From 00e640df21cc780f3155e1d2a8064a4cf49ec953 Mon Sep 17 00:00:00 2001 From: Steve Nyemba Date: Thu, 2 Apr 2020 07:52:09 -0500 Subject: [PATCH] bug fix: @TODO: split partition data so we always process a decent sized data --- pipeline.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/pipeline.py b/pipeline.py index 78ffefe..4985156 100644 --- a/pipeline.py +++ b/pipeline.py @@ -152,6 +152,7 @@ class Components : # reader = args['reader'] # df = reader() df = args['reader']() if 'reader' in args else args['data'] + # bounds = Components.split(df,MAX_ROWS,PART_SIZE) # if partition != '' : # columns = args['columns'] @@ -168,7 +169,7 @@ class Components : # -- Let us tray assessing - df = np.array_split(df,N) + _dc = pd.DataFrame() # for mdf in df : _args['data'] = df