refactor function names in summarize.R

NAMESPACE

@@ -27,17 +27,17 @@ export(combine_full)
 export(combine_ipr)
 export(convert_aln2fa)
 export(convert_fa2tre)
-export(count_bycol)
+export(countByColumn)
 export(count_to_sunburst)
 export(count_to_treemap)
 export(create_all_col_params)
 export(create_lineage_lookup)
 export(create_one_col_params)
 export(domain_network)
 export(efetch_ipg)
-export(filter_by_doms)
-export(filter_freq)
-export(find_paralogs)
+export(filterByDomains)
+export(filterByFrequency)
+export(findParalogs)
 export(find_top_acc)
 export(format_job_args)
 export(gc_undirected_network)
@@ -81,15 +81,15 @@ export(shorten_lineage)
 export(sink.reset)
 export(stacked_lin_plot)
 export(string2accnum)
-export(summ.DA)
-export(summ.DA.byLin)
-export(summ.GC)
-export(summ.GC.byDALin)
-export(summ.GC.byLin)
-export(summarize_bylin)
+export(summarizeByLineage)
+export(summarizeDomArch)
+export(summarizeDomArch_ByLineage)
+export(summarizeGenContext)
+export(summarizeGenContext_ByDomArchLineage)
+export(summarizeGenContext_ByLineage)
 export(theme_genes2)
 export(to_titlecase)
-export(total_counts)
+export(totalGenContextOrDomArchCounts)
 export(upset.plot)
 export(wordcloud2_element)
 export(wordcloud3)

R/summarize.R

@@ -13,7 +13,7 @@
 #' Filter by Domains
 #'
 #' @author Samuel Chen, Janani Ravi
-#' @description filter_by_doms filters a data frame by identifying exact domain matches
+#' @description filterByDomains filters a data frame by identifying exact domain matches
 #' and either keeping or removing rows with the identified domain
 #'
 #' @param prot Dataframe to filter
@@ -33,9 +33,9 @@
 #'
 #' @examples
 #' \dontrun{
-#' filter_by_doms()
+#' filterByDomains()
 #' }
-filter_by_doms <- function(prot, column = "DomArch", doms_keep = c(), doms_remove = c(),
+filterByDomains <- function(prot, column = "DomArch", doms_keep = c(), doms_remove = c(),
     ignore.case = FALSE) {
     # Only rows with a domain in doms_keep will be kept
     # Any row containing a domain in doms_remove will be removed
@@ -102,9 +102,9 @@ filter_by_doms <- function(prot, column = "DomArch", doms_keep = c(), doms_remov
 #'
 #' @examples
 #' \dontrun{
-#' count_bycol()
+#' countByColumn()
 #' }
-count_bycol <- function(prot = prot, column = "DomArch", min.freq = 1) {
+countByColumn <- function(prot = prot, column = "DomArch", min.freq = 1) {
     counts <- prot %>%
         select(column) %>%
         table() %>%
@@ -135,10 +135,10 @@ count_bycol <- function(prot = prot, column = "DomArch", min.freq = 1) {
 #'
 #' @examples
 #' \dontrun{
-#' tibble::tibble(DomArch = c("aaa+bbb", "a+b", "b+c", "b-c")) |> elements2words()
+#' tibble::tibble(DomArch = c("aaa+bbb", "a+b", "b+c", "b-c")) |> elements2Words()
 #' }
 #'
-elements2words <- function(prot, column = "DomArch", conversion_type = "da2doms") {
+elements2Words <- function(prot, column = "DomArch", conversion_type = "da2doms") {
     z1 <- prot %>%
         dplyr::pull(column) %>%
         str_replace_all("\\,", " ") %>%
@@ -184,11 +184,11 @@ elements2words <- function(prot, column = "DomArch", conversion_type = "da2doms"
 #' @examples
 #' \dontrun{
 #' tibble::tibble(DomArch = c("aaa+bbb", "a+b", "b+c", "b-c")) |>
-#'     elements2words() |>
-#'     words2wc()
+#'     elements2Words() |>
+#'     words2WordCounts()
 #' }
 #'
-words2wc <- function(string) {
+words2WordCounts <- function(string) {
     df_word_count <- string %>%
         # reduce spaces with length 2 or greater to a single space
         str_replace_all("\\s{2,}", " ") %>%
@@ -227,9 +227,9 @@ words2wc <- function(string) {
 #'
 #' @examples
 #' \dontrun{
-#' filter_freq()
+#' filterByFrequency()
 #' }
-filter_freq <- function(x, min.freq) {
+filterByFrequency <- function(x, min.freq) {
     x %>%
         filter(freq >= min.freq)
 }
@@ -254,10 +254,10 @@ filter_freq <- function(x, min.freq) {
 #' \dontrun{
 #' library(tidyverse)
 #' tibble(DomArch = c("a+b", "a+b", "b+c", "a+b"), Lineage = c("l1", "l1", "l1", "l2")) |>
-#'     summarize_bylin(query = "all")
+#'     summarizeByLineage(query = "all")
 #' }
 #'
-summarize_bylin <- function(prot = "prot", column = "DomArch", by = "Lineage",
+summarizeByLineage <- function(prot = "prot", column = "DomArch", by = "Lineage",
     query) {
     column <- sym(column)
     by <- sym(by)
@@ -277,7 +277,7 @@ summarize_bylin <- function(prot = "prot", column = "DomArch", by = "Lineage",
 }
 
