Orthophosphate (P)

Orthophosphate (P) 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             31785      
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        7          0
2 Site                  0             1   1   8     0      863          0
3 Parameter             0             1  18  18     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      453631.     164471.     314515  
 2 Latitude                  0        1          26.3         0.697      24.4
 3 Longitude                 0        1         -80.4         0.564     -85.2
 4 Month                     0        1           6.65        3.43        1  
 5 Day                      15        1.00       12.1         7.54        1  
 6 Year                      0        1        2020.          3.52     1998  
 7 Value                     0        1           0.0210      0.0754      0  
 8 Sample.Depth             15        1.00        2.62        6.50        0  
 9 Total.Depth           31098        0.0216      9.11        9.05        0.9
10 verbatimValue             0        1           0.0210      0.0754      0  
11 VerbatimLatitude          0        1          26.3         0.697      24.4
12 verbatimLongitude         0        1         -80.4         0.564     -85.2
13 Value_orig                0        1           0.0210      0.0754      0  
          p25        p50       p75      p100 hist 
 1 331285     339231     675840    683928    ▇▁▁▁▅
 2     25.8       26.2       26.8      30.8  ▂▇▂▁▁
 3    -80.4      -80.1      -80.1     -80.0  ▁▁▁▁▇
 4      4          7         10        12    ▇▅▅▆▇
 5      6         11         17        31    ▇▆▅▃▂
 6   2019       2021       2023      2023    ▁▁▁▂▇
 7      0.002      0.004      0.01      2.09 ▇▁▁▁▁
 8      0.5        0.5        0.5     247    ▇▁▁▁▁
 9      4.9        6.4        8.35     52.7  ▇▁▁▁▁
10      0.002      0.004      0.01      2.09 ▇▁▁▁▁
11     25.8       26.2       26.8      30.8  ▂▇▂▁▁
12    -80.4      -80.1      -80.1     -80.0  ▁▁▁▁▇
13      0.002      0.004      0.01      2.09 ▇▁▁▁▁

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()