Merge pull request #9 from karlropkins/main

updating pls functions

.Rproj.user/shared/notebooks/paths

@@ -1,7 +1,8 @@
 C:/Users/trakradmin/OneDrive - University of Leeds/Documents/ITS/projects/NERC_TRANSISTION/events/Clean Air Networks Conference/naei estimate.Rmd="1BB48545"
 C:/Users/trakradmin/OneDrive - University of Leeds/Documents/_isolateContribution&breakPointAnalysis_KR_20230824.R="F18B98A3"
 C:/Users/trakradmin/OneDrive - University of Leeds/Documents/pkg/respeciate/_projects/_paper_01_IntroToRespeciate/MS Access Versions/speciate_5.2_0/test.R="FCE2E494"
-C:/Users/trakradmin/OneDrive - University of Leeds/Documents/pkg/respeciate/_projects/marylebone02/_marylebone_metals_03.Rmd="63CDB89D"
+C:/Users/trakradmin/OneDrive - University of Leeds/Documents/pkg/respeciate/_projects/marylebone03/_marylebone_analysis_pls_01.Rmd="F2B723A3"
+C:/Users/trakradmin/OneDrive - University of Leeds/Documents/pkg/respeciate/_projects/marylebone03/_marylebone_metals_03.Rmd="D2C38DFE"
 C:/Users/trakradmin/OneDrive - University of Leeds/Documents/pkg/respeciate/_projects/match01/_match_notes_01.Rmd="A446C96C"
 C:/Users/trakradmin/OneDrive - University of Leeds/Documents/pkg/respeciate/test/respeciate/.Rbuildignore="BAFF788D"
 C:/Users/trakradmin/OneDrive - University of Leeds/Documents/pkg/respeciate/test/respeciate/.Rproj.user/shared/notebooks/paths="DB89FCB7"

DESCRIPTION

@@ -1,14 +1,16 @@
 Package: respeciate
 Title: Speciation profiles for gases and aerosols
-Version: 0.2.3
-Date: 2023-09-23
-Description: Acess to the US.EPA Speciate (v5.2) tool, to generate speciation profiles for
-          gases and particles. More details in Simon et al (2010) <doi:10.5094/APR.2010.026>.
+Version: 0.2.4
+Date: 2023-10-14
+Description: Acess to the US.EPA Speciate (v5.2) tool, to generate speciation profiles
+          for gases and particles. More details in Simon et al (2010)
+          <doi:10.5094/APR.2010.026>.
 Type: Package
-Authors@R: c( person(given = "Sergio", family = "Ibarra-Espinosa", role = c("aut", "cre"),
-          email = "[email protected]", comment = c(ORCID = "0000-0002-3162-1905")),
-          person(given = "Karl", family = "Ropkins", role = c("aut"), email =
-          "[email protected]", comment = c(ORCID = "0000-0002-0294-6997")) )
+Authors@R: c( person(given = "Sergio", family = "Ibarra-Espinosa", role = c("aut",
+          "cre"), email = "[email protected]", comment = c(ORCID =
+          "0000-0002-3162-1905")), person(given = "Karl", family = "Ropkins", role =
+          c("aut"), email = "[email protected]", comment = c(ORCID =
+          "0000-0002-0294-6997")) )
 License: MIT + file LICENSE
 URL: https://github.com/atmoschem/respeciate
 BugReports: https://github.com/atmoschem/respeciate/issues

NAMESPACE

@@ -2,15 +2,18 @@
 
 S3method(plot,respeciate)
 S3method(print,respeciate)
+S3method(print,rsp_pls)
 S3method(summary,respeciate)
 export(find_code)
-export(pls_fit_parent)
+export(pls_fit_species)
 export(pls_plot)
 export(pls_plot_profile)
 export(pls_plot_species)
+export(pls_rebuild)
 export(pls_refit_species)
 export(pls_report)
 export(sp_average_profile)
+export(sp_build_rsp_x)
 export(sp_dcast)
 export(sp_dcast_profile)
 export(sp_dcast_species)
@@ -40,7 +43,7 @@ export(spq_pm.simplified)
 export(spx_btex)
 export(spx_copy)
 export(spx_n_alkane)
-import(data.table)
+importFrom(data.table,":=")
 importFrom(grDevices,as.graphicsAnnot)
 importFrom(grDevices,cm.colors)
 importFrom(grDevices,colorRampPalette)

