Merge pull request #577 from SebKrantz/development

Development

Author: SebKrantz

.Rbuildignore

@@ -26,3 +26,8 @@ man/figures
 _cache$
 _snaps
 ^CITATION\.cff$
+^\.DS_Store$
+^revdep$
+\.orig$
+
+

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: collapse
 Title: Advanced and Fast Data Transformation
 Version: 2.0.14
-Date: 2024-05-01
+Date: 2024-05-19
 Authors@R: c(
            person("Sebastian", "Krantz", role = c("aut", "cre"), 
                   email = "[email protected]", 
@@ -28,7 +28,7 @@ Description: A C/C++ based package for advanced data transformation and
     (grouped, weighted) summary statistics, powerful tools to work with nested data, 
     fast data object conversions, functions for memory efficient R programming, and 
     helpers to effectively deal with variable labels, attributes, and missing data. 
-    It is well integrated with base R classes, 'dplyr'/'tibble', 'data.table', 'sf', 
+    It is well integrated with base R classes, 'dplyr'/'tibble', 'data.table', 'sf', 'units', 
     'plm' (panel-series and data frames), and 'xts'/'zoo'.
 URL: https://sebkrantz.github.io/collapse/,  
      https://github.com/SebKrantz/collapse,

NAMESPACE

@@ -405,6 +405,7 @@ importFrom("stats", "as.formula", "complete.cases", "cor", "cov", "var", "pt",
  export(fncol)
  export(fdim)
  export(as_numeric_factor)
+ export(as_integer_factor)
  export(as_character_factor)
  export(as.numeric_factor)
  export(as.character_factor)

NEWS.md

@@ -1,5 +1,9 @@
 # collapse 2.0.14
 
+* Updated '*collapse* and *sf*' vignette to reflect the recent support for *units* objects, and added a few more examples.
+
+* Fixed a bug in `join()` where a full join silently became a left join if there are no matches between the tables (#574). Thanks @D3SL for reporting. 
+
 * Added function `group_by_vars()`: A standard evaluation version of `fgroup_by()` that is slimmer and safer for programming, e.g. `data |> group_by_vars(ind1) |> collapg(custom = list(fmean = ind2, fsum = ind3))`. Or, using *magrittr*: 
 ```r 
 library(magrittr)
@@ -15,6 +19,8 @@ data %>%
 }
 ```
 
+* Added function `as_integer_factor()` to turn factors/factor columns into integer vectors. `as_numeric_factor()` already exists, but is memory inefficient for most factors where levels can be integers. 
+
 * `join()` now internally checks if the rows of the joined datasets match exactly. This check, using `identical(m, seq_row(y))`, is inexpensive, but, if `TRUE`, saves a full subset and deep copy of `y`. Thus `join()` now inherits the intelligence already present in functions like `fsubset()`, `roworder()` and `funique()` - a key for efficient data manipulation is simply doing less.  
 
 * In `join()`, if `attr = TRUE`, the `count` option to `fmatch()` is always invoked, so that the attribute attached always has the same form, regardless of `verbose` or `validate` settings. 

