From 79b83c71d5043427c37bd81f3beebc4637fac9eb Mon Sep 17 00:00:00 2001
From: Steve Nyemba <steve@the-phi.com>
Date: Wed, 12 May 2021 10:14:53 -0500
Subject: [PATCH] bug fix: date, hack put in place

---
 pipeline.py | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/pipeline.py b/pipeline.py
index 252a850..b6e808f 100644
--- a/pipeline.py
+++ b/pipeline.py
@@ -251,13 +251,16 @@ class Components :
 				_value = 0
 				if _item['type'] in ['DATE','TIMESTAMP','DATETIMESTAMP','DATETIME'] :
 					if _item['type'] == 'DATE' :
-						_df[name] = _df[name].dt.date
-						_df[name] = pd.to_datetime(_df[name],errors='coerce')
-
-
-					
-					
-					
+						#
+						# There is an issue with missing dates that needs to be resolved.
+						# for some reason a missing date/time here will cause the types to turn into timestamp (problem)
+						#	The following is a hack to address the issue (alas) assuming 10 digit dates and 'NaT' replaces missing date values (pandas specifications)
+						#
+						_df[name] = _df[name].apply(lambda value: '' if str(value) == 'NaT' else str(value)[:10])
+						#_df[name] = _df[name].dt.date
+						# _df[name] = pd.to_datetime(_df[name].fillna(''),errors='coerce')
+					else:
+						print ([' ** ',name,_item['type']])
 				else:
 					if _item['type'] == 'INTEGER' :
 						_type = np.int64