 
-#' summ.DA.byLin
+#' summarizeDomArch_ByLineage
 #'
 #' @description
 #' Function to summarize and retrieve counts by Domains & Domains+Lineage
@@ -292,9 +292,9 @@ summarize_bylin <- function(prot = "prot", column = "DomArch", by = "Lineage",
 #'
 #' @examples
 #' \dontrun{
-#' summ.DA.byLin()
+#' summarizeDomArch_ByLineage()
 #' }
-summ.DA.byLin <- function(x) {
+summarizeDomArch_ByLineage <- function(x) {
     ## Note: it is better to reserve dots for S3 Objects. Consider replacing '.' with '_'
     x %>%
         filter(!grepl("^-$", DomArch)) %>%
@@ -304,7 +304,7 @@ summ.DA.byLin <- function(x) {
 }
 
 ## Function to retrieve counts of how many lineages a DomArch appears in
-#' summ.DA
+#' summarizeDomArch
 #'
 #' @description
 #' Function to retrieve counts of how many lineages a DomArch appears in
@@ -318,9 +318,9 @@ summ.DA.byLin <- function(x) {
 #'
 #' @examples
 #' \dontrun{
-#' summ.DA()
+#' summarizeDomArch()
 #' }
-summ.DA <- function(x) {
+summarizeDomArch <- function(x) {
     ## Note: it is better to reserve dots for S3 Objects. Consider replacing '.' with '_'
     x %>%
         group_by(DomArch) %>%
@@ -330,7 +330,7 @@ summ.DA <- function(x) {
         filter(!grepl("^-$", DomArch))
 }
 
-#' summ.GC.byDALin
+#' summarizeGenContext_ByDomArchLineage
 #'
 #' @param x
 #'
@@ -341,9 +341,9 @@ summ.DA <- function(x) {
 #'
 #' @examples
 #' \dontrun{
-#' summ.GC.byDALin
+#' summarizeGenContext_ByDomArchLineage
 #' }
-summ.GC.byDALin <- function(x) {
+summarizeGenContext_ByDomArchLineage <- function(x) {
     ## Note: it is better to reserve dots for S3 Objects. Consider replacing '.' with '_'
     x %>%
         filter(!grepl("^-$", GenContext)) %>%
@@ -355,7 +355,7 @@ summ.GC.byDALin <- function(x) {
         arrange(desc(count))
 }
 
-#' summ.GC.byLin
+#' summarizeGenContext_ByLineage
 #'
 #' @param x
 #'
@@ -366,9 +366,9 @@ summ.GC.byDALin <- function(x) {
 #'
 #' @examples
 #' \dontrun{
-#' summ.GC.byLin()
+#' summarizeGenContext_ByLineage()
 #' }
-summ.GC.byLin <- function(x) {
+summarizeGenContext_ByLineage <- function(x) {
     ## Note: it is better to reserve dots for S3 Objects. Consider replacing '.' with '_'
     x %>%
         filter(!grepl("^-$", GenContext)) %>%
@@ -380,7 +380,7 @@ summ.GC.byLin <- function(x) {
         arrange(desc(count))
 }
 
-#' summ.GC
+#' summarizeGenContext
 #'
 #' @param x
 #'
@@ -391,9 +391,9 @@ summ.GC.byLin <- function(x) {
 #'
 #' @examples
 #' \dontrun{
-#' summ.GC()
+#' summarizeGenContext()
 #' }
-summ.GC <- function(x) {
+summarizeGenContext <- function(x) {
     ## Note: it is better to reserve dots for S3 Objects. Consider replacing '.' with '_'
     x %>%
         group_by(GenContext) %>%
@@ -436,9 +436,9 @@ summ.GC <- function(x) {
 #'
 #' @examples
 #' \dontrun{
-#' total_counts(pspa - gc_lin_counts, 0, "GC")
+#' totalGenContextOrDomArchCounts(pspa - gc_lin_counts, 0, "GC")
 #' }
-total_counts <- function(prot, column = "DomArch", lineage_col = "Lineage",
+totalGenContextOrDomArchCounts <- function(prot, column = "DomArch", lineage_col = "Lineage",
     cutoff = 90, RowsCutoff = FALSE, digits = 2
     # type = "GC"
 ) {
@@ -448,7 +448,7 @@ total_counts <- function(prot, column = "DomArch", lineage_col = "Lineage",
         filter(!is.na({{ column }}) & !is.na({{ lineage_col }})) %>%
         filter({{ column }} != "")
 
