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

Fix dataSetToDataFrame #606

Merged
merged 2 commits into from
Sep 8, 2021
Merged

Fix dataSetToDataFrame #606

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a792506
-Add the line "name" to print of data set
PavelBal Sep 8, 2021
851231e
Avoid code repetition
PavelBal Sep 8, 2021
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
1 change: 1 addition & 0 deletions R/data-set.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -223,6 +223,7 @@ DataSet <- R6::R6Class(
#' @param ... Rest arguments.
print = function(...) {
private$printClass()
private$printLine("Name", self$name)
private$printLine("X dimension", self$xDimension)
private$printLine("X unit", self$xUnit)
private$printLine("Y dimension", self$yDimension)
Expand Down
70 changes: 48 additions & 22 deletions R/utilities-data-set.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,38 +55,64 @@ saveDataSetToPKML <- function(dataSet, filePath) {
rClr::clrCall(dataRepositoryTask, "SaveDataRepository", dataSet$dataRepository$ref, filePath)
}

#' Converts a list of DataSet objects to a data.frame
#' Converts a list of `DataSet` objects to a data.frame
#'
#' @param dataSets A list of DataSet objects or a single DataSet
#' @param dataSets A list of `DataSet` objects or a single `DataSet`
#'
#' @return DataSet objects as data.frame with columns name, xValue, yValue, yErrorValues,
#' xDimension, xUnit, yDimension, yUnit, yErrorType, yErrorUnit, yMolWeight
#' @return DataSet objects as data.frame with columns name, xValues, yValues, yErrorValues,
#' xDimension, xUnit, yDimension, yUnit, yErrorType, yErrorUnit, molWeight, lloq,
#' and a column for each meta data that is present in any `DataSet`
#' @export
dataSetToDataFrame <- function(dataSets) {
dataSets <- c(dataSets)
validateIsOfType(dataSets, DataSet)

name <- unlist(mapply(.makeDataFrameColumn, dataSets, "name"))
xUnit <- unlist(mapply(.makeDataFrameColumn, dataSets, "xUnit"))
yUnit <- unlist(mapply(.makeDataFrameColumn, dataSets, "yUnit"))
yErrorUnit <- as.character(unlist(mapply(.makeDataFrameColumn, dataSets, "yErrorUnit")))
xDimension <- unlist(mapply(.makeDataFrameColumn, dataSets, "xDimension"))
yDimension <- unlist(mapply(.makeDataFrameColumn, dataSets, "yDimension"))
yErrorType <- as.character(unlist(mapply(.makeDataFrameColumn, dataSets, "yErrorType")))
yMolWeight <- unlist(mapply(.makeDataFrameColumn, dataSets, "molWeight"))
xValue <- unlist(mapply(.makeDataFrameColumn, dataSets, "xValues"))
yValue <- unlist(mapply(.makeDataFrameColumn, dataSets, "yValues"))
yErrorValues <- unlist(mapply(.makeDataFrameColumn, dataSets, "yErrorValues"))
name <- unlist(lapply(dataSets, function(x) {
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

mapply and sapply and so produce weird results sometimes (in case of data sets loaded from excel the output was a matrix, in the case of manually created data sets it was a vector...), lapply is the only function that always will return a list, so lets use it where possible.

Adding use.naames = FALSE to unlist speeds up the whole thing and should be used when we do not need a named list.

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@hannaei FYI

.makeDataFrameColumn(x, "name")
}), use.names = FALSE)
xUnit <- unlist(lapply(dataSets, function(x) {
.makeDataFrameColumn(x, "xUnit")
}), use.names = FALSE)
yUnit <- unlist(lapply(dataSets, function(x) {
.makeDataFrameColumn(x, "yUnit")
}), use.names = FALSE)
yErrorUnit <- unlist(lapply(dataSets, function(x) {
.makeDataFrameColumn(x, "yErrorUnit")
}), use.names = FALSE)
xDimension <- unlist(lapply(dataSets, function(x) {
.makeDataFrameColumn(x, "xDimension")
}), use.names = FALSE)
yDimension <- unlist(lapply(dataSets, function(x) {
.makeDataFrameColumn(x, "yDimension")
}), use.names = FALSE)
yErrorType <- unlist(lapply(dataSets, function(x) {
.makeDataFrameColumn(x, "yErrorType")
}), use.names = FALSE)
molWeight <- unlist(lapply(dataSets, function(x) {
.makeDataFrameColumn(x, "molWeight")
}), use.names = FALSE)
xValues <- unlist(lapply(dataSets, function(x) {
.makeDataFrameColumn(x, "xValues")
}), use.names = FALSE)
yValues <- unlist(lapply(dataSets, function(x) {
.makeDataFrameColumn(x, "yValues")
}), use.names = FALSE)
yErrorValues <- unlist(lapply(dataSets, function(x) {
.makeDataFrameColumn(x, "yErrorValues")
}), use.names = FALSE)
lloq <- unlist(lapply(dataSets, function(x) {
.makeDataFrameColumn(x, "LLOQ")
}), use.names = FALSE)

