From ec8399193de7adfabb5e2a535248504c9835f320 Mon Sep 17 00:00:00 2001 From: "R.Andres Castaneda Aguilar" Date: Thu, 22 Feb 2024 09:13:03 -0500 Subject: [PATCH 1/9] small modifications in yml files --- .github/workflows/R-CMD-check.yaml | 4 ++-- .github/workflows/test-coverage.yaml | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/.github/workflows/R-CMD-check.yaml b/.github/workflows/R-CMD-check.yaml index 0c284bf9..38a50449 100644 --- a/.github/workflows/R-CMD-check.yaml +++ b/.github/workflows/R-CMD-check.yaml @@ -2,9 +2,9 @@ # Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help on: push: - branches: [main, master, website] + branches: [main, DEV] pull_request: - branches: [main, master, website] + branches: [main, DEV] name: R-CMD-check diff --git a/.github/workflows/test-coverage.yaml b/.github/workflows/test-coverage.yaml index 47d0c11b..ddf8b7bd 100644 --- a/.github/workflows/test-coverage.yaml +++ b/.github/workflows/test-coverage.yaml @@ -2,9 +2,9 @@ # Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help on: push: - branches: [main, master, website] + branches: [main, DEV] pull_request: - branches: [main, master, website] + branches: [main, DEV] name: test-coverage From b2cd508b0abeda20682c24b6e1749c7547f32be9 Mon Sep 17 00:00:00 2001 From: "R.Andres Castaneda Aguilar" Date: Thu, 22 Feb 2024 09:13:13 -0500 Subject: [PATCH 2/9] Increment version number to 0.1.6.9000 --- DESCRIPTION | 2 +- NEWS.md | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/DESCRIPTION b/DESCRIPTION index bd7b7ab1..955f1cdc 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,7 +1,7 @@ Package: joyn Type: Package Title: Tool for Diagnosis of Tables Joins and Complementary Join Features -Version: 0.1.6 +Version: 0.1.6.9000 Authors@R: c(person(given = "R.Andres", family = "Castaneda", email = "acastanedaa@worldbank.org", diff --git a/NEWS.md b/NEWS.md index 3f9dfee0..57f68edb 100644 --- a/NEWS.md +++ b/NEWS.md @@ -1,3 +1,5 @@ +# joyn (development version) + # joyn 0.1.6 # joyn 0.1.5 From df34efaf868529ac54b615fa06dc0e136d3fc584 Mon Sep 17 00:00:00 2001 From: "R.Andres Castaneda Aguilar" Date: Thu, 22 Feb 2024 11:58:10 -0500 Subject: [PATCH 3/9] add try catch to workhorse --- R/info_display.R | 6 +- R/joyn_workhorse.R | 97 ++- _pkgdown.yml | 7 +- docs/dev/LICENSE-text.html | 13 +- docs/dev/LICENSE.html | 13 +- docs/dev/articles/index.html | 203 ++---- docs/dev/authors.html | 22 +- .../deps/bootstrap-5.3.1/bootstrap.min.css | 4 +- docs/dev/deps/bootstrap-5.3.1/font.css | 115 +++- docs/dev/index.html | 401 ++++++++---- docs/dev/news/index.html | 240 +++---- docs/dev/pkgdown.yml | 13 +- docs/dev/reference/freq_table.html | 268 +++----- docs/dev/reference/index.html | 345 +++++----- docs/dev/reference/is_id.html | 306 ++++----- docs/dev/reference/merge.html | 617 ++++++++---------- docs/dev/reference/possible_ids.html | 286 ++++---- 17 files changed, 1423 insertions(+), 1533 deletions(-) diff --git a/R/info_display.R b/R/info_display.R index ffc20a6a..65009360 100644 --- a/R/info_display.R +++ b/R/info_display.R @@ -19,7 +19,8 @@ #' #' joyn_msg("all") -joyn_msg <- function(type = c("all", type_choices())) { +joyn_msg <- function(type = c("all", type_choices()), + msg = NULL) { # Check --------- type_to_use <- match.arg(type, several.ok = TRUE) @@ -39,6 +40,9 @@ joyn_msg <- function(type = c("all", type_choices())) { cli::cli_text(.) }) + if ("err" %in% type_to_use & is.character(msg)) { + cli::cli_abort(msg) + } #~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ # Return --------- diff --git a/R/joyn_workhorse.R b/R/joyn_workhorse.R index 4fc03a9d..e4dfff88 100644 --- a/R/joyn_workhorse.R +++ b/R/joyn_workhorse.R @@ -69,33 +69,78 @@ joyn_workhorse <- function( # Do a full join ------------------------------------------------------------- # if not 1:1 => use merge.data.table - if (match_type == "m:m") { - - dt_result <- data.table::merge.data.table( - x = x, - y = y, - by = by, - all = TRUE, - sort = FALSE, - suffixes = suffixes, - allow.cartesian = TRUE - ) - } else { - - # not m:m => use collapse::join() - dt_result <- collapse::join( x = x, - y = y, - how = "full", - on = by, - multiple = TRUE, # matches row in x with m in y - validate = "m:m", # no checks performed - suffix = suffixes, # data.table suffixes - keep.col.order = TRUE, - verbose = 0, - column = NULL - ) - } + # not m:m => use collapse::join() + dt_result <- tryCatch( + expr = { + souce_pkg <- if (match_type == "m:m") "data.table::merge" else "collapse::join" + if (match_type == "m:m") { + data.table::merge.data.table( + x = x, + y = y, + by = by, + all = TRUE, + sort = FALSE, + suffixes = suffixes, + allow.cartesian = TRUE + ) + + } else { + collapse::join( x = x, + y = y, + how = "full", + on = by, + multiple = TRUE, # matches row in x with m in y + validate = "m:m", # no checks performed + suffix = suffixes, # data.table suffixes + keep.col.order = TRUE, + verbose = 0, + column = NULL) + } + }, # end of expr section + + error = function(e) { + + + joyn_msg("err", c("{.pkg {souce_pkg}} returned the following:", + x = e$message)) + }, # end of error section + + warning = function(w) { + if (grepl("[Oo]veridentified", w$message)) { + store_msg( + type = "warn", + ok = paste(cli::symbol$warning, "\nWarning: "), + pale = "Your data is overidentified. Below the original message from {.pkg {souce_pkg}}:", + bolded_pale = "\n{w$message}" + ) + } else { + store_msg( + type = "warn", + ok = paste(cli::symbol$warning, "\nWarning: "), + pale = "{.pkg {souce_pkg}} returned the following warning:", + bolded_pale = "\n{w$message}" + ) + } + + # This is inefficient but it is the only way to return the table when + # there is a warning + + collapse::join( x = x, + y = y, + how = "full", + on = by, + multiple = TRUE, # matches row in x with m in y + validate = "m:m", # no checks performed + suffix = suffixes, # data.table suffixes + keep.col.order = TRUE, + verbose = 0, + column = NULL) |> + suppressWarnings() + + } + + ) # End of trycatch # Calculate the time taken end_time <- Sys.time() diff --git a/_pkgdown.yml b/_pkgdown.yml index 19415e08..3be63979 100644 --- a/_pkgdown.yml +++ b/_pkgdown.yml @@ -27,11 +27,16 @@ navbar: - reference - articles - news - right: github + right: + - Dev version + - github components: reference: text: Reference href: reference/index.html + dev version: + text: dev version + href: dev/ github: icon: fab fa-github fa-lg href: https://github.com/randrescastaneda/joyn/ diff --git a/docs/dev/LICENSE-text.html b/docs/dev/LICENSE-text.html index 0543716b..36f884e6 100644 --- a/docs/dev/LICENSE-text.html +++ b/docs/dev/LICENSE-text.html @@ -10,7 +10,7 @@ joyn - 0.1.4.9005 + 0.1.6.9000 - - joyn - 0.1.2.9000 - - + + - - - - - - +
  • + dev version +
    • + + + +
    -
    -
    -

