Sanjay Kumar Jaiswal
2017-Jul-18 09:08 UTC
[R] Redundancy canonical analysis plot problem in 3D using VEGAN, RGL, SCATTERPLOT3D and SFSMISC
Hello Sir I am getting problem in plotting in CCA . Could you please help me? I wrote the below command but I don't know why it is taking only first 5 env data rather than all 9.> strain.data <- read.xlsx("Dee rhiz.xlsx", sheetName="strain", header = T, row.names = 1) > env.data <- read.xlsx("Dee rhiz.xlsx", sheetName="env", header = T, row.names = 1) > strain.cca <- cca(strain.data ~ Ph+TotalN+Organicmatter+Ca+K+Na+P+Cu+Mn, data=env.data) > strain.ccaCall: cca(formula = strain.data ~ Ph + TotalN + Organicmatter + Ca + K + Na + P + Cu + Mn, data = env.data) Inertia Proportion Rank Total 5 1 Constrained 5 1 5 Unconstrained 0 0 0 Inertia is mean squared contingency coefficient Some constraints were aliased because they were collinear (redundant) Eigenvalues for constrained axes: CCA1 CCA2 CCA3 CCA4 CCA5 1 1 1 1 1> plot(strain.cca)> summary (strain.cca)Call: cca(formula = strain.data ~ Ph + TotalN + Organicmatter + Ca + K + Na + P + Cu + Mn, data = env.data) Partitioning of mean squared contingency coefficient: Inertia Proportion Total 5 1 Constrained 5 1 Unconstrained 0 0 Eigenvalues, and their contribution to the mean squared contingency coefficient Importance of components: CCA1 CCA2 CCA3 CCA4 CCA5 Eigenvalue 1.0 1.0 1.0 1.0 1.0 0 Proportion Explained 0.2 0.2 0.2 0.2 0.2 0 Cumulative Proportion 0.2 0.4 0.6 0.8 1.0 1 Accumulated constrained eigenvalues Importance of components: CCA1 CCA2 CCA3 CCA4 CCA5 Eigenvalue 1.0 1.0 1.0 1.0 1.0 Proportion Explained 0.2 0.2 0.2 0.2 0.2 Cumulative Proportion 0.2 0.4 0.6 0.8 1.0 Biplot scores for constraining variables CCA1 CCA2 CCA3 CCA4 CCA5 Ph 0.29757 0.85775 -0.3364 0.2242 -0.11088 TotalN -0.01537 -0.67797 0.6132 0.2831 0.28985 Organicmatter 0.14618 0.06462 0.8320 0.3515 0.39827 Ca 0.08310 -0.41940 0.3858 0.8116 0.09834 K 0.37548 0.38360 0.6849 -0.4172 0.26222 ________________________________ ---------------------------------------------------------------------------------- Tshwane University of Technology ---------------------------------------------------------------------------------- This email is sent and received in terms of the Electronic Communications Policy of Tshwane University of Technology. In line with this policy, this email is private, privileged and confidential. The full text of the Electronic Mail Disclaimer can be seen on the TUT web site at http://www.tut.ac.za/Other/disclaimer/Pages/default.aspx or obtained by phoning (012) 382-5911 ________________________________ ---------------------------------------------------------------------------------- Tshwane University of Technology ---------------------------------------------------------------------------------- This email is sent and received in terms of the Electronic Communications Policy of Tshwane University of Technology. In line with this policy, this email is private, privileged and confidential. The full text of the Electronic Mail Disclaimer can be seen on the TUT web site at http://www.tut.ac.za/Other/disclaimer/Pages/default.aspx or obtained by phoning (012) 382-5911 [[alternative HTML version deleted]]
David L Carlson
2017-Jul-18 15:24 UTC
[R] Redundancy canonical analysis plot problem in 3D using VEGAN, RGL, SCATTERPLOT3D and SFSMISC
