use gtsummary
to faster descriptive statistics
a dataframe.In order to reduce the amount of computation, it is
usually necessary to remove very discrete classification variables, such as
patient ID.
Source: R/calcu_med.R
calcu.Rd
use gtsummary
to faster descriptive statistics
a dataframe.In order to reduce the amount of computation, it is
usually necessary to remove very discrete classification variables, such as
patient ID.
Arguments
- data
a dataframe
- sp_conts
default is null;due to the automatic mechanism of
gtsummary
, this parameter is used to define very discrete continuous variables as continuous variables.- cate_stat
default is "n (p%)".See
gtsummary::tbl_summary ()
for more Details.- cont_stat
default is "mean (sd)".See
gtsummary::tbl_summary ()
for more Details.
Examples
if (FALSE) {
data(data_med)
lab_wider = data_med$lab %>%
tr(.,c("test_date"),"dat") %>%
group_by(patient_id,lab_name) %>%
arrange(test_date) %>% slice_tail(n =1) %>% ungroup() %>%
select(patient_id,lab_name ,lab_va) %>%
tr(.,c("lab_va"),"num") %>%
spread(lab_name,lab_va) %>% distinct()
HbA1c <- c(0,6.5,7.0,8.0,9.0,Inf)
TC <- c(0,5.2,6.2,Inf)
LDL <- c(0,3.4,4.1,Inf)
HDL <- c(0,1.0,Inf)
TG <- c(0,1.7,2.3,Inf)
WBC <- c(0,4,10,Inf)
#'
## keep only the columns related to the analysis
lib_name_list <- names(lab_wider)[-1]
## this step need to adjust the order of list subsets in name_list order
list_cut <- list(HbA1c,HDL,LDL,TC,TG,WBC)
## mutate multiple split variable columns
lab_wider_cut = mmc(lab_wider,lib_name_list,list_cut,digits=2)
## Add a missing data to fully demonstrate the function of the function
lab_wider_cut = lab_wider_cut %>%
rbind(.,
matrix(NA,nrow = 1,ncol =dim(lab_wider_cut)[2]) %>% data.frame() %>%
rename_at(vars(names(.)) ,~ names(lab_wider_cut)) ) %>%
mutate(patient_id = replace_na(patient_id, "test_id"))
## faster descriptive statistics.
data_lab_calcu <- calcu(lab_wider_cut[,-1],names(lab_wider)[-1])
}