Re: [R] Remove highly correlated variables from a data frame or matrix
Hi Peter,
Thank you so much!!! I will use complete linkage clustering because
Mendelian Randomization function
(https://cran.r-project.org/web/packages/MendelianRandomization/vignettes/Vignette_MR.pdf)
I plan to use allows for correlations but not as high as 0.9 or more.
I got 40 SNPs out of 246 so improvement!
Regards,
Ana
On Fri, Nov 15, 2019 at 8:01 PM Peter Langfelder
wrote:
>
> Try hclust(as.dist(1-calc.rho), method = "average").
>
> Peter
>
> On Fri, Nov 15, 2019 at 10:02 AM Ana Marija
> wrote:
> >
> > HI Peter,
> >
> > Thank you for getting back to me and shedding light on this. I see
> > your point, doing Jim's method:
> >
> > > keeprows<-apply(calc.rho,1,function(x) return(sum(x>0.8)<3))
> > > ro246.lt.8<-calc.rho[keeprows,keeprows]
> > > ro246.lt.8[ro246.lt.8 == 1] <- NA
> > > (mmax <- max(abs(ro246.lt.8), na.rm=TRUE))
> > [1] 0.566
> >
> > Which is good in general, correlations in my matrix should not be
> > exceeding 0.8. I need to run Mendelian Rendomization on it later on so
> > I can not be having there highly correlated SNPs. But with Jim's
> > method I am only left with 17 SNPs (out of 246) and that means that
> > both pairs of highly correlated SNPs are removed and it would be good
> > to keep one of those highly correlated ones.
> >
> > I tried to do your code:
> > > tree = hclust(1-calc.rho, method = "average")
> > Error in if (is.na(n) || n > 65536L) stop("size cannot be NA nor
> > exceed 65536") :
> > missing value where TRUE/FALSE needed
> >
> > Please advise.
> >
> > Thanks
> > Ana
> >
> > On Thu, Nov 14, 2019 at 7:37 PM Peter Langfelder
> > wrote:
> > >
> > > I suspect that you want to identify which variables are highly
> > > correlated, and then keep only "representative" variables, i.e.,
> > > remove redundant ones. This is a bit of a risky procedure but I have
> > > done such things before as well sometimes to simplify large sets of
> > > highly related variables. If your threshold of 0.8 is approximate, you
> > > could simply use average linkage hierarchical clustering with
> > > dissimilarity = 1-correlation, cut the tree at the appropriate height
> > > (1-0.8=0.2), and from each cluster keep a single representative (e.g.,
> > > the one with the highest mean correlation with other members of the
> > > cluster). Something along these lines (untested)
> > >
> > > tree = hclust(1-calc.rho, method = "average")
> > > clusts = cutree(tree, h = 0.2)
> > > clustLevels = sort(unique(clusts))
> > > representatives = unlist(lapply(clustLevels, function(cl)
> > > {
> > > inClust = which(clusts==cl);
> > > rho1 = calc.rho[inClust, inClust, drop = FALSE];
> > > repr = inClust[ which.max(colSums(rho1)) ]
> > > repr
> > > }))
> > >
> > > the variable representatives now contains indices of the variables you
> > > want to retain, so you could subset the calc.rho matrix as
> > > rho.retained = calc.rho[representatives, representatives]
> > >
> > > I haven't tested the code and it may contain bugs, but something along
> > > these lines should get you where you want to be.
> > >
> > > Oh, and depending on how strict you want to be with the remaining
> > > correlations, you could use complete linkage clustering (will retain
> > > more variables, some correlations will be above 0.8).
> > >
> > > Peter
> > >
> > > On Thu, Nov 14, 2019 at 10:50 AM Ana Marija
> > > wrote:
> > > >
> > > > Hello,
> > > >
> > > > I have a data frame like this (a matrix):
> > > > head(calc.rho)
> > > > rs9900318 rs8069906 rs9908521 rs9908336 rs9908870 rs9895995
> > > > rs56192520 0.903 0.268 0.327 0.327 0.327 0.582
> > > > rs3764410 0.928 0.276 0.336 0.336 0.336 0.598
> > > > rs145984817 0.975 0.309 0.371 0.371 0.371 0.638
> > > > rs1807401 0.975 0.309 0.371 0.371 0.371 0.638
> > > > rs1807402 0.975 0.309 0.371 0.371 0.371 0.638
> > > > rs35350506 0.975 0.309 0.371 0.371 0.371 0.638
> > > >
> > > > > dim(calc.rho)
> > > > [1] 246 246
> > > >
> > > > I would like to remove from this data all highly correlated variables,
> > > > with correlation more than 0.8
> > > >
> > > > I tried this:
> > > >
> > > > > data<- calc.rho[,!apply(calc.rho,2,function(x) any(abs(x) > 0.80))]
> > > > > dim(data)
> > > > [1] 246 0
> > > >
> > > > Can you please advise,
> > > >
> > > > Thanks
> > > > Ana
> > > >
> > > > But this removes everything.
> > > >
> > > > __
> > > > R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
> > > > 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@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
Re: [R] Remove highly correlated variables from a data frame or matrix
Try hclust(as.dist(1-calc.rho), method = "average").
Peter
On Fri, Nov 15, 2019 at 10:02 AM Ana Marija wrote:
>
> HI Peter,
>
> Thank you for getting back to me and shedding light on this. I see
> your point, doing Jim's method:
>
> > keeprows<-apply(calc.rho,1,function(x) return(sum(x>0.8)<3))
> > ro246.lt.8<-calc.rho[keeprows,keeprows]
> > ro246.lt.8[ro246.lt.8 == 1] <- NA
> > (mmax <- max(abs(ro246.lt.8), na.rm=TRUE))
> [1] 0.566
>
> Which is good in general, correlations in my matrix should not be
> exceeding 0.8. I need to run Mendelian Rendomization on it later on so
> I can not be having there highly correlated SNPs. But with Jim's
> method I am only left with 17 SNPs (out of 246) and that means that
> both pairs of highly correlated SNPs are removed and it would be good
> to keep one of those highly correlated ones.