We don't have enough information to replicate your results, but the warning in the output is suggestive: "Some constraints were aliased because they were collinear (redundant)". Are some of your columns perfectly correlated with other columns? This could easily happen if there are more columns than rows. ------------------------------------- David L Carlson Department of Anthropology Texas A&M University College Station, TX 77840-4352 -----Original Message----- From: R-help [mailto:r-help-bounces at r-project.org] On Behalf Of Sanjay Kumar Jaiswal Sent: Tuesday, July 18, 2017 4:08 AM To: r-help at r-project.org Subject: [R] Redundancy canonical analysis plot problem in 3D using VEGAN, RGL, SCATTERPLOT3D and SFSMISC Hello Sir I am getting problem in plotting in CCA . Could you please help me? I wrote the below command but I don't know why it is taking only first 5 env data rather than all 9.> strain.data <- read.xlsx("Dee rhiz.xlsx", sheetName="strain", header = T, row.names = 1) > env.data <- read.xlsx("Dee rhiz.xlsx", sheetName="env", header = T, row.names = 1) > strain.cca <- cca(strain.data ~ Ph+TotalN+Organicmatter+Ca+K+Na+P+Cu+Mn, data=env.data) > strain.ccaCall: cca(formula = strain.data ~ Ph + TotalN + Organicmatter + Ca + K + Na + P + Cu + Mn, data = env.data) Inertia Proportion Rank Total 5 1 Constrained 5 1 5 Unconstrained 0 0 0 Inertia is mean squared contingency coefficient Some constraints were aliased because they were collinear (redundant) Eigenvalues for constrained axes: CCA1 CCA2 CCA3 CCA4 CCA5 1 1 1 1 1> plot(strain.cca)> summary (strain.cca)Call: cca(formula = strain.data ~ Ph + TotalN + Organicmatter + Ca + K + Na + P + Cu + Mn, data = env.data) Partitioning of mean squared contingency coefficient: Inertia Proportion Total 5 1 Constrained 5 1 Unconstrained 0 0 Eigenvalues, and their contribution to the mean squared contingency coefficient Importance of components: CCA1 CCA2 CCA3 CCA4 CCA5 Eigenvalue 1.0 1.0 1.0 1.0 1.0 0 Proportion Explained 0.2 0.2 0.2 0.2 0.2 0 Cumulative Proportion 0.2 0.4 0.6 0.8 1.0 1 Accumulated constrained eigenvalues Importance of components: CCA1 CCA2 CCA3 CCA4 CCA5 Eigenvalue 1.0 1.0 1.0 1.0 1.0 Proportion Explained 0.2 0.2 0.2 0.2 0.2 Cumulative Proportion 0.2 0.4 0.6 0.8 1.0 Biplot scores for constraining variables CCA1 CCA2 CCA3 CCA4 CCA5 Ph 0.29757 0.85775 -0.3364 0.2242 -0.11088 TotalN -0.01537 -0.67797 0.6132 0.2831 0.28985 Organicmatter 0.14618 0.06462 0.8320 0.3515 0.39827 Ca 0.08310 -0.41940 0.3858 0.8116 0.09834 K 0.37548 0.38360 0.6849 -0.4172 0.26222 ________________________________ ---------------------------------------------------------------------------------- Tshwane University of Technology ---------------------------------------------------------------------------------- This email is sent and received in terms of the Electronic Communications Policy of Tshwane University of Technology. In line with this policy, this email is private, privileged and confidential. The full text of the Electronic Mail Disclaimer can be seen on the TUT web site at http://www.tut.ac.za/Other/disclaimer/Pages/default.aspx or obtained by phoning (012) 382-5911 ________________________________ ---------------------------------------------------------------------------------- Tshwane University of Technology ---------------------------------------------------------------------------------- This email is sent and received in terms of the Electronic Communications Policy of Tshwane University of Technology. In line with this policy, this email is private, privileged and confidential. The full text of the Electronic Mail Disclaimer can be seen on the TUT web site at http://www.tut.ac.za/Other/disclaimer/Pages/default.aspx or obtained by phoning (012) 382-5911 [[alternative HTML version deleted]] ______________________________________________ R-help at 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.
