how grouping in this particular case
is used:
one of the sample codes I found online
(http://www.statmethods.net/advstats/discriminant.html)
library(MASS)
fit <- lda(G ~ x1 + x2 + x3, data=mydata, na.action="na.omit", CV=TRU
Behalf Of Joris Meys
> Sent: Friday, May 28, 2010 8:50 AM
> To: cobbler_squad
> Cc: r-help@r-project.org
> Subject: Re: [R] Linear Discriminant Analysis in R
>
> Could you provide us with data to test the code? use dput
> (and limit the
> size!)
>
> eg:
>
Could you provide us with data to test the code? use dput (and limit the
size!)
eg:
dput(vowel_features)
dput(mask_features)
Without this information, it's impossible to say what's going wrong. It
looks like you're doing something wrong in the selection. What should
vowel_features[15] return?
Joris,
You are a life saver. Based on two sample files above, I think lda should go
something like this:
vowel_features <- read.table(file = "mappings_for_vowels.txt")
mask_features <- data.frame(as.matrix(read.table(file =
"3dmaskdump_ICA_37_Combined.txt")))
G <- vowel_features[15]
cvc_lda <-
Why exactly do you need lda and not another method? For lda to be
applicable, you should check :
1) whether the regressors are normally distributed within the classes
2) whether the variance-covariance matrices are equal for all classes
Essentially, this means that the boundary between both classe
Dear R gurus,
Thank you all for continuous support and guidance -- learning without you
would not be efficient.
I have a question regarding LD analysis and how to best code it up in R.
I have a file of (V52 and 671 time points across all columns) and another
file of phonetic features (each vow
Dear R-gurus,
Here is what I need to do..
I have two .txt files that are in a matrix form (each looks something like
this:
0.0334820.02238 0.026677
0.0345530.0232260.028855
0.0350170.0232620.02941
0.0362620.023306
11 matches
Mail list logo
