2018-03-23 14:46:02 +01:00
#' Join a table with \code{microorganisms}
2018-02-21 11:52:31 +01:00
#'
2018-03-23 14:46:02 +01:00
#' Join the dataset \code{\link{microorganisms}} easily to an existing table or character vector.
2018-02-21 11:52:31 +01:00
#' @rdname join
#' @name join
#' @aliases join inner_join
2018-03-19 12:43:22 +01:00
#' @param x existing table to join, also supports character vectors
2018-03-23 14:46:02 +01:00
#' @param by a variable to join by - could be a column name of \code{x} with values that exist in \code{microorganisms$bactid} (like \code{by = "bacteria_id"}), or another column in \code{\link{microorganisms}} (but then it should be named, like \code{by = c("my_genus_species" = "fullname")})
2018-03-19 12:43:22 +01:00
#' @param suffix if there are non-joined duplicate variables in \code{x} and \code{y}, these suffixes will be added to the output to disambiguate them. Should be a character vector of length 2.
2018-02-27 20:01:02 +01:00
#' @param ... other parameters to pass on to \code{dplyr::\link[dplyr]{join}}.
2018-03-19 12:43:22 +01:00
#' @details As opposed to the \code{\link[dplyr]{join}} functions of \code{dplyr}, characters vectors are supported and at default existing columns will get a suffix \code{"2"} and the newly joined columns will not get a suffix. See \code{\link[dplyr]{join}} for more information.
2018-02-21 11:52:31 +01:00
#' @export
2018-02-22 20:48:48 +01:00
#' @examples
2018-03-23 14:46:02 +01:00
#' left_join_microorganisms("STAAUR")
2018-03-19 12:43:22 +01:00
#'
2018-03-19 20:39:23 +01:00
#' library(dplyr)
2018-03-23 14:46:02 +01:00
#' septic_patients %>% left_join_microorganisms()
2018-03-19 20:39:23 +01:00
#'
2018-02-22 20:48:48 +01:00
#' df <- data.frame(date = seq(from = as.Date("2018-01-01"),
#' to = as.Date("2018-01-07"),
#' by = 1),
#' bacteria_id = c("STAAUR", "STAAUR", "STAAUR", "STAAUR",
#' "ESCCOL", "ESCCOL", "ESCCOL"),
#' stringsAsFactors = FALSE)
#' colnames(df)
2018-03-23 14:46:02 +01:00
#' df2 <- left_join_microorganisms(df, "bacteria_id")
2018-02-22 20:48:48 +01:00
#' colnames(df2)
2018-03-23 14:46:02 +01:00
inner_join_microorganisms <- function ( x , by = ' bactid' , suffix = c ( " 2" , " " ) , ... ) {
2018-03-19 12:43:22 +01:00
if ( any ( class ( x ) %in% c ( ' character' , ' factor' ) ) ) {
x <- data.frame ( bactid = x , stringsAsFactors = FALSE )
}
2018-02-21 11:52:31 +01:00
# no name set to `by` parameter
if ( is.null ( names ( by ) ) ) {
2018-03-23 14:46:02 +01:00
joinby <- colnames ( AMR :: microorganisms ) [1 ]
2018-02-21 11:52:31 +01:00
names ( joinby ) <- by
} else {
joinby <- by
}
2018-03-23 14:46:02 +01:00
join <- dplyr :: inner_join ( x = x , y = AMR :: microorganisms , by = joinby , suffix = c ( " 2" , " " ) , ... )
2018-02-21 11:52:31 +01:00
if ( nrow ( join ) > nrow ( x ) ) {
warning ( ' the newly joined tbl contains ' , nrow ( join ) - nrow ( x ) , ' rows more that its original' )
}
join
}
#' @rdname join
#' @export
2018-03-23 14:46:02 +01:00
left_join_microorganisms <- function ( x , by = ' bactid' , suffix = c ( " 2" , " " ) , ... ) {
2018-03-19 12:43:22 +01:00
if ( any ( class ( x ) %in% c ( ' character' , ' factor' ) ) ) {
x <- data.frame ( bactid = x , stringsAsFactors = FALSE )
}
2018-02-21 11:52:31 +01:00
# no name set to `by` parameter
if ( is.null ( names ( by ) ) ) {
2018-03-23 14:46:02 +01:00
joinby <- colnames ( AMR :: microorganisms ) [1 ]
2018-02-21 11:52:31 +01:00
