diff options
Diffstat (limited to 'model')
| -rw-r--r-- | model/__init__.py | 36 | ||||
| -rw-r--r-- | model/dest_simple_mlp.py | 81 | ||||
| -rw-r--r-- | model/dest_simple_mlp_tgtcls.py | 85 | ||||
| -rw-r--r-- | model/joint_simple_mlp_tgtcls.py | 150 | ||||
| -rw-r--r-- | model/mlp.py | 103 | ||||
| -rw-r--r-- | model/time_simple_mlp.py | 76 | ||||
| -rw-r--r-- | model/time_simple_mlp_tgtcls.py | 78 |
7 files changed, 281 insertions, 328 deletions
diff --git a/model/__init__.py b/model/__init__.py index e69de29..5c051f4 100644 --- a/model/__init__.py +++ b/model/__init__.py @@ -0,0 +1,36 @@ +from blocks.bricks import application, Initializable +from blocks.bricks.lookup import LookupTable + + +class ContextEmbedder(Initializable): + def __init__(self, config, **kwargs): + super(ContextEmbedder, self).__init__(**kwargs) + self.dim_embeddings = config.dim_embeddings + self.embed_weights_init = config.embed_weights_init + + self.inputs = [ name for (name, _, _) in self.dim_embeddings ] + self.outputs = [ '%s_embedded' % name for name in self.inputs ] + + self.lookups = { name: LookupTable(name='%s_lookup' % name) for name in self.inputs } + self.children = self.lookups.values() + + def _push_allocation_config(self): + for (name, num, dim) in self.dim_embeddings: + self.lookups[name].length = num + self.lookups[name].dim = dim + + def _push_initialization_config(self): + for name in self.inputs: + self.lookups[name].weights_init = self.embed_weights_init + + @application + def apply(self, **kwargs): + return tuple(self.lookups[name].apply(kwargs[name]) for name in self.inputs) + + @apply.property('inputs') + def apply_inputs(self): + return self.inputs + + @apply.property('outputs') + def apply_outputs(self): + return self.outputs diff --git a/model/dest_simple_mlp.py b/model/dest_simple_mlp.py index a9e97cb..78d7131 100644 --- a/model/dest_simple_mlp.py +++ b/model/dest_simple_mlp.py @@ -1,71 +1,32 @@ -from blocks.bricks import MLP, Rectifier, Linear, Sigmoid, Identity -from blocks.bricks.lookup import LookupTable - from theano import tensor +from blocks.bricks import application, Identity import data import error +from model.mlp import FFMLP, Stream -class Model(object): - def __init__(self, config): - # The input and the targets - x_firstk_latitude = (tensor.matrix('first_k_latitude') - data.train_gps_mean[0]) / data.train_gps_std[0] - x_firstk_longitude = (tensor.matrix('first_k_longitude') - data.train_gps_mean[1]) / data.train_gps_std[1] - - x_lastk_latitude = (tensor.matrix('last_k_latitude') - data.train_gps_mean[0]) / data.train_gps_std[0] - x_lastk_longitude = (tensor.matrix('last_k_longitude') - data.train_gps_mean[1]) / data.train_gps_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.train_gps_std * outputs + data.train_gps_mean - - # outputs = theano.printing.Print("outputs")(outputs) - # y = theano.printing.Print("y")(y) - outputs.name = 'outputs' +class Model(FFMLP): + def __init__(self, config, **kwargs): + super(Model, self).__init__(config, output_layer=Identity, **kwargs) - # Calculate the cost - cost = error.erdist(outputs, y).mean() - cost.name = 'cost' - hcost = error.hdist(outputs, y).mean() - hcost.name = 'hcost' + @application(outputs=['destination']) + def predict(self, **kwargs): + outputs = super(Model, self).predict(**kwargs) + return data.train_gps_std * outputs + data.train_gps_mean - # Initialization - for tbl in embed_tables: - tbl.weights_init = config.embed_weights_init - mlp.weights_init = config.mlp_weights_init - mlp.biases_init = config.mlp_biases_init + @predict.property('inputs') + def predict_inputs(self): + return self.inputs - for tbl in embed_tables: - tbl.initialize() - mlp.initialize() + @application(outputs=['cost']) + def cost(self, **kwargs): + y_hat = self.predict(**kwargs) + y = tensor.concatenate((kwargs['destination_latitude'][:, None], + kwargs['destination_longitude'][:, None]), axis=1) - self.cost = cost - self.monitor = [cost, hcost] - self.outputs = outputs - self.pred_vars = ['destination_latitude', 'destination_longitude'] + return error.erdist(y_hat, y).mean() + @cost.property('inputs') + def cost_inputs(self): + return self.inputs + ['destination_latitude', 'destination_longitude'] diff --git a/model/dest_simple_mlp_tgtcls.py b/model/dest_simple_mlp_tgtcls.py index 1381d4c..2d65097 100644 --- a/model/dest_simple_mlp_tgtcls.py +++ b/model/dest_simple_mlp_tgtcls.py @@ -1,73 +1,34 @@ -import numpy - +import numpy import theano from theano import tensor +from blocks.bricks import application, Softmax -from blocks.bricks import MLP, Rectifier, Linear, Sigmoid, Identity, Softmax -from blocks.bricks.lookup import LookupTable - -import data import error +from model.mlp import FFMLP, Stream -class Model(object): - def __init__(self, config): - # The input and the targets - x_firstk_latitude = (tensor.matrix('first_k_latitude') - data.train_gps_mean[0]) / data.train_gps_std[0] - x_firstk_longitude = (tensor.matrix('first_k_longitude') - data.train_gps_mean[1]) / data.train_gps_std[1] - - x_lastk_latitude = (tensor.matrix('last_k_latitude') - data.train_gps_mean[0]) / data.train_gps_std[0] - x_lastk_longitude = (tensor.matrix('last_k_longitude') - data.train_gps_mean[1]) / data.train_gps_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' +class Model(FFMLP): + def __init__(self, config, **kwargs): + super(Model, self, output_layer=Softmax).