    Articles

    +
    +

    Articles

    Usage

    -
    -
    General use
    -
    -
    Advanced use
    -
    -
    -
    -
    +
    Main functionalities
    +
    +
    Advanced functionalities
    +
    +
    dplyr joins wrappers
    +
    +
    `data.table::merge()` wrapper
    +
    +
    Messages
    +
    +
    Additional functions
    +
    +
    +
    + + +
    + + - - - + diff --git a/docs/dev/authors.html b/docs/dev/authors.html index b95e4cb2..d503f0c0 100644 --- a/docs/dev/authors.html +++ b/docs/dev/authors.html @@ -10,7 +10,7 @@ joyn - 0.1.4.9005 + 0.1.6.9000 - -
    -
    -
    +
  • + dev version +
    • +
    + + +
    -
    -
    -

    Changelog

    - Source: NEWS.md +
    +

    Changelog

    + Source: NEWS.md
    -
    -

    -joyn (development version) Unreleased -

    +
    +

    joyn (development version)

    -
    -

    -joyn 0.1.2 Unreleased -

    -
      -
    • Add function possible_ids() to identify what variables are suitable for uniquely identify de database.
      • -
    -
    -

    -joyn 0.1.1

    -
      -

    • Add function is_id() to check whether the table is uniquely identified by key variables

      • -

    • Add function freq_table() as a substitute for janitor::tabyl. This makes it more convenient for users who do not have janitor installed.

      • -
    +
    +

    joyn 0.1.6

    +
    +
    +

    joyn 0.1.5

    -
    -

    -joyn 0.1.0

    +
    +

    joyn 0.1.4

    CRAN release: 2021-12-14

    +

    • update_NAs now could be FALSE even if update_values is TRUE

      • +

    • Select rows-to-keep before transformation of updated values and NAs to avoid keeping rows from y that did not match in x but whose values got updated because update_values = TRUE

      • +

    • Solve issues #1 and #19

      • +

    • Change to data.table::merge.data.table syntax in all joins. It makes it easier to work with and consistent across different join types.

      • +

    • Remove previous lazy-loaded data.

      • +
    +
    +

    joyn 0.1.3

    CRAN release: 2021-04-28

    +
    • Convert external data to external data.
      • +
    +
    +

    joyn 0.1.2

    +
    • Add function possible_ids() to identify what variables are suitable for uniquely identify the database.
      • +
    +

    joyn 0.1.1

    +

    • Add function is_id() to check whether the table is uniquely identified by key variables

      • +

    • Add function freq_table() as a substitute for janitor::tabyl. This makes it more convenient for users who do not have janitor installed.

      • +
    +
    +

    joyn 0.1.0

    Fix bug on by argument when using “=” or “==”.

    -
    -

    -joyn 0.0.1

    +
    +

    joyn 0.0.1

    First Public release

    -
    - - - -
    +
    -
    + - - - + diff --git a/docs/dev/pkgdown.yml b/docs/dev/pkgdown.yml index 7203c28a..96f0b6f3 100644 --- a/docs/dev/pkgdown.yml +++ b/docs/dev/pkgdown.yml @@ -2,7 +2,14 @@ pandoc: 3.1.1 pkgdown: 2.0.7 pkgdown_sha: ~ articles: - advanced-use: advanced-use.html - general-use: general-use.html -last_built: 2024-02-02T16:04Z + adv-functionalities: adv-functionalities.html + aux-functions: aux-functions.html + dplyr-joins: dplyr-joins.html + main-functionalities: main-functionalities.html + merge-wrapper: merge-wrapper.html + messages: messages.html +last_built: 2024-02-22T14:37Z +urls: + reference: https://randrescastaneda.github.io/joyn/reference + article: https://randrescastaneda.github.io/joyn/articles diff --git a/docs/dev/reference/freq_table.html b/docs/dev/reference/freq_table.html index 1b6d7d3d..fa1e6779 100644 --- a/docs/dev/reference/freq_table.html +++ b/docs/dev/reference/freq_table.html @@ -1,201 +1,131 @@ - - - - - - - -tabulate simple frequencies — freq_table • joyn +Tabulate simple frequencies — freq_table • joyn + Skip to contents + +
    +
    +
    +

    Tabulate simple frequencies

    + Source: R/freq_table.R +
    freq_table.Rd
    +
    - - +
    +

    tabulate one variable frequencies

    +
    - - - +
    +

    Usage

    + 
    freq_table(x, byvar, digits = 1, na.rm = TRUE)
    +
    - - - +
    +

    Arguments

    +
    x
    +

    data frame

    +
    byvar
    +

    character: name of variable to tabulate. Use Standard evaluation.

    - - +
    digits
    +

    numeric: number of decimal places to display. Default is 1.

