From f6bc6e09df3002e33df6c1d10d04d2e8bc2473b4 Mon Sep 17 00:00:00 2001
From: jangevaare <justin.angevaare@wdgpublichealth.ca>
Date: Tue, 23 Apr 2024 13:48:05 +0000
Subject: [PATCH 1/2] Fix erroneous collection dates

---
 processing/process.R | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/processing/process.R b/processing/process.R
index 7390740..6594718 100644
--- a/processing/process.R
+++ b/processing/process.R
@@ -160,14 +160,25 @@ wtisen_data = read_csv(
         "MUNICIPALITY",
         "COUNTY"),
       .fns = \(x) str_replace(x, "_", " ")),
+      
     across(
       .cols = starts_with("DATE_"),
       .fns = \(x) {x |>
           as_datetime(format = c("%m/%d/%Y %I:%M:%S %p", "%Y-%m-%d %H:%M:%S")) |>
           force_tz(tz = "America/Toronto")}),
+          
+    # Convert erroneous collection dates to NAs
+    DATE_COLLECTED = case_when(
+      # Collected >6 months before receipt
+      DATE_COLLECTED < (DATE_RECEIVED - months(6)) ~ NA_POSIXct_,
+      # Collected after lab receipt
+      DATE_COLLECTED > DATE_RECEIVED ~ NA_POSIXct_,
+      .default = DATE_COLLECTED),
+      
     across(
       .cols = where(is.character),
       .fns  = \(x) str_trim(x)),
+      
     POSTAL = postalcode_cleaner(POSTAL),
     ENTRY = as.integer(ENTRY),
     REQ_LEGIBLE = str_detect(REQ_LEGIBLE, "^y|Y$"))

From 64bd978be37b1659f6db84282c58db918492696b Mon Sep 17 00:00:00 2001
From: jangevaare <justin.angevaare@wdgpublichealth.ca>
Date: Tue, 23 Apr 2024 13:53:11 +0000
Subject: [PATCH 2/2] Correct CLI help to parquet file

---
 processing/process.R | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/processing/process.R b/processing/process.R
index 6594718..f4279ee 100644
--- a/processing/process.R
+++ b/processing/process.R
@@ -18,7 +18,7 @@ parser = OptionParser(
 
     make_option(
       opt_str = c("-o", "--output"),
-      help = "Output file, in CSV format.",
+      help = "Output file, in parquet format.",
       type = "character",
       default = ""),