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$parameter_namebounds <- read.csv(here("parameter_bounds.csv"), stringsAsFactors = FALSE, strip.white = T)
lower_bound <- bounds$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 > 200print(glue("{sum(filter_condition)} rows dropped as < {lower_bound} or > {upper_bound}"))0 rows dropped as < 0 or > 200write.csv(data, here("data/df_cleaned_02.csv"), row.names = FALSE)subset_data <- subset(data, Parameter == parameter_name)
print(skimr::skim(subset_data))── Data Summary ────────────────────────
Values
Name subset_data
Number of rows 41076
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 8 0
2 Site 0 1 1 28 0 438 0
3 Parameter 0 1 9 9 0 1 0
4 Units 27 0.999 3 3 0 1 0
── Variable type: numeric ──────────────────────────────────────────────────────
skim_variable n_missing complete_rate mean sd p0
1 ...1 0 1 591053. 17289. 566786
2 Latitude 0 1 25.6 0.748 24.5
3 Longitude 0 1 -80.6 0.644 -82.6
4 Month 0 1 6.58 3.43 1
5 Day 0 1 13.5 8.19 1
6 Year 0 1 2015. 7.43 1995
7 Value 0 1 1.22 2.53 0
8 Sample.Depth 2585 0.937 3.28 6.58 0
9 Total.Depth 23612 0.425 8.23 7.85 0
10 verbatimValue 0 1 1.22 2.53 0
11 VerbatimLatitude 0 1 25.6 0.748 24.5
12 verbatimLongitude 0 1 -80.6 0.644 -82.6
13 Value_orig 0 1 1.22 2.53 0
p25 p50 p75 p100 hist
1 577188. 587522. 604183. 631243 ▇▇▅▃▂
2 24.8 25.7 26.1 27.2 ▇▃▇▅▂
3 -80.9 -80.2 -80.1 -80.0 ▁▁▁▁▇
4 3 7 10 12 ▇▅▅▆▇
5 7 12 19 31 ▇▇▆▃▃
6 2011 2018 2021 2023 ▁▁▂▂▇
7 0.25 0.6 1.3 177 ▇▁▁▁▁
8 0.5 0.5 3.2 121. ▇▁▁▁▁
9 3.15 6 10.4 121. ▇▁▁▁▁
10 0.25 0.6 1.3 177 ▇▁▁▁▁
11 24.8 25.7 26.1 27.2 ▇▃▇▅▂
12 -80.9 -80.2 -80.1 -80.0 ▁▁▁▁▇
13 0.25 0.6 1.3 177 ▇▁▁▁▁params$parameter_name histogramggplot2::ggplot(subset_data, aes(x=Value)) +
geom_histogram(bins=30, fill="blue", color="black") +
scale_y_log10() + # Transform the y-axis to a logarithmic scale
labs(title=paste("Histogram of Values for", params$parameter_name),
x="Value",
y="Log Frequency") +
theme_minimal()