Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
H
HIDDEN
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Iterations
Wiki
Requirements
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Locked files
Build
Pipelines
Jobs
Pipeline schedules
Test cases
Artifacts
Deploy
Releases
Package registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Code review analytics
Issue analytics
Insights
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
sPlot
HIDDEN
Commits
32cd730d
Commit
32cd730d
authored
4 years ago
by
Francesco Sabatini
Browse files
Options
Downloads
Patches
Plain Diff
Aligned to completed trait matrix data
parent
680c334b
Branches
Branches containing commit
No related tags found
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
00_Mesobromion_DataPreparation.R
+41
-23
41 additions, 23 deletions
00_Mesobromion_DataPreparation.R
with
41 additions
and
23 deletions
00_Mesobromion_DataPreparation.R
+
41
−
23
View file @
32cd730d
...
@@ -12,9 +12,10 @@ source("99_HIDDEN_functions.R")
...
@@ -12,9 +12,10 @@ source("99_HIDDEN_functions.R")
##### PART 1 ####
##### PART 1 ####
#### 1. traits data ####
#### 1. traits data ####
traits0
<-
read_delim
(
"_data/Mesobromion/traits
3_cov.txt
"
,
delim
=
"
;
"
,
## manually corrected vowels with umlaut
traits0
<-
read_delim
(
"_data/Mesobromion/traits
4.csv
"
,
delim
=
"
,
"
,
## manually corrected vowels with umlaut
col_names
=
T
,
locale
=
locale
(
encoding
=
'UTF-8'
))
%>%
col_names
=
T
,
locale
=
locale
(
encoding
=
'UTF-8'
))
%>%
column_to_rownames
(
"X1"
)
%>%
column_to_rownames
(
"X1"
)
%>%
dplyr
::
select
(
-
starts_with
(
"X"
))
%>%
dplyr
::
select
(
colnames
(
.
)[
which
(
colSums
(
.
,
na.rm
=
T
)
!=
0
)])
%>%
dplyr
::
select
(
colnames
(
.
)[
which
(
colSums
(
.
,
na.rm
=
T
)
!=
0
)])
%>%
dplyr
::
select
(
!
starts_with
(
"BLM"
))
%>%
dplyr
::
select
(
!
starts_with
(
"BLM"
))
%>%
dplyr
::
select
(
!
starts_with
(
"ZWT"
))
%>%
dplyr
::
select
(
!
starts_with
(
"ZWT"
))
%>%
...
@@ -30,15 +31,22 @@ traits0 <- read_delim("_data/Mesobromion/traits3_cov.txt", delim =";", ## manua
...
@@ -30,15 +31,22 @@ traits0 <- read_delim("_data/Mesobromion/traits3_cov.txt", delim =";", ## manua
mutate
(
species
=
gsub
(
pattern
=
"_"
,
replacement
=
" "
,
x
=
species
))
%>%
mutate
(
species
=
gsub
(
pattern
=
"_"
,
replacement
=
" "
,
x
=
species
))
%>%
mutate
(
species
=
gsub
(
pattern
=
" agg | x | spec$| agg$| s | Sec | "
,
replacement
=
" "
,
x
=
species
))
%>%
mutate
(
species
=
gsub
(
pattern
=
" agg | x | spec$| agg$| s | Sec | "
,
replacement
=
" "
,
x
=
species
))
%>%
mutate
(
species
=
gsub
(
pattern
=
" $"
,
replacement
=
""
,
x
=
species
))
%>%
mutate
(
species
=
gsub
(
pattern
=
" $"
,
replacement
=
""
,
x
=
species
))
%>%
mutate
(
species
=
ifelse
(
is.na
(
word
(
species
,
1
,
2
)),
species
,
word
(
species
,
1
,
2
)))
mutate
(
species
=
ifelse
(
is.na
(
word
(
species
,
1
,
2
)),
species
,
word
(
species
,
1
,
2
)))
%>%
dim
(
traits0
)
#907 obs. of 75 variables:
ungroup
()
dim
(
traits0
)
#902 obs. of 67 variables:
## remove species with NAs
#keep only traits with >=88 completeness
species.to.remove
<-
traits0
%>%
filter
(
all_of
(
is.na
({
.
}
%>%
dplyr
::
select
(
-
species
,
-
species0
))))
%>%
pull
(
species0
)
traits0
<-
traits0
%>%
traits0
<-
traits0
%>%
dplyr
::
select_if
(
~
mean
(
!
is.na
(
.
))
>=
0.88
)
filter
(
!
species0
%in%
species.to.remove
)
dim
(
traits0
)
# 902 x 67
# #keep only traits with >=88 completeness
# traits0 <- traits0 %>%
# dplyr::select_if(~mean(!is.na(.)) >= 0.88)
# dim(traits0)# 902 x 67
...
@@ -88,8 +96,8 @@ all.traits <- traits0 %>%
...
