Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add dataset tests #143

Merged
merged 12 commits into from
Nov 30, 2023
Merged

Add dataset tests #143

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
d43eae0
Update testdata.R
yangsophieee Nov 23, 2023
9da197b
Add test for checking units
yangsophieee Nov 23, 2023
51e5406
Add tests for checking no duplicate `var_in` or `context_property` in…
yangsophieee Nov 23, 2023
22cef13
Add prefixes to filter()
yangsophieee Nov 24, 2023
f39674d
Add `dplyr::` prefixes
yangsophieee Nov 24, 2023
e41e336
Fix `write_metadata` adding spaces to `custom_R_code`
yangsophieee Nov 29, 2023
0430bff
Merge branch 'develop' into add_dataset_tests
yangsophieee Nov 29, 2023
228ba10
Fix comment
yangsophieee Nov 30, 2023
98020a6
Merge branch 'develop' into add_dataset_tests
yangsophieee Nov 30, 2023
9a996f0
Add tidyverse prefixes
yangsophieee Nov 30, 2023
fe4eb5b
Add more prefixes
yangsophieee Nov 30, 2023
988717b
Add more prefixes
yangsophieee Nov 30, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion R/process.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2050,7 +2050,7 @@ check_pivot_duplicates <- function(

# Check for duplicates
database_object$traits %>%
filter(.data$dataset_id %in% dataset_ids) %>%
dplyr::filter(.data$dataset_id %in% dataset_ids) %>%
select(
yangsophieee marked this conversation as resolved.
Show resolved Hide resolved
# `taxon_name` and `original_name` are not needed for pivoting but are included for informative purposes
dplyr::all_of(
Expand Down
12 changes: 6 additions & 6 deletions R/setup.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -900,15 +900,15 @@ metadata_add_taxonomic_change <- function(dataset_id, find, replace, reason, tax
} else {
message(sprintf(red("Existing substitution will be overwritten for ") %+% green("'%s'"), find))
data <- data %>%
filter(.data$find != to_add$find) %>%
dplyr::bind_rows(to_add) %>%
filter(!.data$find == replace) %>%
arrange(.data$find)
dplyr::filter(.data$find != to_add$find) %>%
dplyr::bind_rows(to_add) %>%
dplyr::filter(!.data$find == replace) %>%
arrange(.data$find)
}
} else {
data <- dplyr::bind_rows(data, to_add) %>%
filter(!.data$find == replace) %>%
arrange(.data$find)
dplyr::filter(!.data$find == replace) %>%
arrange(.data$find)
yangsophieee marked this conversation as resolved.
Show resolved Hide resolved
}
}

Expand Down
78 changes: 62 additions & 16 deletions R/testdata.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -590,6 +590,27 @@ dataset_test_worker <-
process_format_contexts(dataset_id, data)
)

# Check that there are no duplicate `var_in` or `context_property` fields
context_properties <- sapply(metadata[["contexts"]], "[[", "context_property")
context_vars_in <- sapply(metadata[["contexts"]], "[[", "var_in")

expect_equal(
context_properties |> duplicated() |> sum(),
dfalster marked this conversation as resolved.
Show resolved Hide resolved
0,
info = sprintf(
"%s\tcontexts - duplicate `context_property` values detected: '%s'",
red(f),
paste(context_properties[duplicated(context_properties)], collapse = "', '"))
)
expect_equal(
context_vars_in |> duplicated() |> sum(),
0,
info = sprintf(
"%s\tcontexts - duplicate `var_in` values detected: '%s'",
red(f),
paste(context_vars_in[duplicated(context_vars_in)], collapse = "', '"))
)

# Check context details load
if (nrow(contexts) > 0) {

Expand All @@ -599,29 +620,30 @@ dataset_test_worker <-
info = paste0(red(f), "\tcontexts"), label = "field names"
)


# Check that unique context `value`'s only have one unique description
expect_equal(
contexts %>% dplyr::group_by(.data$context_property, .data$value) %>% dplyr::summarise(n = dplyr::n_distinct(.data$description)) %>%
filter(.data$n > 1) %>% nrow(),
dplyr::filter(.data$n > 1) %>% nrow(),
0, info = sprintf(
"%s\tcontexts - `value`'s should only have one unique description each: '%s'",
red(f),
paste(
contexts %>% dplyr::group_by(.data$context_property, .data$value) %>% dplyr::summarise(n = dplyr::n_distinct(.data$description)) %>%
filter(.data$n > 1) %>% dplyr::pull(.data$value) %>% unique(),
dplyr::filter(.data$n > 1) %>% dplyr::pull(.data$value) %>% unique(),
collapse = "', '")
)
)

# Check that there are no duplicate `find` fields
expect_equal(
contexts %>% dplyr::group_by(.data$context_property, .data$find) %>% dplyr::summarise(n = dplyr::n()) %>% filter(.data$n > 1) %>%
contexts %>% dplyr::group_by(.data$context_property, .data$find) %>% dplyr::summarise(n = dplyr::n()) %>% dplyr::filter(.data$n > 1) %>%
nrow(),
0, info = sprintf(
"%s\tcontexts - duplicate `find` values detected: '%s'",
red(f),
paste(
contexts %>% dplyr::group_by(.data$context_property, .data$find) %>% dplyr::summarise(n = dplyr::n()) %>% filter(.data$n > 1) %>%
contexts %>% dplyr::group_by(.data$context_property, .data$find) %>% dplyr::summarise(n = dplyr::n()) %>% dplyr::filter(.data$n > 1) %>%
dplyr::pull(.data$find) %>% unique(),
collapse = "', '")
)
Expand Down Expand Up @@ -682,6 +704,7 @@ dataset_test_worker <-
}