NEWS.md

@@ -1,5 +1,12 @@
 # Version 0.0 - Release Notes
 
+* [0.2.4] 
+    * released 2023-11-14 
+    * added functions: pls_fit_species 
+    * added draft rsp_pls and rsp_x object classes 
+    * added draft sp_build_rsp_x  
+    * moved from importing data.table to data.table::as.data.table, etc... 
+
 * [0.2.3] 
     * released 2023-09-26 
     * added functions: sp_rescale_species, sp_dcast, sp_dcast_species 

R/respeciate.generics.R

@@ -8,7 +8,7 @@
 #    multiple functions
 
 #' @description When supplied a \code{respeciate}
-#' object, \code{\link{print}} manages its appearance.
+#' object or similar, \code{\link{print}} manages its appearance.
 #' @description When supplied a \code{respeciate}
 #' object, \code{\link{plot}} provides a basic plot
 #' output. This uses base function \code{\link{barplot}};
@@ -74,6 +74,43 @@ print.respeciate <- function(x, n = NULL, ...){
 
 
 
+#############################################
+#############################################
+## print.rsp_pls
+#############################################
+#############################################
+
+#' @rdname respeciate.generics
+#' @method print rsp_pls
+#' @export
+
+# notes
+############################
+
+#currently just a print tidier
+#    so user not catching this does not get a
+#        screen dump of model lists
+
+#needs work if we want it to actually be useful...
+
+print.rsp_pls <- function(x, n = NULL, ...){
+  #expecting list of nls models
+  report <- "respeciate pls model:"
+  if(!is.list(x)){
+    report <- paste(report, "\n   Suspect!\n", sep="")
+  } else{
+    temp <- unlist(lapply(x, function(x) !is.null(x)))
+    temp <- length(temp[temp])
+    report <- paste(report, "\n   list of ", length(x), " profile models",
+                    "\n   (", temp, " good)\n", sep="")
+  }
+  cat(report)
+}
+
+
+
+
+
 #' @rdname respeciate.generics
 #' @method plot respeciate
 #' @export
@@ -278,7 +315,7 @@ summary.respeciate <-
 
     #v0.3 summary
 
-    xx <- as.data.table(object)
+    xx <- data.table::as.data.table(object)
 
     .xargs <- list(...)
     .max.n <- if("max.n" %in% names(.xargs)){
@@ -339,7 +376,7 @@ summary.respeciate <-
     if(!.silent){
       if(nrow(out) > .max.n){
         print(head(out[c(1,2,5,6)], n = .max.n))
-        cat("  [forestortened - showing ", .max.n, " of ", nrow(out), "]",
+        cat("  [forestortened - showing ", .max.n, " of ", nrow(out), "]\n",
             sep="")
       } else {
         print(out[c(1,2,5,6)])
@@ -518,6 +555,9 @@ rsp_build_respeciate <-
   }
 
 
+
+
+
 ###########################
 #split respeciate by profile
 ###########################

R/sp.R

@@ -1,6 +1,6 @@
 #' @name sp
 #' @title sp_ functions
-#' @aliases sp_profile
+#' @aliases sp_profile sp_build_rsp_x
 
