Nitrate (N)

Nitrate (N) 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 > 10

apply param bounds

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

0 rows dropped as < 0 or > 10

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             3636       
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  10     0        5          0
2 Site                  0             1   1  28     0      285          0
3 Parameter             0             1  11  11     0        1          0
4 Units                 0             1   4   6     0        2          0

── Variable type: numeric ──────────────────────────────────────────────────────
   skim_variable     n_missing complete_rate        mean         sd       p0
 1 ...1                      0         1     438858.     184512.    270777  
 2 Latitude                  0         1         25.7         0.971     24.4
 3 Longitude                 0         1        -81.3         0.962    -83.6
 4 Month                     0         1          6.95        3.45       1  
 5 Day                      28         0.992     14.2         7.71       1  
 6 Year                      0         1       2019.          4.12    2005  
 7 Value                     0         1          0.0566      0.290      0  
 8 Sample.Depth             28         0.992      2.62        7.76       0  
 9 Total.Depth            2332         0.359      5.18        7.79       0.5
10 verbatimValue             0         1          0.0566      0.290      0  
11 VerbatimLatitude          0         1         25.7         0.971     24.4
12 verbatimLongitude         0         1        -81.3         0.962    -83.6
13 Value_orig                0         1          0.0566      0.290      0  
          p25      p50         p75      p100 hist 
 1 276099.    278282.  648180.     649436    ▇▁▁▁▆
 2     24.9       25.6     26.4        28.0  ▇▇▂▃▂
 3    -81.9      -81.2    -80.3       -80.1  ▂▂▅▆▇
 4      4          7       10          12    ▆▅▃▆▇
 5      8         14       20          31    ▇▇▇▆▂
 6   2017       2021     2023        2023    ▁▁▁▅▇
 7      0          0        0.0104      8.11 ▇▁▁▁▁
 8      0          0        0.5       120.   ▇▁▁▁▁
 9      0.704      3        6.4        52.7  ▇▁▁▁▁
10      0          0        0.0104      8.11 ▇▁▁▁▁
11     24.9       25.6     26.4        28.0  ▇▇▂▃▂
12    -81.9      -81.2    -80.3       -80.1  ▂▂▅▆▇
13      0          0        0.0104      8.11 ▇▁▁▁▁

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()