    - +
    na.rm
    +

    logical: if TRUE remove NAs from calculations. Default is TRUE

    - - - +
    +
    +

    Value

    + - - - - - - - -
    -
    - - - - -
    - -
    -
    -
    -

    tabulate simple frequencies

    - Source: R/freq_table.R - +
    +

    Examples

    + 
    library(data.table)
+x4 = data.table(id1 = c(1, 1, 2, 3, 3),
+                id2 = c(1, 1, 2, 3, 4),
+                t   = c(1L, 2L, 1L, 2L, NA_integer_),
+                x   = c(16, 12, NA, NA, 15))
+freq_table(x4, "id1")
+#>       id1     n percent
+#>    <char> <int>  <char>
+#> 1:      1     2     40%
+#> 2:      2     1     20%
+#> 3:      3     2     40%
+#> 4:  total     5    100%
+
    - -
    -

    tabulate one variable in data frame to substitute base::table and -janitor::tabyl using data.table

    -
    - - 
    freq_table(x, byvar, digits = 1, na.rm = TRUE)
    - -

    Arguments

    - - - - - - - - - - - - - - - - - - -
    x

    data frame

    byvar

    character: name of variable to tabulate. Use STandard evaluation.

    digits

    numeric: number of decimal places to display. Default is 1.

    na.rm

    logical: if TRUE remove NAs from calculations. Default is TRUE

    - -

    Value

    - -

    data.table with frequencies.

    - -

    Examples

    - 
    freq_table(x4, "id1")
-
    #>      id1 n percent
-#> 1:     1 2     40%
-#> 2:     2 1     20%
-#> 3:     3 2     40%
-#> 4: total 5    100%
    -
    - -
    +
    -
    + - - - + diff --git a/docs/dev/reference/index.html b/docs/dev/reference/index.html index 415bbc46..a4cc9736 100644 --- a/docs/dev/reference/index.html +++ b/docs/dev/reference/index.html @@ -1,219 +1,184 @@ - - - - - - - -Function reference • joyn - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Function reference • joyn + Skip to contents + - +
    +
    +
    +

    Function reference

    +
    + +
    +

    Main function

    -
    -
    -
    +

    Since the objective of joyn is to join tables with joy, there is only one main function in this package

    +
    + + + - +
    + + joyn() +
    +
    Join two tables
    +
    +

    Dplyr-joins

    + + -
    -
    -
    -

    Reference

    -
    + +
    + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    -

    Main function

    -

    Since the objective of joyn is to join tables with joy, there is only one main function in this package

    -
    -

    merge()

    -

    Merge two tables

    -

    Auxiliary functions

    -

    -
    -

    is_id()

    -

    Make sure the match type is correct

    -

    freq_table()

    -

    tabulate simple frequencies

    -

    possible_ids()

    -

    Find possible unique identifies of data frame

    -
    +
    + + full_join() +
    +
    Full join two data frames
    +
    + + right_join() +
    +
    Right join two data frames
    +
    + + left_join() +
    +
    Left join two data frames
    +
    + + inner_join() +
    +
    Inner join two data frames
    +
    +

    Merge data tables

    + + - -
    + +
    + + + +
    + + merge() +
    +
    Merge two data frames
    +
    +

    Auxiliary functions

    + + -
    + + + -
    + + - - - + diff --git a/docs/dev/reference/is_id.html b/docs/dev/reference/is_id.html index 9779185a..12770bbb 100644 --- a/docs/dev/reference/is_id.html +++ b/docs/dev/reference/is_id.html @@ -1,207 +1,167 @@ - - - - - - - -Make sure the match type is correct — is_id • joyn - - - - - - +Check if dt is uniquely identified by by variable — is_id • joyn + Skip to contents + +
    +
    +
    +

    Check if dt is uniquely identified by by variable

    + Source: R/is_id.R +
    is_id.Rd
    +
    - - - +
    +

    report if dt is uniquely identified by by var or, if report = TRUE, the duplicates in by variable

    +
    +
    +

    Usage

    + 
    is_id(dt, by, verbose = getOption("joyn.verbose"), return_report = FALSE)
    +
    +
    +

    Arguments

    +
    dt
    +

    either right of left table

    - - +
    by
    +

    variable to merge by

    - +
    verbose
    +

    logical: if TRUE messages will be displayed

    - - - - - - - - - - -
    -
    - +
    +
    +

    Value

    + - +

    logical or data.frame, depending on the value of argument return_report

    - -
    -
    -
    -

    Make sure the match type is correct

    - Source: R/is_id.R -
    -
    -

    Make sure the match type is correct

    +
    +

    Examples

    + 
    library(data.table)
+
+# example with data frame not uniquely identified by `by` var
+
+y <- data.table(id = c("c","b", "c", "a"),
+                 y  = c(11L, 15L, 18L, 20L))
+is_id(y, by = "id")
+#> 
+#> ── Duplicates in terms of `id` 
+#>    copies     n percent
+#>    <char> <int>  <char>
+#> 1:      1     2   66.7%
+#> 2:      2     1   33.3%
+#> 3:  total     3    100%
+#> ─────────────────────────────────────────────────────── End of is_id() report ──
+#> [1] FALSE
+is_id(y, by = "id", return_report = TRUE)
+#> 
+#> ── Duplicates in terms of `id` 
+#>    copies     n percent
+#>    <char> <int>  <char>
+#> 1:      1     2   66.7%
+#> 2:      2     1   33.3%
+#> 3:  total     3    100%
+#> ─────────────────────────────────────────────────────── End of is_id() report ──
+#>        id copies
+#>    <char>  <int>
+#> 1:      c      2
+#> 2:      b      1
+#> 3:      a      1
+
+# example with data frame uniquely identified by `by` var
+
+y1 <- data.table(id = c("1","3", "2", "9"),
+                 y  = c(11L, 15L, 18L, 20L))
+is_id(y1, by = "id")
+#> 
+#> ── Duplicates in terms of `id` 
+#>    copies     n percent
+#>    <char> <int>  <char>
+#> 1:      1     4    100%
+#> 2:  total     4    100%
+#> ─────────────────────────────────────────────────────── End of is_id() report ──
+#> [1] TRUE
+
    - - 
    is_id(dt, by, verbose = TRUE, return_report = FALSE)
    - -

    Arguments

    - - - - - - - - - - - - - - - - - - -
    dt

    either right of left table

    by

    by argument in merge

    verbose

    logical: if TRUE messages will be displayed

    return_report

    logical: if TRUE, returns data with summary of duplicates. -If FALSE, returns logical value depending on whether dt is uniquely identified -by by

