Nitrogen- Total

Nitrogen- Total 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 > 6

apply param bounds

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

0 rows dropped as < 0 or > 6

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             23143      
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        4          0
2 Site                  0             1   1  28     0      656          0
3 Parameter             0             1  15  15     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     494765.    111543.    403997  
 2 Latitude                  0         1         25.6        1.05      24.5
 3 Longitude                 0         1        -80.9        0.630    -82.6
 4 Month                     0         1          6.72       3.37       1  
 5 Day                       0         1         15.6        8.63       1  
 6 Year                      0         1       2014.         8.88    1995  
 7 Value                     0         1          0.587      0.631      0  
 8 Sample.Depth             10         1.00       2.17       4.95       0  
 9 Total.Depth            8915         0.615      7.56       7.65       0  
10 verbatimValue             0         1          0.587      0.631      0  
11 VerbatimLatitude          0         1         25.6        1.05      24.5
12 verbatimLongitude         0         1        -80.9        0.630    -82.6
13 Value_orig                0         1          0.587      0.631      0  
          p25        p50        p75      p100 hist 
 1 411570.    424437     651330.    657440    ▇▁▁▁▃
 2     24.7       25.1       26.4       28.4  ▇▂▂▂▁
 3    -81.4      -80.9      -80.3      -80.0  ▁▃▅▅▇
 4      4          7         10         12    ▇▅▆▆▇
 5      8         15         23         31    ▇▇▇▆▆
 6   2007       2016       2023       2023    ▂▂▂▃▇
 7      0.146      0.241      0.992      5.83 ▇▂▁▁▁
 8      0.5        0.5        0.5      121.   ▇▁▁▁▁
 9      2.90       5.25       9.58     121.   ▇▁▁▁▁
10      0.146      0.241      0.992      5.83 ▇▂▁▁▁
11     24.7       25.1       26.4       28.4  ▇▂▂▂▁
12    -81.4      -80.9      -80.3      -80.0  ▁▃▅▅▇
13      0.146      0.241      0.992      5.83 ▇▂▁▁▁

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()