>
> I tried to do your code:
> > tree = hclust(1-calc.rho, method = "average")
> Error in if (is.na(n) || n > 65536L) stop("size cannot be NA nor
> exceed 65536") :
> missing value where TRUE/FALSE needed
>
> Please advise.
>
> Thanks
> Ana
>
> On Thu, Nov 14, 2019 at 7:37 PM Peter Langfelder
> wrote:
> >
> > I suspect that you want to identify which variables are highly
> > correlated, and then keep only "representative" variables, i.e.,
> > remove redundant ones. This is a bit of a risky procedure but I have
> > done such things before as well sometimes to simplify large sets of
> > highly related variables. If your threshold of 0.8 is approximate, you
> > could simply use average linkage hierarchical clustering with
> > dissimilarity = 1-correlation, cut the tree at the appropriate height
> > (1-0.8=0.2), and from each cluster keep a single representative (e.g.,
> > the one with the highest mean correlation with other members of the
> > cluster). Something along these lines (untested)
> >
> > tree = hclust(1-calc.rho, method = "average")
> > clusts = cutree(tree, h = 0.2)
> > clustLevels = sort(unique(clusts))
> > representatives = unlist(lapply(clustLevels, function(cl)
> > {
> > inClust = which(clusts==cl);
> > rho1 = calc.rho[inClust, inClust, drop = FALSE];
> > repr = inClust[ which.max(colSums(rho1)) ]
> > repr
> > }))
> >
> > the variable representatives now contains indices of the variables you
> > want to retain, so you could subset the calc.rho matrix as
> > rho.retained = calc.rho[representatives, representatives]
> >
> > I haven't tested the code and it may contain bugs, but something along
> > these lines should get you where you want to be.
> >
> > Oh, and depending on how strict you want to be with the remaining
> > correlations, you could use complete linkage clustering (will retain
> > more variables, some correlations will be above 0.8).
> >
> > Peter
> >
> > On Thu, Nov 14, 2019 at 10:50 AM Ana Marija
> > wrote:
> > >
> > > Hello,
> > >
> > > I have a data frame like this (a matrix):
> > > head(calc.rho)
> > > rs9900318 rs8069906 rs9908521 rs9908336 rs9908870 rs9895995
> > > rs56192520 0.903 0.268 0.327 0.327 0.327 0.582
> > > rs3764410 0.928 0.276 0.336 0.336 0.336 0.598
> > > rs145984817 0.975 0.309 0.371 0.371 0.371 0.638
> > > rs1807401 0.975 0.309 0.371 0.371 0.371 0.638
> > > rs1807402 0.975 0.309 0.371 0.371 0.371 0.638
> > > rs35350506 0.975 0.309 0.371 0.371 0.371 0.638
> > >
> > > > dim(calc.rho)
> > > [1] 246 246
> > >
> > > I would like to remove from this data all highly correlated variables,
> > > with correlation more than 0.8
> > >
> > > I tried this:
> > >
> > > > data<- calc.rho[,!apply(calc.rho,2,function(x) any(abs(x) > 0.80))]
> > > > dim(data)
> > > [1] 246 0
> > >
> > > Can you please advise,
> > >
> > > Thanks
> > > Ana
> > >
> > > But this removes everything.
> > >
> > > __
> > > R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
> > > 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@r-project.org mailing list -- To UNSUBSCRIBE and more, see
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.
Re: [R] Remove highly correlated variables from a data frame or matrix
While the remedy for your dissatisfaction with my previous solution should be obvious, I will make it explicit. # that is rows containing at most one value > 0.8 # ignoring the diagonal keeprows<-apply(ro246,1,function(x) return(sum(x>0.8)<2)) ro246.lt.8<-ro246[keeprows,keeprows] Jim __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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.
Re: [R] Remove highly correlated variables from a data frame or matrix
if it is of any help my correlation matrix (calc.rho) was done here,
under LDmatrix tab https://ldlink.nci.nih.gov/?tab=ldmatrix
and dataset of 246 is bellow
rs56192520
rs3764410
rs145984817
rs1807401
rs1807402
rs35350506
rs2089177
rs12325677
rs62064624
rs62064631
rs2349295
rs2174369
rs7218554
rs62064634
rs4360974
rs4527060
rs6502526
rs6502527
rs9900318
rs8069906
rs9908521
rs9908336
rs9908870
rs9895995
rs7211086
rs9905280
rs8073305
rs8072086
rs4312350
rs4313843
rs8069610
rs883504
rs8072394
rs4280293
rs4465638
rs12602378
rs9899059
rs6502530
rs4380085
rs6502532
rs4792798
rs4792799
rs4316813
rs148563931
rs74751226
rs8068857
rs8069441
rs77397878
rs75339756
rs4608391
rs79569548
rs4275914
rs11870422
rs8075751
rs11658904
rs138437542
rs80344434
rs7222311
rs7221842
rs7223686
rs78013597
rs74965036
rs78063986
rs118106233
rs117345712
rs113004656
rs9898995
rs4985718
rs9893911
rs79110942
rs7208929
rs12601453
rs4078062
rs75129280
rs76664572
rs78961289
rs146364798
rs76715413
rs4078534
rs79457460
rs74369938
rs76423171
rs74668400
rs75146120
rs1135237
rs9914671
rs117759512
rs4985696
rs16961340
rs17794159
rs4247118
rs78572469
rs12601193
rs2349646
rs2090018
rs12601424
rs4985701
rs8064550
rs2271521
rs2271520
rs11078374
rs4985702
rs1124961
rs11652674
rs3924340
rs112450164
rs7208973
rs9910857
rs78574480
rs8072184
rs12602196
rs6502563
rs3744135
rs148779543
rs77689691
rs41319048
rs117340532
rs78647096
rs77712968
rs16961396
rs80054920
rs7206981
rs4985740
rs3803762
rs77103270
rs7207485
rs77342773
rs3826304
rs3744126
rs7210879
rs7211576
rs117967362
rs75978745
rs6502564
rs9894565
rs36079048
rs8076621
rs7218795
rs3803761
rs12602675
rs7208065
rs4985705
rs8080386
rs8065832
rs2018781
rs1736221
rs1736220
rs1736217
rs1708620
rs1708619
rs1736216
rs76319098
rs1736215
rs1736214
rs1708617
rs12602831
rs12602871
rs1736213
rs1736212
rs76045368
rs34518797
rs11078378