    - -

    Value

    - -

    logical or data.frame, depending on the value of argument return_report

    - -

    Examples

    - 
    is_id(y3, by = "id")
-
    #> 
    #> -- Duplicates in terms of `id` 
    #>    copies n percent
-#> 1:      1 2   66.7%
-#> 2:      2 1   33.3%
-#> 3:  total 3    100%
    #> ------------------------------------------------------- End of is_id() report --
    #> [1] FALSE
    is_id(y3, by = "id", return_report = TRUE)
-
    #> 
    #> -- Duplicates in terms of `id` 
    #>    copies n percent
-#> 1:      1 2   66.7%
-#> 2:      2 1   33.3%
-#> 3:  total 3    100%
    #> ------------------------------------------------------- End of is_id() report --
    #>    id copies
-#> 1:  c      2
-#> 2:  b      1
-#> 3:  a      1
    -
    - -
    +
    -
    + - - - + diff --git a/docs/dev/reference/merge.html b/docs/dev/reference/merge.html index 8bf13e40..81790352 100644 --- a/docs/dev/reference/merge.html +++ b/docs/dev/reference/merge.html @@ -1,398 +1,303 @@ - - - - - - +Merge two data frames — merge • joyn + Skip to contents + -Merge two tables — merge • joyn +
    +
    +
    +

    Merge two data frames

    + Source: R/merge-data.table.R +
    merge.Rd
    +
    - - - +
    +

    This is a joyn wrapper that works in a similar fashion to base::merge and +data.table::merge, which is why merge masks the other two.

    +
    - - +
    +

    Usage

    + 
    merge(
+  x,
+  y,
+  by = NULL,
+  by.x = NULL,
+  by.y = NULL,
+  all = FALSE,
+  all.x = all,
+  all.y = all,
+  sort = TRUE,
+  suffixes = c(".x", ".y"),
+  no.dups = TRUE,
+  allow.cartesian = getOption("datatable.allow.cartesian"),
+  match_type = c("m:m", "m:1", "1:m", "1:1"),
+  keep_common_vars = TRUE,
+  ...
+)
    +
    - - - +
    +

    Arguments

    +
    x, y
    +

    data tables. y is coerced to a data.table if +it isn't one already.

    - - - +
    by
    +

    A vector of shared column names in x and y to merge on. +This defaults to the shared key columns between the two tables. +If y has no key columns, this defaults to the key of x.

    +
    by.x, by.y
    +

    Vectors of column names in x and y to merge on.

    - - +
    all
    +

    logical; all = TRUE is shorthand to save setting both +all.x = TRUE and all.y = TRUE.

    - - - - +
    all.x
    +

    logical; if TRUE, rows from x which have no matching row +in y are included. These rows will have 'NA's in the columns that are usually +filled with values from y. The default is FALSE so that only rows with +data from both x and y are included in the output.

    - - - - - - - -
    -
    - +
    all.y
    +

    logical; analogous to all.x above.

    - -
    +
    sort
    +

    logical. If TRUE (default), the rows of the merged +data.table are sorted by setting the key to the by / by.x columns. If +FALSE, unlike base R's merge for which row order is unspecified, the +row order in x is retained (including retaining the position of missings when +all.x=TRUE), followed by y rows that don't match x (when all.y=TRUE) +retaining the order those appear in y.

    -
    -
    -
    -

    Merge two tables

    - Source: R/merge.R - -
    -
    -

    This is the main and, basically, the only function in joyn.

    -
    +
    suffixes
    +

    A character(2) specifying the suffixes to be used for +making non-by column names unique. The suffix behaviour works in a similar +fashion as the merge.data.frame method does.

    - 
    merge(
-  x,
-  y,
-  by = intersect(names(x), names(y)),
-  yvars = TRUE,
-  match_type = c("m:m", "m:1", "1:m", "1:1"),
-  keep = c("full", "left", "master", "right", "using", "inner"),
-  update_values = FALSE,
-  update_NAs = update_values,
-  reportvar = "report",
-  reporttype = c("character", "numeric"),
-  roll = NULL,
-  keep_y_in_x = FALSE,
-  sort = TRUE,
-  verbose = getOption("joyn.verbose")
-)
    - -

    Arguments

    - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    x

    data frame: referred to left in R terminology, or master in -Stata terminology.

    y

    data frame: referred to right in R terminology, or using in -Stata terminology.

    by

    a character vector of variables to join by. If NULL, the default, -joyn will do a natural join, using all variables with common names across -the two tables. A message lists the variables so that you can check they're -right (to suppress the message, simply explicitly list the variables that -you want to join). To join by different variables on x and y use a vector -of expressions. For example, by = c("a = b", "z") will use "a" in x, "b" -in y, and "z" in both tables.

    yvars

    character: Vector of variable names that will be kept after the -merge. If TRUE (the default), it keeps all the brings all the variables in -y into x. If FALSE or NULL, it does not bring any variable into x, but a -report will be generated.

    match_type

    character: one of "m:m", "m:1", "1:m", "1:1". -Default is "m:m" since this is the default generally used in joins in R. -However, following Stata's recommendation, it is better to be explicit and -use any of the other three match types (See details in match types -sections).

    keep

    character: One of "full", "left", "master", "right", -"using", "inner". Default is "full". Even though this is not the -regular behavior of joins in R, the objective of joyn is to present a -diagnosis of the join, so that it must use by default a full join. Yet, if -"left" or "master", it keeps the observations that matched in both -tables and the ones that did not match in x. The ones in y will be -discarded. If "right" or "using", it keeps the observations that -matched in both tables and the ones that did not match in y. The ones in x -will be discarded. If "inner", it only keeps the observations that -matched both tables.

    update_values

    logical: If TRUE, it will update all values of variables -in x with the actual of variables in y with the same name as the ones in x. -NAs from y won't be used to update actual values in x.

    update_NAs

    logical: If TRUE, it will update NA values of all variables -in x with actual values of variables in y that have the same name as the -ones in x. If FALSE, NA values won't be updated.

    reportvar

    character: Name of reporting variable. Default if "report". + +

    no.dups
    +

    logical indicating that suffixes are also appended to +non-by.y column names in y when they have the same column name +as any by.x.

    + + +
    allow.cartesian
    +

    See allow.cartesian in [.data.table.

    + + +
    match_type
    +

    character: one of "m:m", "m:1", "1:m", "1:1". +Default is "1:1" since this the most restrictive. However, following +Stata's recommendation, it is better to be explicit and use any of the +other three match types (See details in match types sections).

