commit 54613c1f9cf510ca7a71d6619418f2247515aec6
parent 712035b88be1816d3fbd58ce69ae6464767c780e
Author: Alex Auvolat <alex.auvolat@ens.fr>
Date: Tue, 5 May 2015 14:15:21 -0400
Add models for time predictioAdd models for time prediction
Diffstat:
26 files changed, 491 insertions(+), 371 deletions(-)
diff --git a/config/dest_simple_mlp_2_cs.py b/config/dest_simple_mlp_2_cs.py
@@ -0,0 +1,21 @@
+import model.dest_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)
+]
+
+dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
+dim_hidden = [200, 100]
+dim_output = 2
+
+learning_rate = 0.0001
+momentum = 0.99
+batch_size = 32
diff --git a/config/dest_simple_mlp_2_cswdt.py b/config/dest_simple_mlp_2_cswdt.py
@@ -0,0 +1,25 @@
+import model.dest_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),
+]
+
+dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
+dim_hidden = [200, 100]
+dim_output = 2
+
+learning_rate = 0.0001
+momentum = 0.99
+batch_size = 32
diff --git a/config/dest_simple_mlp_2_noembed.py b/config/dest_simple_mlp_2_noembed.py
@@ -0,0 +1,18 @@
+import model.dest_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 = [] # do not use embeddings
+
+dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
+dim_hidden = [200, 100]
+dim_output = 2
+
+learning_rate = 0.0001
+momentum = 0.99
+batch_size = 32
diff --git a/config/dest_simple_mlp_tgtcls_0_cs.py b/config/dest_simple_mlp_tgtcls_0_cs.py
@@ -0,0 +1,25 @@
+import cPickle
+
+import data
+
+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
+
+n_valid = 1000
+
+with open(data.DATA_PATH + "/arrival-clusters.pkl") as f: tgtcls = cPickle.load(f)
+
+dim_embeddings = [
+ ('origin_call', data.n_train_clients+1, 10),
+ ('origin_stand', data.n_stands+1, 10)
+]
+
+dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
+dim_hidden = []
+dim_output = tgtcls.shape[0]
+
+learning_rate = 0.0001
+momentum = 0.99
+batch_size = 32
diff --git a/config/dest_simple_mlp_tgtcls_1_cs.py b/config/dest_simple_mlp_tgtcls_1_cs.py
@@ -0,0 +1,25 @@
+import cPickle
+
+import data
+
+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
+
+n_valid = 1000
+
+with open(data.DATA_PATH + "/arrival-clusters.pkl") as f: tgtcls = cPickle.load(f)
+
+dim_embeddings = [
+ ('origin_call', data.n_train_clients+1, 10),
+ ('origin_stand', data.n_stands+1, 10)
+]
+
+dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
+dim_hidden = [500]
+dim_output = tgtcls.shape[0]
+
+learning_rate = 0.0001
+momentum = 0.99
+batch_size = 32
diff --git a/config/dest_simple_mlp_tgtcls_1_cswdt.py b/config/dest_simple_mlp_tgtcls_1_cswdt.py
@@ -0,0 +1,29 @@
+import cPickle
+
+import data
+
+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
+
+n_valid = 1000
+
+with open(data.DATA_PATH + "/arrival-clusters.pkl") as f: tgtcls = cPickle.load(f)
+
+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),
+]
+
+dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
+dim_hidden = [500]
+dim_output = tgtcls.shape[0]
+
+learning_rate = 0.0001
+momentum = 0.99
+batch_size = 32
diff --git a/config/dest_simple_mlp_tgtcls_1_cswdtx.py b/config/dest_simple_mlp_tgtcls_1_cswdtx.py
@@ -0,0 +1,30 @@
+import cPickle
+
+import data
+
+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
+
+n_valid = 1000
+
+with open(data.DATA_PATH + "/arrival-clusters.pkl") as f: tgtcls = cPickle.load(f)
+
+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]
