Mercurial > repos > ecology > ecoregion_clara_cluster

changeset 2:24a81631a8b5 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/Ecoregionalization_workflow commit 5d48df67919fbc9d77b98a8243d438c397f61a0e
author ecology
date Thu, 21 Mar 2024 14:04:36 +0000
parents edb8d19735a6
children 844b5bf84164
files GeoNN.R cluster.xml recup_liste_taxon.R test-data/ceamarc_env.tsv test-data/fish_wide.tsv
diffstat 5 files changed, 116 insertions(+), 19 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/GeoNN.R	Thu Mar 21 14:04:36 2024 +0000
@@ -0,0 +1,77 @@
+#Date : 09/02/2024
+#Author : Seguineau Pauline
+
+#Load libraries
+library(tidyr)
+library(dplyr)
+library(sf)
+
+#load arguments
+args = commandArgs(trailingOnly=TRUE) 
+if (length(args)==0)
+{
+    stop("This tool needs at least one argument")
+}else{
+    enviro <- args[1]
+    envlong <- as.numeric(args[2])
+    envlat <- as.numeric(args[3])
+    occu <- args[4]
+    occulat <- as.numeric(args[5])
+    occulong <- as.numeric(args[6])
+}
+ 
+env = read.table(enviro, header = TRUE, sep="\t")
+occ = read.table(occu, header = TRUE, sep = "\t")
+
+cols_env = c(names(env[envlong]),names(env[envlat]))
+cols_occ = c(names(occ[occulong]),names(occ[occulat]))
+
+###calculate distances### 
+#transform tables into sf object
+
+env_sf <- st_as_sf(env, coords = cols_env, crs = "+proj=longlat +ellps=WGS84 +datum=WGS84 +no_defs")
+occ_sf <- st_as_sf(occ, coords = cols_occ, crs = "+proj=longlat +ellps=WGS84 +datum=WGS84 +no_defs")
+
+#Find the indices of env_sf entities closest to each point in occ_sf.
+
+nearest_indices <- st_nearest_feature(occ_sf, env_sf)
+
+nearest_points <- env[nearest_indices, ]
+
+# Calculate distances between env_sf and occ_sf points
+distances <- st_distance(env_sf, occ_sf)
+
+#Extract the corresponding distances between occ and env
+
+nearest_distances <- numeric(length(nearest_indices))
+
+for (i in 1:length(nearest_indices)) {
+  nearest_distances[i] <- st_distance(env_sf[nearest_indices[i],], occ_sf[i,])
+}
+
+#assemble occurrences and environmental parameters in the same file
+
+nearest_points <- nearest_points[, !names(nearest_points) %in% cols_env] #remove lat and long from env to clean data
+new_occ = cbind(occ, nearest_points)
+
+#Save the file 
+
+write.table(new_occ, file = "occurrence_env.tsv",sep ="\t",quote = F, row.names = F,col.names = T)
+
+#create an information file with the distances between the points of the two files 
+
+distance_info <- data.frame(
+  occ_geometry = occ_sf$geometry,
+  env_geometry = env_sf$geometry[nearest_indices],
+  distance = nearest_distances
+)
+
+colnames(distance_info)[1] <- "occ_geometry"
+colnames(distance_info)[2] <- "env_geometry"
+colnames(distance_info)[3] <- "Distances (meters)"
+#save the information file
+
+write.table(distance_info, file = "infos_file.tsv",sep ="\t",quote = F, row.names = F,col.names = T)
+
+
+
--- a/cluster.xml	Wed Jan 24 15:53:07 2024 +0000
+++ b/cluster.xml	Thu Mar 21 14:04:36 2024 +0000
@@ -22,7 +22,7 @@
     <inputs>