    + + +
    keep_common_vars
    +

    logical: If TRUE, it will keep the original variable +from y when both tables have common variable names. Thus, the prefix "y." +will be added to the original name to distinguish from the resulting +variable in the joined table.

    + + +
    ...
    +

    Arguments passed on to joyn

    y_vars_to_keep
    +

    character: Vector of variable names in y that will be +kept after the merge. If TRUE (the default), it keeps all the brings all +the variables in y into x. If FALSE or NULL, it does not bring any variable +into x, but a report will be generated.

    + +
    reportvar
    +

    character: Name of reporting variable. Default is ".joyn". This is the same as variable "_merge" in Stata after performing a merge. If FALSE or NULL, the reporting variable will be excluded from the final -table, though a summary of the join will be display after concluding.

    reporttype

    character: One of "character" or "numeric". Default is -"character". If "numeric", the reporting variable will contain numeric -codes of the source and the contents of each observation in the joined -table.

    roll

    double: to be implemented

    keep_y_in_x

    logical: If TRUE, it will keep the original variable from -y when both tables have common variable names. Thus, the prefix "y." will -be added to the original name to distinguish from the resulting variable in -the joined table.

    sort

    logical: If TRUE, sort by key variables in by. Default is -TRUE.

    verbose

    logical: if FALSE, it won't display any message (programmer's -option). Default is TRUE.

    - -

    Value

    - -

    a data.table joining x and y.

    -

    match types

    +table, though a summary of the join will be display after concluding.

    + +
    update_NAs
    +

    logical: If TRUE, it will update NA values of all variables +in x with actual values of variables in y that have the same name as the +ones in x. If FALSE, NA values won't be updated, even if update_values is +TRUE

    + +
    update_values
    +

    logical: If TRUE, it will update all values of variables +in x with the actual of variables in y with the same name as the ones in x. +NAs from y won't be used to update actual values in x. Yet, by default, +NAs in x will be updated with values in y. To avoid this, make sure to set +update_NAs = FALSE

    + +
    verbose
    +

    logical: if FALSE, it won't display any message (programmer's +option). Default is TRUE.

    + + +
    +
    +
    +

    Value

    +

    data.table merging x and y

    +
    -

    Using the same wording of the Stata manual

    -

    1:1: specifies a one-to-one match merge. The variables specified in -by uniquely identify single observations in both table.

    -

    1:m and m:1: specify one-to-many and many-to-one match merges, -respectively. This means that in of the tables the observations are -uniquely identify by the variables in by, while in the other table many -(two or more) of the observations are identify by the variables in by

    -

    m:m refers to many-to-many merge. variables in by does not uniquely -identify the observations in either table. Matching is performed by -combining observations with equal values in by; within matching values, -the first observation in the master (i.e. left or x) table is matched with -the first matching observation in the using (i.e. right or y) table; the -second, with the second; and so on. If there is an unequal number of -observations within a group, then the last observation of the shorter group -is used repeatedly to match with subsequent observations of the longer -group.

    - -

    Examples

    - 
    # Simple merge
-library(data.table)
-x1 = data.table(id = c(1L, 1L, 2L, 3L, NA_integer_),
-t  = c(1L, 2L, 1L, 2L, NA_integer_),
-x  = 11:15)
-
-y1 = data.table(id = 1:2,
-                y  = c(11L, 15L))
-
-x2 = data.table(id = c(1, 1, 2, 3, NA),
-                t  = c(1L, 2L, 1L, 2L, NA_integer_),
-                x  = c(16, 12, NA, NA, 15))
-
-y2 = data.table(id = c(1, 2, 5, 6, 3),
-              yd = c(1, 2, 5, 6, 3),
-              y  = c(11L, 15L, 20L, 13L, 10L),
-              x  = c(16:20))
-merge(x1, y1)
-
    #> > removing key variables `id` from yvars
    #> 
    #> -- JOYn Report --
    #> 
    #>    report n percent
-#> 1:      x 2     40%
-#> 2:  x & y 3     60%
-#> 3:  total 5    100%
    #> ---------------------------------------------------------- End of JOYn report --
    #>    id  t  x  y report
-#> 1:  1  1 11 11  x & y
-#> 2:  1  2 12 11  x & y
-#> 3:  2  1 13 15  x & y
-#> 4:  3  2 14 NA      x
-#> 5: NA NA 15 NA      x
    
-# Bad merge for not specifying by argument
-merge(x2, y2)
-
    #> > removing key variables `id` and `x` from yvars
    #> 
    #> -- JOYn Report --
    #> 
    #>    report n percent
-#> 1:      x 4   44.4%
-#> 2:  x & y 1   11.1%
-#> 3:      y 4   44.4%
-#> 4:  total 9    100%
    #> ---------------------------------------------------------- End of JOYn report --
    #>    id  x  t yd  y report
-#> 1:  1 12  2 NA NA      x
-#> 2:  1 16  1  1 11  x & y
-#> 3:  2 17 NA  2 15      y
-#> 4:  2 NA  1 NA NA      x
-#> 5:  3 20 NA  3 10      y
-#> 6:  3 NA  2 NA NA      x
-#> 7:  5 18 NA  5 20      y
-#> 8:  6 19 NA  6 13      y
-#> 9: NA 15 NA NA NA      x
    
-# good merge, ignoring variable x from y
-merge(x2, y2, by = "id")
-
    #> > removing key variables `id` from yvars
    #> i variable `x` in table y is ignored because arguments `update_NAs` and
-#>   `update_values` are FALSE.
    #> 
    #> -- JOYn Report --
    #> 
    #>    report n percent
-#> 1:      x 1   14.3%
-#> 2:  x & y 4   57.1%
-#> 3:      y 2   28.6%
-#> 4:  total 7    100%
    #> ---------------------------------------------------------- End of JOYn report --
    #>    id  t  x yd  y report
-#> 1:  1  1 16  1 11  x & y
-#> 2:  1  2 12  1 11  x & y
-#> 3:  2  1 NA  2 15  x & y
-#> 4:  3  2 NA  3 10  x & y
-#> 5:  5 NA NA  5 20      y
-#> 6:  6 NA NA  6 13      y
-#> 7: NA NA 15 NA NA      x
    
