Refactor models, clean the code and separate training from testing.

14 files changed, 83 insertions, 21 deletions

diff --git a/config/dest_simple_mlp_2_cs.py b/config/dest_simple_mlp_2_cs.py
index accb611..be93427 100644
--- a/config/dest_simple_mlp_2_cs.py
+++ b/config/dest_simple_mlp_2_cs.py
@@ -1,8 +1,8 @@
 from blocks.initialization import IsotropicGaussian, Constant
 
-import model.dest_simple_mlp as model
-
 import data
+from model.dest_simple_mlp import Model, Stream
+
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
 n_end_pts = 5
diff --git a/config/dest_simple_mlp_2_cswdt.py b/config/dest_simple_mlp_2_cswdt.py
index 62d0db4..a86977c 100644
--- a/config/dest_simple_mlp_2_cswdt.py
+++ b/config/dest_simple_mlp_2_cswdt.py
@@ -1,8 +1,8 @@
-import model.dest_simple_mlp as model
-
 from blocks.initialization import IsotropicGaussian, Constant
 
 import data
+from model.dest_simple_mlp import Model, Stream
+
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
 n_end_pts = 5
diff --git a/config/dest_simple_mlp_2_noembed.py b/config/dest_simple_mlp_2_noembed.py
index bbe7798..5615a5c 100644
--- a/config/dest_simple_mlp_2_noembed.py
+++ b/config/dest_simple_mlp_2_noembed.py
@@ -1,8 +1,8 @@
-import model.dest_simple_mlp as model
-
 from blocks.initialization import IsotropicGaussian, Constant
 
 import data
+from model.dest_simple_mlp import Model, Stream
+
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
 n_end_pts = 5
diff --git a/config/dest_simple_mlp_tgtcls_0_cs.py b/config/dest_simple_mlp_tgtcls_0_cs.py
index 704e62c..f5b9a1e 100644
--- a/config/dest_simple_mlp_tgtcls_0_cs.py
+++ b/config/dest_simple_mlp_tgtcls_0_cs.py
@@ -3,8 +3,8 @@ import cPickle
 from blocks.initialization import IsotropicGaussian, Constant
 
 import data
+from model.dest_simple_mlp_tgtcls import Model, Stream
 
-import model.dest_simple_mlp_tgtcls as model
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
 n_end_pts = 5
diff --git a/config/dest_simple_mlp_tgtcls_1_cs.py b/config/dest_simple_mlp_tgtcls_1_cs.py
index f2a22a5..54457e7 100644
--- a/config/dest_simple_mlp_tgtcls_1_cs.py
+++ b/config/dest_simple_mlp_tgtcls_1_cs.py
@@ -3,8 +3,8 @@ import cPickle
 from blocks.initialization import IsotropicGaussian, Constant
 
 import data
+from model.dest_simple_mlp_tgtcls import Model, Stream
 
-import model.dest_simple_mlp_tgtcls as model
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
 n_end_pts = 5
diff --git a/config/dest_simple_mlp_tgtcls_1_cswdt.py b/config/dest_simple_mlp_tgtcls_1_cswdt.py
index a3ae654..486b7a6 100644
--- a/config/dest_simple_mlp_tgtcls_1_cswdt.py
+++ b/config/dest_simple_mlp_tgtcls_1_cswdt.py
@@ -3,8 +3,8 @@ import cPickle
 from blocks.initialization import IsotropicGaussian, Constant
 
 import data
+from model.dest_simple_mlp_tgtcls import Model, Stream
 
-import model.dest_simple_mlp_tgtcls as model
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
 n_end_pts = 5
diff --git a/config/dest_simple_mlp_tgtcls_1_cswdtx.py b/config/dest_simple_mlp_tgtcls_1_cswdtx.py
index 6306c15..713581d 100644
--- a/config/dest_simple_mlp_tgtcls_1_cswdtx.py
+++ b/config/dest_simple_mlp_tgtcls_1_cswdtx.py
@@ -3,8 +3,8 @@ import cPickle
 from blocks.initialization import IsotropicGaussian, Constant
 
 import data
+from model.dest_simple_mlp_tgtcls import Model, Stream
 
-import model.dest_simple_mlp_tgtcls as model
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
 n_end_pts = 5
diff --git a/config/dest_simple_mlp_tgtcls_1_cswdtx_alexandre.py b/config/dest_simple_mlp_tgtcls_1_cswdtx_alexandre.py
index 8c090c7..c0ba36c 100644
--- a/config/dest_simple_mlp_tgtcls_1_cswdtx_alexandre.py
+++ b/config/dest_simple_mlp_tgtcls_1_cswdtx_alexandre.py
@@ -3,8 +3,8 @@ import cPickle
 from blocks.initialization import IsotropicGaussian, Constant
 
 import data
+from model.dest_simple_mlp_tgtcls import Model, Stream
 
-import model.dest_simple_mlp_tgtcls as model
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
 n_end_pts = 5
diff --git a/config/joint_simple_mlp_tgtcls_111_cswdtx.py b/config/joint_simple_mlp_tgtcls_111_cswdtx.py
index deb6eba..a7e0415 100644
--- a/config/joint_simple_mlp_tgtcls_111_cswdtx.py
+++ b/config/joint_simple_mlp_tgtcls_111_cswdtx.py
@@ -1,10 +1,10 @@
 import cPickle
 
