taxi

commit aa605460eb5891b64b4e795cbeff9cab474dee0d
parent d38cee1ceaed486c1ba3bed9271008dc82fde331
Author: Alex Auvolat <alex.auvolat@ens.fr>
Date:   Fri,  8 May 2015 17:35:28 -0400

Add model with hidden layers specific to time/dest prediction.

Diffstat:
A
config/joint_simple_mlp_tgtcls_111_cswdtx.py
 | 
55
+++++++++++++++++++++++++++++++++++++++++++++++++++++++

1 file changed, 55 insertions(+), 0 deletions(-)
diff --git a/config/joint_simple_mlp_tgtcls_111_cswdtx.py b/config/joint_simple_mlp_tgtcls_111_cswdtx.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 = 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)
+
+learning_rate = 0.0001
+momentum = 0.99
+batch_size = 200
+
+valid_set = 'cuts/test_times_0'