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
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
|
#!/usr/bin/env python
import sys
import logging
import importlib
import csv
from blocks.model import Model
from fuel.transformers import Batch
from fuel.streams import DataStream
from fuel.schemes import ConstantScheme, ShuffledExampleScheme
from blocks.algorithms import GradientDescent, AdaDelta, Momentum
from blocks.graph import ComputationGraph
from blocks.main_loop import MainLoop
from blocks.extensions import Printing, FinishAfter
from blocks.extensions.saveload import Dump, LoadFromDump, Checkpoint
from blocks.extensions.monitoring import DataStreamMonitoring, TrainingDataMonitoring
from blocks.extensions.plot import Plot
from data import transformers
from data.hdf5 import TaxiDataset, TaxiStream
import apply_model
if __name__ == "__main__":
if len(sys.argv) != 2:
print >> sys.stderr, 'Usage: %s config' % sys.argv[0]
sys.exit(1)
model_name = sys.argv[1]
config = importlib.import_module('.%s' % model_name, 'config')
def compile_valid_trip_ids():
valid = TaxiDataset(config.valid_set, 'valid.hdf5', sources=('trip_id',))
ids = valid.get_data(None, slice(0, valid.num_examples))
return set(ids[0])
def setup_train_stream(req_vars, valid_trips_ids):
train = TaxiDataset('train')
train = DataStream(train, iteration_scheme=ShuffledExampleScheme(train.num_examples))
train = transformers.TaxiExcludeTrips(valid_trips_ids, train)
train = transformers.TaxiGenerateSplits(train, max_splits=100)
train = transformers.TaxiAddDateTime(train)
train = transformers.TaxiAddFirstLastLen(config.n_begin_end_pts, train)
train = transformers.Select(train, tuple(req_vars))
train_stream = Batch(train, iteration_scheme=ConstantScheme(config.batch_size))
return train_stream
def setup_valid_stream(req_vars):
valid = TaxiStream(config.valid_set, 'valid.hdf5')
valid = transformers.TaxiAddDateTime(valid)
valid = transformers.TaxiAddFirstLastLen(config.n_begin_end_pts, valid)
valid = transformers.Select(valid, tuple(req_vars))
valid_stream = Batch(valid, iteration_scheme=ConstantScheme(1000))
return valid_stream
def setup_test_stream(req_vars):
test = TaxiStream('test')
test = transformers.TaxiAddDateTime(test)
test = transformers.TaxiAddFirstLastLen(config.n_begin_end_pts, test)
test = transformers.Select(test, tuple(req_vars))
test_stream = Batch(test, iteration_scheme=ConstantScheme(1000))
return test_stream
def main():
model = config.model.Model(config)
cost = model.cost
outputs = model.outputs
req_vars = model.require_inputs + model.pred_vars
req_vars_test = model.require_inputs + [ 'trip_id' ]
valid_trips_ids = compile_valid_trip_ids()
train_stream = setup_train_stream(req_vars, valid_trips_ids)
valid_stream = setup_valid_stream(req_vars)
# Training
cg = ComputationGraph(cost)
params = cg.parameters
algorithm = GradientDescent(
cost=cost,
# step_rule=AdaDelta(decay_rate=0.5),
step_rule=Momentum(learning_rate=config.learning_rate, momentum=config.momentum),
params=params)
plot_vars = [['valid_' + x.name for x in model.monitor]]
# plot_vars = ['valid_cost']
print "Plot: ", plot_vars
extensions=[TrainingDataMonitoring(model.monitor, prefix='train', every_n_batches=1000),
DataStreamMonitoring(model.monitor, valid_stream,
prefix='valid',
every_n_batches=1000),
Printing(every_n_batches=1000),
Plot(model_name, channels=plot_vars, every_n_batches=1000),
# Checkpoint('model.pkl', every_n_batches=100),
Dump('model_data/' + model_name, every_n_batches=1000),
LoadFromDump('model_data/' + model_name),
# FinishAfter(after_epoch=42),
]
main_loop = MainLoop(
model=Model([cost]),
data_stream=train_stream,
algorithm=algorithm,
extensions=extensions)
main_loop.run()
main_loop.profile.report()
# Produce an output on the test data
test_stream = setup_test_stream(req_vars_test)
if 'destination_longitude' in model.pred_vars:
dest_outfile = open("output/test-dest-output-%s.csv" % model_name, "w")
dest_outcsv = csv.writer(dest_outfile)
dest_outcsv.writerow(["TRIP_ID", "LATITUDE", "LONGITUDE"])
if 'travel_time' in model.pred_vars:
time_outfile = open("output/test-time-output-%s.csv" % model_name, "w")
time_outcsv = csv.writer(time_outfile)
time_outcsv.writerow(["TRIP_ID", "TRAVEL_TIME"])
for out in apply_model.Apply(outputs=outputs, stream=test_stream, return_vars=['trip_id', 'outputs']):
outputs = out['outputs']
for i, trip in enumerate(out['trip_id']):
if model.pred_vars == ['travel_time']:
time_outcsv.writerow([trip, int(outputs[i])])
else:
dest_outcsv.writerow([trip, repr(outputs[i, 0]), repr(outputs[i, 1])])
if 'travel_time' in model.pred_vars:
time_outcsv.writerow([trip, int(outputs[i, 2])])
if __name__ == "__main__":
logging.basicConfig(level=logging.INFO)
main()
|
