Add models for time predictioAdd models for time prediction

16 files changed, 152 insertions, 32 deletions

diff --git a/config/simple_mlp_2_cs.py b/config/dest_simple_mlp_2_cs.py
index fa2f4c1..2cec78d 100644
--- a/config/simple_mlp_2_cs.py
+++ b/config/dest_simple_mlp_2_cs.py
@@ -1,4 +1,4 @@
-import model.simple_mlp as model
+import model.dest_simple_mlp as model
 
 import data
 
diff --git a/config/simple_mlp_2_cswdt.py b/config/dest_simple_mlp_2_cswdt.py
index 05c9450..f6ddf34 100644
--- a/config/simple_mlp_2_cswdt.py
+++ b/config/dest_simple_mlp_2_cswdt.py
@@ -1,4 +1,4 @@
-import model.simple_mlp as model
+import model.dest_simple_mlp as model
 
 import data
 
diff --git a/config/simple_mlp_2_noembed.py b/config/dest_simple_mlp_2_noembed.py
index 2f45f63..3832146 100644
--- a/config/simple_mlp_2_noembed.py
+++ b/config/dest_simple_mlp_2_noembed.py
@@ -1,4 +1,4 @@
-import model.simple_mlp as model
+import model.dest_simple_mlp as model
 
 import data
 
diff --git a/config/simple_mlp_tgtcls_0_cs.py b/config/dest_simple_mlp_tgtcls_0_cs.py
index 96faca0..a8a5a0e 100644
--- a/config/simple_mlp_tgtcls_0_cs.py
+++ b/config/dest_simple_mlp_tgtcls_0_cs.py
@@ -2,7 +2,7 @@ import cPickle
 
 import data
 
-import model.simple_mlp_tgtcls as model
+import model.dest_simple_mlp_tgtcls as model
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
 n_end_pts = 5
diff --git a/config/simple_mlp_tgtcls_1_cs.py b/config/dest_simple_mlp_tgtcls_1_cs.py
index 293a0ab..8136f10 100644
--- a/config/simple_mlp_tgtcls_1_cs.py
+++ b/config/dest_simple_mlp_tgtcls_1_cs.py
@@ -2,7 +2,7 @@ import cPickle
 
 import data
 
-import model.simple_mlp_tgtcls as model
+import model.dest_simple_mlp_tgtcls as model
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
 n_end_pts = 5
diff --git a/config/simple_mlp_tgtcls_1_cswdt.py b/config/dest_simple_mlp_tgtcls_1_cswdt.py
index 45bd39e..af7b2a3 100644
--- a/config/simple_mlp_tgtcls_1_cswdt.py
+++ b/config/dest_simple_mlp_tgtcls_1_cswdt.py
@@ -2,7 +2,7 @@ import cPickle
 
 import data
 
-import model.simple_mlp_tgtcls as model
+import model.dest_simple_mlp_tgtcls as model
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
 n_end_pts = 5
diff --git a/config/simple_mlp_tgtcls_1_cswdtx.py b/config/dest_simple_mlp_tgtcls_1_cswdtx.py
index d51ddde..b9832df 100644
--- a/config/simple_mlp_tgtcls_1_cswdtx.py
+++ b/config/dest_simple_mlp_tgtcls_1_cswdtx.py
@@ -2,7 +2,7 @@ import cPickle
 
 import data
 
-import model.simple_mlp_tgtcls as model
+import model.dest_simple_mlp_tgtcls as model
 
 n_begin_end_pts = 5     # how many points we consider at the beginning and end of the known trajectory
 n_end_pts = 5
diff --git a/config/time_simple_mlp_1.py b/config/time_simple_mlp_1.py
new file mode 100644
index 0000000..eea4159
--- /dev/null
+++ b/config/time_simple_mlp_1.py
@@ -0,0 +1,19 @@
+import model.time_simple_mlp as model
+
+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
+
+dim_embeddings = [
+]
+
+dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
+dim_hidden = [200]
+dim_output = 1
+
+learning_rate = 0.00001
+momentum = 0.99
+batch_size = 32
diff --git a/config/time_simple_mlp_2_cswdtx.py b/config/time_simple_mlp_2_cswdtx.py
new file mode 100644
index 0000000..ceb66e8
--- /dev/null
+++ b/config/time_simple_mlp_2_cswdtx.py
@@ -0,0 +1,26 @@
+import model.time_simple_mlp as model
+
+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
+
+dim_embeddings = [
+    ('origin_call', data.n_train_clients+1, 10),
+    ('origin_stand', data.n_stands+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),
+]
+
+dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
+dim_hidden = [500, 100]
+dim_output = 1
+
+learning_rate = 0.00001
+momentum = 0.99
+batch_size = 32
diff --git a/data.py b/data.py
index 39603fc..42ebe1c 100644
--- a/data.py
+++ b/data.py
@@ -179,15 +179,13 @@ taxi_columns_valid = taxi_columns + [
     ("time", lambda l: int(l[11])),
 ]
 