rs8079562
rs8065774
rs8066090
rs41337846
rs1736209
rs1736208
rs12949822
rs76246042
rs12600635
rs55689224
rs1736207
rs1708626
rs1736206
rs9896078
rs16961474
rs1708627
rs1736205
rs1708628
rs7220577
rs2294155
rs1736204
rs1736203
rs1736202
rs12937908
rs1736200
rs1708623
rs1708624
rs9894884
rs9901894
rs9903294
rs2472689
rs1630656
rs111478970
rs3182911
rs7219012
rs9890657
rs12453455
rs12947291
rs150267386
rs16961493
rs11652745
rs9907107
rs8070574
rs4985759
rs3866959
rs7219248
rs6502568
rs7220275
rs12450037
rs7225876
rs9892352
rs4985760
rs6502569
rs1029830
rs2012954
rs1029832
rs2270180
rs8072402
rs7221553
rs145597919
rs150772017
rs2041393
rs6502578
rs11078382
rs9912109
rs12601631
rs11869054
rs11869079
rs9912599
rs7220057
rs9896970
rs34121330
rs34668117
rs67773570
rs242252
rs955893
rs28583584
rs9944423
rs7217764
rs11651957
rs73978990
rs8071007
rs56044345
rs17804843
On Fri, Nov 15, 2019 at 12:03 PM Ana Marija wrote:
>
> HI Peter,
>
> Thank you for getting back to me and shedding light on this. I see
> your point, doing Jim's method:
>
> > keeprows<-apply(calc.rho,1,function(x) return(sum(x>0.8)<3))
> > ro246.lt.8<-calc.rho[keeprows,keeprows]
> > ro246.lt.8[ro246.lt.8 == 1] <- NA
> > (mmax <- max(abs(ro246.lt.8), na.rm=TRUE))
> [1] 0.566
>
> Which is good in general, correlations in my matrix should not be
> exceeding 0.8. I need to run Mendelian Rendomization on it later on so
> I can not be having there highly correlated SNPs. But with Jim's
> method I am only left with 17 SNPs (out of 246) and that means that
> both pairs of highly correlated SNPs are removed and it would be good
> to keep one of those highly correlated ones.
>
> I tried to do your code:
> > tree = hclust(1-calc.rho, method = "average")
> Error in if (is.na(n) || n > 65536L) stop("size cannot be NA nor
> exceed 65536") :
> missing value where TRUE/FALSE needed
>
> Please advise.
>
> Thanks
> Ana
>
> On Thu, Nov 14, 2019 at 7:37 PM Peter Langfelder
> wrote:
> >
> > I suspect that you want to identify which variables are highly
> > correlated, and then keep only "representative" variables, i.e.,
> > remove redundant ones. This is a bit of a risky procedure but I have
> > done such things before as well sometimes to simplify large sets of
> > highly related variables. If your threshold of 0.8 is approximate, you
> > could simply use average linkage hierarchical clustering with
> > dissimilarity = 1-correlation, cut the tree at the appropriate height
> > (1-0.8=0.2), and from each cluster keep a single representative (e.g.,
> > the one with the highest mean correlation with other members of the
> > cluster). Something along these lines (untested)
> >
> > tree = hclust(1-calc.rho, method = "average")
> > clusts = cutree(tree, h = 0.2)
> > clustLevels = sort(unique(clusts))
> > representatives = unlist(lapply(clustLevels, function(cl)
> > {
> > inClust = which(clusts==cl);
> > rho1 = calc.rho[inClust, inClust, drop = FALSE];
> > repr = inClust[ which.max(colSums(rho1)) ]
> > repr
> > }))
> >
> > the variable representatives now contains indices of the variables you
> > want to retain, so you could subset the calc.rho
Re: [R] Remove highly correlated variables from a data frame or matrix
HI Peter,
Thank you for getting back to me and shedding light on this. I see
your point, doing Jim's method:
> keeprows<-apply(calc.rho,1,function(x) return(sum(x>0.8)<3))
> ro246.lt.8<-calc.rho[keeprows,keeprows]
> ro246.lt.8[ro246.lt.8 == 1] <- NA
> (mmax <- max(abs(ro246.lt.8), na.rm=TRUE))
[1] 0.566
Which is good in general, correlations in my matrix should not be
exceeding 0.8. I need to run Mendelian Rendomization on it later on so
I can not be having there highly correlated SNPs. But with Jim's
method I am only left with 17 SNPs (out of 246) and that means that
both pairs of highly correlated SNPs are removed and it would be good
to keep one of those highly correlated ones.
I tried to do your code:
> tree = hclust(1-calc.rho, method = "average")
Error in if (is.na(n) || n > 65536L) stop("size cannot be NA nor
exceed 65536") :
missing value where TRUE/FALSE needed
Please advise.
Thanks
Ana
On Thu, Nov 14, 2019 at 7:37 PM Peter Langfelder
wrote:
>
> I suspect that you want to identify which variables are highly
> correlated, and then keep only "representative" variables, i.e.,
> remove redundant ones. This is a bit of a risky procedure but I have
> done such things before as well sometimes to simplify large sets of
> highly related variables. If your threshold of 0.8 is approximate, you
> could simply use average linkage hierarchical clustering with
> dissimilarity = 1-correlation, cut the tree at the appropriate height
> (1-0.8=0.2), and from each cluster keep a single representative (e.g.,
> the one with the highest mean correlation with other members of the
> cluster). Something along these lines (untested)
>
> tree = hclust(1-calc.rho, method = "average")
> clusts = cutree(tree, h = 0.2)
> clustLevels = sort(unique(clusts))
> representatives = unlist(lapply(clustLevels, function(cl)
> {
> inClust = which(clusts==cl);
> rho1 = calc.rho[inClust, inClust, drop = FALSE];
> repr = inClust[ which.max(colSums(rho1)) ]
> repr
> }))
>
> the variable representatives now contains indices of the variables you
> want to retain, so you could subset the calc.rho matrix as
> rho.retained = calc.rho[representatives, representatives]
>
> I haven't tested the code and it may contain bugs, but something along
> these lines should get you where you want to be.
>
> Oh, and depending on how strict you want to be with the remaining
> correlations, you could use complete linkage clustering (will retain
> more variables, some correlations will be above 0.8).
>
> Peter
>
> On Thu, Nov 14, 2019 at 10:50 AM Ana Marija
> wrote:
> >
> > Hello,
> >
> > I have a data frame like this (a matrix):
> > head(calc.rho)
> > rs9900318 rs8069906 rs9908521 rs9908336 rs9908870 rs9895995
> > rs56192520 0.903 0.268 0.327 0.327 0.327 0.582
> > rs3764410 0.928 0.276 0.336 0.336 0.336 0.598
> > rs145984817 0.975 0.309 0.371 0.371 0.371 0.638
> > rs1807401 0.975 0.309 0.371 0.371 0.371 0.638
> > rs1807402 0.975 0.309 0.371 0.371 0.371 0.638
> > rs35350506 0.975 0.309 0.371 0.371 0.371 0.638
> >
> > > dim(calc.rho)
> > [1] 246 246
> >
> > I would like to remove from this data all highly correlated variables,
> > with correlation more than 0.8
> >
> > I tried this:
> >
> > > data<- calc.rho[,!apply(calc.rho,2,function(x) any(abs(x) > 0.80))]
> > > dim(data)
> > [1] 246 0
> >
> > Can you please advise,
> >
> > Thanks
> > Ana
> >
> > But this removes everything.
> >
> > __
> > R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
> > 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@r-project.org mailing list -- To UNSUBSCRIBE and more, see
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.
Re: [R] Remove highly correlated variables from a data frame or matrix
I suspect that you want to identify which variables are highly
correlated, and then keep only "representative" variables, i.e.,
remove redundant ones. This is a bit of a risky procedure but I have
done such things before as well sometimes to simplify large sets of
highly related variables. If your threshold of 0.8 is approximate, you
could simply use average linkage hierarchical clustering with
dissimilarity = 1-correlation, cut the tree at the appropriate height
(1-0.8=0.2), and from each cluster keep a single representative (e.g.,
the one with the highest mean correlation with other members of the
cluster). Something along these lines (untested)
tree = hclust(1-calc.rho, method = "average")
clusts = cutree(tree, h = 0.2)
clustLevels = sort(unique(clusts))
representatives = unlist(lapply(clustLevels, function(cl)
{
inClust = which(clusts==cl);
rho1 = calc.rho[inClust, inClust, drop = FALSE];
repr = inClust[ which.max(colSums(rho1)) ]
repr
}))
the variable representatives now contains indices of the variables you
want to retain, so you could subset the calc.rho matrix as
rho.retained = calc.rho[representatives, representatives]
I haven't tested the code and it may contain bugs, but something along
these lines should get you where you want to be.
Oh, and depending on how strict you want to be with the remaining
correlations, you could use complete linkage clustering (will retain
more variables, some correlations will be above 0.8).
Peter
On Thu, Nov 14, 2019 at 10:50 AM Ana Marija wrote:
>
> Hello,
>
> I have a data frame like this (a matrix):
> head(calc.rho)
> rs9900318 rs8069906 rs9908521 rs9908336 rs9908870 rs9895995
> rs56192520 0.903 0.268 0.327 0.327 0.327 0.582
> rs3764410 0.928 0.276 0.336 0.336 0.336 0.598
> rs145984817 0.975 0.309 0.371 0.371 0.371 0.638
> rs1807401 0.975 0.309 0.371 0.371 0.371 0.638
> rs1807402 0.975 0.309 0.371 0.371 0.371 0.638
> rs35350506 0.975 0.309 0.371 0.371 0.371 0.638
>
> > dim(calc.rho)
> [1] 246 246
>
> I would like to remove from this data all highly correlated variables,
> with correlation more than 0.8
>
> I tried this:
>
> > data<- calc.rho[,!apply(calc.rho,2,function(x) any(abs(x) > 0.80))]
> > dim(data)
> [1] 246 0
>
> Can you please advise,
>
> Thanks
> Ana
>
> But this removes everything.
>
> __
> R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
> 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@r-project.org mailing list -- To UNSUBSCRIBE and more, see
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.
Re: [R] Remove highly correlated variables from a data frame or matrix
HI Jim,
This:
colnames(calc.jim)[colSums(abs(calc.jim)>0.8)<3]
was the master take!
Thank you so much!!!
On Thu, Nov 14, 2019 at 3:39 PM Jim Lemon wrote:
>
> I thought you were going to trick us. What I think you are asking now
> is how to get the variable names in the columns that have at most one
> _absolute_ value greater than 0.8. OK:
>
> # I'm not going to try to recreate your correlation matrix
> calc.jim<-matrix(runif(100,min=-1,max=1),nrow=10)
> for(i in 1:10) calc.jim[i,i]<-1
> rownames(calc.jim)<-<-colnames(calc.jim)<-paste0("rs",1:10)
>
> Now that we have a plausible fake correlation matrix, all we have to
> do is extract the column names:
>
> colnames(calc.jim)[colSums(abs(calc.jim)>0.8)<2]
>
> Of course, what you really meant could have been, "I want the column
> names of the variables with at most one absolute value greater than
> 0.8 ignoring the diagonal values because I don't care about those". If
> so:
>
> colnames(calc.jim)[colSums(abs(calc.jim)>0.8)<3]
>
> Any more tricks?
