Make indexing faster by indexing only one column and querying a range

2 files changed, 6 insertions, 3 deletions

diff --git a/model/dest_simple_mlp_tgtcls.py b/model/dest_simple_mlp_tgtcls.py
index 2d65097..46fca2b 100644
--- a/model/dest_simple_mlp_tgtcls.py
+++ b/model/dest_simple_mlp_tgtcls.py
@@ -9,7 +9,7 @@ from model.mlp import FFMLP, Stream
 
 class Model(FFMLP):
     def __init__(self, config, **kwargs):
-        super(Model, self, output_layer=Softmax).__init__(config, **kwargs)
+        super(Model, self).__init__(config, output_layer=Softmax, **kwargs)
         self.classes = theano.shared(numpy.array(config.tgtcls, dtype=theano.config.floatX), name='classes')
 
     @application(outputs=['destination'])
diff --git a/model/mlp.py b/model/mlp.py
index 576b45b..05898a5 100644
--- a/model/mlp.py
+++ b/model/mlp.py
@@ -1,6 +1,6 @@
 from theano import tensor
 
-from fuel.transformers import Batch
+from fuel.transformers import Batch, MultiProcessing
 from fuel.streams import DataStream
 from fuel.schemes import ConstantScheme, ShuffledExampleScheme
 from blocks.bricks import application, MLP, Rectifier, Initializable
@@ -63,7 +63,10 @@ class Stream(object):
         stream = transformers.TaxiAddDateTime(stream)
         stream = transformers.TaxiAddFirstLastLen(self.config.n_begin_end_pts, stream)
         stream = transformers.Select(stream, tuple(req_vars))
-        return Batch(stream, iteration_scheme=ConstantScheme(self.config.batch_size))
+        
+        stream = Batch(stream, iteration_scheme=ConstantScheme(self.config.batch_size))
+
+        return stream
 
     def valid(self, req_vars):
         stream = TaxiStream(self.config.valid_set, 'valid.hdf5')