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
150
151
|
import logging
import os
import sys
import importlib
from argparse import ArgumentParser
import csv
import numpy
import theano
from theano import printing
from theano import tensor
from theano.ifelse import ifelse
from blocks.filter import VariableFilter
from blocks.model import Model
from fuel.datasets.hdf5 import H5PYDataset
from fuel.transformers import Batch
from fuel.streams import DataStream
from fuel.schemes import ConstantScheme, SequentialExampleScheme, ShuffledExampleScheme
from blocks.algorithms import GradientDescent, Scale, 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
import data
import transformers
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(model_name)
def setup_train_stream(req_vars):
# Load the training and test data
train = H5PYDataset(data.H5DATA_PATH,
which_set='train',
subset=slice(0, data.dataset_size),
load_in_memory=True)
train = DataStream(train, iteration_scheme=ShuffledExampleScheme(data.dataset_size))
train = transformers.TaxiExcludeTrips(data.valid_trips, train)
train = transformers.TaxiGenerateSplits(train, max_splits=100)
train = transformers.TaxiAddDateTime(train)
train = transformers.TaxiAddFirstK(config.n_begin_end_pts, train)
train = transformers.TaxiAddLastK(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 = DataStream(data.valid_data)
valid = transformers.TaxiAddDateTime(valid)
valid = transformers.TaxiAddFirstK(config.n_begin_end_pts, valid)
valid = transformers.TaxiAddLastK(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 = DataStream(data.test_data)
test = transformers.TaxiAddDateTime(test)
test = transformers.TaxiAddFirstK(config.n_begin_end_pts, test)
test = transformers.TaxiAddLastK(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' ]
train_stream = setup_train_stream(req_vars)
valid_stream = setup_valid_stream(req_vars)
# Training
cg = ComputationGraph(cost)
params = cg.parameters # VariableFilter(bricks=[Linear])(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)
extensions=[DataStreamMonitoring(model.monitor, valid_stream,
prefix='valid',
every_n_batches=1000),
Printing(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)
outfile = open("output/test-output-%s.csv" % model_name, "w")
outcsv = csv.writer(outfile)
if model.pred_vars == ['time']:
outcsv.writerow(["TRIP_ID", "TRAVEL_TIME"])
for out in apply_model.Apply(outputs=outputs, stream=test_stream, return_vars=['trip_id', 'outputs']):
time = out['outputs']
for i, trip in enumerate(out['trip_id']):
outcsv.writerow([trip, int(time[i, 0])])
else:
outcsv.writerow(["TRIP_ID", "LATITUDE", "LONGITUDE"])
for out in apply_model.Apply(outputs=outputs, stream=test_stream, return_vars=['trip_id', 'outputs']):
dest = out['outputs']
for i, trip in enumerate(out['trip_id']):
outcsv.writerow([trip, repr(dest[i, 0]), repr(dest[i, 1])])
outfile.close()
if __name__ == "__main__":
logging.basicConfig(level=logging.INFO)
main()
|