>
> Jim
>
> On Fri, Nov 15, 2019 at 8:17 AM Ana Marija
> wrote:
> >
> > what would be the approach to remove variable that has at least 2
> > correlation coefficients >0.8?
> > this is the whole output of the head()
> >
> > > head(calc.rho)
> > rs56192520 rs3764410 rs145984817 rs1807401 rs1807402 rs35350506
> > rs56192520 1.000 0.976 0.927 0.927 0.927 0.927
> > rs37644100.976 1.000 0.952 0.952 0.952 0.952
> > rs145984817 0.927 0.952 1.000 1.000 1.000 1.000
> > rs18074010.927 0.952 1.000 1.000 1.000 1.000
> > rs18074020.927 0.952 1.000 1.000 1.000 1.000
> > rs35350506 0.927 0.952 1.000 1.000 1.000 1.000
> > rs2089177 rs12325677 rs62064624 rs62064631 rs2349295 rs2174369
> > rs56192520 0.927 0.927 0.927 0.927 0.709 0.903
> > rs3764410 0.952 0.952 0.952 0.952 0.728 0.928
> > rs145984817 1.000 1.000 1.000 1.000 0.771 0.975
> > rs1807401 1.000 1.000 1.000 1.000 0.771 0.975
> > rs1807402 1.000 1.000 1.000 1.000 0.771 0.975
> > rs35350506 1.000 1.000 1.000 1.000 0.771 0.975
> > rs7218554 rs62064634 rs4360974 rs4527060 rs6502526 rs6502527
> > rs56192520 0.903 0.903 0.903 0.903 0.903 0.903
> > rs3764410 0.928 0.928 0.928 0.928 0.928 0.928
> > rs145984817 0.975 0.975 0.975 0.975 0.975 0.975
> > rs1807401 0.975 0.975 0.975 0.975 0.975 0.975
> > rs1807402 0.975 0.975 0.975 0.975 0.975 0.975
> > rs35350506 0.975 0.975 0.975 0.975 0.975 0.975
> > rs9900318 rs8069906 rs9908521 rs9908336 rs9908870 rs9895995
> > rs56192520 0.903 0.268 0.327 0.327 0.327 0.582
> > rs3764410 0.928 0.276 0.336 0.336 0.336 0.598
> > rs145984817 0.975 0.309 0.371 0.371 0.371 0.638
> > rs1807401 0.975 0.309 0.371 0.371 0.371 0.638
> > rs1807402 0.975 0.309 0.371 0.371 0.371 0.638
> > rs35350506 0.975 0.309 0.371 0.371 0.371 0.638
> > rs7211086 rs9905280 rs8073305 rs8072086 rs4312350 rs4313843
> > rs56192520 0.880 0.268 0.327 0.880 0.880 0.880
> > rs3764410 0.905 0.276 0.336 0.905 0.905 0.905
> > rs145984817 0.951 0.309 0.371 0.951 0.951 0.951
> > rs1807401 0.951 0.309 0.371 0.951 0.951 0.951
> > rs1807402 0.951 0.309 0.371 0.951 0.951 0.951
> > rs35350506 0.951 0.309 0.371 0.951 0.951 0.951
> > rs8069610 rs883504 rs8072394 rs4280293 rs4465638 rs12602378
> > rs56192520 0.5820.903 0.582 0.582 0.811 0.302
> > rs3764410 0.5980.928 0.598 0.598 0.836 0.311
> > rs145984817 0.6380.975 0.638 0.638 0.879 0.344
> > rs1807401 0.6380.975 0.638 0.638 0.879 0.344
> > rs1807402 0.6380.975 0.638 0.638 0.879 0.344
> > rs35350506 0.6380.975 0.638 0.638 0.879 0.344
> > rs9899059 rs6502530 rs4380085 rs6502532 rs4792798 rs4792799
> > rs56192520 0.302 0.309 0.834 0.251 0.063 0.063
> > rs3764410 0.311 0.318 0.858 0.259 0.080 0.080
> > rs145984817 0.344 0.352 0.902 0.291 0.086 0.086
> > rs1807401 0.344 0.352 0.902 0.291 0.086 0.086
> > rs1807402 0.344 0.352 0.902 0.291 0.086 0.086
> > rs35350506 0.344 0.352
Re: [R] Remove highly correlated variables from a data frame or matrix
I thought you were going to trick us. What I think you are asking now
is how to get the variable names in the columns that have at most one
_absolute_ value greater than 0.8. OK:
# I'm not going to try to recreate your correlation matrix
calc.jim<-matrix(runif(100,min=-1,max=1),nrow=10)
for(i in 1:10) calc.jim[i,i]<-1
rownames(calc.jim)<-<-colnames(calc.jim)<-paste0("rs",1:10)
Now that we have a plausible fake correlation matrix, all we have to
do is extract the column names:
colnames(calc.jim)[colSums(abs(calc.jim)>0.8)<2]
Of course, what you really meant could have been, "I want the column
names of the variables with at most one absolute value greater than
0.8 ignoring the diagonal values because I don't care about those". If
so:
colnames(calc.jim)[colSums(abs(calc.jim)>0.8)<3]
Any more tricks?
Jim
On Fri, Nov 15, 2019 at 8:17 AM Ana Marija wrote:
>
> what would be the approach to remove variable that has at least 2
> correlation coefficients >0.8?
