File size savers, and large files removed

viralemergence · May 6, 2021 · 0a6950e · 0a6950e
1 parent 863929d
commit 0a6950e
Show file tree

Hide file tree

Showing 9 changed files with 4 additions and 221,588 deletions.
diff --git a/Code/02_1a_Digest GenBank.R b/Code/02_1a_Digest GenBank.R
@@ -39,4 +39,4 @@ write_csv(virus.table, 'Intermediate/GBVirusTax.csv')
 gb %<>% rename(VirusOriginal = "Species") %>%
   left_join(virus.table)
 
-write_csv(gb, "Intermediate/Unformatted/GenBankUnformatted.csv")
+vroom_write(gb, "Intermediate/Unformatted/GenBankUnformatted.csv.gz")
diff --git a/Code/02_1b_Format GenBank.R b/Code/02_1b_Format GenBank.R
@@ -70,4 +70,4 @@ gb %<>% mutate_at(c("Host", "HostGenus", "HostFamily", "HostOrder", "HostClass",
                          "Virus", "VirusGenus", "VirusFamily", "VirusOrder", "VirusClass"),
                        tolower)
 
-write_csv(gb, "Intermediate/Formatted/GenbankFormatted.csv")
+vroom_write(gb, "Intermediate/Formatted/GenbankFormatted.csv.gz")
diff --git a/Code/03_Merge clean files.R b/Code/03_Merge clean files.R
@@ -13,5 +13,5 @@ if(class(clo$NCBIAccession)=='numeric') {clo %<>% mutate(NCBIAccession = as.char
 
 virion <- bind_rows(clo, pred, gb, sra, globi)
 
-vroom_write(virion, "Intermediate/Formatted/VIRIONUnprocessed.tsv.gz")
+vroom_write(virion, "Intermediate/Formatted/VIRIONUnprocessed.csv.gz")
 
diff --git a/Code/04_High level VIRION checks.R b/Code/04_High level VIRION checks.R
@@ -1,5 +1,5 @@
 
-virion <- vroom("Intermediate/Formatted/VIRIONUnprocessed.tsv.gz")
+virion <- vroom("Intermediate/Formatted/VIRIONUnprocessed.csv.gz")
 
 # Is there anything that's not vertebrate in here?
 

diff --git a/Code/05_Dissolve_VIRION.R b/Code/05_Dissolve_VIRION.R
@@ -79,7 +79,6 @@ virion %<>%
 virion %<>% 
   group_by(HostTaxID, VirusTaxID) %>%
   summarise_at(vars(c("AssocID")), ~list(.x)) %>%
-  arrange(Host, Virus) %>%
   mutate(AssocID = sapply(AssocID, fixer))
 
 write_csv(virion, "Virion/Edgelist.csv")
diff --git a/Intermediate/Formatted/GenbankFormatted.csv b/Intermediate/Formatted/GenbankFormatted.csv
diff --git a/Intermediate/Formatted/VIRIONUnprocessed.csv b/Intermediate/Formatted/VIRIONUnprocessed.csv
diff --git a/Intermediate/Formatted/VIRIONUnprocessed.tsv.gz b/Intermediate/Formatted/VIRIONUnprocessed.tsv.gz
diff --git a/Intermediate/Formatted/VirionPartialDiscovery.csv b/Intermediate/Formatted/VirionPartialDiscovery.csv
Original file line number	Diff line number	Diff line change
Expand Up		@@ -13,5 +13,5 @@ if(class(clo$NCBIAccession)=='numeric') {clo %<>% mutate(NCBIAccession = as.char

		virion <- bind_rows(clo, pred, gb, sra, globi)

		vroom_write(virion, "Intermediate/Formatted/VIRIONUnprocessed.tsv.gz")
		vroom_write(virion, "Intermediate/Formatted/VIRIONUnprocessed.csv.gz")