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.

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 parse_data() (wrangle_data() from preproc.iquizoo) #85

Merged
merged 5 commits into from
Apr 3, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
3 changes: 2 additions & 1 deletion DESCRIPTION
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
Package: tarflow.iquizoo
Title: Setup "targets" Workflows for "iquizoo" Data Processing
Version: 3.10.2
Version: 3.10.2.9000
Authors@R: c(
person("Liang", "Zhang", , "[email protected]", role = c("aut", "cre"),
comment = c(ORCID = "0000-0001-9041-1150")),
Expand All @@ -22,6 +22,7 @@ Imports:
cli,
data.iquizoo (>= 2024.3.31.2),
DBI,
jsonlite,
memoise,
rlang (>= 1.0.0),
stringr,
Expand Down
1 change: 1 addition & 0 deletions NAMESPACE
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@ export(check_source)
export(fetch_data)
export(fetch_iquizoo)
export(fetch_iquizoo_mem)
export(parse_data)
export(setup_option_file)
export(setup_source)
export(setup_templates)
Expand Down
6 changes: 6 additions & 0 deletions NEWS.md
Original file line number Diff line number Diff line change
@@ -1,3 +1,9 @@
# tarflow.iquizoo (development version)

## Breaking Changes

* Added `parse_data()`, previously named as `wrangle_data()`. See <https://github.com/psychelzh/preproc.iquizoo/issues/86>.

# tarflow.iquizoo 3.10.2

* Fixed compatibility issue with 'data.iquizoo' 2024.03.31-2.
Expand Down
38 changes: 38 additions & 0 deletions R/database.R
Original file line number Diff line number Diff line change
Expand Up @@ -127,3 +127,41 @@ fetch_data <- function(project_id, game_id, ...,
params = list(project_id, game_id)
)
}

#' Parse Raw Data
#'
#' Raw data fetched from iQuizoo database is stored in json string format. This
#' function is used to parse raw json string data as [data.frame()] and store
#' them in a list column.
#'
#' @param data The raw data.
#' @param col_raw_json The column name storing raw json string data.
#' @param name_raw_parsed The name used to store parsed data.
#' @return A [data.frame] contains the parsed data.
#' @export
parse_data <- function(data,
col_raw_json = "game_data",
name_raw_parsed = "raw_parsed") {
data[[name_raw_parsed]] <- lapply(
data[[col_raw_json]],
parse_raw_json
)
data[, names(data) != col_raw_json, drop = FALSE]
}

# helper functions
parse_raw_json <- function(jstr) {
tryCatch(
jsonlite::fromJSON(jstr),
error = function(cnd) {
warn(
c(
"Failed to parse json string:",
conditionMessage(cnd),
i = "Will parse it as `NULL` instead."
)
)
return()
}
)
}
13 changes: 8 additions & 5 deletions R/targets.R
Original file line number Diff line number Diff line change
Expand Up @@ -240,12 +240,11 @@ tar_prep_raw <- function(contents,
contents$tar_indices <- syms(sprintf("%s_%s", name_indices, contents$game_id))
list(
raw_data_parsed = if ("parse" %in% action_raw_data) {
check_installed("preproc.iquizoo", "becasue required in wrangling.")
tarchetypes::tar_eval(
targets::tar_target(
tar_parsed,
wrangle_data(tar_data),
packages = "preproc.iquizoo"
parse_data(tar_data),
packages = "tarflow.iquizoo"
),
contents
)
Expand All @@ -255,7 +254,12 @@ tar_prep_raw <- function(contents,
tarchetypes::tar_eval(
targets::tar_target(
tar_indices,
preproc_data(tar_parsed, prep_fun, .input = input, .extra = extra),
preproc.iquizoo::preproc_data(
tar_parsed,
prep_fun,
.input = input,
.extra = extra
),
packages = "preproc.iquizoo"
),
data.iquizoo::merge_preproc(contents)
Expand All @@ -271,7 +275,6 @@ objects <- function() {
utils::globalVariables(
c(
"tar_data", "tar_parsed", "tar_indices",
"wrangle_data", "preproc_data",
"prep_fun", "input", "extra"
)
)
1 change: 1 addition & 0 deletions _pkgdown.yml
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@ reference:
- fetch_iquizoo
- fetch_iquizoo_mem
- fetch_data
- parse_data
- title: "Miscellaneous Option Functions"
desc: Functions to help you set up options.
contents:
Expand Down
23 changes: 23 additions & 0 deletions man/parse_data.Rd

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

19 changes: 19 additions & 0 deletions tests/testthat/test-database.R
Original file line number Diff line number Diff line change
Expand Up @@ -10,3 +10,22 @@ test_that("Ensure source checking works", {
check_source(source = source_invalid) |>
expect_false()
})

test_that("`parse_data()` works", {
js_str <- r"([{"a": 1, "b": 2}])"
data <- data.frame(game_data = js_str)
parse_data(data)$raw_parsed[[1]] |>
expect_identical(jsonlite::fromJSON(js_str))
parse_data(data, name_raw_parsed = "parsed") |>
expect_named("parsed")
})

test_that("Can deal with invalid or empty json", {
data_case_invalid <- data.frame(game_data = "[1")
parse_data(data_case_invalid)$raw_parsed[[1]] |>
expect_null() |>
expect_warning("Failed to parse json string")
data_case_empty <- data.frame(game_data = c("[]", "{}"))
parse_data(data_case_empty)$raw_parsed |>
lapply(expect_length, 0)
})