Phosphorus- Total

Phosphorus- 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 > 2

apply param bounds

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

0 rows dropped as < 0 or > 2

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             50322      
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      986          0
3 Parameter             0             1  17  17     0        1          0
4 Units                 0             1   4   6     0        3          0

── Variable type: numeric ──────────────────────────────────────────────────────
   skim_variable     n_missing complete_rate        mean         sd       p0
 1 ...1                      0         1     565170.     63974.     505005  
 2 Latitude                  0         1         25.9        0.850      24.5
 3 Longitude                 0         1        -80.5        0.618     -85.7
 4 Month                     0         1          6.68       3.41        1  
 5 Day                       0         1         13.5        8.19        1  
 6 Year                      0         1       2018.         6.62     1995  
 7 Value                     0         1          0.0357     0.0842      0  
 8 Sample.Depth           2845         0.943      1.97      17.8         0  
 9 Total.Depth           37414         0.257      7.19       7.61        0  
10 verbatimValue             0         1          0.0357     0.0842      0  
11 VerbatimLatitude          0         1         25.9        0.850      24.5
12 verbatimLongitude         0         1        -80.5        0.618     -85.7
13 Value_orig                0         1          0.0357     0.0842      0  
          p25        p50        p75      p100 hist 
 1 517649.    530820.    659085.    672577    ▇▁▁▁▃
 2     25.4       25.9       26.4       30.8  ▅▇▂▁▁
 3    -80.8      -80.2      -80.1      -80.0  ▁▁▁▂▇
 4      4          7         10         12    ▇▅▅▆▇
 5      7         12         20         31    ▇▇▆▃▃
 6   2017       2020       2023       2024    ▁▁▁▂▇
 7      0.006      0.014      0.026      1.97 ▇▁▁▁▁
 8      0.5        0.5        0.5     2494    ▇▁▁▁▁
 9      2.55       4.83       9.26     121.   ▇▁▁▁▁
10      0.006      0.014      0.026      1.97 ▇▁▁▁▁
11     25.4       25.9       26.4       30.8  ▅▇▂▁▁
12    -80.8      -80.2      -80.1      -80.0  ▁▁▁▂▇
13      0.006      0.014      0.026      1.97 ▇▁▁▁▁

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()