names ( joinby ) <- by
} else {
joinby <- by
}
2018-03-23 14:46:02 +01:00
join <- dplyr :: left_join ( x = x , y = AMR :: microorganisms , by = joinby , suffix = c ( " 2" , " " ) , ... )
2018-02-21 11:52:31 +01:00
if ( nrow ( join ) > nrow ( x ) ) {
warning ( ' the newly joined tbl contains ' , nrow ( join ) - nrow ( x ) , ' rows more that its original' )
}
join
}
#' @rdname join
#' @export
2018-03-23 14:46:02 +01:00
right_join_microorganisms <- function ( x , by = ' bactid' , suffix = c ( " 2" , " " ) , ... ) {
2018-03-19 12:43:22 +01:00
if ( any ( class ( x ) %in% c ( ' character' , ' factor' ) ) ) {
x <- data.frame ( bactid = x , stringsAsFactors = FALSE )
}
2018-02-21 11:52:31 +01:00
# no name set to `by` parameter
if ( is.null ( names ( by ) ) ) {
2018-03-23 14:46:02 +01:00
joinby <- colnames ( AMR :: microorganisms ) [1 ]
2018-02-21 11:52:31 +01:00
names ( joinby ) <- by
} else {
joinby <- by
}
2018-03-23 14:46:02 +01:00
join <- dplyr :: right_join ( x = x , y = AMR :: microorganisms , by = joinby , suffix = c ( " 2" , " " ) , ... )
2018-02-21 11:52:31 +01:00
if ( nrow ( join ) > nrow ( x ) ) {
warning ( ' the newly joined tbl contains ' , nrow ( join ) - nrow ( x ) , ' rows more that its original' )
}
join
}
#' @rdname join
#' @export
2018-03-23 14:46:02 +01:00
full_join_microorganisms <- function ( x , by = ' bactid' , suffix = c ( " 2" , " " ) , ... ) {
2018-03-19 12:43:22 +01:00
if ( any ( class ( x ) %in% c ( ' character' , ' factor' ) ) ) {
x <- data.frame ( bactid = x , stringsAsFactors = FALSE )
}
2018-02-21 11:52:31 +01:00
# no name set to `by` parameter
if ( is.null ( names ( by ) ) ) {
2018-03-23 14:46:02 +01:00
joinby <- colnames ( AMR :: microorganisms ) [1 ]
2018-02-21 11:52:31 +01:00
names ( joinby ) <- by
} else {
joinby <- by
}
2018-03-27 17:43:42 +02:00
join <- dplyr :: full_join ( x = x , y = AMR :: microorganisms , by = joinby , suffix = c ( " 2" , " " ) , ... )
if ( nrow ( join ) > nrow ( x ) ) {
warning ( ' the newly joined tbl contains ' , nrow ( join ) - nrow ( x ) , ' rows more that its original' )
}
join
2018-02-21 11:52:31 +01:00
}
#' @rdname join
#' @export
2018-03-23 14:46:02 +01:00
semi_join_microorganisms <- function ( x , by = ' bactid' , ... ) {
2018-03-19 12:43:22 +01:00
if ( any ( class ( x ) %in% c ( ' character' , ' factor' ) ) ) {
x <- data.frame ( bactid = x , stringsAsFactors = FALSE )
}
2018-02-21 11:52:31 +01:00
# no name set to `by` parameter
if ( is.null ( names ( by ) ) ) {
2018-03-23 14:46:02 +01:00
joinby <- colnames ( AMR :: microorganisms ) [1 ]
2018-02-21 11:52:31 +01:00
names ( joinby ) <- by
} else {
joinby <- by
}
2018-03-23 14:46:02 +01:00
dplyr :: semi_join ( x = x , y = AMR :: microorganisms , by = joinby , ... )
2018-02-21 11:52:31 +01:00
}
#' @rdname join
#' @export
2018-03-23 14:46:02 +01:00
anti_join_microorganisms <- function ( x , by = ' bactid' , ... ) {
2018-03-19 12:43:22 +01:00
if ( any ( class ( x ) %in% c ( ' character' , ' factor' ) ) ) {
x <- data.frame ( bactid = x , stringsAsFactors = FALSE )
}
2018-02-21 11:52:31 +01:00
# no name set to `by` parameter
if ( is.null ( names ( by ) ) ) {
2018-03-23 14:46:02 +01:00
joinby <- colnames ( AMR :: microorganisms ) [1 ]
2018-02-21 11:52:31 +01:00
names ( joinby ) <- by
} else {
joinby <- by
}
2018-03-23 14:46:02 +01:00
dplyr :: anti_join ( x = x , y = AMR :: microorganisms , by = joinby , ... )
2018-02-21 11:52:31 +01:00
}