Variable labels can be created using ff_label. Some functions
strip variable labels (variable attributes), e.g. forcats::fct_recode.
Use this function to create a vector of variable labels from a data frame.
Then use ff_relabel to relabel variables in data frame.
ff_relabel(.data, .labels)
finalfit_relabel(.data, .labels)Data frame to be relabelled
Vector of variable labels (usually created using
extract_variable_label).
# Label variable
colon_s$sex.factor %>%
ff_label("Sex") %>%
str()
#> Factor w/ 2 levels "Female","Male": 2 2 1 1 2 1 2 2 2 1 ...
#> - attr(*, "label")= chr "Sex"
# Make factor level "Unknown" NA
colon_s %>%
dplyr::mutate_if(is.factor, forcats::fct_recode,
NULL = "Unknown") %>%
str()
#> 'data.frame': 929 obs. of 32 variables:
#> $ id : num 1 2 3 4 5 6 7 8 9 10 ...
#> $ rx : Factor w/ 3 levels "Obs","Lev","Lev+5FU": 3 3 1 3 1 3 2 1 2 3 ...
#> $ sex : num 1 1 0 0 1 0 1 1 1 0 ...
#> $ age : num 43 63 71 66 69 57 77 54 46 68 ...
#> ..- attr(*, "label")= chr "Age (years)"
#> $ obstruct : num NA 0 0 1 0 0 0 0 0 0 ...
#> $ perfor : num 0 0 0 0 0 0 0 0 0 0 ...
#> $ adhere : num 0 0 1 0 0 0 0 0 1 0 ...
#> $ nodes : num 5 1 7 6 22 9 5 1 2 1 ...
#> $ status : num 1 0 1 1 1 1 1 0 0 0 ...
#> $ differ : num 2 2 2 2 2 2 2 2 2 2 ...
#> $ extent : num 3 3 2 3 3 3 3 3 3 3 ...
#> $ surg : num 0 0 0 1 1 0 1 0 0 1 ...
#> $ node4 : num 1 0 1 1 1 1 1 0 0 0 ...
#> $ time : num 1521 3087 963 293 659 ...
#> $ sex.factor : Factor w/ 2 levels "Female","Male": 2 2 1 1 2 1 2 2 2 1 ...
#> $ rx.factor : Factor w/ 3 levels "Obs","Lev","Lev+5FU": 3 3 1 3 1 3 2 1 2 3 ...
#> $ obstruct.factor: Factor w/ 2 levels "No","Yes": NA 1 1 2 1 1 1 1 1 1 ...
#> $ perfor.factor : Factor w/ 2 levels "No","Yes": 1 1 1 1 1 1 1 1 1 1 ...
#> $ adhere.factor : Factor w/ 2 levels "No","Yes": 1 1 2 1 1 1 1 1 2 1 ...
#> $ differ.factor : Factor w/ 3 levels "Well","Moderate",..: 2 2 2 2 2 2 2 2 2 2 ...
#> $ extent.factor : Factor w/ 4 levels "Submucosa","Muscle",..: 3 3 2 3 3 3 3 3 3 3 ...
#> $ surg.factor : Factor w/ 2 levels "Short","Long": 1 1 1 2 2 1 2 1 1 2 ...
#> $ node4.factor : Factor w/ 2 levels "No","Yes": 2 1 2 2 2 2 2 1 1 1 ...
#> $ status.factor : Factor w/ 2 levels "Alive","Died": 2 1 2 2 2 2 2 1 1 1 ...
#> $ age.factor : Factor w/ 3 levels "<40 years","40-59 years",..: 2 3 3 3 3 2 3 2 2 3 ...
#> $ loccomp : num NA 0 1 1 0 0 0 0 1 0 ...
#> $ loccomp.factor : Factor w/ 2 levels "No","Yes": NA 1 2 2 1 1 1 1 2 1 ...
#> $ time.years : num 4.167 8.458 2.638 0.803 1.805 ...
#> ..- attr(*, "label")= chr "Time (years)"
#> $ mort_5yr : Factor w/ 2 levels "Alive","Died": 2 1 2 2 2 2 2 1 1 1 ...
#> $ age.10 : num 4.3 6.3 7.1 6.6 6.9 5.7 7.7 5.4 4.6 6.8 ...
#> $ mort_5yr.num : num 2 1 2 2 2 2 2 1 1 1 ...
#> $ hospital : Factor w/ 5 levels "hospital_1","hospital_2",..: 5 3 5 4 5 4 2 2 2 2 ...
# Reset data
data(colon_s)
# Extract variable labels
vlabels = colon_s %>% extract_variable_label()
# Run function where labels are lost
colon_s %>%
dplyr::mutate_if(is.factor, forcats::fct_recode,
NULL = "Unknown") %>%
str()
#> 'data.frame': 929 obs. of 32 variables:
#> $ id : num 1 2 3 4 5 6 7 8 9 10 ...
#> $ rx : Factor w/ 3 levels "Obs","Lev","Lev+5FU": 3 3 1 3 1 3 2 1 2 3 ...
#> $ sex : num 1 1 0 0 1 0 1 1 1 0 ...
#> $ age : num 43 63 71 66 69 57 77 54 46 68 ...
#> ..- attr(*, "label")= chr "Age (years)"
#> $ obstruct : num NA 0 0 1 0 0 0 0 0 0 ...
#> $ perfor : num 0 0 0 0 0 0 0 0 0 0 ...
#> $ adhere : num 0 0 1 0 0 0 0 0 1 0 ...
#> $ nodes : num 5 1 7 6 22 9 5 1 2 1 ...
#> $ status : num 1 0 1 1 1 1 1 0 0 0 ...
#> $ differ : num 2 2 2 2 2 2 2 2 2 2 ...
#> $ extent : num 3 3 2 3 3 3 3 3 3 3 ...
#> $ surg : num 0 0 0 1 1 0 1 0 0 1 ...
#> $ node4 : num 1 0 1 1 1 1 1 0 0 0 ...
#> $ time : num 1521 3087 963 293 659 ...
#> $ sex.factor : Factor w/ 2 levels "Female","Male": 2 2 1 1 2 1 2 2 2 1 ...
#> $ rx.factor : Factor w/ 3 levels "Obs","Lev","Lev+5FU": 3 3 1 3 1 3 2 1 2 3 ...
#> $ obstruct.factor: Factor w/ 2 levels "No","Yes": NA 1 1 2 1 1 1 1 1 1 ...
#> $ perfor.factor : Factor w/ 2 levels "No","Yes": 1 1 1 1 1 1 1 1 1 1 ...
#> $ adhere.factor : Factor w/ 2 levels "No","Yes": 1 1 2 1 1 1 1 1 2 1 ...
#> $ differ.factor : Factor w/ 3 levels "Well","Moderate",..: 2 2 2 2 2 2 2 2 2 2 ...
#> $ extent.factor : Factor w/ 4 levels "Submucosa","Muscle",..: 3 3 2 3 3 3 3 3 3 3 ...
#> $ surg.factor : Factor w/ 2 levels "Short","Long": 1 1 1 2 2 1 2 1 1 2 ...
#> $ node4.factor : Factor w/ 2 levels "No","Yes": 2 1 2 2 2 2 2 1 1 1 ...
#> $ status.factor : Factor w/ 2 levels "Alive","Died": 2 1 2 2 2 2 2 1 1 1 ...
#> $ age.factor : Factor w/ 3 levels "<40 years","40-59 years",..: 2 3 3 3 3 2 3 2 2 3 ...
#> $ loccomp : num NA 0 1 1 0 0 0 0 1 0 ...
#> $ loccomp.factor : Factor w/ 2 levels "No","Yes": NA 1 2 2 1 1 1 1 2 1 ...
#> $ time.years : num 4.167 8.458 2.638 0.803 1.805 ...
#> ..- attr(*, "label")= chr "Time (years)"
#> $ mort_5yr : Factor w/ 2 levels "Alive","Died": 2 1 2 2 2 2 2 1 1 1 ...
#> $ age.10 : num 4.3 6.3 7.1 6.6 6.9 5.7 7.7 5.4 4.6 6.8 ...
#> $ mort_5yr.num : num 2 1 2 2 2 2 2 1 1 1 ...
#> $ hospital : Factor w/ 5 levels "hospital_1","hospital_2",..: 5 3 5 4 5 4 2 2 2 2 ...
# Relabel
colon_s %<>% ff_relabel(vlabels)
colon_s %>% str()
#> 'data.frame': 929 obs. of 32 variables:
#> $ id : num 1 2 3 4 5 6 7 8 9 10 ...
#> ..- attr(*, "label")= chr "id"
#> $ rx : Factor w/ 3 levels "Obs","Lev","Lev+5FU": 3 3 1 3 1 3 2 1 2 3 ...
#> ..- attr(*, "label")= chr "rx"
#> $ sex : num 1 1 0 0 1 0 1 1 1 0 ...
#> ..- attr(*, "label")= chr "sex"
#> $ age : num 43 63 71 66 69 57 77 54 46 68 ...
#> ..- attr(*, "label")= chr "Age (years)"
#> $ obstruct : num NA 0 0 1 0 0 0 0 0 0 ...