 
 #' @description sp function to get profiles from the R (re)SPECIATE archive
@@ -14,17 +14,48 @@
 #' the \code{code}s as a named \code{PROFILE_NAME} column.
 #' @param include.refs logical, include profile reference information when
 #' getting the requested profile(s) from the archive, default \code{FALSE}.
+#' @param x (for \code{sp_build}s only) A \code{data.frame} or similar to
+#' be converted into a \code{respeciate} object for comparison with
+#' SPECIATE profiles.
+#' @param profile_name,profile_code (for \code{sp_build}s only;
+#' \code{character})  The name of the column in \code{x} containing
+#' profile name and code, respectively. If not already named according
+#' to SPECIATE conventions, at least one of these will need to be assigned.
+#' @param species_name,species_id (for \code{sp_build}s only;
+#' \code{character})  The name of the column in \code{x} containing
+#' species name and id, respectively. If not already named according
+#' to SPECIATE conventions, at least one of these will need to be assigned.
+#' @param value (for \code{sp_build}s only; \code{character})  The name
+#' of the column in \code{x} containing measurement values. If not already
+#' named according to SPECIATE conventions, this will need to be assigned.
+#' @param ... additional arguments, currently ignored.
 #' @return \code{sp_profile} returns a object of
 #' \code{respeciate} class, a \code{data.frame} containing a
 #' (re)SPECIATE profile.
-#' @note The option \code{include.refs} adds profile source reference
+#'
+#' \code{sp_build}s attempt to build and return a (re)SPECIATE-like profile
+#' that can be compared with with data in re(SPECIATE).
+#' @note With \code{sp_profile}:
+#'
+#' The option \code{include.refs} adds profile source reference
 #' information to the returned \code{respeciate} data set. The default option
 #' is to not include these because some profiles have several associated
 #' references and including these replicates records, once per reference.
 #' \code{respeciate} code is written to handle this but if you are developing
 #' own methods or code and include references in any profile build you may be
 #' biasing some analyses in favor of those multiple-reference profile unless
 #' you check and account such cases.
+#'
+#' With \code{sp_build}s:
+#'
+#' It is particularly IMPORTANT that you use EPA SPECIATE conventions when
+#' assign species information if you want to compare your data with SPECIATE
+#' profiles. Currently, working on option to improve on this (and very happy
+#' to discuss if anyone has ideas), but current best suggestion is: (1)
+#' identify the SPECIATE species code for all the species in your data set,
+#' and (2) assign these as \code{species_id} when \code{sp_build}ing. The
+#' function will associate the \code{species_name}.
+#'
 #' @references
 #' Simon, H., Beck, L., Bhave, P.V., Divita, F., Hsu, Y., Luecken, D.,
 #' Mobley, J.D., Pouliot, G.A., Reff, A., Sarwar, G. and Strum, M., 2010.
@@ -94,11 +125,11 @@ sp_profile <- function(code, include.refs=FALSE) {
          call.=FALSE)
   }
 
-  PROFILES <- as.data.table(sysdata$PROFILES)
-  SPECIES <- as.data.table(sysdata$SPECIES)
-  SPECIES_PROPERTIES <- as.data.table(sysdata$SPECIES_PROPERTIES)
-  PROFILE_REFERENCE <- as.data.table(sysdata$PROFILE_REFERENCE)
-  REFERENCES <- as.data.table(sysdata$REFERENCES)
+  PROFILES <- data.table::as.data.table(sysdata$PROFILES)
+  SPECIES <- data.table::as.data.table(sysdata$SPECIES)
+  SPECIES_PROPERTIES <- data.table::as.data.table(sysdata$SPECIES_PROPERTIES)
+  PROFILE_REFERENCE <- data.table::as.data.table(sysdata$PROFILE_REFERENCE)
+  REFERENCES <- data.table::as.data.table(sysdata$REFERENCES)
 
   ##########################
   #testing tolower below
@@ -131,6 +162,131 @@ sp_profile <- function(code, include.refs=FALSE) {
 
 
 