Jeff Newmiller
2017-Jul-18 15:38 UTC
[R] Redundancy canonical analysis plot problem in 3D using VEGAN, RGL, SCATTERPLOT3D and SFSMISC
I don't know much about what you are doing with your data, but I do know that your example is not reproducible [1][2][3]. It is very important to be clear both to yourself and to anyone you ask to help you what your data are like. Details like what the column names are, whether they are numeric, character, factor, etc., can completely alter the result. The dput() function can be used to share just enough of your data or a simulated version of it so that we can run your statements also, or point out that your data were imported incorrectly in the first place. Also, do read the Posting Guide mentioned in the footer of this email. This is a plain text mailing list so what you saw when you sent it (HTML formatted) is not what we saw (see below)... but if you post in plain text format we are much more likely to solve your problem without back and forth about what you really meant. [1] http://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example [2] http://adv-r.had.co.nz/Reproducibility.html [3] https://cran.r-project.org/web/packages/reprex/index.html (read the vignette) -- Sent from my phone. Please excuse my brevity. On July 18, 2017 2:08:04 AM PDT, Sanjay Kumar Jaiswal <JaiswalSK at tut.ac.za> wrote:>Hello Sir > >I am getting problem in plotting in CCA . Could you please help me? I >wrote the below command but I don't know why it is taking only first 5 >env data rather than all 9. > >> strain.data <- read.xlsx("Dee rhiz.xlsx", sheetName="strain", header >= T, row.names = 1) >> env.data <- read.xlsx("Dee rhiz.xlsx", sheetName="env", header = T, >row.names = 1) >> strain.cca <- cca(strain.data ~ >Ph+TotalN+Organicmatter+Ca+K+Na+P+Cu+Mn, data=env.data) >> strain.cca >Call: cca(formula = strain.data ~ Ph + TotalN + Organicmatter + Ca + K >+ Na + P >+ Cu + Mn, data = env.data) > > Inertia Proportion Rank >Total 5 1 >Constrained 5 1 5 >Unconstrained 0 0 0 >Inertia is mean squared contingency coefficient >Some constraints were aliased because they were collinear (redundant) > >Eigenvalues for constrained axes: >CCA1 CCA2 CCA3 CCA4 CCA5 > 1 1 1 1 1 > > >> plot(strain.cca) > >> summary (strain.cca) > > > >Call: > >cca(formula = strain.data ~ Ph + TotalN + Organicmatter + Ca + K + >Na + P + Cu + Mn, data = env.data) > > > >Partitioning of mean squared contingency coefficient: > > Inertia Proportion > >Total 5 1 > >Constrained 5 1 > >Unconstrained 0 0 > > > >Eigenvalues, and their contribution to the mean squared contingency >coefficient > > > >Importance of components: > > CCA1 CCA2 CCA3 CCA4 CCA5 > >Eigenvalue 1.0 1.0 1.0 1.0 1.0 0 > >Proportion Explained 0.2 0.2 0.2 0.2 0.2 0 > >Cumulative Proportion 0.2 0.4 0.6 0.8 1.0 1 > > > >Accumulated constrained eigenvalues > >Importance of components: > > CCA1 CCA2 CCA3 CCA4 CCA5 > >Eigenvalue 1.0 1.0 1.0 1.0 1.0 > >Proportion Explained 0.2 0.2 0.2 0.2 0.2 > >Cumulative Proportion 0.2 0.4 0.6 0.8 1.0 > > >Biplot scores for constraining variables > > > > CCA1 CCA2 CCA3 CCA4 CCA5 > >Ph 0.29757 0.85775 -0.3364 0.2242 -0.11088 > >TotalN -0.01537 -0.67797 0.6132 0.2831 0.28985 > >Organicmatter 0.14618 0.06462 0.8320 0.3515 0.39827 > >Ca 0.08310 -0.41940 0.3858 0.8116 0.09834 > >K 0.37548 0.38360 0.6849 -0.4172 0.26222 > > >________________________________ > >---------------------------------------------------------------------------------- >Tshwane University of Technology >---------------------------------------------------------------------------------- >This email is sent and received in terms of the Electronic >Communications Policy of Tshwane University of Technology. >In line with this policy, this email is private, privileged and >confidential. The full text of the Electronic Mail Disclaimer >can be seen on the TUT web site at >http://www.tut.ac.za/Other/disclaimer/Pages/default.aspx >or obtained by phoning (012) 382-5911 > >________________________________ > >---------------------------------------------------------------------------------- >Tshwane University of Technology >---------------------------------------------------------------------------------- >This email is sent and received in terms of the Electronic >Communications Policy of Tshwane University of Technology. >In line with this policy, this email is private, privileged and >confidential. The full text of the Electronic Mail Disclaimer >can be seen on the TUT web site at >http://www.tut.ac.za/Other/disclaimer/Pages/default.aspx >or obtained by phoning (012) 382-5911 > > [[alternative HTML version deleted]] > >______________________________________________ >R-help at 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.