> this is the whole output of the head()
>
> > head(calc.rho)
> rs56192520 rs3764410 rs145984817 rs1807401 rs1807402 rs35350506
> rs56192520 1.000 0.976 0.927 0.927 0.927 0.927
> rs37644100.976 1.000 0.952 0.952 0.952 0.952
> rs145984817 0.927 0.952 1.000 1.000 1.000 1.000
> rs18074010.927 0.952 1.000 1.000 1.000 1.000
> rs18074020.927 0.952 1.000 1.000 1.000 1.000
> rs35350506 0.927 0.952 1.000 1.000 1.000 1.000
> rs2089177 rs12325677 rs62064624 rs62064631 rs2349295 rs2174369
> rs56192520 0.927 0.927 0.927 0.927 0.709 0.903
> rs3764410 0.952 0.952 0.952 0.952 0.728 0.928
> rs145984817 1.000 1.000 1.000 1.000 0.771 0.975
> rs1807401 1.000 1.000 1.000 1.000 0.771 0.975
> rs1807402 1.000 1.000 1.000 1.000 0.771 0.975
> rs35350506 1.000 1.000 1.000 1.000 0.771 0.975
> rs7218554 rs62064634 rs4360974 rs4527060 rs6502526 rs6502527
> rs56192520 0.903 0.903 0.903 0.903 0.903 0.903
> rs3764410 0.928 0.928 0.928 0.928 0.928 0.928
> rs145984817 0.975 0.975 0.975 0.975 0.975 0.975
> rs1807401 0.975 0.975 0.975 0.975 0.975 0.975
> rs1807402 0.975 0.975 0.975 0.975 0.975 0.975
> rs35350506 0.975 0.975 0.975 0.975 0.975 0.975
> rs9900318 rs8069906 rs9908521 rs9908336 rs9908870 rs9895995
> rs56192520 0.903 0.268 0.327 0.327 0.327 0.582
> rs3764410 0.928 0.276 0.336 0.336 0.336 0.598
> rs145984817 0.975 0.309 0.371 0.371 0.371 0.638
> rs1807401 0.975 0.309 0.371 0.371 0.371 0.638
> rs1807402 0.975 0.309 0.371 0.371 0.371 0.638
> rs35350506 0.975 0.309 0.371 0.371 0.371 0.638
> rs7211086 rs9905280 rs8073305 rs8072086 rs4312350 rs4313843
> rs56192520 0.880 0.268 0.327 0.880 0.880 0.880
> rs3764410 0.905 0.276 0.336 0.905 0.905 0.905
> rs145984817 0.951 0.309 0.371 0.951 0.951 0.951
> rs1807401 0.951 0.309 0.371 0.951 0.951 0.951
> rs1807402 0.951 0.309 0.371 0.951 0.951 0.951
> rs35350506 0.951 0.309 0.371 0.951 0.951 0.951
> rs8069610 rs883504 rs8072394 rs4280293 rs4465638 rs12602378
> rs56192520 0.5820.903 0.582 0.582 0.811 0.302
> rs3764410 0.5980.928 0.598 0.598 0.836 0.311
> rs145984817 0.6380.975 0.638 0.638 0.879 0.344
> rs1807401 0.6380.975 0.638 0.638 0.879 0.344
> rs1807402 0.6380.975 0.638 0.638 0.879 0.344
> rs35350506 0.6380.975 0.638 0.638 0.879 0.344
> rs9899059 rs6502530 rs4380085 rs6502532 rs4792798 rs4792799
> rs56192520 0.302 0.309 0.834 0.251 0.063 0.063
> rs3764410 0.311 0.318 0.858 0.259 0.080 0.080
> rs145984817 0.344 0.352 0.902 0.291 0.086 0.086
> rs1807401 0.344 0.352 0.902 0.291 0.086 0.086
> rs1807402 0.344 0.352 0.902 0.291 0.086 0.086
> rs35350506 0.344 0.352 0.902 0.291 0.086 0.086
> rs4316813 rs148563931 rs74751226 rs8068857 rs8069441 rs77397878
> rs56192520 0.006 0.006 0.006 0.006 0.006 0.006
> rs3764410 0.006 0.006 0.006 0.006 0.006 0.006
> rs145984817 0.006 0.006 0.006
Re: [R] Remove highly correlated variables from a data frame or matrix
Hi Ana,
Rather than addressing the question of why you want to do this, Let's
get make the question easier to answer:
calc.rho<-matrix(c(0.903,0.268,0.327,0.327,0.327,0.582,
0.928,0.276,0.336,0.336,0.336,0.598,
0.975,0.309,0.371,0.371,0.371,0.638,
0.975,0.309,0.371,0.371,0.371,0.638,
0.975,0.309,0.371,0.371,0.371,0.638,
0.975,0.309,0.371,0.371,0.371,0.638),ncol=6,byrow=TRUE)
rnames<-c("rs56192520","rs3764410","rs145984817","rs1807401",
"rs1807402","rs35350506")
rownames(calc.rho)<-rnames
cnames<-c("rs9900318","rs8069906","rs9908521","rs9908336",
"rs9908870","rs9895995")
colnames(calc.rho)<-cnames
Now if you just want a vector of the values less than 0.8, it's trivial:
calc.rho[calc.rho<0.8]
However, based on your previous questions, I suspect you want
something else. Maybe the pairs of row/column names that correspond to
the values less than 0.8. To ensure that you haven't tricked us by not
including columns in which values range around 0.8, I'll do it this
way:
# make the new variable name possible to decode
calc.lt.8<-calc.rho<0.8
varnames.lt.8<-data.frame(var1=NA,var2=NA)
for(row in 1:nrow(calc.rho)) {
for(col in 1:ncol(calc.rho))
if(calc.lt.8[row,col])
varnames.lt.8<-rbind(varnames.lt.8,c(rnames[row],cnames[col]))
}
# now get rid of the first row of NA values
varnames.lt.8<-varnames.lt.8[-1,]
Clunky, but effective. You now have those variable pairs that you may
want. Let us know in the next episode of this soap operation.
