changed the behaviour of import.Statechanges to display helpful infos…

… after import. Also updated interval2state to work with existing state columns

R/Brown.R

@@ -59,7 +59,7 @@ Brown2reference <- function(dataset,
 
   #give an error or warning if the reference column is present
   if(Brown.rec.colname.str %in% names(dataset) & !overwrite.Reference) 
-    stop("A Reference column with the given (or default) name is already part of the dataset. Please remove the column or choose a different name")
+    stop("A Reference column with the given (or default) name is already part of the dataset. Please remove the column, choose a different name, or set `overwrite.Reference = TRUE`")
   if(Brown.rec.colname.str %in% names(dataset)) 
     warning("A Reference column with the given (or default) name is already part of the dataset. It is overwritten, because `overwrite.Reference = TRUE ` was set.")
 

R/import_States.R

@@ -158,8 +158,9 @@ import.Statechanges <- function(filename, path = NULL,
   # Rename columns using the {{ }} syntax, remove NA and group by ID, arrange 
   # it, recode, and set Datetimes as POSIXct
   data <- dplyr::rename(data,
-                        {{ ID.newname }} := {{ ID.colname }}) %>% 
-    dplyr::filter(!is.na({{ ID.newname }}), !is.na({{ Datetime.column }})) %>% 
+                        {{ ID.newname }} := {{ ID.colname }},
+                        Datetime = {{ Datetime.column }}) %>% 
+    dplyr::filter(!is.na({{ ID.newname }}), !is.na(Datetime)) %>% 
     dplyr::group_by({{ ID.newname }})
 
   data <- 
@@ -169,13 +170,17 @@ import.Statechanges <- function(filename, path = NULL,
     } else data %>% 
         dplyr::rename({{ State.newname }} := {{ State.colnames }})
 
+  if(!lubridate::is.POSIXct(data$Datetime)){
+    data <- data %>%  
+      dplyr::mutate(Datetime = 
+                      lubridate::parse_date_time(Datetime,   
+                                                 orders = Datetime.format, tz
+                      ))
+  }
+
   data <- data %>%  
-    dplyr::mutate(Datetime = 
-                    lubridate::parse_date_time({{ Datetime.column }},   
-                                               orders = Datetime.format, tz
-                    ),
-                  {{ ID.newname }} := factor({{ ID.newname }})) %>% 
-    dplyr::arrange({{ Datetime.column }}, .by_group = TRUE)
+    dplyr::mutate({{ ID.newname }} := factor({{ ID.newname }})) %>% 
+    dplyr::arrange(Datetime, .by_group = TRUE)
 
   # Return the Data ----------------------------------------------------------
 
@@ -194,5 +199,7 @@ import.Statechanges <- function(filename, path = NULL,
       )
   }
 
+  import.info(data, "Statechanges", tz, {{ ID.newname }})
+
   return(data)
 }

R/interval2state.R

@@ -10,14 +10,18 @@
 #'   `Interval` columns. Interval data can be created, e.g., through
 #'   [sc2interval()].
 #' @param State.colname,Interval.colname  Column names of the `State` and
-#'   `Interval` in the `State.interval.dataset`. Expects a `symbol`.
+#'   `Interval` in the `State.interval.dataset`. Expects a `symbol`. `State`
+#'   can't be in the `dataset` yet or the function will give an error. You can
+#'   also set `overwrite.State = TRUE`.
 #' @param ID.colname.dataset,ID.colname.interval Column names of the
 #'   participant's `Id` in both the `dataset` and the `State.interval.dataset`.
 #'   On the off-chance that there are inconsistencies, the names can be
 #'   different. If the datasets where imported and preprocessed with
 #'   [LightLogR], this just works. Both datasets need an `Id`, because the
 #'   states will be added based not only on the `Datetime`, but also depending
 #'   on the dataset.
+#' @param overwrite.State If `TRUE` (defaults to `FALSE`), the function will
+#'   overwrite the `State.colname` column if it already exists.
 #'
 #' @return One of
 #' * a `data.frame` object identical to `dataset` but with the state column added
@@ -65,6 +69,7 @@ interval2state <- function(dataset,
                            Interval.colname = Interval,
                            ID.colname.dataset = Id,
                            ID.colname.interval = Id,
+                           overwrite.State = FALSE,
                            output.dataset = TRUE) {
 
   # Initial Checks ----------------------------------------------------------
@@ -93,8 +98,25 @@ interval2state <- function(dataset,
     "output.dataset must be a logical" = is.logical(output.dataset)
   )
 
+  #give an error or warning if the reference column is present
+  if(all(
+    State.colname.defused %in% names(dataset),
+    !overwrite.State,
+    State.colname.defused %in% names(State.interval.dataset)))
+    stop("A `State` column with the given (or default) name is already part of the dataset. Please remove the column, rename it, or set `overwrite.State = TRUE`")
+    if(all(
+      State.colname.defused %in% names(dataset),
+      State.colname.defused %in% names(State.interval.dataset))) 
+      warning("A `State` column with the given (or default) name is already part of the dataset. It is overwritten, because `overwrite.State = TRUE ` was set.")
+
+
   # Manipulation ----------------------------------------------------------
 
+  #remove the State.colname from the dataset if it is already present
+  if(State.colname.defused %in% names(dataset)) {
+    dataset <- dataset %>% dplyr::select(- {{ State.colname }})
+  }
+
   #add a marker to the dataset that tells us, what the original Timepoints were
   dataset <- 
     dataset %>% 

README.Rmd

@@ -21,6 +21,7 @@ knitr::opts_chunk$set(
 
 <!-- badges: end -->
 
+
 Personalized luminous exposure data is progressively gaining importance in various sectors, including research, occupational affairs, and fitness tracking. Data are collected through a proliferating selection of wearable loggers and dosimeters, varying in size, shape, functionality, and output format. Despite or maybe because of numerous use cases, the field lacks a unified framework for collecting, validating, and analyzing the accumulated data. This issue increases the time and expertise necessary to handle such data and also compromises the FAIRness (Findability, Accessibility, Interoperability, Reusability) of the results, especially in meta-analyses.
 
 ##### Please note that LightLogR is work in progress! If you are interested in the project and want to know more, please give us a [message](mailto:[email protected])

README.md

@@ -89,11 +89,11 @@ dataset <- import.LYS(filename, tz = "Europe/Berlin")
 #> End: 2023-06-22 23:59:48
 #> Timespan: 2 days
 #> Observation intervals: 
-#>   interval.time     n pct    
-#> 1 15 secs       10015 87.689%
-#> 2 16 secs        1367 11.969%
-#> 3 17 secs          23 0.201% 
-#> 4 18 secs          16 0.140%
+#>   Id              interval.time     n pct    
+#> 1 sample_data_LYS 15s           10015 87.689%
+#> 2 sample_data_LYS 16s            1367 11.969%
+#> 3 sample_data_LYS 17s              23 0.201% 
+#> 4 sample_data_LYS 18s              16 0.140%
 
 dataset %>% select(Datetime, lux, kelvin, MEDI) %>%  slice(8000:8005) %>% 
   flextable() %>% autofit()

tests/testthat/_snaps/import_States.md

@@ -7,6 +7,27 @@
         State.colnames = c("sleep", "offset"), State.encoding = c("sleep", "wake"),
         ID.colname = record_id, sep = ";", dec = ",")
     Output
+      Successfully read in 14 observations from Statechanges-file
+      Timezone set is UTC.
+      The system timezone is Europe/Berlin. Please correct if necessary!
+      Start: 2023-08-28 23:20:00
+      End: 2023-09-04 07:25:00
+      Timespan: 6.3 days
+      Observation intervals: 
+         Id    interval.time             n pct  
+       1 205   34860s (~9.68 hours)      1 8%   
+       2 205   35520s (~9.87 hours)      1 8%   
+       3 205   35700s (~9.92 hours)      1 8%   
+       4 205   36000s (~10 hours)        1 8%   
+       5 205   36900s (~10.25 hours)     1 8%   
+       6 205   37020s (~10.28 hours)     1 8%   
+       7 205   37920s (~10.53 hours)     1 8%   
+       8 205   45780s (~12.72 hours)     1 8%   
+       9 205   48480s (~13.47 hours)     1 8%   
+      10 205   49200s (~13.67 hours)     1 8%   
+      11 205   49500s (~13.75 hours)     1 8%   
+      12 205   50040s (~13.9 hours)      1 8%   
+      13 205   50580s (~14.05 hours)     1 8%   
       # A tibble: 14 x 3
       # Groups:   Id [1]
          Id    State Datetime           
@@ -35,15 +56,29 @@
         State.colnames = "comments", Datetime.column = sleep, ID.colname = record_id,
         sep = ";", dec = ",", structure = "long")
     Output
+      Successfully read in 7 observations from Statechanges-file
+      Timezone set is UTC.
+      The system timezone is Europe/Berlin. Please correct if necessary!
+      Start: 2023-08-28 23:20:00
+      End: 2023-09-03 21:30:00
+      Timespan: 5.9 days
+      Observation intervals: 
+        Id    interval.time             n pct  
+      1 205   81300s (~22.58 hours)     1 17%  
+      2 205   84900s (~23.58 hours)     1 17%  
+      3 205   85500s (~23.75 hours)     1 17%  
+      4 205   86100s (~23.92 hours)     1 17%  
+      5 205   86400s (~1 days)          1 17%  
+      6 205   87600s (~1.01 days)       1 17%  
       # A tibble: 7 x 3
       # Groups:   Id [1]
         Id    State                                                Datetime           
         <fct> <chr>                                                <dttm>             
-      1 205   woke Up and could Not Fall asleep. went to the dini~ 2023-09-01 23:10:00
-      2 205   none                                                 2023-09-02 22:55:00
-      3 205   no                                                   2023-09-03 21:30:00
-      4 205   Slept longer than usual since my kids are on Summer~ 2023-08-28 23:20:00
-      5 205   no                                                   2023-08-29 23:40:00
-      6 205   Kids slept in my bed                                 2023-08-30 23:15:00
-      7 205   none                                                 2023-08-31 23:15:00
+      1 205   Slept longer than usual since my kids are on Summer~ 2023-08-28 23:20:00
+      2 205   no                                                   2023-08-29 23:40:00
+      3 205   Kids slept in my bed                                 2023-08-30 23:15:00
+      4 205   none                                                 2023-08-31 23:15:00
+      5 205   woke Up and could Not Fall asleep. went to the dini~ 2023-09-01 23:10:00
+      6 205   none                                                 2023-09-02 22:55:00
+      7 205   no                                                   2023-09-03 21:30:00
 

vignettes/articles/Styling.Rmd

@@ -609,7 +609,7 @@ Plot +
   annotate("text", x=x, y = 4000, label = "- Daylight Potential", 
            hjust = 0, col = "#0073C2DD")
 
-ggplot2::ggsave("Brown_et_al_2022.png", width = 7, height = 4, dpi = 600)
+# ggplot2::ggsave("Brown_et_al_2022.png", width = 7, height = 4, dpi = 600)
 
 ```