@@ -88,8 +96,8 @@ all.traits <- traits0 %>%
by
=
"species"
)
by
=
"species"
)
traits
<-
all.traits
%>%
traits
<-
all.traits
%>%
filter
(
!
is.na
(
LeafArea
))
filter
(
!
is.na
(
LeafArea
))
dim
(
all.traits
)
#[1]
902
82
dim
(
all.traits
)
#[1]
898
82
dim
(
traits
)
#[1]
801
82
dim
(
traits
)
#[1]
799
82
...
@@ -114,22 +122,23 @@ env.all <- env
...
@@ -114,22 +122,23 @@ env.all <- env
### 3. Import species data ####
### 3. Import species data ####
# columns in species correspond to those in env
# columns in species correspond to those in env
# there is no PlotObservationID (yet)
# there is no PlotObservationID (yet)
species0
<-
read_csv
(
"_data/Mesobromion/GVRD_Mes2_proz2.csv"
,
locale
=
locale
(
encoding
=
'latin1'
))
species0
<-
read_csv
(
"_data/Mesobromion/GVRD_Mes2_proz2.csv"
,
locale
=
locale
(
encoding
=
'latin1'
))
%>%
dim
(
species0
)
#6868 obs. of 903 variables:
dplyr
::
select
(
-
species.to.remove
)
%>%
rownames
(
species0
)
<-
env0
$
RELEVE_NR
mutate
(
RELEVE_NR
=
env0
$
RELEVE_NR
)
dim
(
species0
)
#6868 obs. of 899 variables:
## select only plots already selected in env
## select only plots already selected in env
species
<-
env
%>%
species
<-
env
%>%
dplyr
::
select
(
RELEVE_NR
)
%>%
dplyr
::
select
(
RELEVE_NR
)
%>%
left_join
(
species0
%>%
left_join
(
species0
,
mutate
(
RELEVE_NR
=
env0
$
RELEVE_NR
),
by
=
"RELEVE_NR"
)
%>%
by
=
"RELEVE_NR"
)
%>%
column_to_rownames
(
"RELEVE_NR"
)
%>%
column_to_rownames
(
"RELEVE_NR"
)
%>%
## delete species not appearing in any plot
## delete species not appearing in any plot
dplyr
::
select
(
colnames
(
.
)[
which
(
colSums
(
.
)
!=
0
)])
dplyr
::
select
(
colnames
(
.
)[
which
(
colSums
(
.
)
!=
0
)])
#dplyr::select(traits$species0)
#dplyr::select(traits$species0)
dim
(
species
)
# [1] 5810 87
7
dim
(
species
)
# [1] 5810 87
3
releve08trait
<-
species
%>%
releve08trait
<-
species
%>%
rownames_to_column
(
"RELEVE_NR"
)
%>%
rownames_to_column
(
"RELEVE_NR"
)
%>%
...
@@ -310,7 +319,6 @@ species.cov <- species.cov %>%
...
@@ -310,7 +319,6 @@ species.cov <- species.cov %>%
dplyr
::
select
(
-
sumVar
)
dplyr
::
select
(
-
sumVar
)
dim
(
species.cov
)
#[1] 581 510
dim
(
species.cov
)
#[1] 581 510
## export
## export
write_delim
(
species.pa
,
path
=
"_data/Mesobromion/species.v2.10perc.pa.txt"
,
delim
=
"\t"
)
write_delim
(
species.pa
,
path
=
"_data/Mesobromion/species.v2.10perc.pa.txt"
,
delim
=
"\t"
)
write_delim
(
species.cov
,
path
=
"_data/Mesobromion/species.v2.10perc.cov.txt"
,
delim
=
"\t"
)
write_delim
(
species.cov
,
path
=
"_data/Mesobromion/species.v2.10perc.cov.txt"
,
delim
=
"\t"
)
...
@@ -323,18 +331,16 @@ write_delim(species %>%
...
@@ -323,18 +331,16 @@ write_delim(species %>%
path
=
"_data/Mesobromion/ReleveList.txt"
,
delim
=
"\t"
)
path
=
"_data/Mesobromion/ReleveList.txt"
,
delim
=
"\t"
)
##check for species without trait info
##check for species without trait info
traits
%>%
traits
%>%
filter_at
(
.vars
=
vars
(
-
"species0"
),
filter_at
(
.vars
=
vars
(
-
"species0"
),
all_vars
(
is.na
(
.
)))
%>%
all_vars
(
is.na
(
.
)))
%>%
nrow
()
## [1] no species with no trait info ##
nrow
()
## [1] no species with no trait info ##
## simply because those 7 species without TRY data were excluded already
traits
%>%
traits
%>%
filter_at
(
.vars
=
vars
(
-
"species0"
),
filter_at
(
.vars
=
vars
(
-
"species0"
),
any_vars
(
is.na
(
.
)))
%>%
any_vars
(
is.na
(
.
)))
%>%
nrow
()
## [1]
109
# species with at least 1 NA in traits
nrow
()
## [1]
36
# species with at least 1 NA in traits
#### CORRELATION BETWEEN FUZZY WEIGHTED AND BEALS MATRICES
#### CORRELATION BETWEEN FUZZY WEIGHTED AND BEALS MATRICES
...
