From 8585fd5b59f294f8ef2716f86f3efd7ba2426a2b Mon Sep 17 00:00:00 2001 From: Maya Tydykov Date: Thu, 21 Apr 2016 15:01:03 -0400 Subject: [PATCH] MAINT: move filtering for nulls in date column to blaze loader --- zipline/pipeline/loaders/blaze/events.py | 4 +++- zipline/pipeline/loaders/events.py | 3 +-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/zipline/pipeline/loaders/blaze/events.py b/zipline/pipeline/loaders/blaze/events.py index 6fae418f..e951cac0 100644 --- a/zipline/pipeline/loaders/blaze/events.py +++ b/zipline/pipeline/loaders/blaze/events.py @@ -78,7 +78,9 @@ class BlazeEventsLoader(PipelineLoader): expected_fields = self._expected_fields self._expr = bind_expression_to_resources( - expr[list(expected_fields)], + expr[list(expected_fields)][expr[ + self.concrete_loader.event_date_col + ].notnull()], resources, ) self._odo_kwargs = odo_kwargs if odo_kwargs is not None else {} diff --git a/zipline/pipeline/loaders/events.py b/zipline/pipeline/loaders/events.py index 19f68e7a..42afac97 100644 --- a/zipline/pipeline/loaders/events.py +++ b/zipline/pipeline/loaders/events.py @@ -152,8 +152,7 @@ class EventsLoader(PipelineLoader): raise ValueError( WRONG_MANY_COL_DATA_FORMAT_ERROR.format(sid=k) ) - self.events_by_sid = {sid: df.dropna(subset=[self.event_date_col]) for - sid, df in self.events_by_sid.iteritems()} + self.dataset = dataset def get_loader(self, column):