commit f4d3ee6449217535bdbe19ac9c5fdd825d71b0d3
parent 54613c1f9cf510ca7a71d6619418f2247515aec6
Author: AdeB <adbrebs@gmail.com>
Date: Tue, 5 May 2015 22:15:22 -0400
New hyperparameters. Training error is monitored.
Diffstat:
3 files changed, 108 insertions(+), 2 deletions(-)
diff --git a/config/dest_simple_mlp_tgtcls_1_cswdtx_alexandre.py b/config/dest_simple_mlp_tgtcls_1_cswdtx_alexandre.py
@@ -0,0 +1,30 @@
+import cPickle
+
+import data
+
+import model.dest_simple_mlp_tgtcls_alexandre 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 = 0.01
+momentum = 0.9
+batch_size = 200
diff --git a/model/dest_simple_mlp_tgtcls_alexandre.py b/model/dest_simple_mlp_tgtcls_alexandre.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(0.01)
+ mlp.weights_init = IsotropicGaussian(0.1)
+ mlp.biases_init = Constant(0.01)
+
+ 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/train.py b/train.py
@@ -27,7 +27,7 @@ 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
+from blocks.extensions.monitoring import DataStreamMonitoring, TrainingDataMonitoring
import data
import transformers
@@ -107,7 +107,8 @@ def main():
step_rule=Momentum(learning_rate=config.learning_rate, momentum=config.momentum),
params=params)
- extensions=[DataStreamMonitoring(model.monitor, valid_stream,
+ 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),