       <param name="envfile" type="data" format="tabular" label="Environmental file (tabular only)"/>
       <param name="predictionmatrix" type="data" format="tabular" label="Prediction matrix (file 'data to cluster' from Cluster Estimate tool)"/>
-      <param name="predictionfile" type="data" format="tabular" label="Prediction file (file 'data.bio table' from Cluster Estimate tool)"/>
+      <param name="predictionfile" type="data" format="tabular" label="Prediction table (file 'data.bio table' from Cluster Estimate tool)"/>
       <param name="k" type="integer" label="Number of Cluster wanted" min= "1" value="2"/>
       <param name="metric" type="select" label="What metric to use to calculate dissimilarities between observations ?">
              <option value = "manhattan">manhattan</option>
@@ -46,7 +46,7 @@
             <param name='sample' value="10"/>
             <output name='output1'>
                 <assert_contents>
-            	    <has_size value="7369" delta="1000"/>
+            	    <has_size value="8359" delta="500"/>
             	</assert_contents>
             </output>
             <output name='output2'>
--- a/recup_liste_taxon.R	Wed Jan 24 15:53:07 2024 +0000
+++ b/recup_liste_taxon.R	Thu Mar 21 14:04:36 2024 +0000
@@ -82,7 +82,7 @@
 #extraction of the have_model object
 write.table(have_model,file = "have_model.tsv", sep="\t", quote = F, row.names = F)
 
-#getting list of taxa for next if not using worms
+#getting list of taxa for next step if not using worms
 list_taxon = have_model3$Taxa
 write.table(list_taxon, file= "list_taxa.txt", quote = F, row.names = F, col.names = F)
 
--- a/test-data/ceamarc_env.tsv	Wed Jan 24 15:53:07 2024 +0000
+++ b/test-data/ceamarc_env.tsv	Thu Mar 21 14:04:36 2024 +0000
@@ -1,16 +1,16 @@
-long	lat	Carbo	Grav	Maxbearing	Maxmagnit	Meancurmag	Meansal	Meantheta	Mud	Prof	Rugosity	Sand	Seaice_prod	Sili	Slope	Standcurmag	Standsal	Standtheta	long_round	lat_round
-1	139.22	-65.57	0.88	28.59	3.67	0.03	0.03	34.62	-0.13	22.72	-441	-9999	55.76	0.24	3.27	0.28	0.01	0.01	0.18	139,22	-65,57
-2	139.22	-65.57	0.88	28.61	3.64	0.02	0.03	34.62	-0.13	22.48	-439	-9999	55.74	0.24	3.29	0.27	0.01	0.01	0.18	139,22	-65,57
-3	139.23	-65.57	0.92	28.62	3.59	0.02	0.03	34.62	-0.14	22.25	-438	-9999	56.28	0.25	3.32	0.22	0.01	0.01	0.19	139,23	-65,57
-4	139.24	-65.57	0.92	28.63	3.51	0.01	0.03	34.62	-0.14	21.95	-436	-9999	56.57	0.26	3.3	0.08	0.01	0.01	0.19	139,24	-65,57
-5	139.24	-65.57	0.92	28.64	3.35	0.01	0.03	34.62	-0.14	21.7	-437	-9999	56.58	0.26	3.28	0.05	0.01	0.01	0.19	139,24	-65,57
-6	139.25	-65.57	0.93	28.65	3	0.0096293305978179	0.03	34.62	-0.15	21.44	-436	-9999	56.63	0.26	3.26	0.29	0.01	0.01	0.19	139,25	-65,57
-7	139.26	-65.57	0.93	28.63	2.49	0.00871255807578564	0.03	34.62	-0.15	21.11	-432	-9999	56.67	0.26	3.23	0.43	0.01	0.01	0.19	139,26	-65,57
-8	139.26	-65.57	0.93	28.64	2.01	0.01	0.03	34.62	-0.16	20.83	-429	-9999	56.71	0.26	3.21	0.37	0.01	0.01	0.19	139,26	-65,57
-9	139.27	-65.57	0.94	28.65	1.71	0.01	0.03	34.62	-0.16	20.55	-427	-9999	56.75	0.26	3.19	0.32	0.01	0.01	0.2	139,27	-65,57