-# update NAs in x variable form x
-merge(x2, y2, by = "id", update_NAs = TRUE)
-
    #> > removing key variables `id` from yvars
    #> 
    #> -- JOYn Report --
    #> 
    #>        report n percent
-#> 1: NA updated 2   28.6%
-#> 2:          x 1   14.3%
-#> 3:      x & y 2   28.6%
-#> 4:          y 2   28.6%
-#> 5:      total 7    100%
    #> ---------------------------------------------------------- End of JOYn report --
    #>    id  t  x yd  y     report
-#> 1:  1  1 16  1 11      x & y
-#> 2:  1  2 12  1 11      x & y
-#> 3:  2  1 17  2 15 NA updated
-#> 4:  3  2 20  3 10 NA updated
-#> 5:  5 NA 18  5 20          y
-#> 6:  6 NA 19  6 13          y
-#> 7: NA NA 15 NA NA          x
    
-# Update values in x with variables from y
-merge(x2, y2, by = "id", update_values = TRUE)
-
    #> > removing key variables `id` from yvars
    #> 
    #> -- JOYn Report --
    #> 
    #>           report n percent
-#> 1:    NA updated 2   28.6%
-#> 2:   not updated 1   14.3%
-#> 3: value updated 1   14.3%
-#> 4:         x & y 1   14.3%
-#> 5:             y 2   28.6%
-#> 6:         total 7    100%
    #> ---------------------------------------------------------- End of JOYn report --
    #>    id  t  x yd  y        report
-#> 1:  1  1 16  1 11         x & y
-#> 2:  1  2 16  1 11 value updated
-#> 3:  2  1 17  2 15    NA updated
-#> 4:  3  2 20  3 10    NA updated
-#> 5:  5 NA 18  5 20             y
-#> 6:  6 NA 19  6 13             y
-#> 7: NA NA 15 NA NA   not updated
    
-
    -
    - -
    +
    +

    Examples

    + 
    x1 = data.frame(id = c(1L, 1L, 2L, 3L, NA_integer_),
+                t  = c(1L, 2L, 1L, 2L, NA_integer_),
+                x  = 11:15)
+y1 = data.frame(id = c(1,2, 4),
+                y  = c(11L, 15L, 16))
+joyn::merge(x1, y1, by = "id")
+#> 
+#> ── JOYn Report ──
+#> 
+#>     .joyn     n percent
+#>    <char> <int>  <char>
+#> 1:  x & y     3    100%
+#> 2:  total     3    100%
+#> ────────────────────────────────────────────────────────── End of JOYn report ──
+#> ⚠ Warning: Supplied both by and by.x/by.y. by argument will be ignored.
+#> ℹ ❯ Joyn's report available in variable .joyn
+#> ⚠ Warning: The keys supplied uniquely identify y therefore a m:1 join is
+#> executed.
+#> ℹ ❯ Removing key variables id from id and y
+#> ● Timing: The full joyn is executed in 0.00457 seconds
+#> ● Timing: The entire joyn function, including checks, is executed in 0.053809
+#> seconds
+#>   id t  x  y .joyn
+#> 1  1 1 11 11 x & y
+#> 2  1 2 12 11 x & y
+#> 3  2 1 13 15 x & y
+# example of using by.x and by.y
+x2 = data.frame(id1 = c(1, 1, 2, 3, 3),
+                id2 = c(1, 1, 2, 3, 4),
+                t   = c(1L, 2L, 1L, 2L, NA_integer_),
+                x   = c(16, 12, NA, NA, 15))
+y2 = data.frame(id  = c(1, 2, 5, 6, 3),
+                id2 = c(1, 1, 2, 3, 4),
+                y   = c(11L, 15L, 20L, 13L, 10L),
+                x   = c(16:20))
+jn <- joyn::merge(x2,
+            y2,
+            match_type = "m:m",
+            all.x = TRUE,
+            by.x = "id1",
+            by.y = "id2")
+#> 
+#> ── JOYn Report ──
+#> 
+#>     .joyn     n percent
+#>    <char> <int>  <char>
+#> 1:  x & y     7    100%
+#> 2:  total     7    100%
+#> ────────────────────────────────────────────────────────── End of JOYn report ──
+#> ⚠ Warning: Supplied both by and by.x/by.y. by argument will be ignored.
+#> ℹ ❯ Joyn's report available in variable .joyn
+#> ℹ ❯ Removing key variables keyby1 from id, keyby1, y, and x
+#> ● Timing: The full joyn is executed in 0.0029 seconds
+#> ● Timing: The entire joyn function, including checks, is executed in 0.039003
+#> seconds
+# example with all = TRUE
+jn <- joyn::merge(x2,
+            y2,
+            match_type = "m:m",
+            by.x = "id1",
+            by.y = "id2",
+            all = TRUE)
+#> 
+#> ── JOYn Report ──
+#> 
+#>     .joyn     n percent
+#>    <char> <int>  <char>
+#> 1:  x & y     7   87.5%
+#> 2:      y     1   12.5%
+#> 3:  total     8    100%
+#> ────────────────────────────────────────────────────────── End of JOYn report ──
+#> ⚠ Warning: Supplied both by and by.x/by.y. by argument will be ignored.
+#> ℹ ❯ Joyn's report available in variable .joyn
+#> ℹ ❯ Removing key variables keyby1 from id, keyby1, y, and x
+#> ● Timing: The full joyn is executed in 0.00191 seconds
+#> ● Timing: The entire joyn function, including checks, is executed in 0.032904
+#> seconds
+
    +
    + - + - - - + diff --git a/docs/dev/reference/possible_ids.html b/docs/dev/reference/possible_ids.html index 79af3200..853af5df 100644 --- a/docs/dev/reference/possible_ids.html +++ b/docs/dev/reference/possible_ids.html @@ -1,203 +1,151 @@ - - - - - - - -Find possible unique identifies of data frame — possible_ids • joyn - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Find possible unique identifies of data frame — possible_ids • joyn + Skip to contents + - +
    -
    -
    -

    Find possible unique identifies of data frame

    - Source: R/possible_ids.R - +
    +

    Find possible unique identifies of data frame

    + Source: R/possible_ids.R +
    possible_ids.Rd
    -
    -

    Find possible unique identifies of data frame

    +
    +

    Identify possible variables uniquely identifying x

    - 
    possible_ids(dt, verbose = TRUE)
    +
    +

    Usage

    + 
    possible_ids(
+  dt,
+  exclude = NULL,
+  include = NULL,
+  verbose = getOption("possible_ids.verbose")
+)
    +
    -

    Arguments

    - - - - - - - - - - -
    dt

    data frame

    verbose

    logical: fi FALSE no message will be displayed. Default is TRUE

    +
    +

    Arguments

    +
    dt
    +

    data frame

    -

    Value

    - +
    exclude
    +

    character: Exclude variables to be selected as identifiers. It +could be either the name of the variables of one type of the variable +prefixed by "_". For instance, "_numeric" or "_character".

