1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
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'
|