+dim_output = tgtcls.shape[0]
+
+learning_rate = 0.0001
+momentum = 0.99
+batch_size = 32
diff --git a/config/simple_mlp_2_cs.py b/config/simple_mlp_2_cs.py
@@ -1,21 +0,0 @@
-import model.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)
-]
-
-dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
-dim_hidden = [200, 100]
-dim_output = 2
-
-learning_rate = 0.0001
-momentum = 0.99
-batch_size = 32
diff --git a/config/simple_mlp_2_cswdt.py b/config/simple_mlp_2_cswdt.py
@@ -1,25 +0,0 @@
-import model.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),
-]
-
-dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
-dim_hidden = [200, 100]
-dim_output = 2
-
-learning_rate = 0.0001
-momentum = 0.99
-batch_size = 32
diff --git a/config/simple_mlp_2_noembed.py b/config/simple_mlp_2_noembed.py
@@ -1,18 +0,0 @@
-import model.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 = [] # do not use embeddings
-
-dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
-dim_hidden = [200, 100]
-dim_output = 2
-
-learning_rate = 0.0001
-momentum = 0.99
-batch_size = 32
diff --git a/config/simple_mlp_tgtcls_0_cs.py b/config/simple_mlp_tgtcls_0_cs.py
@@ -1,25 +0,0 @@
-import cPickle
-
-import data
-
-import model.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
-
-n_valid = 1000
-
-with open(data.DATA_PATH + "/arrival-clusters.pkl") as f: tgtcls = cPickle.load(f)
-
-dim_embeddings = [
- ('origin_call', data.n_train_clients+1, 10),
- ('origin_stand', data.n_stands+1, 10)
-]
-
-dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
-dim_hidden = []
-dim_output = tgtcls.shape[0]
-
-learning_rate = 0.0001
-momentum = 0.99
-batch_size = 32
diff --git a/config/simple_mlp_tgtcls_1_cs.py b/config/simple_mlp_tgtcls_1_cs.py
@@ -1,25 +0,0 @@
-import cPickle
-
-import data
-
-import model.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
-
-n_valid = 1000
-
-with open(data.DATA_PATH + "/arrival-clusters.pkl") as f: tgtcls = cPickle.load(f)
-
-dim_embeddings = [
- ('origin_call', data.n_train_clients+1, 10),
- ('origin_stand', data.n_stands+1, 10)
-]
-
-dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
-dim_hidden = [500]
-dim_output = tgtcls.shape[0]
-
-learning_rate = 0.0001
-momentum = 0.99
-batch_size = 32
diff --git a/config/simple_mlp_tgtcls_1_cswdt.py b/config/simple_mlp_tgtcls_1_cswdt.py
@@ -1,29 +0,0 @@
-import cPickle
-
-import data
-
-import model.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
-
-n_valid = 1000
-
-with open(data.DATA_PATH + "/arrival-clusters.pkl") as f: tgtcls = cPickle.load(f)
-
-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),
-]
-
-dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
-dim_hidden = [500]
-dim_output = tgtcls.shape[0]
-
-learning_rate = 0.0001
-momentum = 0.99
-batch_size = 32
diff --git a/config/simple_mlp_tgtcls_1_cswdtx.py b/config/simple_mlp_tgtcls_1_cswdtx.py
@@ -1,30 +0,0 @@
-import cPickle
-
-import data
-
-import model.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
-
-n_valid = 1000
-
-with open(data.DATA_PATH + "/arrival-clusters.pkl") as f: tgtcls = cPickle.load(f)
-
-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]
-dim_output = tgtcls.shape[0]
-
-learning_rate = 0.0001
-momentum = 0.99
-batch_size = 32
diff --git a/config/time_simple_mlp_1.py 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
@@ -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
