From 12eee6923a2dd038baa93459f9fa4c6715945de7 Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Tue, 17 Nov 2020 17:31:22 +0000
Subject: [PATCH] added checks.R

---
 checks.R | 62 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)
 create mode 100755 checks.R

diff --git a/checks.R b/checks.R
new file mode 100755
index 0000000..90a296a
--- /dev/null
+++ b/checks.R
@@ -0,0 +1,62 @@
+#!/usr/bin/Rscript   
+getwd()
+setwd("~/git/mosaic_2020/")
+getwd()
+########################################################################
+# TASK: read data 
+########################################################################
+# load libraries, packages and local imports
+source("Header_TT.R")
+########################################################################
+maindir = "~/git/mosaic_2020/"
+outdir = paste0(maindir, "output/")
+ifelse(!dir.exists(outdir), dir.create(outdir), FALSE)
+
+outdir_stats = paste0(maindir, "output/stats/")
+ifelse(!dir.exists(outdir_stats), dir.create(outdir_stats), FALSE)
+
+outdir_plots = paste0(maindir, "output/plots")
+ifelse(!dir.exists(outdir_plots), dir.create(outdir_plots), FALSE)
+########################################################################
+# static file read: csv
+#==============
+# all patients
+#==============
+all_df <- read.csv("/home/backup/MOSAIC/MEDIATOR_Data/master_file/Mosaic_master_file_from_stata.csv"
+                   , fileEncoding = 'latin1') 
+
+# meta data columns                   
+meta_data_cols = c("mosaic", "gender", "age", "adult", "flustat", "type"
+                   , "obesity", "obese2", "height", "height_unit", "weight"
+                   , "weight_unit", "visual_est_bmi", "bmi_rating")
+
+# check if these columns to select are present in the data
+meta_data_cols%in%colnames(all_df)
+all(meta_data_cols%in%colnames(all_df))
+
+metadata_all = all_df[, meta_data_cols]
+
+#============
+# hc
+#============
+#hc_data<- read.csv("/home/backup/MOSAIC/MEDIATOR_Data/master_file/Mediators_for_HC.csv")
+#str(hc_data)
+#table(hc_data$Timepoint, hc_data$Sample)
+########################################################################
+# quick checks on obesity and obese2
+aki_flupos = read.csv(paste0(outdir, "aki_flupos.csv"))
+
+obesity_check = as.data.frame(cbind(all_df$mosaic, all_df$age, all_df$adult, all_df$flustat, all_df$obesity, all_df$obese2))
+colnames(obesity_check) = c("mosaic", "age", "adult", "flustat", "obesity", "obese2")
+
+obesity_check$adult_check = ifelse(all_df$age>=18 && all_df$adult == 1, "PASS", "FAIL")
+table(obesity_check$adult_check)
+
+table(obesity_check$adult)
+table(obesity_check$adult, obesity_check$flustat)
+
+ob_adults = obesity_check[obesity_check$adult == 1,]
+ob_adults2 = obesity_check[obesity_check$adult == 1 & obesity_check$age>=18,] # AHA!
+
+# check where the discrepancy is?
+c = ob_adults$mosaic[!ob_adults$mosaic%in%aki_flupos$Subject_ID]; c