R/global_macros.R

@@ -105,7 +105,7 @@ get_collapse <- function(opts = NULL) if(is.null(opts)) as.list(.op) else if(len
                             "%r-%", "%r*%", "%r/%", "%r+%", "%rr%", "add_stub", "add_vars",
                             "add_vars<-", "all_funs", "all_identical", "all_obj_equal", "allNA",
                             "alloc", "allv", "any_duplicated", "anyv", "as_character_factor",
-                            "as_factor_GRP", "as_factor_qG", "as_numeric_factor", "as.character_factor",
+                            "as_factor_GRP", "as_factor_qG", "as_numeric_factor", "as_integer_factor", "as.character_factor",
                             "as.factor_GRP", "as.factor_qG", "as.numeric_factor", "atomic_elem",
                             "atomic_elem<-", "av", "av<-", "B", "BY", "BY.data.frame", "BY.default",
                             "BY.matrix", "cat_vars", "cat_vars<-", "char_vars", "char_vars<-",
@@ -177,7 +177,7 @@ get_collapse <- function(opts = NULL) if(is.null(opts)) as.list(.op) else if(len
 .COLLAPSE_ALL <- sort(unique(c("%-=%", "%!=%", "%!iin%", "%!in%", "%*=%", "%/=%", "%+=%", "%=%", "%==%", "%c-%", "%c*%", "%c/%", "%c+%",
                                "%cr%", "%iin%", "%r-%", "%r*%", "%r/%", "%r+%", "%rr%", "add_stub", "add_vars", "add_vars<-", "all_funs",
                                "all_identical", "all_obj_equal", "allNA", "alloc", "allv", "any_duplicated", "anyv", "as_character_factor",
-                               "as_factor_GRP", "as_factor_qG", "as_numeric_factor", "atomic_elem", "atomic_elem<-", "av", "av<-", "B", "BY",
+                               "as_factor_GRP", "as_factor_qG", "as_numeric_factor", "as_integer_factor", "atomic_elem", "atomic_elem<-", "av", "av<-", "B", "BY",
                                "cat_vars", "cat_vars<-", "char_vars", "char_vars<-", "cinv", "ckmatch", "collap", "collapg", "collapv", "colorder",
                                "colorderv", "copyAttrib", "copyMostAttrib", "copyv", "D", "dapply", "date_vars", "Date_vars", "date_vars<-",
                                "Date_vars<-", "descr", "Dlog", "fact_vars", "fact_vars<-", "fbetween", "fcompute", "fcomputev", "fcount",

R/small_helper.R

@@ -501,6 +501,16 @@ as_numeric_factor <- function(X, keep.attr = TRUE) {
   res
 }
 
+as_integer_factor <- function(X, keep.attr = TRUE) {
+  if(is.atomic(X)) if(keep.attr) return(ffka(X, as.integer)) else
+    return(as.integer(attr(X, "levels"))[X])
+  res <- duplAttributes(lapply(unattrib(X),
+    if(keep.attr) (function(y) if(is.factor(y)) ffka(y, as.integer) else y) else
+                  (function(y) if(is.factor(y)) as.integer(attr(y, "levels"))[y] else y)), X)
+  if(inherits(X, "data.table")) return(alc(res))
+  res
+}
+
 as_character_factor <- function(X, keep.attr = TRUE) {
   if(is.atomic(X)) if(keep.attr) return(ffka(X, tochar)) else
     return(as.character.factor(X))

README.md

@@ -21,7 +21,7 @@
 * To facilitate complex data transformation, exploration and computing tasks in R.
 * To help make R code fast, flexible, parsimonious and programmer friendly. 
 
-It further implements a [class-agnostic approach to R programming](https://sebkrantz.github.io/collapse/articles/collapse_object_handling.html), supporting base R, *tibble*, *grouped_df* (*tidyverse*), *data.table*, *sf*, *pseries*, *pdata.frame* (*plm*), and preserving many others (e.g. *units*, *xts*/*zoo*, *tsibble*). 
+It further implements a [class-agnostic approach to R programming](https://sebkrantz.github.io/collapse/articles/collapse_object_handling.html), supporting base R, *tibble*, *grouped_df* (*tidyverse*), *data.table*, *sf*, *units*, *pseries*, *pdata.frame* (*plm*), and *xts*/*zoo*. 
 
 **Key Features:**
 

_pkgdown.yml

@@ -210,6 +210,7 @@ articles:
   contents:
   - collapse_documentation
   - collapse_for_tidyverse_users
+  - collapse_and_sf
   - collapse_object_handling
 - title: Legacy (Pre v1.7)
   desc: Vignettes that cover functionality of versions <1.7. These
@@ -219,5 +220,4 @@ articles:
   - collapse_and_dplyr
   - collapse_and_data.table
   - collapse_and_plm
-  - collapse_and_sf
 

man/collapse-documentation.Rd

@@ -26,7 +26,7 @@ The following table fully summarizes the contents of \emph{\link{collapse}}. The
 \link[=fast-data-manipulation]{Fast Data Manipulation} \tab\tab Fast and flexible select, subset, summarise, mutate/transform, sort/reorder, combine, join, reshape, rename and relabel data. Some functions modify by reference and/or allow assignment. In addition a set of (standard evaluation) functions for fast selecting, replacing or adding data frame columns, including shortcuts to select and replace variables by data type.
 \tab\tab \code{\link[=fselect]{fselect(<-)}}, \code{\link[=fsubset]{fsubset/ss}}, \code{\link{fsummarise}}, \code{\link{fmutate}}, \code{\link{across}}, \code{\link[=ftransform]{(f/set)transform(v)(<-)}}, \code{\link[=fcompute]{fcompute(v)}}, \code{\link[=roworder]{roworder(v)}}, \code{\link[=colorder]{colorder(v)}}, \code{\link{rowbind}}, \code{\link{join}}, \code{\link{pivot}}, \code{\link[=frename]{(f/set)rename}}, \code{\link[=relabel]{(set)relabel}}, \code{\link[=get_vars]{get_vars(<-)}}, \code{\link[=add_vars]{add_vars(<-)}}, \code{\link[=num_vars]{num_vars(<-)}}, \code{\link[=cat_vars]{cat_vars(<-)}}, \code{\link[=char_vars]{char_vars(<-)}}, \code{\link[=fact_vars]{fact_vars(<-)}}, \code{\link[=logi_vars]{logi_vars(<-)}}, \code{\link[=date_vars]{date_vars(<-)}} \cr \cr \cr
 
-\link[=quick-conversion]{Quick Data Conversion} \tab\tab Quick conversions: data.frame <> data.table <> tibble <> matrix (row- or column-wise) <> list | array > matrix, data.frame, data.table, tibble | vector > factor, matrix, data.frame, data.table, tibble; and converting factors / all factor columns. \tab\tab \code{qDF}, \code{qDT}, \code{qTBL}, \code{qM}, \code{qF}, \code{mrtl}, \code{mctl}, \code{as_numeric_factor}, \code{as_character_factor} \cr \cr \cr
+\link[=quick-conversion]{Quick Data Conversion} \tab\tab Quick conversions: data.frame <> data.table <> tibble <> matrix (row- or column-wise) <> list | array > matrix, data.frame, data.table, tibble | vector > factor, matrix, data.frame, data.table, tibble; and converting factors / all factor columns. \tab\tab \code{qDF}, \code{qDT}, \code{qTBL}, \code{qM}, \code{qF}, \code{mrtl}, \code{mctl}, \code{as_numeric_factor}, \code{as_integer_factor}, \code{as_character_factor} \cr \cr \cr
 
 \link[=advanced-aggregation]{Advanced Data Aggregation} \tab\tab Fast and easy (weighted and parallelized) aggregation of multi-type data, with different functions applied to numeric and categorical variables. Custom specifications allow mappings of functions to variables + renaming. \tab\tab \code{collap(v/g)} \cr \cr \cr
 

man/collapse-package.Rd

@@ -12,7 +12,7 @@ Advanced and Fast Data Transformation
 \item To help make R code fast, flexible, parsimonious and programmer friendly. % \emph{collapse} is a fast  %to facilitate (advanced) data manipulation in R   % To achieve the latter,
 % collapse provides a broad set.. -> Nah, its not a misc package
 }
-It is made compatible with the \emph{tidyverse}, \emph{data.table}, \emph{sf} and the \emph{plm} approach to panel data, and non-destructively handles other classes such as \emph{xts}.
+It is made compatible with the \emph{tidyverse}, \emph{data.table}, \emph{sf}, \emph{units}, \emph{xts/zoo}, and the \emph{plm} approach to panel data.
 