Jim
On Fri, Nov 15, 2019 at 5:50 AM Ana Marija wrote:
>
> Hello,
>
> I have a data frame like this (a matrix):
> head(calc.rho)
> rs9900318 rs8069906 rs9908521 rs9908336 rs9908870 rs9895995
> rs56192520 0.903 0.268 0.327 0.327 0.327 0.582
> rs3764410 0.928 0.276 0.336 0.336 0.336 0.598
> rs145984817 0.975 0.309 0.371 0.371 0.371 0.638
> rs1807401 0.975 0.309 0.371 0.371 0.371 0.638
> rs1807402 0.975 0.309 0.371 0.371 0.371 0.638
> rs35350506 0.975 0.309 0.371 0.371 0.371 0.638
>
> > dim(calc.rho)
> [1] 246 246
>
> I would like to remove from this data all highly correlated variables,
> with correlation more than 0.8
>
> I tried this:
>
> > data<- calc.rho[,!apply(calc.rho,2,function(x) any(abs(x) > 0.80))]
> > dim(data)
> [1] 246 0
>
> Can you please advise,
>
> Thanks
> Ana
>
> But this removes everything.
>
> __
> R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
> 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@r-project.org mailing list -- To UNSUBSCRIBE and more, see
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.
Re: [R] Remove highly correlated variables from a data frame or matrix
what would be the approach to remove variable that has at least 2 correlation coefficients >0.8? this is the whole output of the head() > head(calc.rho) rs56192520 rs3764410 rs145984817 rs1807401 rs1807402 rs35350506 rs56192520 1.000 0.976 0.927 0.927 0.927 0.927 rs37644100.976 1.000 0.952 0.952 0.952 0.952 rs145984817 0.927 0.952 1.000 1.000 1.000 1.000 rs18074010.927 0.952 1.000 1.000 1.000 1.000 rs18074020.927 0.952 1.000 1.000 1.000 1.000 rs35350506 0.927 0.952 1.000 1.000 1.000 1.000 rs2089177 rs12325677 rs62064624 rs62064631 rs2349295 rs2174369 rs56192520 0.927 0.927 0.927 0.927 0.709 0.903 rs3764410 0.952 0.952 0.952 0.952 0.728 0.928 rs145984817 1.000 1.000 1.000 1.000 0.771 0.975 rs1807401 1.000 1.000 1.000 1.000 0.771 0.975 rs1807402 1.000 1.000 1.000 1.000 0.771 0.975 rs35350506 1.000 1.000 1.000 1.000 0.771 0.975 rs7218554 rs62064634 rs4360974 rs4527060 rs6502526 rs6502527 rs56192520 0.903 0.903 0.903 0.903 0.903 0.903 rs3764410 0.928 0.928 0.928 0.928 0.928 0.928 rs145984817 0.975 0.975 0.975 0.975 0.975 0.975 rs1807401 0.975 0.975 0.975 0.975 0.975 0.975 rs1807402 0.975 0.975 0.975 0.975 0.975 0.975 rs35350506 0.975 0.975 0.975 0.975 0.975 0.975 rs9900318 rs8069906 rs9908521 rs9908336 rs9908870 rs9895995 rs56192520 0.903 0.268 0.327 0.327 0.327 0.582 rs3764410 0.928 0.276 0.336 0.336 0.336 0.598 rs145984817 0.975 0.309 0.371 0.371 0.371 0.638 rs1807401 0.975 0.309 0.371 0.371 0.371 0.638 rs1807402 0.975 0.309 0.371 0.371 0.371 0.638 rs35350506 0.975 0.309 0.371 0.371 0.371 0.638 rs7211086 rs9905280 rs8073305 rs8072086 rs4312350 rs4313843 rs56192520 0.880 0.268 0.327 0.880 0.880 0.880 rs3764410 0.905 0.276 0.336 0.905 0.905 0.905 rs145984817 0.951 0.309 0.371 0.951 0.951 0.951 rs1807401 0.951 0.309 0.371 0.951 0.951 0.951 rs1807402 0.951 0.309 0.371 0.951 0.951 0.951 rs35350506 0.951 0.309 0.371 0.951 0.951 0.951 rs8069610 rs883504 rs8072394 rs4280293 rs4465638 rs12602378 rs56192520 0.5820.903 0.582 0.582 0.811 0.302 rs3764410 0.5980.928 0.598 0.598 0.836 0.311 rs145984817 0.6380.975 0.638 0.638 0.879 0.344 rs1807401 0.6380.975 0.638 0.638 0.879 0.344 rs1807402 0.6380.975 0.638 0.638 0.879 0.344 rs35350506 0.6380.975 0.638 0.638 0.879 0.344 rs9899059 rs6502530 rs4380085 rs6502532 rs4792798 rs4792799 rs56192520 0.302 0.309 0.834 0.251 0.063 0.063 rs3764410 0.311 0.318 0.858 0.259 0.080 0.080 rs145984817 0.344 0.352 0.902 0.291 0.086 0.086 rs1807401 0.344 0.352 0.902 0.291 0.086 0.086 rs1807402 0.344 0.352 0.902 0.291 0.086 0.086 rs35350506 0.344 0.352 0.902 0.291 0.086 0.086 rs4316813 rs148563931 rs74751226 rs8068857 rs8069441 rs77397878 rs56192520 0.006 0.006 0.006 0.006 0.006 0.006 rs3764410 0.006 0.006 0.006 0.006 0.006 0.006 rs145984817 0.006 0.006 0.006 0.006 0.006 0.006 rs1807401 0.006 0.006 0.006 0.006 0.006 0.006 rs1807402 0.006 0.006 0.006 0.006 0.006 0.006 rs35350506 0.006 0.006 0.006 0.006 0.006 0.006 rs75339756 rs4608391 rs79569548 rs4275914 rs11870422 rs8075751 rs56192520 0.006 0.006 0.006 0.044 0.007 0.004 rs37644100.006 0.006 0.006 0.042 0.005 0.005 rs145984817 0.006 0.006 0.006 0.047 0.002 0.015 rs18074010.006 0.006 0.006 0.047 0.002 0.015 rs18074020.006 0.006 0.006 0.047 0.002 0.015 rs35350506 0.006 0.006 0.006 0.047 0.002 0.015 rs11658904 rs138437542 rs80344434 rs7222311 rs7221842 rs7223686 rs56192520 0.003 0.004 0.004 0.033 0.009 0.000 rs37644100.004 0.004 0.004
Re: [R] Remove highly correlated variables from a data frame or matrix
That's assuming your data was returned by head(). __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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.
