From 0f88e4133dfc8e42f639db7f9d31ef53fa7cefd6 Mon Sep 17 00:00:00 2001
From: Thomas Wiecki <thomas.wiecki@gmail.com>
Date: Sun, 30 Dec 2012 17:26:07 -0500
Subject: [PATCH] ENH: New batch_transform feature: compute_only_full.

---
 tests/test_transforms.py    |  3 +++
 zipline/test_algorithms.py  | 10 +++++++++-
 zipline/transforms/utils.py | 23 +++++++++++++----------
 3 files changed, 25 insertions(+), 11 deletions(-)

diff --git a/tests/test_transforms.py b/tests/test_transforms.py
index 1d0197a9..8b775990 100644
--- a/tests/test_transforms.py
+++ b/tests/test_transforms.py
@@ -359,6 +359,9 @@ class TestBatchTransform(TestCase):
         for data in algo.history_return_ticks[wl:]:
             self.assertTrue(isinstance(data, deque))
 
+        for data in algo.history_return_not_full:
+            self.assertIsNot(data, None)
+
         # test overloaded class
         for test_history in [algo.history_return_price_class,
                              algo.history_return_price_decorator]:
diff --git a/zipline/test_algorithms.py b/zipline/test_algorithms.py
index c82edcf8..b22d2719 100644
--- a/zipline/test_algorithms.py
+++ b/zipline/test_algorithms.py
@@ -273,6 +273,7 @@ class BatchTransformAlgorithm(TradingAlgorithm):
         self.history_return_field_filter = []
         self.history_return_field_no_filter = []
         self.history_return_ticks = []
+        self.history_return_not_full = []
 
         self.return_price_class = ReturnPriceBatchTransform(
             refresh_period=self.refresh_period,
@@ -333,10 +334,15 @@ class BatchTransformAlgorithm(TradingAlgorithm):
         self.return_ticks = return_data(
             refresh_period=self.refresh_period,
             window_length=self.window_length,
-            clean_nans=True,
             create_panel=False
         )
 
+        self.return_not_full = return_data(
+            refresh_period=0,
+            window_length=self.window_length,
+            compute_only_full=False
+        )
+
         self.iter = 0
 
         self.set_slippage(FixedSlippage())
@@ -351,6 +357,8 @@ class BatchTransformAlgorithm(TradingAlgorithm):
                 data, *self.args, **self.kwargs))
         self.history_return_ticks.append(
             self.return_ticks.handle_data(data))
+        self.history_return_not_full.append(
+            self.return_not_full.handle_data(data))
 
         new_data = deepcopy(data)
         for sid in new_data:
diff --git a/zipline/transforms/utils.py b/zipline/transforms/utils.py
index 8182441c..0fd647b5 100644
--- a/zipline/transforms/utils.py
+++ b/zipline/transforms/utils.py
@@ -346,7 +346,9 @@ class BatchTransform(EventWindow):
                  clean_nans=True,
                  sids=None,
                  fields=None,
-                 create_panel=True):
+                 create_panel=True,
+                 compute_only_full=True):
+
         """Instantiate new batch_transform object.
 
         :Arguments:
@@ -374,6 +376,9 @@ class BatchTransform(EventWindow):
                 If True, will pass the underlying deque reference
                 directly to the function which will be significantly
                 faster.
+            compute_only_full : bool <default=True>
+                Only call the user-defined function once the window is
+                full. Returns None if window is not full yet.
         """
 
         super(BatchTransform, self).__init__(True,
@@ -386,6 +391,7 @@ class BatchTransform(EventWindow):
 
         self.clean_nans = clean_nans
         self.create_panel = create_panel
+        self.compute_only_full = compute_only_full
 
         self.sids = sids
         if isinstance(self.sids, (str, int)):
@@ -451,7 +457,6 @@ class BatchTransform(EventWindow):
             if self.field_names is None:
                 self.field_names = self._extract_field_names(event)
             self.last_dt = event.dt
-            return
 
         # update trading day counters
         if self.last_dt.day != event.dt.day:
@@ -459,15 +464,14 @@ class BatchTransform(EventWindow):
             self.trading_days_since_update += 1
             self.trading_days_total += 1
 
-        if (
-            self.trading_days_total >= self.window_length and
-            self.trading_days_since_update >= self.refresh_period
-        ):
+        if self.trading_days_total >= self.window_length:
+            self.full = True
+
+        if self.trading_days_since_update >= self.refresh_period:
             # Setting updated to True will cause get_transform_value()
             # to call the user-defined batch-transform with the most
             # recent datapanel
             self.updated = True
-            self.full = True
             self.trading_days_since_update = 0
         else:
             self.updated = False
@@ -517,8 +521,7 @@ class BatchTransform(EventWindow):
         return data
 
     def handle_remove(self, event):
-        # since an event is expiring, we know the window is full
-        self.full = True
+        pass
 
     def get_value(self, *args, **kwargs):
         raise NotImplementedError(
@@ -532,7 +535,7 @@ class BatchTransform(EventWindow):
         has actually been updated. Otherwise, the previously, cached
         value will be returned.
         """
-        if not self.full:
+        if self.compute_only_full and not self.full:
             return None
 
         if self.updated: