transfer from old repo

1 PA Decline/data_format.R

@@ -0,0 +1,50 @@
+## Article 1 outcome group definition script
+## To be enriched from Statistics Denmark
+## 
+## Based on the ItMLiHSmar2022 course
+
+library(Hmisc)
+library(dplyr)
+# library(daDoctoR)
+library(tidyselect)
+
+# Setting final primary output from "pout"
+if (pout=="drop"){
+  X_tbl <- X_tbl|>
+    mutate(group=pase_drop_fac)
+  
+  # print(quantile(as.numeric(X_tbl$pase_0)))
+  # print(quantile(as.numeric(X_tbl$pase_6)))
+  # print(summary(X_tbl$pase_0_cut))
+  
+  X_tbl_f <- X_tbl|>
+    filter(pase_0_cut!=1)|>
+    select(-starts_with("pase_"))
+}
+
+if (pout=="hop"){
+  X_tbl <- X_tbl|>
+    mutate(group=pase_hop_fac)
+  
+  # print(quantile(as.numeric(X_tbl$pase_0)))
+  # print(quantile(as.numeric(X_tbl$pase_6)))
+  # print(summary(X_tbl$pase_0_cut))
+  
+  X_tbl_f <- X_tbl|>
+    filter(pase_6_cut!=1)|>
+    select(-starts_with("pase_"))
+}
+
+# Dropping non-complete for analysis
+Xy <- X_tbl_f|> 
+  na.omit()|> # Keeping only complete observations
+  select(-c(tci) # Left out of model as no present in drop-group
+  )|>
+  mutate(mrs_0=factor(ifelse(mrs_0==1,1,2))) # Sets binary mRS 0 to include in glmnet, 0 or above
+
+label(Xy) = as.list(var.labels[match(names(Xy), names(var.labels))])
+
+X<-dplyr::select(Xy,-c(group, -starts_with("pase_")) # Exclude primary outcome
+                 )
+y<-Xy$group
+