    +
    include
    +

    character: Name of variable to be included, that might belong +to the group excluded in the exclude

    -

    Examples

    - 
    possible_ids(x4)
-
    #> v There are no duplicates in data frame
    #> > we found 5 possible ids
    #> $V1
-#> [1] "id1" "t"  
-#> 
-#> $V2
-#> [1] "id1" "x"  
-#> 
-#> $V3
-#> [1] "id2" "t"  
-#> 
-#> $V4
-#> [1] "id2" "x"  
-#> 
-#> $V5
-#> [1] "t" "x"
-#>
    -
    - -
    +
    verbose
    +

    logical: If FALSE no message will be displayed. Default is +TRUE

    + +
    +
    +

    Value

    + + +

    list with possible identifiers

    +
    + +
    +

    Examples

    + 
    library(data.table)
+x4 = data.table(id1 = c(1, 1, 2, 3, 3),
+                id2 = c(1, 1, 2, 3, 4),
+                t   = c(1L, 2L, 1L, 2L, NA_integer_),
+                x   = c(16, 12, NA, NA, 15))
+possible_ids(x4)
+#> ✔ There are no duplicates in data frame
+#> → we found 5 possible ids
+#> $V1
+#> [1] "id1" "t"  
+#> 
+#> $V2
+#> [1] "id1" "x"  
+#> 
+#> $V3
+#> [1] "id2" "t"  
+#> 
+#> $V4
+#> [1] "id2" "x"  
+#> 
+#> $V5
+#> [1] "t" "x"
+#> 
+
    +
    +
    -
    + - - - + From 4e1c991b4171b456b57a5f58dbdd27ff33e89438 Mon Sep 17 00:00:00 2001 From: "R.Andres Castaneda Aguilar" Date: Thu, 22 Feb 2024 14:30:01 -0500 Subject: [PATCH 4/9] document --- R/info_display.R | 6 ++++-- R/joyn_workhorse.R | 36 +++++++++++++++++++++++++----------- man/joyn_msg.Rd | 9 ++++++--- man/msg_type_dt.Rd | 4 ++-- man/store_msg.Rd | 4 ++-- 5 files changed, 39 insertions(+), 20 deletions(-) diff --git a/R/info_display.R b/R/info_display.R index 65009360..a4fc943a 100644 --- a/R/info_display.R +++ b/R/info_display.R @@ -1,7 +1,9 @@ #' display type of joyn message #' -#' @param type character: one or more of the following: -#' `r cli::format_inline("{.or {.val {type_choices()}}}")` or `all` +#' @param type character: one or more of the following: `r joyn:::type_choices()` +#' cli::format_inline("{.or {.val {type_choices()}}}")` or `all` +#' @param msg character vector to be parsed to [cli::cli_abort()]. Default is +#' NULL. It only works if `"err" %in% type` #' #' @return returns data frame with message invisibly. print message in console #' @export diff --git a/R/joyn_workhorse.R b/R/joyn_workhorse.R index e4dfff88..972fc64c 100644 --- a/R/joyn_workhorse.R +++ b/R/joyn_workhorse.R @@ -126,17 +126,31 @@ joyn_workhorse <- function( # This is inefficient but it is the only way to return the table when # there is a warning - collapse::join( x = x, - y = y, - how = "full", - on = by, - multiple = TRUE, # matches row in x with m in y - validate = "m:m", # no checks performed - suffix = suffixes, # data.table suffixes - keep.col.order = TRUE, - verbose = 0, - column = NULL) |> - suppressWarnings() + if (match_type == "m:m") { + data.table::merge.data.table( + x = x, + y = y, + by = by, + all = TRUE, + sort = FALSE, + suffixes = suffixes, + allow.cartesian = TRUE + ) |> + suppressWarnings() + + } else { + collapse::join( x = x, + y = y, + how = "full", + on = by, + multiple = TRUE, # matches row in x with m in y + validate = "m:m", # no checks performed + suffix = suffixes, # data.table suffixes + keep.col.order = TRUE, + verbose = 0, + column = NULL) |> + suppressWarnings() + } } diff --git a/man/joyn_msg.Rd b/man/joyn_msg.Rd index 95e34ecd..0694d0e1 100644 --- a/man/joyn_msg.Rd +++ b/man/joyn_msg.Rd @@ -4,11 +4,14 @@ \alias{joyn_msg} \title{display type of joyn message} \usage{ -joyn_msg(type = c("all", type_choices())) +joyn_msg(type = c("all", type_choices()), msg = NULL) } \arguments{ -\item{type}{character: one or more of the following: -"info", "note", "warn", "timing", or "err" or \code{all}} +\item{type}{character: one or more of the following: info, note, warn, timing, err +cli::format_inline("{.or {.val {type_choices()}}}")\code{or}all`} + +\item{msg}{character vector to be parsed to \code{\link[cli:cli_abort]{cli::cli_abort()}}. Default is +NULL. It only works if \code{"err" \%in\% type}} } \value{ returns data frame with message invisibly. print message in console diff --git a/man/msg_type_dt.Rd b/man/msg_type_dt.Rd index 75dbd18e..fff355e9 100644 --- a/man/msg_type_dt.Rd +++ b/man/msg_type_dt.Rd @@ -7,8 +7,8 @@ msg_type_dt(type, ...) } \arguments{ -\item{type}{character: one or more of the following: -"info", "note", "warn", "timing", or "err" or \code{all}} +\item{type}{character: one or more of the following: info, note, warn, timing, err +cli::format_inline("{.or {.val {type_choices()}}}")\code{or}all`} } \value{ data frame with two variables, type and msg diff --git a/man/store_msg.Rd b/man/store_msg.Rd index b56dc660..03563e2c 100644 --- a/man/store_msg.Rd +++ b/man/store_msg.Rd @@ -7,8 +7,8 @@ store_msg(type, ...) } \arguments{ -\item{type}{character: one or more of the following: -"info", "note", "warn", "timing", or "err" or \code{all}} +\item{type}{character: one or more of the following: info, note, warn, timing, err +cli::format_inline("{.or {.val {type_choices()}}}")\code{or}all`} \item{...}{combination of type and text in the form \verb{style1 = text1, style2 = text2}, etc.