df <- data.frame(
name, xValue, yValue, yErrorValues, xDimension, xUnit, yDimension,
yUnit, yErrorType, yErrorUnit, yMolWeight
name, xValues, yValues, yErrorValues, xDimension, xUnit, yDimension,
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Renamed column names (using plural) and added a LLOQ column.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

if feels like you could write a method

makeColums <- function(dataSets, columnName) {
  unlist(lapply(dataSet, function(x){
.makeDatqaFrameColumn(x, columnsName)
}
}

or sthg like this

yUnit, yErrorType, yErrorUnit, molWeight, lloq
)

# get all names of meta data entries from all data sets
metaDataNames <- unique(unlist(sapply(dataSets, function(dataSets) {
return(names(dataSets[["metaData"]]))
})))
metaDataNames <- unique(unlist(lapply(dataSets, function(dataSets) {
names(dataSets[["metaData"]])
}), use.names = FALSE))
# add one column for each one
for (name in metaDataNames) {
col <- unlist(lapply(dataSets, .makeDataFrameColumn, "metaData", metaDataName = name))
Expand Down Expand Up @@ -127,11 +153,11 @@ loadDataSetsFromExcel <- function(xlsFilePath, importerConfiguration, importAllS
dataImporterTask <- getNetTask("DataImporterTask")
rClr::clrSet(dataImporterTask, "IgnoreSheetNamesAtImport", importAllSheets)
dataRepositories <- rClr::clrCall(dataImporterTask, "ImportExcelFromConfiguration", importerConfiguration$ref, xlsFilePath)
dataSets <- lapply(dataRepositories, function(x){
dataSets <- lapply(dataRepositories, function(x) {
repository <- DataRepository$new(x)
DataSet$new(repository)
})
names(dataSets) <- lapply(dataSets, function(x){
names(dataSets) <- lapply(dataSets, function(x) {
x$name
})

Expand Down
11 changes: 6 additions & 5 deletions man/dataSetToDataFrame.Rd
View file
Open in desktop

