From 19918b04a3c4825322c25da329bfc3578fd43548 Mon Sep 17 00:00:00 2001
From: Kyle Belanger <kyleb44@hotmail.com>
Date: Fri, 6 Jan 2023 08:49:22 -0500
Subject: [PATCH] Update 0-data_prep.R

---
 ML/0-data_prep.R | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/ML/0-data_prep.R b/ML/0-data_prep.R
index 63ff9d3..f3d09b0 100644
--- a/ML/0-data_prep.R
+++ b/ML/0-data_prep.R
@@ -70,7 +70,8 @@ testds <- readr::read_csv(
 )
 
 
-
+#using chart time instead of spceimen id results in less NA values.
+# total protien still have very low resulting
 
 ds1 <- dplyr$tbl(db, "labevents") %>%
   dplyr$filter(itemid %in% test_list) %>%
@@ -88,6 +89,9 @@ count2 <- data.frame(colSums(is.na(ds1))) %>% tibble::rownames_to_column()
 counts <- count %>%
   dplyr$left_join(count2)
 
+# using charttime, total of 5,424 rows with all values filled in
+ds1 %>% dplyr$filter(dplyr$across(where(is.numeric), ~!is.na(.x)))
+
 # close database ----------------------------------------------------------
 
 dbDisconnect(db)