taxi

commit 27a0e0949c6ca3f7bd18569a23ddd0e1b3e9a64e
parent 793be7b049cecba43072858341dc7006fef352e7
Author: Alex Auvolat <alex.auvolat@ens.fr>
Date:   Fri, 10 Jul 2015 17:16:20 -0400

Batch shuffling

Diffstat:
M
config/dest_mlp_tgtcls_1_cswdtx_batchshuffle.py
 | 
4
++--
M
model/mlp.py
 | 
18
+++++++++++-------

2 files changed, 13 insertions(+), 9 deletions(-)
diff --git a/config/dest_mlp_tgtcls_1_cswdtx_batchshuffle.py b/config/dest_mlp_tgtcls_1_cswdtx_batchshuffle.py
@@ -23,14 +23,14 @@ dim_embeddings = [
 ]
 
 dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
-dim_hidden = [1000]
+dim_hidden = [500]
 dim_output = tgtcls.shape[0]
 
 embed_weights_init = IsotropicGaussian(0.01)
 mlp_weights_init = IsotropicGaussian(0.1) 
 mlp_biases_init = Constant(0.01)
 
-step_rule = Momentum(learning_rate=0.01, momentum=0.9)
+step_rule = Momentum(learning_rate=0.001, momentum=0.99)
 
 batch_size = 200
 
diff --git a/model/mlp.py b/model/mlp.py
@@ -52,6 +52,12 @@ class FFMLP(Initializable):
     def predict_inputs(self):
         return self.inputs
 
+class UniformGenerator(object):
+    def __init__(self):
+        self.rng = numpy.random.RandomState(123)
+    def __call__(self, *args):
+        return float(self.rng.uniform())
+
 class Stream(object):
     def __init__(self, config):
         self.config = config
@@ -69,17 +75,15 @@ class Stream(object):
 
         stream = transformers.TaxiExcludeTrips(stream, valid_trips_ids)
         stream = transformers.TaxiGenerateSplits(stream, max_splits=self.config.max_splits)
-        stream = transformers.add_destination(stream)
-
-        stream = transformers.taxi_add_datetime(stream)
-        stream = transformers.taxi_add_first_last_len(stream, self.config.n_begin_end_pts)
-        stream = transformers.Select(stream, tuple(req_vars))
 
         if hasattr(self.config, 'shuffle_batch_size'):
             stream = transformers.Batch(stream, iteration_scheme=ConstantScheme(self.config.shuffle_batch_size))
-            rng = numpy.random.RandomState(123)
-            stream = Mapping(stream, SortMapping(lambda x: float(rng.uniform())))
+            stream = Mapping(stream, SortMapping(key=UniformGenerator()))
             stream = Unpack(stream)
+
+        stream = transformers.taxi_add_datetime(stream)
+        stream = transformers.taxi_add_first_last_len(stream, self.config.n_begin_end_pts)
+        stream = transformers.Select(stream, tuple(req_vars))
         
         stream = Batch(stream, iteration_scheme=ConstantScheme(self.config.batch_size))