David L Carlson
2017-Jul-19 02:11 UTC
[R] Redundancy canonical analysis plot problem in 3D using VEGAN, RGL, SCATTERPLOT3D and SFSMISC
We need to keep the discussion on the list. When I run your code, there are
several problems.
strain.data <- read.xlsx("Dee rhiz.xlsx", sheetName
="strain", header = T, row.names = 1)
str(strain.data) # lists 9 columns at the end with all NAs
strain.data1 <- (strain.data, sqrt.dist = TRUE) # this is not a valid R line.
I get
Error: unexpected ',' in "strain.data1 <- (strain.data,"
strain.cca1 <- cca(log1p(strain.data) ~ Ph + TotalN + Organicmatter + Ca + K
+ Na + P + Cu + Mn, env.data) # More errors resulting from all the NA values
Error in Math.data.frame(strain.data) :
non-numeric variable in data frame:
NA..1NA..2NA..3NA..4NA..5NA..6NA..7NA..8NA..9
You have only 6 observations. In strain.data, since each column has a single 1
and the other 5 rows are 0's. Assuming that the columns are taxa, each taxon
is found at only one site. I suspect there is a problem with your data or with
the way you have coded the data.
David L Carlson
-----Original Message-----
From: Sanjay Kumar Jaiswal [mailto:JaiswalSK at tut.ac.za]
Sent: Tuesday, July 18, 2017 4:27 PM
To: David L Carlson <dcarlson at tamu.edu>
Subject: RE: [R] Redundancy canonical analysis plot problem in 3D using VEGAN,
RGL, SCATTERPLOT3D and SFSMISC
Dear Sir
I am attaching herewith data which I used to analyse. Please correct the command
if you find anything wrong with it. I am sending herewith command line too.
Please see it and suggest me. I will be very grateful for the same.
getwd()
setwd("C:\\Users\\sanju\\Documents\\Dee")
library(xlsx)
strain.data <- read.xlsx("Dee rhiz.xlsx",
sheetName="strain", header = T, row.names = 1)
strain.data1 <- (strain.data, sqrt.dist = TRUE)
env.data <- read.xlsx("Dee rhiz.xlsx", sheetName="env",
header = T, row.names = 1)
library(vegan)
strain.cca1 <- cca(log1p(strain.data) ~ Ph + TotalN + Organicmatter + Ca + K
+ Na + P + Cu + Mn, env.data)
strain.cca1
strain.cca1plot <- plot(strain.cca1, type = "n", scaling = 3)
text(strain.cca1, display = "cn")
points(strain.cca1, display = "sites", pch=21, col="black",
bg="grey", cex=1.2)
text(strain.cca1, "species", col="black", cex=0.8)
summary(strain.cca1)
Regards
Sanjay
-----Original Message-----
From: David L Carlson [mailto:dcarlson at tamu.edu]
Sent: 18 July 2017 20:55
To: Sanjay Kumar Jaiswal; r-help at r-project.org
Subject: RE: [R] Redundancy canonical analysis plot problem in 3D using VEGAN,
RGL, SCATTERPLOT3D and SFSMISC
We don't have enough information to replicate your results, but the warning
in the output is suggestive: "Some constraints were aliased because they
were collinear (redundant)".
Are some of your columns perfectly correlated with other columns? This could
easily happen if there are more columns than rows.
-------------------------------------
David L Carlson
Department of Anthropology
Texas A&M University
College Station, TX 77840-4352
-----Original Message-----
From: R-help [mailto:r-help-bounces at r-project.org] On Behalf Of Sanjay Kumar
Jaiswal
Sent: Tuesday, July 18, 2017 4:08 AM
To: r-help at r-project.org
Subject: [R] Redundancy canonical analysis plot problem in 3D using VEGAN, RGL,
SCATTERPLOT3D and SFSMISC
Hello Sir
I am getting problem in plotting in CCA . Could you please help me? I wrote the
below command but I don't know why it is taking only first 5 env data rather
than all 9.