-    prot <- summarize_bylin(prot, column, by = lineage_col, query = "all")
+    prot <- summarizeByLineage(prot, column, by = lineage_col, query = "all")
     col_count <- prot %>%
         group_by({{ column }}) %>%
         summarise(totalcount = sum(count))
@@ -504,7 +504,7 @@ total_counts <- function(prot, column = "DomArch", lineage_col = "Lineage",
 
 
 
-# total_counts_by_query <- function(query_data, queries, colname,cutoff, RemoveAstrk = F)
+# totalGenContextOrDomArchCounts_by_query <- function(query_data, queries, colname,cutoff, RemoveAstrk = F)
 # {
 #   ## Get the total counts by the Queries.
 #
@@ -560,19 +560,19 @@ total_counts <- function(prot, column = "DomArch", lineage_col = "Lineage",
 #     lin_count_totals$CumulativePercent[x] = total_counter
 #   }
 #
-#   query_total_counts <- left_join(query_lin_counts, lin_count_totals, by = "Lineage")
+#   query_totalGenContextOrDomArchCounts <- left_join(query_lin_counts, lin_count_totals, by = "Lineage")
 #
-#   query_total_counts <- query_total_counts%>% group_by(total_c,count) %>% arrange(-total_c, -count)
+#   query_totalGenContextOrDomArchCounts <- query_totalGenContextOrDomArchCounts%>% group_by(total_c,count) %>% arrange(-total_c, -count)
 #   # Get lineages that are above the cutoff percentage value
-#   count_cutoff <- (query_total_counts %>% filter(CumulativePercent >= (100-cutoff)))
+#   count_cutoff <- (query_totalGenContextOrDomArchCounts %>% filter(CumulativePercent >= (100-cutoff)))
 #
-#   query_total_counts <- (query_total_counts %>% filter(total_c >= count_cutoff$total_c[nrow(count_cutoff)]))
+#   query_totalGenContextOrDomArchCounts <- (query_totalGenContextOrDomArchCounts %>% filter(total_c >= count_cutoff$total_c[nrow(count_cutoff)]))
 #
 #   # Round to 3 digits
-#   query_total_counts$CumulativePercent <- query_total_counts$CumulativePercent %>% round(digits = 3)
-#   query_total_counts$IndividualPercent <- query_total_counts$IndividualPercent %>% round(digits = 3)
+#   query_totalGenContextOrDomArchCounts$CumulativePercent <- query_totalGenContextOrDomArchCounts$CumulativePercent %>% round(digits = 3)
+#   query_totalGenContextOrDomArchCounts$IndividualPercent <- query_totalGenContextOrDomArchCounts$IndividualPercent %>% round(digits = 3)
 #
-#   return(query_total_counts)
+#   return(query_totalGenContextOrDomArchCounts)
 # }
 
 
@@ -598,9 +598,9 @@ total_counts <- function(prot, column = "DomArch", lineage_col = "Lineage",
 #'
 #' @examples
 #' \dontrun{
-#' find_paralogs(pspa)
+#' findParalogs(pspa)
 #' }
-find_paralogs <- function(prot) {
+findParalogs <- function(prot) {
     # Remove eukaryotes
     prot <- prot %>% filter(!grepl("^eukaryota", Lineage))
     paralogTable <- prot %>%
@@ -635,17 +635,17 @@ find_paralogs <- function(prot) {
 # query.sub$GenContext %>%
 # counts(n)")
 
-# ## elements2words: Function to break up ELEMENTS to WORDS for DA and GC
+# ## elements2Words: Function to break up ELEMENTS to WORDS for DA and GC
 # cat("Converting DA to domains and GC to DAs.\n2 switches: da2doms and gc2da
 # \nFor e.g.:
 # query.sub$DA.doms <- query.sub$DomArch.norep %>%
-#   elements2words(\"da2doms\")
+#   elements2Words(\"da2doms\")
 # query.sub$GC.da <- query.sub$GenContext %>%
-# 	elements2words(\"gc2da\")")
+# 	elements2Words(\"gc2da\")")
 
 
-# ## words2wc: Function to get WORD COUNTS [DOMAINS (DA) or DOMAIN ARCHITECTURES (GC)]
+# ## words2WordCounts: Function to get WORD COUNTS [DOMAINS (DA) or DOMAIN ARCHITECTURES (GC)]
 # cat("Word counts for broken up domains from DAs and DAs from GCs.
 # \nFor e.g.:
 # DA.doms.wc <- query.sub$DA.doms %>%
-#   words2wc()")
+#   words2WordCounts()")