## Traits

expect_list_elements_contains_names(
metadata[["traits"]],
c("var_in", "unit_in", "trait_name", "value_type", "basis_of_value"),
Expand All @@ -707,8 +730,31 @@ dataset_test_worker <-
label = "`trait_name`'s"
)

# Check units are found in `unit_conversions.csv`
units <- read_csv("config/unit_conversions.csv")
expect_is_in(
traits$unit_in, units$unit_from,
info = paste0(red(f), "\ttraits"),
label = "`unit_in`'s"
)

# Check no duplicate `var_in`'s

expect_equal(
traits %>% dplyr::group_by(.data$var_in) %>% dplyr::summarise(n = dplyr::n()) %>%
dplyr::filter(.data$n > 1) %>% nrow(),
0,
info = sprintf(
"%s\ttraits - duplicate `var_in` values detected: '%s'",
red(f),
paste(
traits %>% dplyr::group_by(.data$var_in) %>% dplyr::summarise(n = dplyr::n()) %>%
dplyr::filter(.data$n > 1) %>% dplyr::pull(.data$var_in) %>% unique(),
collapse = "', '")
)
)


# Now that traits loaded, check details of contexts match
if (nrow(contexts > 0)) {

Expand All @@ -723,7 +769,7 @@ dataset_test_worker <-

for (j in unique(contexts[["var_in"]])) {

contextsub <- contexts %>% filter(var_in == j)
contextsub <- contexts %>% dplyr::filter(var_in == j)

# Context values align either with a column of data or a column of traits table
if (is.null(data[[j]])) {
Expand Down Expand Up @@ -852,13 +898,14 @@ dataset_test_worker <-

# First check no duplicate combinations of `find`
expect_equal(
x[[trait]] %>% dplyr::group_by(.data$find) %>% dplyr::summarise(n = dplyr::n()) %>% filter(.data$n > 1) %>% nrow(),
x[[trait]] %>% dplyr::group_by(.data$find) %>% dplyr::summarise(n = dplyr::n()) %>%
dplyr::filter(.data$n > 1) %>% nrow(),
0, info = sprintf(
"%s\tsubstitutions - duplicate `find` values detected: '%s'",
red(f),
paste(
x[[trait]] %>% dplyr::group_by(.data$find) %>% dplyr::summarise(n = dplyr::n()) %>% filter(.data$n > 1) %>%
dplyr::pull(.data$find) %>% unique(),
x[[trait]] %>% dplyr::group_by(.data$find) %>% dplyr::summarise(n = dplyr::n()) %>%
dplyr::filter(.data$n > 1) %>% dplyr::pull(.data$find) %>% unique(),
collapse = "', '")
)
)
Expand Down Expand Up @@ -898,12 +945,12 @@ dataset_test_worker <-

# Check no duplicate `find` values
expect_equal(
x %>% dplyr::group_by(.data$find) %>% dplyr::summarise(n = dplyr::n()) %>% filter(.data$n > 1) %>% nrow(),
x %>% dplyr::group_by(.data$find) %>% dplyr::summarise(n = dplyr::n()) %>% dplyr::filter(.data$n > 1) %>% nrow(),
0, info = sprintf(
"%s\ttaxonomic_updates - duplicate `find` values detected: '%s'",
red(f),
paste(
x %>% dplyr::group_by(.data$find) %>% dplyr::summarise(n = dplyr::n()) %>% filter(.data$n > 1) %>%
x %>% dplyr::group_by(.data$find) %>% dplyr::summarise(n = dplyr::n()) %>% dplyr::filter(.data$n > 1) %>%
dplyr::pull(.data$find) %>% unique(),
collapse = "', '")
)
Expand Down Expand Up @@ -1005,13 +1052,13 @@ dataset_test_worker <-
# Check no duplicate `find` values
expect_equal(
x %>% dplyr::group_by(.data$variable, .data$find) %>%
dplyr::summarise(n = dplyr::n()) %>% filter(.data$n > 1) %>% nrow(),
dplyr::summarise(n = dplyr::n()) %>% dplyr::filter(.data$n > 1) %>% nrow(),
0, info = sprintf(
"%s\texclude_observations - duplicate `find` values detected: '%s'",
red(f),
paste(
x %>% dplyr::group_by(.data$variable, .data$find) %>% dplyr::summarise(n = dplyr::n()) %>%
filter(.data$n > 1) %>% dplyr::pull(.data$find) %>% unique(),
dplyr::filter(.data$n > 1) %>% dplyr::pull(.data$find) %>% unique(),
collapse = "', '")
)
)
Expand Down Expand Up @@ -1061,9 +1108,8 @@ dataset_test_worker <-
} else {

# For wide datasets, expect variables in traits are headers in the data
values <- names(data)
expect_is_in(
traits[["var_in"]], values,
traits[["var_in"]], names(data),
info = paste0(red(files[2]), "\ttraits"), label = "`var_in`"
)

Expand All @@ -1083,10 +1129,10 @@ dataset_test_worker <-

## Check traits are not only NAs
yangsophieee marked this conversation as resolved.
Show resolved Hide resolved
expect_false(
nrow(metadata[["traits"]] %>% util_list_to_df2() %>% dplyr::filter(!is.na(.data$trait_name))) == 0,
nrow(traits %>% dplyr::filter(!is.na(.data$trait_name))) == 0,
info = paste0(red(f), "\ttraits - only contain NA `trait_name`'s"))

if (nrow(metadata[["traits"]] %>% util_list_to_df2() %>% dplyr::filter(!is.na(.data$trait_name))) > 0) {
if (nrow(traits %>% dplyr::filter(!is.na(.data$trait_name))) > 0) {

# Test build dataset
expect_no_error(
Expand Down
Loading