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

108 changes: 54 additions & 54 deletions tests/testthat/test-utilities-data-set.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,9 +15,10 @@ test_that("It can convert an empty data set", {
expect_equal(
dataSetToDataFrame(dataSet),
data.frame(
name = character(0), xValue = logical(0), yValue = logical(0), yErrorValues = logical(0),
name = character(0), xValues = logical(0), yValues = logical(0), yErrorValues = logical(0),
xDimension = character(0), xUnit = character(0), yDimension = character(0),
yUnit = character(0), yErrorType = character(0), yErrorUnit = character(0), yMolWeight = logical(0)
yUnit = character(0), yErrorType = character(0), yErrorUnit = character(0), molWeight = logical(0),
lloq = logical(0)
)
)
})
Expand All @@ -27,10 +28,10 @@ test_that("It can convert a data set with xValues and yValues set by setValues,
expect_equal(
dataSetToDataFrame(dataSet),
data.frame(
name = rep("", 5), xValue = dataSet$xValues, yValue = dataSet$yValues, yErrorValues = rep(NA, 5),
name = rep("", 5), xValues = dataSet$xValues, yValues = dataSet$yValues, yErrorValues = rep(NA, 5),
xDimension = rep(dataSet$xDimension, 5), xUnit = rep(dataSet$xUnit, 5),
yDimension = rep(dataSet$yDimension, 5), yUnit = rep(dataSet$yUnit, 5),
yErrorType = rep(NA_character_, 5), yErrorUnit = rep(NA_character_, 5), yMolWeight = rep(NA, 5)
yErrorType = rep(NA_character_, 5), yErrorUnit = rep(NA_character_, 5), molWeight = rep(NA, 5), lloq = rep(NA, 5)
)
)
})
Expand All @@ -39,88 +40,56 @@ test_that("It can convert a data set with only non-empty fields, except for meta
dataSet$setValues(xValues = c(1, 2, 3, 4, 5), yValues = c(10, 20, 30, 40, 50), yErrorValues = c(0, 1, 2, 3, 0))
dataSet$name <- "Data1"
dataSet$molWeight <- 123
dataSet$LLOQ <- 0.2
expect_equal(
dataSetToDataFrame(dataSet),
data.frame(
name = rep(dataSet$name, 5), xValue = dataSet$xValues,
yValue = dataSet$yValues, yErrorValues = dataSet$yErrorValues,
name = rep(dataSet$name, 5), xValues = dataSet$xValues,
yValues = dataSet$yValues, yErrorValues = dataSet$yErrorValues,
xDimension = rep(dataSet$xDimension, 5), xUnit = rep(dataSet$xUnit, 5),
yDimension = rep(dataSet$yDimension, 5), yUnit = rep(dataSet$yUnit, 5),
yErrorType = rep(dataSet$yErrorType, 5), yErrorUnit = rep(dataSet$yErrorUnit, 5),
yMolWeight = rep(dataSet$molWeight, 5)
molWeight = rep(dataSet$molWeight, 5), lloq = rep(dataSet$LLOQ, 5)
)
)
})

test_that("It can convert a list of data sets", {
dataSet$setValues(xValues = c(1, 2, 3, 4, 5), yValues = c(10, 20, 30, 40, 50), yErrorValues = c(0, 1, 2, 3, 0))
dataSet$name <- "Data1"
dataSet$molWeight <- 123
dataSet2 <- DataSet$new()
dataSet2$setValues(xValues = c(6, 7, 8), yValues = c(11, 21, 31))
dataSet2$molWeight <- 456

expect_equal(
dataSetToDataFrame(list(dataSet, dataSet2)),
data.frame(
name = c(rep(dataSet$name, 5), rep("", 3)), xValue = c(dataSet$xValues, dataSet2$xValues),
yValue = c(dataSet$yValues, dataSet2$yValues), yErrorValues = c(dataSet$yErrorValues, rep(NA, 3)),
xDimension = c(rep(dataSet$xDimension, 5), rep(dataSet2$xDimension, 3)),
xUnit = c(rep(dataSet$xUnit, 5), rep(dataSet2$xUnit, 3)),
yDimension = c(rep(dataSet$yDimension, 5), rep(dataSet2$yDimension, 3)),
yUnit = c(rep(dataSet$yUnit, 5), rep(dataSet2$yUnit, 3)),
yErrorType = c(rep(dataSet$yErrorType, 5), rep(NA_character_, 3)),
yErrorUnit = c(rep(dataSet$yErrorUnit, 5), rep(NA_character_, 3)),
yMolWeight = c(rep(dataSet$molWeight, 5), rep(dataSet2$molWeight, 3))
)
)
})

test_that("It can convert a single data set with meta data", {
dataSet$setValues(xValues = c(1, 2, 3, 4, 5), yValues = c(10, 20, 30, 40, 50))
dataSet$name <- "Data1"
dataSet$molWeight <- 123
dataSet$addMetaData("City", "Rome")

test_that("It can convert a data set with metaData", {
dataSet$addMetaData("Organ", "Blood")
expect_equal(
dataSetToDataFrame(dataSet),
data.frame(
name = rep(dataSet$name, 5), xValue = dataSet$xValues, yValue = dataSet$yValues, yErrorValues = rep(NA, 5),
name = rep(dataSet$name, 5), xValues = dataSet$xValues,
yValues = dataSet$yValues, yErrorValues = dataSet$yErrorValues,
xDimension = rep(dataSet$xDimension, 5), xUnit = rep(dataSet$xUnit, 5),
yDimension = rep(dataSet$yDimension, 5), yUnit = rep(dataSet$yUnit, 5),
yErrorType = rep(NA_character_, 5), yErrorUnit = rep(NA_character_, 5), yMolWeight = rep(123, 5),
City = rep("Rome", 5)
yErrorType = rep(dataSet$yErrorType, 5), yErrorUnit = rep(dataSet$yErrorUnit, 5),
molWeight = rep(dataSet$molWeight, 5), lloq = rep(dataSet$LLOQ, 5),
Organ = rep("Blood", 5)
)
)
})

