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 > 0.5print(glue("{sum(filter_condition)} rows dropped as < {lower_bound} or > {upper_bound}"))0 rows dropped as < 0 or > 0.5write.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 19515
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 0 575 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 355482. 194320. 211877
2 Latitude 0 1 26.3 0.667 24.4
3 Longitude 0 1 -80.4 0.661 -83.6
4 Month 0 1 6.57 3.46 1
5 Day 21 0.999 12.3 7.42 1
6 Year 0 1 2021. 2.35 2005
7 Value 0 1 0.00449 0.0165 0
8 Sample.Depth 21 0.999 3.95 8.00 0
9 Total.Depth 18336 0.0604 5.84 8.14 0.5
10 verbatimValue 0 1 0.00449 0.0165 0
11 VerbatimLatitude 0 1 26.3 0.667 24.4
12 verbatimLongitude 0 1 -80.4 0.661 -83.6
13 Value_orig 0 1 0.00449 0.0165 0
p25 p50 p75 p100 hist
1 222842. 227721 642000. 647323 ▇▁▁▁▃
2 25.9 26.3 26.8 28.4 ▁▅▇▅▁
3 -80.1 -80.1 -80.1 -80.0 ▁▁▁▁▇
4 4 7 10 12 ▇▅▆▆▇
5 6 12 18 31 ▇▇▆▃▂
6 2019 2021 2023 2023 ▁▁▁▃▇
7 0.00102 0.002 0.004 0.5 ▇▁▁▁▁
8 0.5 0.5 4.4 247 ▇▁▁▁▁
9 0.719 4 7 52.7 ▇▁▁▁▁
10 0.00102 0.002 0.004 0.5 ▇▁▁▁▁
11 25.9 26.3 26.8 28.4 ▁▅▇▅▁
12 -80.1 -80.1 -80.1 -80.0 ▁▁▁▁▇
13 0.00102 0.002 0.004 0.5 ▇▁▁▁▁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()