@@ -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/error.py b/error.py
@@ -0,0 +1,40 @@
+from theano import tensor
+import theano
+import numpy
+
+def const(v):
+ if theano.config.floatX == 'float32':
+ return numpy.float32(v)
+ else:
+ return numpy.float64(v)
+
+rearth = const(6371)
+deg2rad = const(3.141592653589793 / 180)
+
+def hdist(a, b):
+ lat1 = a[:, 0] * deg2rad
+ lon1 = a[:, 1] * deg2rad
+ lat2 = b[:, 0] * deg2rad
+ lon2 = b[:, 1] * deg2rad
+
+ dlat = abs(lat1-lat2)
+ dlon = abs(lon1-lon2)
+
+ al = tensor.sin(dlat/2)**2 + tensor.cos(lat1) * tensor.cos(lat2) * (tensor.sin(dlon/2)**2)
+ d = tensor.arctan2(tensor.sqrt(al), tensor.sqrt(const(1)-al))
+
+ hd = const(2) * rearth * d
+
+ return tensor.switch(tensor.eq(hd, float('nan')), (a-b).norm(2, axis=1), hd)
+
+def erdist(a, b):
+ lat1 = a[:, 0] * deg2rad
+ lon1 = a[:, 1] * deg2rad
+ lat2 = b[:, 0] * deg2rad
+ lon2 = b[:, 1] * deg2rad
+ 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/hdist.py b/hdist.py
@@ -1,37 +0,0 @@
-from theano import tensor
-import theano
-import numpy
-
-def const(v):
- if theano.config.floatX == 'float32':
- return numpy.float32(v)
- else:
- return numpy.float64(v)
-
-rearth = const(6371)
-deg2rad = const(3.141592653589793 / 180)
-
-def hdist(a, b):
- lat1 = a[:, 0] * deg2rad
- lon1 = a[:, 1] * deg2rad
- lat2 = b[:, 0] * deg2rad
- lon2 = b[:, 1] * deg2rad
-
- dlat = abs(lat1-lat2)
- dlon = abs(lon1-lon2)
-
- al = tensor.sin(dlat/2)**2 + tensor.cos(lat1) * tensor.cos(lat2) * (tensor.sin(dlon/2)**2)
- d = tensor.arctan2(tensor.sqrt(al), tensor.sqrt(const(1)-al))
-
- hd = const(2) * rearth * d
-
- return tensor.switch(tensor.eq(hd, float('nan')), (a-b).norm(2, axis=1), hd)
-
-def erdist(a, b):
- lat1 = a[:, 0] * deg2rad
- lon1 = a[:, 1] * deg2rad
- lat2 = b[:, 0] * deg2rad
- lon2 = b[:, 1] * deg2rad
- x = (lon2-lon1) * tensor.cos((lat1+lat2)/2)
- y = (lat2-lat1)
- return tensor.sqrt(tensor.sqr(x) + tensor.sqr(y)) * rearth
diff --git a/model/dest_simple_mlp.py b/model/dest_simple_mlp.py
@@ -0,0 +1,73 @@
+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.concatenate((tensor.vector('destination_latitude')[:, None],
+ tensor.vector('destination_longitude')[:, None]), axis=1)
+
+ # 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 = mlp.apply(inputs)
+
+ # Normalize & Center
+ # outputs = theano.printing.Print("normal_outputs")(outputs)
+ outputs = data.data_std * outputs + data.porto_center
+
+ # outputs = theano.printing.Print("outputs")(outputs)
+ # y = theano.printing.Print("y")(y)
+
+ outputs.name = 'outputs'
+
+ # Calculate the cost
+ cost = error.erdist(outputs, y).mean()
+ cost.name = 'cost'
+ hcost = error.hdist(outputs, y).mean()
+ hcost.name = 'hcost'
+
+ # 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, hcost]
+ self.outputs = outputs
+ self.pred_vars = ['destination_latitude', 'destination_longitude']
+
diff --git a/model/dest_simple_mlp_tgtcls.py b/model/dest_simple_mlp_tgtcls.py
@@ -0,0 +1,75 @@
+import numpy
+
+import theano
+from theano import tensor
+
+from blocks.bricks import MLP, Rectifier, Linear, Sigmoid, Identity, Softmax
+from blocks.bricks.lookup import LookupTable
+
+from blocks.initialization import IsotropicGaussian, Constant
+
+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.concatenate((tensor.vector('destination_latitude')[:, None],
+ tensor.vector('destination_longitude')[:, None]), axis=1)
+
+ # Define the model
