taxi

commit 2a20bc827a8c1c9b6e74ef4e1234788207be45b8
parent d3dbbe68642320b9a225b1d3515f0181916df8ad
Author: Alex Auvolat <alex.auvolat@ens.fr>
Date:   Sat, 25 Jul 2015 17:31:17 -0400

Add batch sorting

Diffstat:
M
config/memory_network_bidir_momentum.py
 | 
6
+++---
M
model/memory_network.py
 | 
27
++++++++++++++++++---------
M
model/stream.py
 | 
10
+++++-----

3 files changed, 26 insertions(+), 17 deletions(-)
diff --git a/config/memory_network_bidir_momentum.py b/config/memory_network_bidir_momentum.py
@@ -51,8 +51,8 @@ batch_sort_size = 20
 max_splits = 100
 num_cuts = 1000
 
-train_candidate_size = 1000
-valid_candidate_size = 1000
-test_candidate_size = 1000
+train_candidate_size = 300
+valid_candidate_size = 300
+test_candidate_size = 300
 
 step_rule = Momentum(learning_rate=0.01, momentum=0.9)
diff --git a/model/memory_network.py b/model/memory_network.py
@@ -215,7 +215,7 @@ class StreamRecurrent(StreamBase):
         ]
         self.candidate_inputs = self.prefix_inputs
 
-    def candidate_stream(self, n_candidates):
+    def candidate_stream(self, n_candidates, sortmap=True):
         candidate_stream = DataStream(self.train_dataset,
                                       iteration_scheme=ShuffledExampleScheme(self.train_dataset.num_examples))
         if not data.tvt:
@@ -226,8 +226,14 @@ class StreamRecurrent(StreamBase):
         if not data.tvt:
             candidate_stream = transformers.add_destination(candidate_stream)
 
-        candidate_stream = Batch(candidate_stream,
-                                 iteration_scheme=ConstantScheme(n_candidates))
+        if sortmap:
+            candidate_stream = transformers.balanced_batch(candidate_stream,
+                                                           key='latitude',
+                                                           batch_size=n_candidates,
+                                                           batch_sort_size=self.config.batch_sort_size)
+        else:
+            candidate_stream = Batch(candidate_stream,
+                                     iteration_scheme=ConstantScheme(n_candidates))
 
         candidate_stream = Padding(candidate_stream,
                                    mask_sources=['latitude', 'longitude'])
@@ -247,9 +253,9 @@ class StreamRecurrent(StreamBase):
         prefix_stream = transformers.taxi_add_datetime(prefix_stream)
 
         prefix_stream = transformers.balanced_batch(prefix_stream,
-                                                  key='latitude',
-                                                  batch_size=self.config.batch_size,
-                                                  batch_sort_size=self.config.batch_sort_size)
+                                                    key='latitude',
+                                                    batch_size=self.config.batch_size,
+                                                    batch_sort_size=self.config.batch_sort_size)
 
         prefix_stream = Padding(prefix_stream, mask_sources=['latitude', 'longitude'])
 
@@ -271,8 +277,11 @@ class StreamRecurrent(StreamBase):
 
         prefix_stream = transformers.taxi_add_datetime(prefix_stream)
 
-        prefix_stream = Batch(prefix_stream,
-                              iteration_scheme=ConstantScheme(self.config.batch_size))
+        prefix_stream = transformers.balanced_batch(prefix_stream,
+                                                    key='latitude',
+                                                    batch_size=self.config.batch_size,
+                                                    batch_sort_size=self.config.batch_sort_size)
+
         prefix_stream = Padding(prefix_stream, mask_sources=['latitude', 'longitude'])
 
         candidate_stream = self.candidate_stream(self.config.valid_candidate_size)
@@ -298,7 +307,7 @@ class StreamRecurrent(StreamBase):
                               iteration_scheme=ConstantScheme(self.config.batch_size))
         prefix_stream = Padding(prefix_stream, mask_sources=['latitude', 'longitude'])
 
-        candidate_stream = self.candidate_stream(self.config.test_candidate_size)
+        candidate_stream = self.candidate_stream(self.config.test_candidate_size, False)
 
         sources = prefix_stream.sources + tuple('candidate_%s' % k for k in candidate_stream.sources)
         stream = Merge((prefix_stream, candidate_stream), sources)
diff --git a/model/stream.py b/model/stream.py
@@ -33,17 +33,13 @@ class StreamRec(object):
 
         stream = transformers.TaxiExcludeEmptyTrips(stream)
         stream = transformers.taxi_add_datetime(stream)
-
         stream = transformers.Select(stream, tuple(v for v in req_vars if not v.endswith('_mask')))
 
         stream = transformers.balanced_batch(stream, key='latitude',
                                              batch_size=self.config.batch_size,
                                              batch_sort_size=self.config.batch_sort_size)
-
         stream = Padding(stream, mask_sources=['latitude', 'longitude'])
-        
         stream = transformers.Select(stream, req_vars)
-
         stream = MultiProcessing(stream)
 
         return stream
@@ -54,9 +50,13 @@ class StreamRec(object):
         stream = transformers.taxi_add_datetime(stream)
         stream = transformers.Select(stream, tuple(v for v in req_vars if not v.endswith('_mask')))
 
-        stream = Batch(stream, iteration_scheme=ConstantScheme(self.config.batch_size))
+        stream = transformers.balanced_batch(stream, key='latitude',
+                                             batch_size=self.config.batch_size,
+                                             batch_sort_size=self.config.batch_sort_size)
         stream = Padding(stream, mask_sources=['latitude', 'longitude'])
         stream = transformers.Select(stream, req_vars)
+        stream = MultiProcessing(stream)
+
         return stream
 
     def test(self, req_vars):