#> ..- attr(*, "label")= chr "obstruct"
#> $ perfor : num 0 0 0 0 0 0 0 0 0 0 ...
#> ..- attr(*, "label")= chr "perfor"
#> $ adhere : num 0 0 1 0 0 0 0 0 1 0 ...
#> ..- attr(*, "label")= chr "adhere"
#> $ nodes : num 5 1 7 6 22 9 5 1 2 1 ...
#> ..- attr(*, "label")= chr "nodes"
#> $ status : num 1 0 1 1 1 1 1 0 0 0 ...
#> ..- attr(*, "label")= chr "status"
#> $ differ : num 2 2 2 2 2 2 2 2 2 2 ...
#> ..- attr(*, "label")= chr "differ"
#> $ extent : num 3 3 2 3 3 3 3 3 3 3 ...
#> ..- attr(*, "label")= chr "extent"
#> $ surg : num 0 0 0 1 1 0 1 0 0 1 ...
#> ..- attr(*, "label")= chr "surg"
#> $ node4 : num 1 0 1 1 1 1 1 0 0 0 ...
#> ..- attr(*, "label")= chr "node4"
#> $ time : num 1521 3087 963 293 659 ...
#> ..- attr(*, "label")= chr "time"
#> $ sex.factor : Factor w/ 2 levels "Female","Male": 2 2 1 1 2 1 2 2 2 1 ...
#> ..- attr(*, "label")= chr "Sex"
#> $ rx.factor : Factor w/ 3 levels "Obs","Lev","Lev+5FU": 3 3 1 3 1 3 2 1 2 3 ...
#> ..- attr(*, "label")= chr "Treatment"
#> $ obstruct.factor: Factor w/ 2 levels "No","Yes": NA 1 1 2 1 1 1 1 1 1 ...
#> ..- attr(*, "label")= chr "Obstruction"
#> $ perfor.factor : Factor w/ 2 levels "No","Yes": 1 1 1 1 1 1 1 1 1 1 ...
#> ..- attr(*, "label")= chr "Perforation"
#> $ adhere.factor : Factor w/ 2 levels "No","Yes": 1 1 2 1 1 1 1 1 2 1 ...
#> ..- attr(*, "label")= chr "Adherence"
#> $ differ.factor : Factor w/ 3 levels "Well","Moderate",..: 2 2 2 2 2 2 2 2 2 2 ...
#> ..- attr(*, "label")= chr "Differentiation"
#> $ extent.factor : Factor w/ 4 levels "Submucosa","Muscle",..: 3 3 2 3 3 3 3 3 3 3 ...
#> ..- attr(*, "label")= chr "Extent of spread"
#> $ surg.factor : Factor w/ 2 levels "Short","Long": 1 1 1 2 2 1 2 1 1 2 ...
#> ..- attr(*, "label")= chr "Time from surgery"
#> $ node4.factor : Factor w/ 2 levels "No","Yes": 2 1 2 2 2 2 2 1 1 1 ...
#> ..- attr(*, "label")= chr ">4 positive nodes"
#> $ status.factor : Factor w/ 2 levels "Alive","Died": 2 1 2 2 2 2 2 1 1 1 ...
#> ..- attr(*, "label")= chr "Status"
#> $ age.factor : Factor w/ 3 levels "<40 years","40-59 years",..: 2 3 3 3 3 2 3 2 2 3 ...
#> ..- attr(*, "label")= chr "Age"
#> $ loccomp : num NA 0 1 1 0 0 0 0 1 0 ...
#> ..- attr(*, "label")= chr "loccomp"
#> $ loccomp.factor : Factor w/ 2 levels "No","Yes": NA 1 2 2 1 1 1 1 2 1 ...
#> ..- attr(*, "label")= chr "Local complications"
#> $ time.years : num 4.167 8.458 2.638 0.803 1.805 ...
#> ..- attr(*, "label")= chr "Time (years)"
#> $ mort_5yr : Factor w/ 2 levels "Alive","Died": 2 1 2 2 2 2 2 1 1 1 ...
#> ..- attr(*, "label")= chr "Mortality 5 year"
#> $ age.10 : num 4.3 6.3 7.1 6.6 6.9 5.7 7.7 5.4 4.6 6.8 ...
#> ..- attr(*, "label")= chr "age.10"
#> $ mort_5yr.num : num 2 1 2 2 2 2 2 1 1 1 ...
#> ..- attr(*, "label")= chr "mort_5yr.num"
#> $ hospital : Factor w/ 5 levels "hospital_1","hospital_2",..: 5 3 5 4 5 4 2 2 2 2 ...
#> ..- attr(*, "label")= chr "hospital"