+##############################
+# sp_build_rsp_x
+##############################
+
+#' @rdname sp
+#' @export
+
+sp_build_rsp_x <-
+  function(x, profile_code, profile_name,
+           species_name, species_id,
+           value, ...){
+
+    # light build for a rsp_x data object
+    # might need spec_mwt
+
+    # current build rules
+    # profile_name:  if not there, if sent in call use,
+    #                              else if there use profile_code
+    # profile_code:  if not there, if sent in call use,
+    #                              else if there use profile_name
+    # species_name:  if not there, if sent in call use,
+    #                              else if there use use species_id to look-up
+    #                              if any missing, warn
+    # species_id:    if not there, if sent in call use,
+    #                              else if there use species_name to look-up
+    #                              if any missing, warn
+    # .value:        if not there, if sent in call use.
+    # WEIGHT_PERCENT:if not there, if sent in call use.
+    #                              else if there use .value to look-up
+
+    # don't build/error if any of these missing and end of build
+
+    # redundant?
+    # currently not using ...
+    .x.args <- list(...)
+
+    #if not there and sent in call
+
+    #note:
+    #current making all BUT values, character class
+    if(!"PROFILE_NAME" %in% names(x) & (!missing(profile_name))){
+      if(!profile_name %in% names(x)){
+        stop("sp_build> '", as.character(profile_name)[1],
+             "' not in 'x'...", sep="", call. = FALSE)
+      }
+      x$PROFILE_NAME <- as.character(x[, profile_name])
+    }
+    if(!"PROFILE_CODE" %in% names(x) & (!missing(profile_code))){
+      if(!profile_code %in% names(x)){
+        stop("sp_build> '", as.character(profile_code)[1],
+             "' not in 'x'...", sep="", call. = FALSE)
+      }
+      x$PROFILE_CODE <- as.character(x[, profile_code])
+    }
+    if(!"SPECIES_NAME" %in% names(x) & (!missing(species_name))){
+      if(!species_name %in% names(x)){
+        stop("sp_build> '", as.character(species_name)[1],
+             "' not in 'x'...", sep="", call. = FALSE)
+      }
+      x$SPECIES_NAME <- as.character(x[, species_name])
+    }
+    if(!"SPECIES_ID" %in% names(x) & (!missing(species_id))){
+      if(!species_id %in% names(x)){
+        stop("sp_build> '", as.character(species_id)[1],
+             "' not in 'x'...", sep="", call. = FALSE)
+      }
+      x$SPECIES_ID <- as.character(x[, species_id])
+    }
+    if(!".value" %in% names(x) & (!missing(value))){
+      if(!value %in% names(x)){
+        stop("sp_build> '", as.character(value)[1],
+             "' not in 'x'...", sep="", call. = FALSE)
+      }
+      x$.value <- x[, value]
+    }
+
+    #if still not there try to assign using what is there
+
+    if("PROFILE_NAME" %in% names(x) & !"PROFILE_CODE" %in% names(x)){
+      x$PROFILE_CODE <- x$PROFILE_NAME
+    }
+    if("PROFILE_CODE" %in% names(x) & !"PROFILE_NAME" %in% names(x)){
+      x$PROFILE_NAME <- x$PROFILE_CODE
+    }
+    test <- c("SPECIES_NAME", "SPECIES_ID")[c("SPECIES_NAME", "SPECIES_ID")
+                                            %in% names(x)]
+    if(length(test)==1){
+      #one there, other as look-up
+      .tmp <- data.table::as.data.table(
+        sysdata$SPECIES_PROPERTIES[c("SPECIES_NAME", "SPECIES_ID")]
+      )
+      .tmp$SPECIES_NAME <- as.character(.tmp$SPECIES_NAME)
+      .tmp$SPECIES_ID <- as.character(.tmp$SPECIES_ID)
+      x <- merge(data.table::as.data.table(x),
+                 data.table::as.data.table(.tmp),
+                 all.x=TRUE, all.y=FALSE, allow.cartesian=TRUE)
+      x <- as.data.frame(x)
+    }
+    if(".value" %in% names(x) & !"WEIGHT_PERCENT" %in% names(x)){
+      x$WEIGHT_PERCENT <- x$.value
+    }
+
+    #test what we have
+
+    .test <- c("PROFILE_NAME", "PROFILE_CODE", "SPECIES_NAME", "SPECIES_ID",
+               ".value", "WEIGHT_PERCENT")
+    .test <- .test[!.test %in% names(x)]
+    if(length(.test)>0){
+      stop("sp_build> bad data structure, expected column(s) missing/unassigned:\n",
+           paste(.test, sep="", collapse = ", "), "\n", sep="", call.=FALSE)
+    }
+    if(any(is.na(x$SPECIES_ID)) | any(is.na(x$SPECIES_NAMES))){
+      warning("sp_build> suspect species data, values missing:\n",
+              "(respeciate needs valid species entries)\n",
+              sep="", call.=FALSE)
+    }
+
+    x <- as.data.frame(x)
+    class(x) <- c("rsp_x", "respeciate", "data.frame")
+    x
+  }
+
+
+
+
 
 
 

R/sp.average.R

@@ -82,7 +82,7 @@ sp_average_profile <- function(x, code = NULL, name = NULL, method = 1,
   #save class to return as is..
   #    thinking about this
   tmp <- class(x)
-  xx <- as.data.table(x)
+  xx <- data.table::as.data.table(x)
 
   #save profiles
   test <- unique(x$PROFILE_CODE)
@@ -109,7 +109,10 @@ sp_average_profile <- function(x, code = NULL, name = NULL, method = 1,
   out <- xx[,
             .(PROFILE_NAME = PROFILE_NAME[1],
               SPECIES_NAME = SPECIES_NAME[1],
-              SPEC_MW = SPEC_MW[1],
+  ##########################
+  # testing
+              #SPEC_MW = SPEC_MW[1],
+  ##########################
               .total = sum(.value, na.rm = TRUE),
               .value = mean(.value, na.rm = TRUE),
               .n = length(.value[!is.na(.value)]),