Nitrogen- Total Kjeldahl

Nitrogen- Total Kjeldahl Report

Code

if (!requireNamespace("librarian", quietly = TRUE)) {
  # If not installed, install the package
  install.packages("librarian")
}

librarian::shelf(
  glue,
  here,
  skimr,
  ggplot2
)

data <- read.csv(here("data/df_cleaned.csv"))
parameter_name <- params$parameter_name

apply param bounds

bounds <- read.csv(here("parameter_bounds.csv"), stringsAsFactors = FALSE, strip.white = T)
lower_bound <- bounds$min[bounds$param == parameter_name]
upper_bound <- bounds$max[bounds$param == parameter_name]

filter_condition <- (data$Parameter == parameter_name & (data$Value < lower_bound | data$Value > upper_bound))

tryCatch({  # this tryCatch is for when filter_condition is logical(0) i.e. no matches
  data <- dplyr::filter(
    data, 
    !filter_condition
  )
  print(glue("{sum(filter_condition)} rows dropped as < {lower_bound} or > {upper_bound}"))
}, error = function(e){
  print(glue("no rows removed"))
})

0 rows dropped as < 0 or > 5

apply param bounds

print(glue("{sum(filter_condition)} rows dropped as < {lower_bound} or > {upper_bound}"))

0 rows dropped as < 0 or > 5

write cleaned DataFrame to a file

write.csv(data, here("data/df_cleaned_02.csv"), row.names = FALSE)

load data & skim

subset_data <- subset(data, Parameter == parameter_name)
print(skimr::skim(subset_data))

── Data Summary ────────────────────────
                           Values     
Name                       subset_data
Number of rows             35116      
Number of columns          17         
_______________________               
Column type frequency:                
  character                4          
  numeric                  13         
________________________              
Group variables            None       

── Variable type: character ────────────────────────────────────────────────────
  skim_variable n_missing complete_rate min max empty n_unique whitespace
1 Source                0             1   3  21     0        9          0
2 Site                  0             1   1  28     0      504          0
3 Parameter             0             1  24  24     0        1          0
4 Units                 0             1   4   4     0        1          0

── Variable type: numeric ──────────────────────────────────────────────────────
   skim_variable     n_missing complete_rate       mean        sd       p0
 1 ...1                      0         1     486850.    63252.    442538  
 2 Latitude                  0         1         25.7       0.811     24.5
 3 Longitude                 0         1        -80.5       0.659    -85.7
 4 Month                     0         1          6.66      3.40       1  
 5 Day                       0         1         12.7       7.82       1  
 6 Year                      0         1       2017.        7.45    1995  
 7 Value                     0         1          0.235     0.292      0  
 8 Sample.Depth            888         0.975      3.37     21.1        0  
 9 Total.Depth           24186         0.311      7.47      6.93       0  
10 verbatimValue             0         1          0.235     0.292      0  
11 VerbatimLatitude          0         1         25.7       0.811     24.5
12 verbatimLongitude         0         1        -80.5       0.659    -85.7
13 Value_orig                0         1          0.235     0.292      0  
          p25        p50       p75     p100 hist 
 1 451331.    460110.    481313.   639713   ▇▁▁▁▂
 2     25.0       25.8       26.3      30.8 ▆▇▁▁▁
 3    -80.5      -80.2      -80.1     -80.0 ▁▁▁▁▇
 4      4          7         10        12   ▇▅▆▆▇
 5      6         12         18        31   ▇▇▅▃▂
 6   2016       2020       2022      2024   ▁▁▁▂▇
 7      0.043      0.139      0.28      4.4 ▇▁▁▁▁
 8      0.5        0.5        2.9    2494   ▇▁▁▁▁
 9      3          5.25       9.72    104.  ▇▁▁▁▁
10      0.043      0.139      0.28      4.4 ▇▁▁▁▁
11     25.0       25.8       26.3      30.8 ▆▇▁▁▁
12    -80.5      -80.2      -80.1     -80.0 ▁▁▁▁▇
13      0.043      0.139      0.28      4.4 ▇▁▁▁▁

create params$parameter_name histogram

ggplot2::ggplot(subset_data, aes(x=Value)) +
    geom_histogram(bins=30, fill="blue", color="black") +
    scale_y_log10() +  # Transform the y-axis to a logarithmic scale
    labs(title=paste("Histogram of Values for", params$parameter_name),
         x="Value",
         y="Log Frequency") +
    theme_minimal()