renamed reg_cols_extraction.R to colnames_clinical_meds.R

data_extraction_formatting_clinical.R

@@ -10,7 +10,7 @@ getwd()
 # Input: source data
 #====================
 source("read_data.R")
-source("reg_cols_extraction.R")
+source("colnames_clinical_meds.R")
 ########################################################################
 # quick sanity checks
 table(adult_df$ia_exac_copd==1 & adult_df$asthma == 1) # check this is 4 

data_extraction_formatting_regression.R

@@ -10,7 +10,7 @@ getwd()
 # Input: source data for clinical
 #====================
 source("data_extraction_formatting_clinical.R")
-#source("reg_cols_extraction.R")
+#source("colnames_clinical_meds.R")
 #=======================================
 # Data for mediator to include in regression
 #=======================================

flu_stats_unpaired_clinical.R

@@ -20,31 +20,7 @@ source("data_extraction_formatting_clinical.R")
 outfile_name_clinical = paste0("flu_stats_clinical_unpaired.csv")
 outfile_clinical_unpaired = paste0(outdir_stats, outfile_name_clinical)
 outfile_clinical_unpaired 
-#===============================
-# data assignment for stats
-#================================
-wf = npa_wf[npa_wf$flustat == 1,]
-lf = npa_lf[npa_lf$flustat == 1,]
-lf$timepoint = paste0("t", lf$timepoint)
-lf = lf[!lf$mediator == "vitd",]
-########################################################################
-# clear variables
-rm(sam_lf, sam_wf
-, serum_lf, serum_wf) 
-rm(colnames_sam_df, expected_rows_sam_lf
-, colnames_serum_df, expected_rows_serum_lf)
 
-rm(pivot_cols)
-
-# sanity checks
-table(lf$timepoint)
-
-#if (table(lf$flustat) == table(npa_lf$flustat)[[2]]){
-#  cat("Analysing Flu positive patients for:", my_sample_type)
-#}else{
-#  cat("FAIL: problem with subsetting data for:", my_sample_type)
-#  quit()
-#}
 ########################################################################
 # Unpaired stats for clinical data b/w groups: wilcoxon UNpaired analysis 
 # No correction required
@@ -73,9 +49,9 @@ gathercols <- c("age", "los", "onset2final", "onsfindeath", "onset_2_initial", "
 
 clinical_lf = gather_(clinical_df_numerical, keycol, valuecol, gathercols)
 
-#==============
-# unpaired: t1
-#==============
+#====================
+# unpaired: clinical
+#====================
 sum(is.na(clinical_lf$value))
 
 foo = clinical_lf[which(is.na(clinical_lf$value)),]