-import model.joint_simple_mlp_tgtcls as model
-
 from blocks.initialization import IsotropicGaussian, Constant
 
 import data
+from model.joint_simple_mlp_tgtcls import Model, Stream
+
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
 n_end_pts = 5
diff --git a/config/joint_simple_mlp_tgtcls_111_cswdtx_noise_dout.py b/config/joint_simple_mlp_tgtcls_111_cswdtx_noise_dout.py
new file mode 100644
index 0000000..1faea15
--- /dev/null
+++ b/config/joint_simple_mlp_tgtcls_111_cswdtx_noise_dout.py
@@ -0,0 +1,62 @@
+import cPickle
+
+from blocks import roles
+from blocks.bricks import Rectifier
+from blocks.filter import VariableFilter
+from blocks.initialization import IsotropicGaussian, Constant
+
+import data
+from model.joint_simple_mlp_tgtcls import Model, Stream
+
+
+n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
+n_end_pts = 5
+
+n_valid = 1000
+
+with open("%s/arrival-clusters.pkl" % data.path) as f:
+    dest_tgtcls = cPickle.load(f)
+
+# generate target classes for time prediction as a Fibonacci sequence
+time_tgtcls = [1, 2]
+for i in range(22):
+    time_tgtcls.append(time_tgtcls[-1] + time_tgtcls[-2])
+
+dim_embeddings = [
+    ('origin_call', data.origin_call_size+1, 10),
+    ('origin_stand', data.stands_size+1, 10),
+    ('week_of_year', 52, 10),
+    ('day_of_week', 7, 10),
+    ('qhour_of_day', 24 * 4, 10),
+    ('day_type', 3, 10),
+    ('taxi_id', 448, 10),
+]
+
+# Common network part
+dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
+dim_hidden = [500]
+
+# Destination prediction part
+dim_hidden_dest = [100]
+dim_output_dest = len(dest_tgtcls)
+
+# Time prediction part
+dim_hidden_time = [100]
+dim_output_time = len(time_tgtcls)
+
+# Cost ratio between distance cost and time cost
+time_cost_factor = 4
+
+embed_weights_init = IsotropicGaussian(0.001)
+mlp_weights_init = IsotropicGaussian(0.01)
+mlp_biases_init = Constant(0.001)
+
+batch_size = 200
+
+dropout = 0.5
+dropout_inputs = VariableFilter(bricks=[Rectifier], name='output')
+
+noise = 0.01
+noise_inputs = VariableFilter(roles=[roles.PARAMETER])
+
+valid_set = 'cuts/test_times_0'
diff --git a/config/joint_simple_mlp_tgtcls_1_cswdtx.py b/config/joint_simple_mlp_tgtcls_1_cswdtx.py
index 74b3c75..c4bc2fb 100644
--- a/config/joint_simple_mlp_tgtcls_1_cswdtx.py
+++ b/config/joint_simple_mlp_tgtcls_1_cswdtx.py
@@ -1,10 +1,10 @@
 import cPickle
 
-import model.joint_simple_mlp_tgtcls as model
-
 from blocks.initialization import IsotropicGaussian, Constant
 
 import data
+from model.joint_simple_mlp_tgtcls import Model, Stream
+
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
 n_end_pts = 5
diff --git a/config/time_simple_mlp_1.py b/config/time_simple_mlp_1.py
index bf3699d..c9203c8 100644
--- a/config/time_simple_mlp_1.py
+++ b/config/time_simple_mlp_1.py
@@ -1,8 +1,8 @@
-import model.time_simple_mlp as model
-
 from blocks.initialization import IsotropicGaussian, Constant
 
 import data
+from model.time_simple_mlp import Model, Stream
+
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
 n_end_pts = 5
diff --git a/config/time_simple_mlp_2_cswdtx.py b/config/time_simple_mlp_2_cswdtx.py
index 98467e3..dac585f 100644
--- a/config/time_simple_mlp_2_cswdtx.py
+++ b/config/time_simple_mlp_2_cswdtx.py
@@ -1,8 +1,8 @@
-import model.time_simple_mlp as model
-
 from blocks.initialization import IsotropicGaussian, Constant
 
 import data
+from model.time_simple_mlp import Model, Stream
+
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
 n_end_pts = 5
diff --git a/config/time_simple_mlp_tgtcls_2_cswdtx.py b/config/time_simple_mlp_tgtcls_2_cswdtx.py
index eb69714..eb06334 100644
--- a/config/time_simple_mlp_tgtcls_2_cswdtx.py
+++ b/config/time_simple_mlp_tgtcls_2_cswdtx.py
@@ -1,8 +1,8 @@
-import model.time_simple_mlp_tgtcls as model
-
 from blocks.initialization import IsotropicGaussian, Constant
 
 import data
+from model.time_simple_mlp_tgtcls import Model, Stream
+
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
 n_end_pts = 5