4 files changed, 171 insertions, 0 deletions
diff --git a/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger.py b/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger.py
new file mode 100644
index 0000000..8adb6e7
--- /dev/null
+++ b/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger.py
@@ -0,0 +1,56 @@
+import cPickle
+
+import model.joint_simple_mlp_tgtcls as model
+
+from blocks.initialization import IsotropicGaussian, Constant
+
+import data
+
+n_begin_end_pts = 10     # how many points we consider at the beginning and end of the known trajectory
+n_end_pts = 10
+
+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(21):
+    time_tgtcls.append(time_tgtcls[-1] + time_tgtcls[-2])
+
+dim_embeddings = [
+    ('origin_call', data.origin_call_size+1, 15),
+    ('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 = [1000]
+
+# Destination prediction part
+dim_hidden_dest = [400]
+dim_output_dest = dest_tgtcls.shape[0]
+
+# Time prediction part
+dim_hidden_time = [400]
+dim_output_time = len(time_tgtcls)
+
+# Cost ratio between distance cost and time cost
+time_cost_factor = 4
+
+embed_weights_init = IsotropicGaussian(0.01)
+mlp_weights_init = IsotropicGaussian(0.1)
+mlp_biases_init = Constant(0.01)
+
+learning_rate = 0.000001
+momentum = 0.99
+batch_size = 200
+
+valid_set = 'cuts/test_times_0'
+
diff --git a/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger_dropout.py b/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger_dropout.py
new file mode 100644
index 0000000..02c8bd8
--- /dev/null
+++ b/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger_dropout.py
@@ -0,0 +1,59 @@
+import cPickle
+
+import model.joint_simple_mlp_tgtcls as model
+
+from blocks.initialization import IsotropicGaussian, Constant
+
+import data
+
+n_begin_end_pts = 10     # how many points we consider at the beginning and end of the known trajectory
+n_end_pts = 10
+
+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(21):
+    time_tgtcls.append(time_tgtcls[-1] + time_tgtcls[-2])
+
+dim_embeddings = [
+    ('origin_call', data.origin_call_size+1, 15),
+    ('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 = [5000]
+
+# Destination prediction part
+dim_hidden_dest = [1000]
+dim_output_dest = dest_tgtcls.shape[0]
+
+# Time prediction part
+dim_hidden_time = [500]
+dim_output_time = len(time_tgtcls)
+
+# Cost ratio between distance cost and time cost
+time_cost_factor = 4
+
+embed_weights_init = IsotropicGaussian(0.01)
+mlp_weights_init = IsotropicGaussian(0.1)
+mlp_biases_init = Constant(0.01)
+
+# apply_dropout = True
+# dropout_p = 0.5
+
+learning_rate = 0.001
+momentum = 0.9
+batch_size = 200
+
+valid_set = 'cuts/test_times_0'
+
diff --git a/config/joint_simple_mlp_tgtcls_1_cswdtx_bigger.py b/config/joint_simple_mlp_tgtcls_1_cswdtx_bigger.py
new file mode 100644
index 0000000..995f858
--- /dev/null
+++ b/config/joint_simple_mlp_tgtcls_1_cswdtx_bigger.py
@@ -0,0 +1,55 @@
+import cPickle
+
+import model.joint_simple_mlp_tgtcls as model
+
+from blocks.initialization import IsotropicGaussian, Constant
+
+import data
+
+n_begin_end_pts = 7     # how many points we consider at the beginning and end of the known trajectory
+n_end_pts = 7
+
+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(21):
+    time_tgtcls.append(time_tgtcls[-1] + time_tgtcls[-2])
+
+dim_embeddings = [
+    ('origin_call', data.origin_call_size+1, 15),
+    ('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 = [5000]
+
+# Destination prediction part
+dim_hidden_dest = []
+dim_output_dest = dest_tgtcls.shape[0]
+
+# Time prediction part
+dim_hidden_time = []
+dim_output_time = len(time_tgtcls)
+
+# Cost ratio between distance cost and time cost
+time_cost_factor = 4
+
+embed_weights_init = IsotropicGaussian(0.01)
+mlp_weights_init = IsotropicGaussian(0.1)
+mlp_biases_init = Constant(0.01)
+
+learning_rate = 0.0001
+momentum = 0.99
+batch_size = 200
+
+valid_set = 'cuts/test_times_0'
diff --git a/train.py b/train.py
index 97d8bb3..17fa612 100755
--- a/train.py
+++ b/train.py
@@ -68,6 +68,7 @@ if __name__ == "__main__":
         step_rule=CompositeRule([
                 RemoveNotFinite(),
                 AdaDelta(),
+                #Momentum(learning_rate=config.learning_rate, momentum=config.momentum),
             ]),
         params=params)