-train_files=["%s/split/train-%02d.csv" % (DATA_PATH, i) for i in range(100)]
-valid_files=["%s/split/valid2-cut.csv" % (DATA_PATH,)]
+valid_files=["%s/valid2-cut.csv" % (DATA_PATH,)]
 test_file="%s/test.csv" % (DATA_PATH,)
 
-train_data=TaxiData(train_files, taxi_columns)
 valid_data = TaxiData(valid_files, taxi_columns_valid)
 test_data = TaxiData(test_file, taxi_columns, has_header=True)
 
-valid_trips = [l for l in open(DATA_PATH + "/split/valid2-cut-ids.txt")]
+valid_trips = [l for l in open(DATA_PATH + "/valid2-cut-ids.txt")]
 
 def train_it():
     return DataIterator(DataStream(train_data))
diff --git a/hdist.py b/error.py
index 866aea4..5ea37ad 100644
--- a/hdist.py
+++ b/error.py
@@ -35,3 +35,6 @@ def erdist(a, b):
     x = (lon2-lon1) * tensor.cos((lat1+lat2)/2)
     y = (lat2-lat1)
     return tensor.sqrt(tensor.sqr(x) + tensor.sqr(y)) * rearth
+
+def rmsle(a, b):
+    return tensor.sqrt( ( (tensor.log(a+1)-tensor.log(b+1)) ** 2 ).mean() )
diff --git a/model/simple_mlp.py b/model/dest_simple_mlp.py
index fc065f7..896f219 100644
--- a/model/simple_mlp.py
+++ b/model/dest_simple_mlp.py
@@ -6,7 +6,7 @@ from blocks.initialization import IsotropicGaussian, Constant
 from theano import tensor
 
 import data
-import hdist
+import error
 
 class Model(object):
     def __init__(self, config):
@@ -51,9 +51,9 @@ class Model(object):
         outputs.name = 'outputs'
 
         # Calculate the cost
-        cost = hdist.erdist(outputs, y).mean()
+        cost = error.erdist(outputs, y).mean()
         cost.name = 'cost'
-        hcost = hdist.hdist(outputs, y).mean()
+        hcost = error.hdist(outputs, y).mean()
         hcost.name = 'hcost'
 
         # Initialization
@@ -67,5 +67,7 @@ class Model(object):
         mlp.initialize()
 
         self.cost = cost
-        self.hcost = hcost
+        self.monitor = [cost, hcost]
         self.outputs = outputs
+        self.pred_vars = ['destination_latitude', 'destination_longitude']
+
diff --git a/model/simple_mlp_tgtcls.py b/model/dest_simple_mlp_tgtcls.py
index b2a1a6e..d8fdeb3 100644
--- a/model/simple_mlp_tgtcls.py
+++ b/model/dest_simple_mlp_tgtcls.py
@@ -9,7 +9,7 @@ from blocks.bricks.lookup import LookupTable
 from blocks.initialization import IsotropicGaussian, Constant
 
 import data
-import hdist
+import error
 
 class Model(object):
     def __init__(self, config):
@@ -53,9 +53,9 @@ class Model(object):
         outputs.name = 'outputs'
 
         # Calculate the cost
-        cost = hdist.erdist(outputs, y).mean()
+        cost = error.erdist(outputs, y).mean()
         cost.name = 'cost'
-        hcost = hdist.hdist(outputs, y).mean()
+        hcost = error.hdist(outputs, y).mean()
         hcost.name = 'hcost'
 
         # Initialization
@@ -69,5 +69,7 @@ class Model(object):
         mlp.initialize()
 
         self.cost = cost
-        self.hcost = hcost
+        self.monitor = [cost, hcost]
         self.outputs = outputs
+        self.pred_vars = ['destination_latitude', 'destination_longitude']
+
diff --git a/model/time_simple_mlp.py b/model/time_simple_mlp.py
new file mode 100644
index 0000000..1568ed3
--- /dev/null
+++ b/model/time_simple_mlp.py
@@ -0,0 +1,65 @@
+from blocks.bricks import MLP, Rectifier, Linear, Sigmoid, Identity
+from blocks.bricks.lookup import LookupTable
+
+from blocks.initialization import IsotropicGaussian, Constant
+
+from theano import tensor
+
+import data
+import error
+
+class Model(object):
+    def __init__(self, config):
+        # The input and the targets
+        x_firstk_latitude = (tensor.matrix('first_k_latitude') - data.porto_center[0]) / data.data_std[0]
+        x_firstk_longitude = (tensor.matrix('first_k_longitude') - data.porto_center[1]) / data.data_std[1]
+
+        x_lastk_latitude = (tensor.matrix('last_k_latitude') - data.porto_center[0]) / data.data_std[0]
+        x_lastk_longitude = (tensor.matrix('last_k_longitude') - data.porto_center[1]) / data.data_std[1]
+
+        input_list = [x_firstk_latitude, x_firstk_longitude, x_lastk_latitude, x_lastk_longitude]
+        embed_tables = []
+
+        self.require_inputs = ['first_k_latitude', 'first_k_longitude', 'last_k_latitude', 'last_k_longitude']
+
+        for (varname, num, dim) in config.dim_embeddings:
+            self.require_inputs.append(varname)
+            vardata = tensor.lvector(varname)
+            tbl = LookupTable(length=num, dim=dim, name='%s_lookup'%varname)
+            embed_tables.append(tbl)
+            input_list.append(tbl.apply(vardata))
+
+        y = tensor.lvector('time')
+
+        # Define the model
+        mlp = MLP(activations=[Rectifier() for _ in config.dim_hidden] + [Identity()],
+                           dims=[config.dim_input] + config.dim_hidden + [config.dim_output])
+
+        # Create the Theano variables
+        inputs = tensor.concatenate(input_list, axis=1)
+        # inputs = theano.printing.Print("inputs")(inputs)
+        outputs = tensor.exp(mlp.apply(inputs) + 2)
+
+        # outputs = theano.printing.Print("outputs")(outputs)
+        # y = theano.printing.Print("y")(y)
+
+        outputs.name = 'outputs'
+
+        # Calculate the cost
+        cost = error.rmsle(outputs.flatten(), y.flatten())
+        cost.name = 'cost'
+
+        # Initialization
+        for tbl in embed_tables:
+            tbl.weights_init = IsotropicGaussian(0.001)
+        mlp.weights_init = IsotropicGaussian(0.01)
+        mlp.biases_init = Constant(0.001)
+
+        for tbl in embed_tables:
+            tbl.initialize()
+        mlp.initialize()
+
+        self.cost = cost
+        self.monitor = [cost]
+        self.outputs = outputs
+        self.pred_vars = ['time']
diff --git a/train.py b/train.py
index 2c9522e..4cbd526 100644
--- a/train.py
+++ b/train.py
@@ -20,7 +20,7 @@ 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
+from fuel.schemes import ConstantScheme, SequentialExampleScheme, ShuffledExampleScheme
 
 from blocks.algorithms import GradientDescent, Scale, AdaDelta, Momentum
 from blocks.graph import ComputationGraph
@@ -31,7 +31,6 @@ from blocks.extensions.monitoring import DataStreamMonitoring
 
 import data
 import transformers
-import hdist
 import apply_model
 
 if __name__ == "__main__":
@@ -48,7 +47,7 @@ def setup_train_stream(req_vars):
                         which_set='train',
                         subset=slice(0, data.dataset_size),
                         load_in_memory=True)
-    train = DataStream(train, iteration_scheme=SequentialExampleScheme(data.dataset_size - config.n_valid))
+    train = DataStream(train, iteration_scheme=ShuffledExampleScheme(data.dataset_size))
 
     train = transformers.TaxiExcludeTrips(data.valid_trips, train)
     train = transformers.TaxiGenerateSplits(train, max_splits=100)
@@ -91,10 +90,9 @@ def main():
     model = config.model.Model(config)
 
     cost = model.cost
-    hcost = model.hcost
     outputs = model.outputs
 
-    req_vars = model.require_inputs + [ 'destination_latitude', 'destination_longitude' ]
+    req_vars = model.require_inputs + model.pred_vars
     req_vars_test = model.require_inputs + [ 'trip_id' ]
 
     train_stream = setup_train_stream(req_vars)
@@ -109,7 +107,7 @@ def main():
         step_rule=Momentum(learning_rate=config.learning_rate, momentum=config.momentum),
         params=params)
 
-    extensions=[DataStreamMonitoring([cost, hcost], valid_stream,
+    extensions=[DataStreamMonitoring(model.monitor, valid_stream,
                                      prefix='valid',
                                      every_n_batches=1000),
                 Printing(every_n_batches=1000),
@@ -132,11 +130,18 @@ def main():
 
     outfile = open("output/test-output-%s.csv" % model_name, "w")
     outcsv = csv.writer(outfile)
-    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])])
+    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()
 
 
diff --git a/transformers.py b/transformers.py
index 6ee0df1..73e3868 100644
--- a/transformers.py
+++ b/transformers.py
@@ -32,7 +32,7 @@ class Select(Transformer):
 class TaxiGenerateSplits(Transformer):
     def __init__(self, data_stream, max_splits=-1):
         super(TaxiGenerateSplits, self).__init__(data_stream)
-        self.sources = data_stream.sources + ('destination_latitude', 'destination_longitude')
+        self.sources = data_stream.sources + ('destination_latitude', 'destination_longitude', 'time')
         self.max_splits = max_splits
         self.data = None
         self.splits = []
@@ -63,7 +63,7 @@ class TaxiGenerateSplits(Transformer):
         dlat = numpy.float32(self.data[self.id_latitude][-1])
         dlon = numpy.float32(self.data[self.id_longitude][-1])
 
-        return tuple(r + [dlat, dlon])
+        return tuple(r + [dlat, dlon, 15 * (len(self.data[self.id_longitude]) - 1)])
 
 class TaxiAddFirstK(Transformer):
     def __init__(self, k, stream):