} } From 0a629d5cbe4caeb548d9eda3441a75cc4337ec9b Mon Sep 17 00:00:00 2001 From: "R.Andres Castaneda Aguilar" Date: Thu, 22 Feb 2024 14:35:06 -0500 Subject: [PATCH 5/9] Increment version number to 0.1.6.9001 --- DESCRIPTION | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/DESCRIPTION b/DESCRIPTION index 955f1cdc..3436cd6c 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,7 +1,7 @@ Package: joyn Type: Package Title: Tool for Diagnosis of Tables Joins and Complementary Join Features -Version: 0.1.6.9000 +Version: 0.1.6.9001 Authors@R: c(person(given = "R.Andres", family = "Castaneda", email = "acastanedaa@worldbank.org", From 7a04cb125387afea1567e1bb2cd630efc93a321c Mon Sep 17 00:00:00 2001 From: zander-prinsloo Date: Fri, 23 Feb 2024 15:56:31 -0500 Subject: [PATCH 6/9] correct typo --- R/joyn_workhorse.R | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/R/joyn_workhorse.R b/R/joyn_workhorse.R index 972fc64c..09a78015 100644 --- a/R/joyn_workhorse.R +++ b/R/joyn_workhorse.R @@ -73,7 +73,7 @@ joyn_workhorse <- function( # not m:m => use collapse::join() dt_result <- tryCatch( expr = { - souce_pkg <- if (match_type == "m:m") "data.table::merge" else "collapse::join" + source_pkg <- if (match_type == "m:m") "data.table::merge" else "collapse::join" if (match_type == "m:m") { data.table::merge.data.table( x = x, @@ -102,7 +102,7 @@ joyn_workhorse <- function( error = function(e) { - joyn_msg("err", c("{.pkg {souce_pkg}} returned the following:", + joyn_msg("err", c("{.pkg {source_pkg}} returned the following:", x = e$message)) }, # end of error section @@ -111,14 +111,14 @@ joyn_workhorse <- function( store_msg( type = "warn", ok = paste(cli::symbol$warning, "\nWarning: "), - pale = "Your data is overidentified. Below the original message from {.pkg {souce_pkg}}:", + pale = "Your data is overidentified. Below the original message from {.pkg {source_pkg}}:", bolded_pale = "\n{w$message}" ) } else { store_msg( type = "warn", ok = paste(cli::symbol$warning, "\nWarning: "), - pale = "{.pkg {souce_pkg}} returned the following warning:", + pale = "{.pkg {source_pkg}} returned the following warning:", bolded_pale = "\n{w$message}" ) } From c897e8312ae2b9db833a2d927bb8e520dcb77ca7 Mon Sep 17 00:00:00 2001 From: zander-prinsloo Date: Mon, 26 Feb 2024 13:26:42 -0500 Subject: [PATCH 7/9] fix changing column names of input tables --- R/joyn-merge.R | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/R/joyn-merge.R b/R/joyn-merge.R index a935dcc4..4f15c4a7 100644 --- a/R/joyn-merge.R +++ b/R/joyn-merge.R @@ -212,12 +212,8 @@ joyn <- function(x, #~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ start_joyn <- Sys.time() # copy objects if data.tables - if (any(class(x) == "data.table")) { - x <- copy(x) - } - if (any(class(y) == "data.table")) { - y <- copy(y) - } + x <- copy(x) + y <- copy(y) ## X and Y ----------- check_xy(x,y) From 3c188a9e672592c1ce60727bfc6c4757cc800b8c Mon Sep 17 00:00:00 2001 From: zander-prinsloo Date: Mon, 26 Feb 2024 14:18:18 -0500 Subject: [PATCH 8/9] fix order bug --- R/joyn-merge.R | 23 +++++------------------ tests/testthat/test-joyn.R | 4 ++-- 2 files changed, 7 insertions(+), 20 deletions(-) diff --git a/R/joyn-merge.R b/R/joyn-merge.R index 4f15c4a7..001948ed 100644 --- a/R/joyn-merge.R +++ b/R/joyn-merge.R @@ -234,7 +234,6 @@ joyn <- function(x, y <- as.data.table(y) } - ## Modify BY when is expression --------- fixby <- check_by_vars(by, x, y) by <- fixby$by @@ -388,19 +387,6 @@ joyn <- function(x, #~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ # Update x --------- #~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - - # if (isTRUE(update_values) || isTRUE(update_NAs)) { - # var_use <- sub( - # pattern = "\\.y$", - # replacement = "", - # x = newyvars[ - # grepl( - # pattern = "\\.y$", - # x = newyvars - # ) - # ] - # ) - # } var_use <- NULL if (isTRUE(update_values) || isTRUE(update_NAs)) { var_use <- common_vars @@ -462,6 +448,11 @@ joyn <- function(x, .yreport = NULL) + if (sort) { + setorderv(x, by, na.last = na.last) + setattr(x, 'sorted', by) + } + ## Rename by variables ----- if (!is.null(fixby$xby)) { @@ -519,10 +510,6 @@ joyn <- function(x, x |> fselect(get(reportvar)) <- NULL } - if (sort) { - setorderv(x, by, na.last = na.last) - setattr(x, 'sorted', by) - } if (verbose == TRUE) { end_joyn <- Sys.time() diff --git a/tests/testthat/test-joyn.R b/tests/testthat/test-joyn.R index 1d33af34..2fd86a6d 100644 --- a/tests/testthat/test-joyn.R +++ b/tests/testthat/test-joyn.R @@ -568,8 +568,8 @@ test_that("different names in key vars are working fine", { ".joyn" = c("x & y", "x & y", "x", "y", "x", "x & y", "y", "y") ) - setorderv(dd, "id1", na.last = TRUE) - setattr(dd, 'sorted', "id1") + setorderv(dd, c("id1", "id2"), na.last = TRUE) + setattr(dd, 'sorted', c("id1", "id2")) expect_equal(df, dd) From 2699753153dbb2b6f326978de03f8298b4932085 Mon Sep 17 00:00:00 2001 From: zander-prinsloo Date: Mon, 26 Feb 2024 14:21:17 -0500 Subject: [PATCH 9/9] Increment version number to 0.1.6.9002 --- DESCRIPTION | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/DESCRIPTION b/DESCRIPTION index 3436cd6c..a52f48aa 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,7 +1,7 @@ Package: joyn Type: Package Title: Tool for Diagnosis of Tables Joins and Complementary Join Features -Version: 0.1.6.9001 +Version: 0.1.6.9002 Authors@R: c(person(given = "R.Andres", family = "Castaneda", email = "acastanedaa@worldbank.org",