test_that("It can convert a list of data sets with meta data", {
dataSet$setValues(xValues = c(1, 2, 3, 4, 5), yValues = c(10, 20, 30, 40, 50), yErrorValues = c(0, 1, 2, 3, 0))
dataSet$name <- "Data1"
dataSet$molWeight <- 123
dataSet$addMetaData("City", "Rome")
test_that("It can convert a list of data sets", {
dataSet2 <- DataSet$new()
dataSet2$setValues(xValues = c(6, 7, 8), yValues = c(11, 21, 31))
dataSet2$molWeight <- 456
dataSet2$addMetaData("City", "Berlin")
dataSet2$addMetaData("ZIP", "10245")
dataSet2$addMetaData("Country", "Germany")
dataSet2$addMetaData("Compartment", "Plasma")

expect_equal(
dataSetToDataFrame(list(dataSet, dataSet2)),
data.frame(
name = c(rep(dataSet$name, 5), rep("", 3)), xValue = c(dataSet$xValues, dataSet2$xValues),
yValue = c(dataSet$yValues, dataSet2$yValues), yErrorValues = c(dataSet$yErrorValues, rep(NA, 3)),
name = c(rep(dataSet$name, 5), rep("", 3)), xValues = c(dataSet$xValues, dataSet2$xValues),
yValues = c(dataSet$yValues, dataSet2$yValues), yErrorValues = c(dataSet$yErrorValues, rep(NA, 3)),
xDimension = c(rep(dataSet$xDimension, 5), rep(dataSet2$xDimension, 3)),
xUnit = c(rep(dataSet$xUnit, 5), rep(dataSet2$xUnit, 3)),
yDimension = c(rep(dataSet$yDimension, 5), rep(dataSet2$yDimension, 3)),
yUnit = c(rep(dataSet$yUnit, 5), rep(dataSet2$yUnit, 3)),
yErrorType = c(rep(dataSet$yErrorType, 5), rep(NA_character_, 3)),
yErrorUnit = c(rep(dataSet$yErrorUnit, 5), rep(NA_character_, 3)),
yMolWeight = c(rep(dataSet$molWeight, 5), rep(dataSet2$molWeight, 3)),
City = c(rep("Rome", 5), rep("Berlin", 3)),
ZIP = c(rep(NA_character_, 5), rep("10245", 3)),
Country = c(rep(NA_character_, 5), rep("Germany", 3))
molWeight = c(rep(dataSet$molWeight, 5), rep(dataSet2$molWeight, 3)),
lloq = c(rep(dataSet$LLOQ, 5), rep(NA, 3)),
Organ = c(rep("Blood", 5), rep(NA, 3)), Compartment = c(rep(NA, 5), rep("Plasma", 3))
)
)
})
Expand Down Expand Up @@ -191,3 +160,34 @@ test_that("it can load when loading from file with one sheet without
expect_true(isOfType(dataSets, DataSet))
expect_equal(length(dataSets), 4)
})

test_that("it can convert DataSets loaded from excel to data.frame", {
dataSets <- loadDataSetsFromExcel(xlsFilePath = xlsFilePath, importerConfiguration = importerConfiguration, importAllSheets = TRUE)
dataSetsFrame <- dataSetToDataFrame(dataSets)
expect_equal(names(dataSetsFrame), c(
"name",
"xValues",
"yValues",
"yErrorValues",
"xDimension",
"xUnit",
"yDimension",
"yUnit",
"yErrorType",
"yErrorUnit",
"molWeight",
"lloq",
"Source",
"Sheet",
"Study Id",
"Organ",
"Compartment",
"Species",
"Gender",
"Molecule",
"Route",
"Subject Id",
"Dose",
"Group Id"
))
})