> strain.data <- read.xlsx("Dee rhiz.xlsx",
sheetName="strain", header > T, row.names = 1) env.data <-
read.xlsx("Dee rhiz.xlsx",
> sheetName="env", header = T, row.names = 1) strain.cca <-
> cca(strain.data ~ Ph+TotalN+Organicmatter+Ca+K+Na+P+Cu+Mn,
> data=env.data) strain.cca
Call: cca(formula = strain.data ~ Ph + TotalN + Organicmatter + Ca + K + Na + P
+ Cu + Mn, data = env.data)
Inertia Proportion Rank
Total 5 1
Constrained 5 1 5
Unconstrained 0 0 0
Inertia is mean squared contingency coefficient Some constraints were aliased
because they were collinear (redundant)
Eigenvalues for constrained axes:
CCA1 CCA2 CCA3 CCA4 CCA5
1 1 1 1 1
> plot(strain.cca)
> summary (strain.cca)
Call:
cca(formula = strain.data ~ Ph + TotalN + Organicmatter + Ca + K + Na + P +
Cu + Mn, data = env.data)
Partitioning of mean squared contingency coefficient:
Inertia Proportion
Total 5 1
Constrained 5 1
Unconstrained 0 0
Eigenvalues, and their contribution to the mean squared contingency coefficient
Importance of components:
CCA1 CCA2 CCA3 CCA4 CCA5
Eigenvalue 1.0 1.0 1.0 1.0 1.0 0
Proportion Explained 0.2 0.2 0.2 0.2 0.2 0
Cumulative Proportion 0.2 0.4 0.6 0.8 1.0 1
Accumulated constrained eigenvalues
Importance of components:
CCA1 CCA2 CCA3 CCA4 CCA5
Eigenvalue 1.0 1.0 1.0 1.0 1.0
Proportion Explained 0.2 0.2 0.2 0.2 0.2
Cumulative Proportion 0.2 0.4 0.6 0.8 1.0
Biplot scores for constraining variables
CCA1 CCA2 CCA3 CCA4 CCA5
Ph 0.29757 0.85775 -0.3364 0.2242 -0.11088
TotalN -0.01537 -0.67797 0.6132 0.2831 0.28985
Organicmatter 0.14618 0.06462 0.8320 0.3515 0.39827
Ca 0.08310 -0.41940 0.3858 0.8116 0.09834
K 0.37548 0.38360 0.6849 -0.4172 0.26222
________________________________
----------------------------------------------------------------------------------
Tshwane University of Technology
----------------------------------------------------------------------------------
This email is sent and received in terms of the Electronic Communications Policy
of Tshwane University of Technology.
In line with this policy, this email is private, privileged and confidential.
The full text of the Electronic Mail Disclaimer can be seen on the TUT web site
at http://www.tut.ac.za/Other/disclaimer/Pages/default.aspx
or obtained by phoning (012) 382-5911
________________________________
----------------------------------------------------------------------------------
Tshwane University of Technology
----------------------------------------------------------------------------------
This email is sent and received in terms of the Electronic Communications Policy
of Tshwane University of Technology.
In line with this policy, this email is private, privileged and confidential.
The full text of the Electronic Mail Disclaimer can be seen on the TUT web site
at http://www.tut.ac.za/Other/disclaimer/Pages/default.aspx
or obtained by phoning (012) 382-5911
[[alternative HTML version deleted]]
______________________________________________
R-help at 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.
________________________________
----------------------------------------------------------------------------------
Tshwane University of Technology
----------------------------------------------------------------------------------
This email is sent and received in terms of the Electronic
Communications Policy of Tshwane University of Technology.
In line with this policy, this email is private, privileged and
confidential. The full text of the Electronic Mail Disclaimer
can be seen on the TUT web site at
http://www.tut.ac.za/Other/disclaimer/Pages/default.aspx
or obtained by phoning (012) 382-5911
________________________________
----------------------------------------------------------------------------------
Tshwane University of Technology
----------------------------------------------------------------------------------
This email is sent and received in terms of the Electronic
Communications Policy of Tshwane University of Technology.
In line with this policy, this email is private, privileged and
confidential. The full text of the Electronic Mail Disclaimer
can be seen on the TUT web site at
http://www.tut.ac.za/Other/disclaimer/Pages/default.aspx
or obtained by phoning (012) 382-5911