-10	139.28	-65.57	0.94	28.66	1.54	0.01	0.03	34.62	-0.16	20.21	-424	-9999	56.8	0.26	3.17	0.28	0.01	0.01	0.2	139,28	-65,57
-11	139.28	-65.57	0.94	28.67	1.44	0.02	0.03	34.62	-0.17	19.74	-422	-9999	56.84	0.26	3.14	0.26	0.01	0.01	0.2	139,28	-65,57
-12	139.29	-65.57	0.94	28.68	1.74	0.01	0.03	34.62	-0.17	20.86	-421	-9999	56.87	0.26	3.13	0.22	0.01	0.01	0.2	139,29	-65,57
-13	139.3	-65.57	0.95	28.7	3.46	0.01	0.03	34.62	-0.17	21.3	-420	-9999	56.91	0.26	3.11	0.32	0.01	0.01	0.2	139,30	-65,57
-14	139.3	-65.57	0.95	28.71	3.91	0.03	0.03	34.62	-0.18	21.01	-414	-9999	57.18	0.26	3.09	0.59	0.01	0.01	0.21	139,30	-65,57
-15	139.31	-65.57	0.96	28.72	4.03	0.05	0.03	34.62	-0.18	20.76	-406	-9999	57.54	0.26	3.07	0.53	0.01	0.01	0.21	139,31	-65,57
+long	lat	Carbo	Grav	Maxbearing	Maxmagnit	Meancurmag	Meansal	Meantheta	Mud	Prof	Rugosity	Sand	Seaice_prod	Sili	Slope	Standcurmag	Standsal	Standtheta
+139.22	-65.57	0.88	28.59	3.67	0.03	0.03	34.62	-0.13	22.72	-441	-9999	55.76	0.24	3.27	0.28	0.01	0.01	0.18
+139.22	-65.57	0.88	28.61	3.64	0.02	0.03	34.62	-0.13	22.48	-439	-9999	55.74	0.24	3.29	0.27	0.01	0.01	0.18
+139.23	-65.57	0.92	28.62	3.59	0.02	0.03	34.62	-0.14	22.25	-438	-9999	56.28	0.25	3.32	0.22	0.01	0.01	0.19
+139.24	-65.57	0.92	28.63	3.51	0.01	0.03	34.62	-0.14	21.95	-436	-9999	56.57	0.26	3.3	0.08	0.01	0.01	0.19
+139.24	-65.57	0.92	28.64	3.35	0.01	0.03	34.62	-0.14	21.7	-437	-9999	56.58	0.26	3.28	0.05	0.01	0.01	0.19
+139.25	-65.57	0.93	28.65	3	0.0096293305978179	0.03	34.62	-0.15	21.44	-436	-9999	56.63	0.26	3.26	0.29	0.01	0.01	0.19
+139.26	-65.57	0.93	28.63	2.49	0.00871255807578564	0.03	34.62	-0.15	21.11	-432	-9999	56.67	0.26	3.23	0.43	0.01	0.01	0.19
+139.26	-65.57	0.93	28.64	2.01	0.01	0.03	34.62	-0.16	20.83	-429	-9999	56.71	0.26	3.21	0.37	0.01	0.01	0.19
+139.27	-65.57	0.94	28.65	1.71	0.01	0.03	34.62	-0.16	20.55	-427	-9999	56.75	0.26	3.19	0.32	0.01	0.01	0.2
+139.28	-65.57	0.94	28.66	1.54	0.01	0.03	34.62	-0.16	20.21	-424	-9999	56.8	0.26	3.17	0.28	0.01	0.01	0.2
+139.28	-65.57	0.94	28.67	1.44	0.02	0.03	34.62	-0.17	19.74	-422	-9999	56.84	0.26	3.14	0.26	0.01	0.01	0.2
+139.29	-65.57	0.94	28.68	1.74	0.01	0.03	34.62	-0.17	20.86	-421	-9999	56.87	0.26	3.13	0.22	0.01	0.01	0.2
+139.3	-65.57	0.95	28.7	3.46	0.01	0.03	34.62	-0.17	21.3	-420	-9999	56.91	0.26	3.11	0.32	0.01	0.01	0.2
+139.3	-65.57	0.95	28.71	3.91	0.03	0.03	34.62	-0.18	21.01	-414	-9999	57.18	0.26	3.09	0.59	0.01	0.01	0.21
+139.31	-65.57	0.96	28.72	4.03	0.05	0.03	34.62	-0.18	20.76	-406	-9999	57.54	0.26	3.07	0.53	0.01	0.01	0.21
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/fish_wide.tsv	Thu Mar 21 14:04:36 2024 +0000
@@ -0,0 +1,20 @@
+lat	long	rajidae_bathyraja_sp.	myctophidae_electrona_antarctica	myctophidae_protomyctophum_bolini
+-67.22	139.96	4	1	0
+-65.46	139.31	0	4	0
+-65.82	142.96	0	0	1
+-65.77	142.92	0	1	1
+-65.64	140.45	0	2	0
+-65.74	142.86	0	1	0
+-65.85	144.04	0	2	0
+-65.44	139.32	0	0	0
+-65.71	140.6	0	0	0
+-66.75	143.95	0	0	0
+-66.41	140.51	0	0	0
+-66.34	140.03	0	0	0
+-66.17	139.35	0	0	0
+-66.33	143.36	0	0	0
+-66.39	140.43	0	0	0
+-66.75	144.96	0	0	0
+-66.34	143.04	0	0	0
+-67.05	145.15	0	0	0
+