@@ -350,7 +356,7 @@ traits %>%
...
@@ -350,7 +356,7 @@ traits %>%
source
(
"01b_MesobromionCluster.R"
)
source
(
"01b_MesobromionCluster.R"
)
#### 1. Traits individually significant for COVER data#### na.exclude=T ########
#### 1. Traits individually significant for COVER data#### na.exclude=T ########
traits
<-
read_delim
(
"_data/Mesobromion/traits.v2.10perc.txt"
,
delim
=
"\t"
)
traits
<-
read_delim
(
"_data/Mesobromion/traits.v2.10perc.txt"
,
delim
=
"\t"
)
myfilelist
<-
list.files
(
path
=
"_derived/Mesobromion/Cover"
,
pattern
=
"HIDDENcov_[0-9]+_.RData"
,
full.names
=
T
)
myfilelist
<-
list.files
(
path
=
"_derived/Mesobromion/Cover"
,
pattern
=
"HIDDENcov
-nona2
_[0-9]+_.RData"
,
full.names
=
T
)
dataFiles
=
purrr
::
map
(
myfilelist
,
function
(
x
){
get
(
load
(
x
))})
dataFiles
=
purrr
::
map
(
myfilelist
,
function
(
x
){
get
(
load
(
x
))})
corXY
=
bind_rows
(
dataFiles
)
%>%
corXY
=
bind_rows
(
dataFiles
)
%>%
as_tibble
()
as_tibble
()
...
@@ -373,7 +379,7 @@ traits.sign <- traits %>%
...
@@ -373,7 +379,7 @@ traits.sign <- traits %>%
dplyr
::
select
(
species0
,
any_of
(
traits.sign.alone
))
dplyr
::
select
(
species0
,
any_of
(
traits.sign.alone
))
#write_delim(traits.sign, path="_data/Mesobromion/traits.out.10perc.cov.sign.txt", delim="\t")
#write_delim(traits.sign, path="_data/Mesobromion/traits.out.10perc.cov.sign.txt", delim="\t")
### COV - NONAs
### COV - NONAs
- all species with at least 1 NAs in traits excluded BEFORE The analysis
" Trait.comb Coef.obs Coef.perm q025 q975 greater.than.perm n sign_plus sign_minus ntraits trait.name
" Trait.comb Coef.obs Coef.perm q025 q975 greater.than.perm n sign_plus sign_minus ntraits trait.name
<chr> <dbl> <dbl> <dbl> <dbl> <dbl> <int> <lgl> <lgl> <int> <fct>
<chr> <dbl> <dbl> <dbl> <dbl> <dbl> <int> <lgl> <lgl> <int> <fct>
1 36 0.316 0.154 0.290 0.370 0.997 999 TRUE FALSE 1 PlantHeight
1 36 0.316 0.154 0.290 0.370 0.997 999 TRUE FALSE 1 PlantHeight
...
@@ -385,6 +391,18 @@ traits.sign <- traits %>%
...
@@ -385,6 +391,18 @@ traits.sign <- traits %>%
7 32 0.251 0.127 0.226 0.303 0.968 999 TRUE FALSE 1 SLA
7 32 0.251 0.127 0.226 0.303 0.968 999 TRUE FALSE 1 SLA
8 35 0.241 0.128 0.217 0.289 0.970 999 TRUE FALSE 1 LeafP "
8 35 0.241 0.128 0.217 0.289 0.970 999 TRUE FALSE 1 LeafP "
### COV - NONA2 - modified Matrix.x to deal with NAs INSIDE the analysis
" Trait.comb Coef.obs Coef.perm q025 q975 greater.than.perm n sign_plus sign_minus ntraits trait.name
<chr> <dbl> <dbl> <dbl> <dbl> <dbl> <int> <lgl> <lgl> <int> <fct>
1 36 0.304 0.134 0.281 0.356 0.990 199 TRUE FALSE 1 PlantHeight
2 50 0.290 0.126 0.261 0.339 0.985 199 TRUE FALSE 1 BL_ANAT
3 2 0.252 0.0621 0.214 0.303 0.985 199 TRUE FALSE 1 LEB_F_Nanophaneroph…
4 20 0.251 0.145 0.206 0.320 0.975 199 TRUE FALSE 1 V_VER_Fragmentation
5 30 0.250 0.137 0.228 0.298 0.970 199 TRUE FALSE 1 BL_DAU
6 32 0.247 0.0932 0.225 0.292 0.965 199 TRUE FALSE 1 SLA
7 49 0.236 0.0784 0.212 0.284 0.975 199 TRUE FALSE 1 STRAT_T
8 35 0.241 0.127 0.218 0.288 0.940 199 FALSE FALSE 1 LeafP "
### COV - without deleting NAs
### COV - without deleting NAs
"# A tibble: 53 x 11
"# A tibble: 53 x 11
Trait.comb Coef.obs Coef.perm q025 q975 greater.than.perm n sign_plus sign_minus ntraits trait.name
Trait.comb Coef.obs Coef.perm q025 q975 greater.than.perm n sign_plus sign_minus ntraits trait.name
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment