Data Availability Waterworks Friedrichshagen

1 Install R packages

if (! require("remotes")) {
  install.packages("remotes", repos = "https://cloud.r-project.org")
}

remotes::install_github("kwb-r/kwb.geosalz", dependencies = TRUE)

2 Define paths

# Define paths and resolve placeholders
paths <- kwb.utils::resolve(list(
  servername = Sys.getenv("servername"),
  root_server = "//<servername>",
  project = "geosalz",
  rawdata = "<root_server>/rawdata/<project>/BWB_labor",
  processing = "<root_server>/processing/<project>",
  cleaned_data_dir = "<processing>/labor/cleaned-data",
  cleaned_data_rds = "<cleaned_data_dir>/cleaned-data.Rds",
  foerdermengen = "<rawdata>/2018-04-27 Rohwasser Bericht - Galeriefördermengen.xlsx",
  parameters = "<rawdata>/2018-06-01 Lab Parameter.xlsx",
  figures_dir = "<processing>/figures"
))

3 Input data

Checkout the Workflow vignette for reproducing the creation of cleaned-data.Rds.

library(kwb.geosalz)

## Load water quality data (<= 2000, prepared within first phase of Geosalz
## project!); for creation see the "workflow.Rmd" vignette
load(file = paths$cleaned_data_rds)

foerdermengen_ww <- kwb.geosalz::get_foerdermengen(paths$foerdermengen)

foerdermengen_fri_gal <- paths$foerdermengen %>%
  kwb.geosalz::get_foerdermengen_gal_fri() %>% 
  dplyr::filter(!is.na(!.data$foerdermenge_m3))

readr::write_csv2(
  foerdermengen_fri_gal, 
  file = file.path(paths$figures_dir, "foerdermengen_fri_gal.csv")
)

para_info <- kwb.geosalz::get_parameters_meta(paths$parameters)

labordaten_ww_timeseries <- labordaten_ww %>%
  dplyr::filter(
    prufgegenstand == "Rohwasser", 
    werk == "FRI"
  ) 

readr::write_csv2(
  labordaten_ww_timeseries,
  file = file.path(paths$figures_dir, "Zeitreihen_FRI_Guete_Rohwasser.csv")
)

labordaten_ww_stats <- labordaten_ww_timeseries %>%
  dplyr::group_by(
    .data$para_id,
    .data$para_kuerzel, 
    .data$para_kurzname,
    .data$werk, 
    .data$galerie
  ) %>% 
  dplyr::summarise(
    date_min = as.Date(min(.data$Date)),
    date_max = as.Date(max(.data$Date)),
    period_days = diff(c(.data$date_min, .data$date_max)),
    number_of_samples = dplyr::n(), 
    mean_sampling_intervall_days = round(
      .data$period_days/.data$number_of_samples
    )
  ) %>% 
  dplyr::arrange(.data$para_id, .data$galerie)

readr::write_csv2(
  labordaten_ww_stats,
  file = file.path(paths$figures_dir, "Stats_FRI_Guete_Rohwasser.csv")
)

4 Visualisation

4.1 Water quality

#Check and in case the export directory is not available create it:
fs::dir_create(paths$figures_dir, recurse = TRUE)

print(sprintf("Export figures/plots to: %s", paths$figures_dir))

water_types <- c("Rohwasser")

for (water_type in water_types) {
  
  pdf_file <- file.path(
    paths$figures_dir,
    sprintf("Zeitreihen_FRI_%s_Guete.pdf", water_type)
  )
  
  cat(sprintf("Creating plot:\n%s\n", pdf_file))
  
  pdf(file = pdf_file, width = 14, height = 9)
  
  for (sel_para_id in unique(labordaten_ww$para_id)) {
    
    my_selection <- sprintf(
      "%s (%s)",
      para_info$para_kurzname[para_info$para_id == sel_para_id],
      water_type
    )
    
    tmp <- labordaten_ww %>%
      dplyr::filter(
        prufgegenstand == water_type,
        para_id == sel_para_id, 
        werk == "FRI"
      ) %>%
      dplyr::filter(
        stringr::str_detect(.data$galerie, pattern = "GWW", negate = TRUE)
      )
    
    y_label <-  sprintf(
      "%s (%s)",
      para_info$para_kurzname[para_info$para_id == sel_para_id],
      paste0(unique(tmp$UnitName_org), collapse = ", ")
    )
    
    if (nrow(tmp) > 0) {
      
      cat(sprintf("for %s\n", my_selection))
      
      g <- ggplot2::ggplot(tmp, mapping = ggplot2::aes_string(
        x = "Date",
        y = "DataValue",
        col = "galerie"
      )) +
        ggplot2::geom_point() +
        ggplot2::geom_line() +
        ggplot2::theme_bw() +
        ggplot2::ggtitle(label = my_selection) +
        ggplot2::labs(x = "", y = y_label)
      
      print(g)
      
    } else {
      
      cat(sprintf("not data availabe for %s\n", my_selection))
    }
  }
  
  dev.off()
}

4.2 Yearly Abstraction Volume

4.2.1 Total

pdf_file <- file.path(
  paths$figures_dir,
  "Zeitreihen_FRI_Gesamt_Jahresfoerdermengen.pdf"
)

pdf(file = pdf_file, width = 14, height = 9)

foerdermengen_ww %>%
  dplyr::filter(.data$Wasserwerk == "Friedrichshagen") %>% 
  ggplot2::ggplot(mapping = ggplot2::aes_string(
    x = "year",
    y = "Foerdermenge_m3",
    col = "werk"
  )) + 
  ggplot2::geom_point() +
  ggplot2::geom_line() +
  ggplot2::theme_bw() +
  ggplot2::ggtitle(label = "Wasserwerk Friedrichshagen") +
  ggplot2::labs(x = "Datum", y = "Jahresf\u00F6rdermenge (m3)")

dev.off()

4.2.2 By Well Galeries

pdf_file <- file.path(
  paths$figures_dir,
  "Zeitreihen_FRI_Galerien_Jahresfoerdermengen.pdf"
)

pdf(file = pdf_file, width = 14, height = 9)

foerdermengen_fri_gal %>%  
  ggplot2::ggplot(mapping = ggplot2::aes_string(
    x = "date",
    y = "foerdermenge_m3", 
    col = "galerie"
  )) + 
  ggplot2::geom_point() +
  ggplot2::geom_line() +
  ggplot2::theme_bw() +
  ggplot2::ggtitle(label = "Brunnengalerien FRI") +
  ggplot2::labs(x = "Datum", y = "Jahresf\u00F6rdermenge (m3)")

dev.off()

pdf_file <- file.path(
  paths$figures_dir,
  "Zeitreihen_FRI_Galerien_Jahresfoerdermengen_multipage.pdf"
)

pdf(file = pdf_file, width = 14, height = 9)

tmp <- foerdermengen_fri_gal %>%  
  dplyr::mutate(foerdermenge_million_m3 = .data$foerdermenge_m3/1000000)

n_pages <- tmp %>% 
  dplyr::count(.data$galerie) %>% 
  dplyr::pull(.data$galerie) %>% 
  length()

for (page in seq_len(n_pages)) {
  print(
    tmp %>% 
      ggplot2::ggplot(mapping = ggplot2::aes_string(
        x = "date", 
        y = "foerdermenge_million_m3"
      )) + 
      ggforce::facet_wrap_paginate(~ galerie, ncol = 1, nrow = 1, page = page) +
      #ggplot2::facet_wrap(~ galerie, ncol = 1) + 
      ggplot2::geom_point() +
      ggplot2::geom_line() +
      ggplot2::labs(x = "Datum", y = "Foerdermenge (m3/Jahr)") +
      ggplot2::theme_bw()
  )
}

#dev.off()

kwb.utils::finishAndShowPdf(PDF = pdf_file)

5 Session Info

Plattform

name	value
version	R version 4.4.2 (2024-10-31 ucrt)
os	Windows Server 2022 x64 (build 20348)
system	x86_64, mingw32
ui	RTerm
language	en
collate	English_United States.utf8
ctype	English_United States.utf8
tz	UTC
date	2024-12-23
pandoc	3.1.11 @ C:/HOSTED_{1/windows/pandoc/31F387}1.11/x64/PANDOC~1.11/ (via rmarkdown)

Packages

#>  package     * version date (UTC) lib source
#>  bslib         0.8.0   2024-07-29 [1] CRAN (R 4.4.1)
#>  cachem        1.1.0   2024-05-16 [1] CRAN (R 4.4.0)
#>  cli           3.6.3   2024-06-21 [1] RSPM (R 4.4.0)
#>  desc          1.4.3   2023-12-10 [1] CRAN (R 4.4.0)
#>  digest        0.6.37  2024-08-19 [1] RSPM (R 4.4.0)
#>  dplyr       * 1.1.4   2023-11-17 [1] CRAN (R 4.4.0)
#>  evaluate      1.0.1   2024-10-10 [1] CRAN (R 4.4.1)
#>  fastmap       1.2.0   2024-05-15 [1] CRAN (R 4.4.0)
#>  fs            1.6.5   2024-10-30 [1] CRAN (R 4.4.1)
#>  generics      0.1.3   2022-07-05 [1] CRAN (R 4.4.0)
#>  glue          1.8.0   2024-09-30 [1] CRAN (R 4.4.1)
#>  htmltools     0.5.8.1 2024-04-04 [1] CRAN (R 4.4.0)
#>  htmlwidgets   1.6.4   2023-12-06 [1] CRAN (R 4.4.0)
#>  jquerylib     0.1.4   2021-04-26 [1] CRAN (R 4.4.0)
#>  jsonlite      1.8.9   2024-09-20 [1] RSPM (R 4.4.0)
#>  knitr         1.49    2024-11-08 [1] RSPM (R 4.4.0)
#>  kwb.utils     0.15.0  2024-04-25 [1] Github (kwb-r/kwb.utils@4415aa2)
#>  lifecycle     1.0.4   2023-11-07 [1] CRAN (R 4.4.0)
#>  magrittr      2.0.3   2022-03-30 [1] CRAN (R 4.4.0)
#>  pillar        1.10.0  2024-12-17 [1] CRAN (R 4.4.2)
#>  pkgconfig     2.0.3   2019-09-22 [1] CRAN (R 4.4.0)
#>  pkgdown       2.1.1   2024-09-17 [1] RSPM (R 4.4.0)
#>  purrr         1.0.2   2023-08-10 [1] CRAN (R 4.4.0)
#>  R6            2.5.1   2021-08-19 [1] CRAN (R 4.4.0)
#>  ragg          1.3.0   2024-03-13 [1] CRAN (R 4.4.0)
#>  rlang         1.1.4   2024-06-04 [1] CRAN (R 4.4.0)
#>  rmarkdown     2.29    2024-11-04 [1] CRAN (R 4.4.2)
#>  sass          0.4.9   2024-03-15 [1] CRAN (R 4.4.0)
#>  sessioninfo   1.2.2   2021-12-06 [1] CRAN (R 4.4.0)
#>  systemfonts   1.1.0   2024-05-15 [1] CRAN (R 4.4.0)
#>  textshaping   0.3.7   2023-10-09 [1] CRAN (R 4.4.0)
#>  tibble        3.2.1   2023-03-20 [1] CRAN (R 4.4.0)
#>  tidyr       * 1.3.1   2024-01-24 [1] CRAN (R 4.4.0)
#>  tidyselect    1.2.1   2024-03-11 [1] CRAN (R 4.4.0)
#>  vctrs         0.6.5   2023-12-01 [1] CRAN (R 4.4.0)
#>  xfun          0.49    2024-10-31 [1] CRAN (R 4.4.1)
#>  yaml          2.3.10  2024-07-26 [1] RSPM (R 4.4.0)
#> 
#>  [1] D:/a/_temp/Library
#>  [2] C:/R/library

Pandoc

#>                                                pandoc_directory pandoc_version
#> 1 C:/HOSTED~1/windows/pandoc/31F387~1.11/x64/PANDOC~1.11/pandoc         3.1.11

Michael Rustler

2024-12-23

1 Install R packages

2 Define paths

3 Input data

4 Visualisation

4.1 Water quality

4.2 Yearly Abstraction Volume

4.2.1 Total

4.2.2 By Well Galeries

5 Session Info

Plattform

Packages

Pandoc