comparison recup_liste_taxon.R @ 1:b38b954b92b9 draft

planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/Ecoregionalization_workflow commit 459ba1277acd7d8d4a02f90dbd7ff444bf8eac92

0:3d750279158b

    data <- args[1]
    preds <- args[2]
    enviro <- args[3]
}

env = read.table(enviro, header=T, na.strings = "na")
occurrence_files = strsplit(data,",")
preds_files = strsplit(preds,",")

#########functions##########

  return(have_model)}

##########Execution########
brt = NULL
for (j in 1:length(preds_files[[1]])){
    brt <- rbind(brt,read.table(preds_files[[1]][j], header = TRUE, na.strings = "na"))
}

for (i in 1:length(occurrence_files[[1]])) {
  occurrence <- NULL
  cmpt <- NULL
  taxon <- list()
  
  occurrence <- read.table(occurrence_files[[1]][i], dec = ",", sep = ";", header = TRUE, na.strings = "na")
  
  taxon_names <- names(occurrence)
  new_taxon <- taxon_names[!(taxon_names %in% names(env)) & taxon_names != "station"]
  taxon <- c(taxon, new_taxon)
  

  
  have_model <- have.model(taxon, occurrence, cmpt, brt)
}

#Taxa for which a model was obtained
have_model2 = subset(have_model, have_model$`Model` != "N")
have_model3 = subset(have_model, have_model$`Model` != "N")

#Obtain a list of taxa (cleaned) that have obtained a BRT model (file that can be submitted to the match taxa tool of the WoRMS database to obtain their classification and be able to sort duplicates between taxonomic ranks)

have_model2$Taxa <- as.character(trim_taxa(have_model2$Taxa))

have_model2 <- have_model2 %>% filter(!str_ends(Taxa, "sp.1|sp[0-9]"))
have_model3 <- have_model3 %>% filter(!str_ends(Taxa, "sp.1|sp[0-9]"))
have_model <- have_model %>% filter(!str_ends(Taxa, "sp.1|sp[0-9]"))

#extraction of the have_model object
write.csv(have_model,file = "have_model.csv", quote = F, row.names = F)

#getting list of taxa for next 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)

1:b38b954b92b9

    data <- args[1]
    preds <- args[2]
    enviro <- args[3]
}

env = read.table(enviro, sep="\t", dec=".", header=T, na.strings = "-9999")
occurrence_files = strsplit(data,",")
preds_files = strsplit(preds,",")

#########functions##########

  return(have_model)}

##########Execution########
brt = NULL
for (j in 1:length(preds_files[[1]])){
    brt <- rbind(brt,read.table(preds_files[[1]][j], sep="\t", header = TRUE, na.strings = "na"))
}

for (i in 1:length(occurrence_files[[1]])) {
  occurrence <- NULL
  cmpt <- NULL
  taxon <- list()
  
  occurrence <- read.table(occurrence_files[[1]][i], sep = "\t", header = TRUE, na.strings = "na")
  
  taxon_names <- names(occurrence)
  new_taxon <- taxon_names[!(taxon_names %in% names(env)) & taxon_names != "station"]
  taxon <- c(taxon, new_taxon)
  

  
  have_model <- have.model(taxon, occurrence, cmpt, brt)
}

#Taxa for which a model was obtained
have_model2 = subset(have_model, have_model$`Model` != "No")
have_model3 = subset(have_model, have_model$`Model` != "No")

#Obtain a list of taxa (cleaned) that have obtained a BRT model (file that can be submitted to the match taxa tool of the WoRMS database to obtain their classification and be able to sort duplicates between taxonomic ranks)

have_model2$Taxa <- as.character(trim_taxa(have_model2$Taxa))

have_model2 <- have_model2 %>% filter(!str_ends(Taxa, "sp.1|sp[0-9]"))
have_model3 <- have_model3 %>% filter(!str_ends(Taxa, "sp.1|sp[0-9]"))
have_model <- have_model %>% filter(!str_ends(Taxa, "sp.1|sp[0-9]"))

#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
list_taxon = have_model3$Taxa
write.table(list_taxon, file= "list_taxa.txt", quote = F, row.names = F, col.names = F)