Prepare release v0.2.0

Author: mrustl

DESCRIPTION

@@ -1,11 +1,11 @@
 Package: kwb.BerlinWaterModel.public
 Title: R Package of Berlin Water Model
-Version: 0.1.0
+Version: 0.2.0
 Authors@R: c(
-    person("Daniel", "Wicke", , "daniel.wicke@kompetenz-wasser.de", role = "aut",
-           comment = c(ORCID = "0000-0002-5722-5433")),
     person("Michael", "Rustler", , "michael.rustler@kompetenz-wasser.de", role = c("aut", "cre"),
            comment = c(ORCID = "0000-0003-0647-7726")),
+    person("Daniel", "Wicke", , "daniel.wicke@kompetenz-wasser.de", role = "aut",
+           comment = c(ORCID = "0000-0002-5722-5433")),
     person("IMPETUS", role = "fnd"),
     person("Kompetenzzentrum Wasser Berlin gGmbH (KWB)", role = "cph")
   )
@@ -36,7 +36,9 @@ Imports:
     units
 Suggests: 
     covr,
+    DT,
     knitr,
+    openxlsx, 
     rmarkdown
 VignetteBuilder: 
     knitr

NEWS.md

@@ -1,10 +1,15 @@
+# [kwb.BerlinWaterModel.public 0.2.0](https://github.com/KWB-R/kwb.BerlinWaterModel.public/releases/tag/v0.2.0) <small>2026-03-20</small>
+
+* Finalisation of example input dataset for year 2019 (including WW/WWTP flows) 
+
+
 # [kwb.BerlinWaterModel.public 0.1.0](https://github.com/KWB-R/kwb.BerlinWaterModel.public/releases/tag/v0.1.0) <small>2025-12-17</small>
 
-* first public version of kwb.BerlinWaterMode.public for data management plan of IMPETUS EU project (flow data for gallery abstraction
+* First public version of kwb.BerlinWaterMode.public for data management plan of IMPETUS EU project (flow data for gallery abstraction
 of water works and wastewater treatment plants preliminary set to 0, public data set in coordination by BWB and will be available soon)
 
 * Added a `NEWS.md` file to track changes to the package.
 
-* see https://style.tidyverse.org/news.html for writing a good `NEWS.md`
+* See https://style.tidyverse.org/news.html for writing a good `NEWS.md`
 
 

R/dataset_cso.R

@@ -1,8 +1,9 @@
-#' Dataset: Combined Sewer Overflows (cso) for a few rainfall events simulated with Infoworks
+#' Dataset: Combined Sewer Overflows (cso) for one rainfall event simulated with Infoworks in 2019
 #'
-#' Dataset with combined sewer overflow events for a few rainfall events simulated with Infoworks
+#' Dataset with combined sewer overflow events for one rainfall rainfall event simulated with Infoworks
+#' in 2019
 #'
-#' @format A tibble with 336,672 rows and five columns
+#' @format A tibble with 12,096 rows and five columns
 #' \describe{
 #'   \item{file_name}{filename of data origin}
 #'   \item{datetime}{datetime}

R/dataset_evapo_p.R

@@ -2,7 +2,7 @@
 #'
 #' Daily potential evaporation based on DWD 1x1 km raster data.
 #'
-#' @format A tibble with 7,670 rows and 10 columns:
+#' @format A tibble with 365 rows and 10 columns:
 #' \describe{
 #'   \item{file}{Name of the file from the DWD https/ftp server}
 #'   \item{date}{Date}

R/dataset_inflows.R

@@ -1,8 +1,8 @@
-#' Dataset: Inflows
+load#' Dataset: Inflows
 #'
 #' Dataset with inflows
 #'
-#' @format A tibble with 398,840 rows and three columns
+#' @format A tibble with 21,170 rows and three columns
 #' \describe{
 #'   \item{date}{date}
 #'   \item{id}{id of inflow station}

R/dataset_rain.R

@@ -2,7 +2,7 @@
 #'
 #' Dataset with rainfall data (based on DWD station 0433)
 #'
-#' @format A tibble with 247,076 rows and two columns
+#' @format A tibble with 8,721 rows and two columns
 #' \describe{
 #'   \item{datetime}{datetime}
 #'   \item{DWD_0433}{hourly rainfall in mm for DWD rainstation 0433}

R/dataset_ww.R

@@ -2,7 +2,7 @@
 #'
 #' Dataset with waterworks abstractions per gallery
 #'
-#' @format A tibble with 17,141 rows and three columns
+#' @format A tibble with 828 rows and three columns
 #' \describe{
 #'   \item{date}{date}
 #'   \item{id}{id of WW gallery}

R/dataset_wwtp.R

@@ -2,7 +2,7 @@
 #'
 #' Dataset with WWTP inflows
 #'
-#' @format A tibble with 1,152 rows and three columns
+#' @format A tibble with 4015 rows and three columns
 #' \describe{
 #'   \item{date}{date}
 #'   \item{id}{id of WWTP}

data-raw/config_complete.R

@@ -9,20 +9,20 @@ config <- kwb.BerlinWaterModel.public::add_rain_direct_and_evaporation(config)
 
 config <- kwb.BerlinWaterModel.public::add_tracers(config)
 
-config <- kwb.BerlinWaterModel.public::add_substances(config)
+#config <- kwb.BerlinWaterModel.public::add_substances(config)
 
 network <- kwb.BerlinWaterModel.public::prepare_network(config)
 
 
 # plot interactive network map ###############################################
 
 ### Network graph
-#net_complex <- kwb.BerlinWaterModel.public::plot_network_complex(network,
-#                                                        config,
-#                                                        show_labels = TRUE)
+net_complex <- kwb.BerlinWaterModel.public::plot_network_complex(
+  network,
+  config,
+  show_labels = TRUE)
 
-#htmlwidgets::saveWidget(net_complex, file = "water-cycle_complex.html")
-#zip(zipfile = "water-cycle_complex.zip", files = "water-cycle_complex.html")
+htmlwidgets::saveWidget(net_complex, file = "water-cycle_complex.html")
 
 
 # data preparation ###########################################################
@@ -48,30 +48,33 @@ input_list <- kwb.BerlinWaterModel.public::prepare_input(temporal_resolution = t
                                                   ww = inputs$ww,
                                                   wwtp = inputs$wwtp,
                                                   bfshare_dynamic = FALSE,  # use TRUE for dynamic bank filtration share (depending on Q)
-                                                  date_min = "2002-01-01",
-                                                  date_max = "2022-12-31")
+                                                  date_min = "2019-01-01",
+                                                  date_max = "2019-12-31")
 
 ################################################################################################
 ### Calculate flows ############################################################################
 ################################################################################################
 
 system.time(
-  flows_dynamic <- kwb.BerlinWaterModel.public::calculate_flows_auto(config = config,
-                                                              input_list = input_list,
-                                                              network = network,
-                                                              use_dynamic = TRUE, # FALSE: static values for flow shares at river branchings
-                                                              debug = TRUE)
+  flows_dynamic <- kwb.BerlinWaterModel.public::calculate_flows_auto(
+    config = config,
+    input_list = input_list,
+    network = network,
+    use_dynamic = TRUE, # FALSE: static values for flow shares at river branchings
+    debug = TRUE)
 )
 
-flows_stats <- kwb.BerlinWaterModel.public::calculate_flow_stats(flows = flows_dynamic)
+flows_stats <- kwb.BerlinWaterModel.public::calculate_flow_stats(
+  flows = flows_dynamic)
 
-flows_dynamic_neg_flows_stat <- kwb.BerlinWaterModel.public::get_reverse_flows_per_section(flows = flows_dynamic)
-#openxlsx::write.xlsx(x = flows_neg_stat_evap_30, file = "flows_neg_stat_evap30_2019.xlsx")
+DT::datatable(flows_stats$per_section, caption = "Flow stats (per section)")
+DT::datatable(flows_stats$per_year, caption = "Flow stats (per year)")
+DT::datatable(flows_stats$per_month, caption = "Flow stats (per month)")
 
+flows_dynamic_neg_flows_stat <- kwb.BerlinWaterModel.public::get_reverse_flows_per_section(
+  flows = flows_dynamic)
 
-# Save flows of one or all sections to xls
-openxlsx::write.xlsx(x = flows_dynamic, file = "flows_days_2019_start-con-2019.xlsx")
-# openxlsx::write.xlsx(x = flows_dynamic[c("date", "H03")], file = "flows_H03_days.xlsx")
+DT::datatable(flows_dynamic_neg_flows_stat, caption = "Sections with negative flows in 2019")
 
 
 ################################################################################################
@@ -88,60 +91,13 @@ system.time(
                                                                     debug = FALSE)
 )
 
-### Save qualities for one or all sections in XLSX
-#openxlsx::write.xlsx(x = qualities$conc$S21, file = "qualities_S21_days_dynamic_branching_fixJOH.xlsx")
-openxlsx::write.xlsx(x = qualities_00_dynamic_reverse$conc, file = "qualities_hours_2017-2022_Fluoranthen_KW-0,0037_RW-0,22_MWÜ-0,2.xlsx")
+### Save qualities for all sections in XLSX
+openxlsx::write.xlsx(x = qualities_00_dynamic_reverse$conc, file = "qualities_00_dynamic_reverse_concentrations.xlsx")
 
 # save RDS for flows and qualities
-#saveRDS(flows_dynamic, file = "flows_hours_2002-2022.Rds")
-saveRDS(qualities_00_dynamic_reverse, file = "qualities_hours_2016-2022_Fluoranthen_KW-0,0037_RW-0,22_MWÜ-0,20.Rds")
-
-# Read RDS for flows and qualities
-qualities_00_dynamic_reverse <- readRDS(file = "qualities_hours_2016-2022_Fluoranthen_KW-0,0037_RW-0,22_MWÜ-0,20.Rds")
-flows_dynamic <- readRDS(file = "flows_hours_2002-2022.Rds")
 
+saveRDS(qualities_00_dynamic_reverse, file = "qualities_00_dynamic_reverse_concentrations.Rds")
 
-#############################################################################################
-### prepare qsimVis output for map visualisation ############################################
-#############################################################################################
-
-if(FALSE) {
-
-  qsimVis_input <- kwb.BerlinWaterModel.public::prepare_qsimVis_input(
-    config = config,
-    flows = flows_dynamic,
-    qualities = qualities_00_dynamic_reverse) %>%
-    dplyr::select(GewaesserId,
-                  Strang = "section_id",
-                  Km,
-                  tidyselect::starts_with("date"),
-                  cbm_per_second,
-                  tracer.cso,
-                  tracer.rain_runoff,
-                  tracer.wwtp
-                  #, ValsartansaeureAeq.mg.m3
-                  #, Fluoranthen.mg.m3
-    ) %>%
-    dplyr::rename(Q = cbm_per_second)
-
-  # add section name
-  for(x in config$sections$section_id){
-    qsimVis_input$Strang[qsimVis_input$Strang == x] <-
-      paste(x,config$sections$section_name[config$sections$section_id == x], sep = ".")
-  }
-
-#  qsimVis_input[is.na(qsimVis_input)] <- 0
-
-  col_date_time_idx <- stringr::str_detect(names(qsimVis_input), "^date")
-  names(qsimVis_input)[col_date_time_idx] <- "Datum"
-
-  qsimVis_input <- qsimVis_input %>%
-  dplyr::mutate(Datum = format(Datum, format = "%d.%m.%Y %H:%M", tz = "UTC"))
-
-  #readr::write_csv2(qsimVis_input,"qsimVis_input2.csv") takes much longer for big datasets
-  system.time(data.table::fwrite(qsimVis_input, "qsimVis_input_hours_2017-2022_Fluoranthen_KW-0,0037_RW-0,22_MWÜ-0,20.csv", sep = ";", dec = ","))
-
-}
 
 #############################################################################################
 ### Diverse checks ##########################################################################

data-raw/inputs_public.R

@@ -1,16 +1,16 @@
 config <- kwb.BerlinWaterModel.public::config_read(config_dir = "inst/extdata/config/network_complete")
 
-datetime_min <- lubridate::as_datetime("2018-01-01 00:00:00", tz = "UTC")
-datetime_max <- lubridate::as_datetime("2018-12-31 23:59:59", tz = "UTC")
-reduce_temporal_coverage <- FALSE
-no_ww_and_wwtp <- TRUE
+datetime_min <- lubridate::as_datetime("2019-01-01 00:00:00", tz = "UTC")
+datetime_max <- lubridate::as_datetime("2019-12-31 23:59:59", tz = "UTC")
+reduce_temporal_coverage <- TRUE
+no_ww_and_wwtp <- FALSETRUE
 
 ################################################################################################
 # CSO data #####################################################################################
 ################################################################################################
 
-unzip("inst/extdata/input_data/cso/cso.zip",
-      exdir = "inst/extdata/input_data/cso/csv/")
+# unzip("inst/extdata/input_data/cso/cso.zip",
+#       exdir = "inst/extdata/input_data/cso/csv/")
 
 cso_files <- list.files("inst/extdata/input_data/cso/csv/",
                         pattern = "\\.csv$",
@@ -347,3 +347,61 @@ rain <- if(reduce_temporal_coverage) {
 
 usethis::use_data(rain, overwrite = TRUE)
 
+
+# 4. Wasserflächen vorbereiten
+url <- "https://fbinter.stadt-berlin.de/fb/atom/Gewaesserkarte/Gewaesserkarte.zip"
+tfile <- basename(url)
+
+download.file(url, destfile = basename(url))
+
+unzip(zipfile = tfile,
+      exdir = "lakes_berlin")
+
+
+lakes_berlin <- sf::read_sf("lakes_berlin/Gewaesser_Berlin_Flaechen.shp",
+                            options = "ENCODING=WINDOWS-1252") %>%
+  dplyr::mutate(area = sf::st_area(.) %>% as.numeric()) %>%
+  dplyr::arrange(dplyr::desc(area)) %>%
+  sf::st_transform(4326) %>%
+  sf::st_make_valid()
+
+
+lakes_berlin_sel <- lakes_berlin %>%
+  dplyr::filter(area > 150000)
+
+
+## DWD datasets
+remotes::install_github("kwb-r/kwb.dwd@get-rid-of-rgdal")
+
+
+sf::write_sf(lakes_berlin_sel, "lakes_berlin_selected.shp")
+shape_file <- "lakes_berlin_selected.shp"
+
+
+
+# Only data of full months can currently be read!
+evapo_p_raw <- kwb.dwd::read_daily_data_over_shape(
+  #file = shape_file,
+  shape = lakes_berlin_sel,
+  variable = "evapo_p",
+  from = "201901",
+  to = "201912"
+  #to = "202212"
+)
+
+
+evapo_p <- evapo_p_raw %>%
+  dplyr::mutate(date = sprintf("%02d-%02d-%02d", year, month, day) %>%  as.Date()) %>%
+  tibble::as_tibble()
+
+
+evapo_p  <- if(reduce_temporal_coverage) {
+  evapo_p  %>%
+    dplyr::filter(date  >= lubridate::as_date(datetime_min),
+                  date <= lubridate::as_date(datetime_max))
+} else {
+  evapo_p
+}
+
+
+usethis::use_data(evapo_p, overwrite = TRUE)