+ mlp = MLP(activations=[Rectifier() for _ in config.dim_hidden] + [Softmax()],
+ dims=[config.dim_input] + config.dim_hidden + [config.dim_output])
+ classes = theano.shared(numpy.array(config.tgtcls, dtype=theano.config.floatX), name='classes')
+
+ # Create the Theano variables
+ inputs = tensor.concatenate(input_list, axis=1)
+
+ # inputs = theano.printing.Print("inputs")(inputs)
+ cls_probas = mlp.apply(inputs)
+ outputs = tensor.dot(cls_probas, classes)
+
+ # outputs = theano.printing.Print("outputs")(outputs)
+ # y = theano.printing.Print("y")(y)
+
+ outputs.name = 'outputs'
+
+ # Calculate the cost
+ cost = error.erdist(outputs, y).mean()
+ cost.name = 'cost'
+ hcost = error.hdist(outputs, y).mean()
+ hcost.name = 'hcost'
+
+ # 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, hcost]
+ self.outputs = outputs
+ self.pred_vars = ['destination_latitude', 'destination_longitude']
+
diff --git a/model/simple_mlp.py b/model/simple_mlp.py
@@ -1,71 +0,0 @@
-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 hdist
-
-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.concatenate((tensor.vector('destination_latitude')[:, None],
- tensor.vector('destination_longitude')[:, None]), axis=1)
-
- # 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 = mlp.apply(inputs)
-
- # Normalize & Center
- # outputs = theano.printing.Print("normal_outputs")(outputs)
- outputs = data.data_std * outputs + data.porto_center
-
- # outputs = theano.printing.Print("outputs")(outputs)
- # y = theano.printing.Print("y")(y)
-
- outputs.name = 'outputs'
-
- # Calculate the cost
- cost = hdist.erdist(outputs, y).mean()
- cost.name = 'cost'
- hcost = hdist.hdist(outputs, y).mean()
- hcost.name = 'hcost'
-
- # 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.hcost = hcost
- self.outputs = outputs
diff --git a/model/simple_mlp_tgtcls.py b/model/simple_mlp_tgtcls.py
@@ -1,73 +0,0 @@
-import numpy
-
-import theano
-from theano import tensor
-
-from blocks.bricks import MLP, Rectifier, Linear, Sigmoid, Identity, Softmax
-from blocks.bricks.lookup import LookupTable
-
-from blocks.initialization import IsotropicGaussian, Constant
-
-import data
-import hdist
-
-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.concatenate((tensor.vector('destination_latitude')[:, None],
- tensor.vector('destination_longitude')[:, None]), axis=1)
-
- # Define the model
- mlp = MLP(activations=[Rectifier() for _ in config.dim_hidden] + [Softmax()],
- dims=[config.dim_input] + config.dim_hidden + [config.dim_output])
- classes = theano.shared(numpy.array(config.tgtcls, dtype=theano.config.floatX), name='classes')
-
- # Create the Theano variables
- inputs = tensor.concatenate(input_list, axis=1)
-
- # inputs = theano.printing.Print("inputs")(inputs)
- cls_probas = mlp.apply(inputs)
- outputs = tensor.dot(cls_probas, classes)
-
- # outputs = theano.printing.Print("outputs")(outputs)
- # y = theano.printing.Print("y")(y)
-
- outputs.name = 'outputs'
-
- # Calculate the cost
- cost = hdist.erdist(outputs, y).mean()
- cost.name = 'cost'
- hcost = hdist.hdist(outputs, y).mean()
- hcost.name = 'hcost'
-
- # 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.hcost = hcost
- self.outputs = outputs
diff --git a/model/time_simple_mlp.py 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
@@ -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
@@ -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):