 }
 \section{Getting Started}{

man/quick-conversion.Rd

@@ -8,6 +8,7 @@
 \alias{mctl}
 \alias{mrtl}
 \alias{as_numeric_factor}
+\alias{as_integer_factor}
 \alias{as_character_factor}
 %- Also NEED an '\alias' for EACH other topic documented here.
 \title{Quick Data Conversion}
@@ -18,7 +19,7 @@ Fast, flexible and precise conversion of common data objects, without method dis
 \item \code{qM} converts vectors, higher-dimensional arrays, data frames and suitable lists to matrix.
 \item \code{mctl} and \code{mrtl} column- or row-wise convert a matrix to list, data frame or \emph{data.table}. They are used internally by \code{qDF/qDT/qTBL}, \code{\link{dapply}}, \code{\link{BY}}, etc\dots
 \item \code{\link{qF}} converts atomic vectors to factor (documented on a separate page).
-\item \code{as_numeric_factor} and \code{as_character_factor} convert factors, or all factor columns in a data frame / list, to character or numeric (by converting the levels).
+\item \code{as_numeric_factor}, \code{as_integer_factor}, and \code{as_character_factor} convert factors, or all factor columns in a data frame / list, to character or numeric (by converting the levels).
 }
 }
 \usage{
@@ -37,12 +38,13 @@ mrtl(X, names = FALSE, return = "list")
 # Converting factors or factor columns
 
   as_numeric_factor(X, keep.attr = TRUE)
+  as_integer_factor(X, keep.attr = TRUE)
 as_character_factor(X, keep.attr = TRUE)
 
 }
 %- maybe also 'usage' for other objects documented here.
 \arguments{
-  \item{X}{a vector, factor, matrix, higher-dimensional array, data frame or list. \code{mctl} and \code{mrtl} only accept matrices, \code{as_numeric_factor} and \code{as_character_factor} only accept factors, data frames or lists.}
+  \item{X}{a vector, factor, matrix, higher-dimensional array, data frame or list. \code{mctl} and \code{mrtl} only accept matrices, \code{as_numeric_factor}, \code{as_integer_factor} and \code{as_character_factor} only accept factors, data frames or lists.}
   \item{row.names.col}{can be used to add an column saving names or row.names when converting objects to data frame using \code{qDF/qDT/qTBL}. \code{TRUE} will add a column \code{"row.names"}, or you can supply a name e.g. \code{row.names.col = "variable"}. With \code{qM}, the argument has the opposite meaning, and can be used to select one or more columns in a data frame/list which will be used to create the rownames of the matrix e.g. \code{qM(iris, row.names.col = "Species")}. In this case the column(s) can be specified using names, indices, a logical vector or a selector function. See Examples.}
   \item{keep.attr}{logical. \code{FALSE} (default) yields a \emph{hard} / \emph{thorough} object conversion: All unnecessary attributes are removed from the object yielding a plain matrix / data.frame / \emph{data.table}. \code{FALSE} yields a \emph{soft} / \emph{minimal} object conversion: Only the attributes 'names', 'row.names', 'dim', 'dimnames' and 'levels' are modified in the conversion. Other attributes are preserved. See also \code{class}.}
   \item{class}{if a vector of classes is passed here, the converted object will be assigned these classes. If \code{NULL} is passed, the default classes are assigned: \code{qM} assigns no class, \code{qDF} a class \code{"data.frame"}, and \code{qDT} a class \code{c("data.table", "data.frame")}. If \code{keep.attr = TRUE} and \code{class = NULL} and the object already inherits the default classes, further inherited classes are preserved. See Details and the Example. }
@@ -77,7 +79,8 @@ The default \code{keep.attr = FALSE} ensures \emph{hard} conversions so that all
 \code{qM} - returns a matrix\cr
 \code{mctl}, \code{mrtl} - return a list, data frame or \emph{data.table} \cr
 \code{qF} - returns a factor\cr
-\code{as_numeric_factor} - returns X with factors converted to numeric variables\cr
+\code{as_numeric_factor} - returns X with factors converted to numeric (double) variables\cr
+\code{as_integer_factor} - returns X with factors converted to integer variables\cr
 \code{as_character_factor} - returns X with factors converted to character variables
 }
 % \note{