Re: [R] Remove highly correlated variables from a data frame or matrix
> I basically want to remove all entries for pairs which have value in > between them (correlation calculated not in R, bit it is correlation, > r2) > so for example I would not keep: rs883504 because it has r2>0.8 for > all those rs... I'm still not sure what "remove all entries" means? In your example rs883504, has all correlation coefficients > 0.8, in the data returned by head(). However, most of its correlation coefficients are < 0.8, if you include the entire matrix. If you remove a variable that has at least one correlation coefficient > 0.8, you would remove all the variables. However, if you remove a variable that has all correlation coefficients > 0.8, you would (probably) remove no variables. __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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.
Re: [R] Remove highly correlated variables from a data frame or matrix
Sorry, but I don't understand your question. When I first looked at this, I thought it was a correlation (or covariance) matrix. e.g. > cor (quakes) > cov (quakes) However, your row and column variables are different, implying two different data sets. Also, some of the (correlation?) coefficients are the same, implying that some of the variables are the same, or very close. Also, note that a matrix is not a data.frame. > I have a data frame like this (a matrix): > head(calc.rho) > rs9900318 rs8069906 rs9908521 rs9908336 rs9908870 rs9895995 > rs56192520 0.903 0.268 0.327 0.327 0.327 0.582 > rs3764410 0.928 0.276 0.336 0.336 0.336 0.598 > rs145984817 0.975 0.309 0.371 0.371 0.371 0.638 > rs1807401 0.975 0.309 0.371 0.371 0.371 0.638 > rs1807402 0.975 0.309 0.371 0.371 0.371 0.638 > rs35350506 0.975 0.309 0.371 0.371 0.371 0.638 > > dim(calc.rho) > [1] 246 246 > I would like to remove from this data all highly correlated variables, > with correlation more than 0.8 __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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.
Re: [R] Remove highly correlated variables from a data frame or matrix
I don't understand. I have to keep only pairs of variables with correlation less than 0.8 in order to proceed with some calculations On Thu, Nov 14, 2019 at 2:09 PM Bert Gunter wrote: > > Obvious advice: > > DON'T DO THIS! > > Bert Gunter > > "The trouble with having an open mind is that people keep coming along and > sticking things into it." > -- Opus (aka Berkeley Breathed in his "Bloom County" comic strip ) > > > On Thu, Nov 14, 2019 at 10:50 AM Ana Marija > wrote: >> >> Hello, >> >> I have a data frame like this (a matrix): >> head(calc.rho) >> rs9900318 rs8069906 rs9908521 rs9908336 rs9908870 rs9895995 >> rs56192520 0.903 0.268 0.327 0.327 0.327 0.582 >> rs3764410 0.928 0.276 0.336 0.336 0.336 0.598 >> rs145984817 0.975 0.309 0.371 0.371 0.371 0.638 >> rs1807401 0.975 0.309 0.371 0.371 0.371 0.638 >> rs1807402 0.975 0.309 0.371 0.371 0.371 0.638 >> rs35350506 0.975 0.309 0.371 0.371 0.371 0.638 >> >> > dim(calc.rho) >> [1] 246 246 >> >> I would like to remove from this data all highly correlated variables, >> with correlation more than 0.8 >> >> I tried this: >> >> > data<- calc.rho[,!apply(calc.rho,2,function(x) any(abs(x) > 0.80))] >> > dim(data) >> [1] 246 0 >> >> Can you please advise, >> >> Thanks >> Ana >> >> But this removes everything. >> >> __ >> R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see >> 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@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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.
Re: [R] Remove highly correlated variables from a data frame or matrix
Obvious advice: DON'T DO THIS! Bert Gunter "The trouble with having an open mind is that people keep coming along and sticking things into it." -- Opus (aka Berkeley Breathed in his "Bloom County" comic strip ) On Thu, Nov 14, 2019 at 10:50 AM Ana Marija wrote: > Hello, > > I have a data frame like this (a matrix): > head(calc.rho) > rs9900318 rs8069906 rs9908521 rs9908336 rs9908870 rs9895995 > rs56192520 0.903 0.268 0.327 0.327 0.327 0.582 > rs3764410 0.928 0.276 0.336 0.336 0.336 0.598 > rs145984817 0.975 0.309 0.371 0.371 0.371 0.638 > rs1807401 0.975 0.309 0.371 0.371 0.371 0.638 > rs1807402 0.975 0.309 0.371 0.371 0.371 0.638 > rs35350506 0.975 0.309 0.371 0.371 0.371 0.638 > > > dim(calc.rho) > [1] 246 246 > > I would like to remove from this data all highly correlated variables, > with correlation more than 0.8 > > I tried this: > > > data<- calc.rho[,!apply(calc.rho,2,function(x) any(abs(x) > 0.80))] > > dim(data) > [1] 246 0 > > Can you please advise, > > Thanks > Ana > > But this removes everything. > > __ > R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see > 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. > [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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] Remove highly correlated variables from a data frame or matrix
Hello, I have a data frame like this (a matrix): head(calc.rho) rs9900318 rs8069906 rs9908521 rs9908336 rs9908870 rs9895995 rs56192520 0.903 0.268 0.327 0.327 0.327 0.582 rs3764410 0.928 0.276 0.336 0.336 0.336 0.598 rs145984817 0.975 0.309 0.371 0.371 0.371 0.638 rs1807401 0.975 0.309 0.371 0.371 0.371 0.638 rs1807402 0.975 0.309 0.371 0.371 0.371 0.638 rs35350506 0.975 0.309 0.371 0.371 0.371 0.638 > dim(calc.rho) [1] 246 246 I would like to remove from this data all highly correlated variables, with correlation more than 0.8 I tried this: > data<- calc.rho[,!apply(calc.rho,2,function(x) any(abs(x) > 0.80))] > dim(data) [1] 246 0 Can you please advise, Thanks Ana But this removes everything. __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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.