__init__(config, **kwargs) + self.classes = theano.shared(numpy.array(config.tgtcls, dtype=theano.config.floatX), name='classes') - # Calculate the cost - cost = error.erdist(outputs, y).mean() - cost.name = 'cost' - hcost = error.hdist(outputs, y).mean() - hcost.name = 'hcost' + @application(outputs=['destination']) + def predict(self, **kwargs): + cls_probas = super(Model, self).predict(**kwargs) + return tensor.dot(cls_probas, self.classes) - # Initialization - for tbl in embed_tables: - tbl.weights_init = config.embed_weights_init - mlp.weights_init = config.mlp_weights_init - mlp.biases_init = config.mlp_biases_init + @predict.property('inputs') + def predict_inputs(self): + return self.inputs - for tbl in embed_tables: - tbl.initialize() - mlp.initialize() + @application(outputs=['cost']) + def cost(self, **kwargs): + y_hat = self.predict(**kwargs) + y = tensor.concatenate((kwargs['destination_latitude'][:, None], + kwargs['destination_longitude'][:, None]), axis=1) - self.cost = cost - self.monitor = [cost, hcost] - self.outputs = outputs - self.pred_vars = ['destination_latitude', 'destination_longitude'] + return error.erdist(y_hat, y).mean() + @cost.property('inputs') + def cost_inputs(self): + return self.inputs + ['destination_latitude', 'destination_longitude'] diff --git a/model/joint_simple_mlp_tgtcls.py b/model/joint_simple_mlp_tgtcls.py index 0aaf554..d6d4e49 100644 --- a/model/joint_simple_mlp_tgtcls.py +++ b/model/joint_simple_mlp_tgtcls.py @@ -1,111 +1,71 @@ -from blocks.bricks import MLP, Rectifier, Linear, Sigmoid, Identity, Softmax -from blocks.bricks.lookup import LookupTable - -from blocks.filter import VariableFilter -from blocks.graph import ComputationGraph, apply_dropout - import numpy import theano from theano import tensor +from blocks import roles +from blocks.bricks import application, MLP, Rectifier, Softmax -import data import error +from model.mlp import FFMLP, Stream -class Model(object): - def __init__(self, config): - # The input and the targets - x_firstk_latitude = (tensor.matrix('first_k_latitude') - data.train_gps_mean[0]) / data.train_gps_std[0] - x_firstk_longitude = (tensor.matrix('first_k_longitude') - data.train_gps_mean[1]) / data.train_gps_std[1] - x_lastk_latitude = (tensor.matrix('last_k_latitude') - data.train_gps_mean[0]) / data.train_gps_std[0] - x_lastk_longitude = (tensor.matrix('last_k_longitude') - data.train_gps_mean[1]) / data.train_gps_std[1] +class Model(FFMLP): + def __init__(self, config, **kwargs): + super(Model, self).__init__(config, **kwargs) + + self.dest_mlp = MLP(activations=[Rectifier() for _ in config.dim_hidden_dest] + [Softmax()], + dims=[config.dim_hidden[-1]] + config.dim_hidden_dest + [config.dim_output_dest], + name='dest_mlp') + self.time_mlp = MLP(activations=[Rectifier() for _ in config.dim_hidden_time] + [Softmax()], + dims=[config.dim_hidden[-1]] + config.dim_hidden_time + [config.dim_output_time], + name='time_mlp') - x_input_time = tensor.lvector('input_time') + self.dest_classes = theano.shared(numpy.array(config.dest_tgtcls, dtype=theano.config.floatX), name='dest_classes') + self.time_classes = theano.shared(numpy.array(config.time_tgtcls, dtype=theano.config.floatX), name='time_classes') - input_list = [x_firstk_latitude, x_firstk_longitude, x_lastk_latitude, x_lastk_longitude] - embed_tables = [] + self.inputs.append('input_time') + self.children.extend([self.dest_mlp, self.time_mlp]) - self.require_inputs = ['first_k_latitude', 'first_k_longitude', 'last_k_latitude', 'last_k_longitude', 'input_time'] + def _push_initialization_config(self): + super(Model, self)._push_initialization_config() + for mlp in [self.dest_mlp, self.time_mlp]: + mlp.weights_init = self.config.mlp_weights_init + mlp.biases_init = self.config.mlp_biases_init - 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)) + @application(outputs=['destination', 'duration']) + def predict(self, **kwargs): + hidden = super(Model, self).predict(**kwargs) - y_dest = tensor.concatenate((tensor.vector('destination_latitude')[:, None], - tensor.vector('destination_longitude')[:, None]), axis=1) - y_time = tensor.lvector('travel_time') + dest_cls_probas = self.dest_mlp.apply(hidden) + dest_outputs = tensor.dot(dest_cls_probas, self.dest_classes) - # Define the model - common_mlp = MLP(activations=[Rectifier() for _ in config.dim_hidden], - dims=[config.dim_input] + config.dim_hidden) + time_cls_probas = self.time_mlp.apply(hidden) + time_outputs = kwargs['input_time'] + tensor.dot(time_cls_probas, self.time_classes) - dest_mlp = MLP(activations=[Rectifier() for _ in config.dim_hidden_dest] + [Softmax()], - dims=[config.dim_hidden[-1]] + config.dim_hidden_dest + [config.dim_output_dest], - name='dest_mlp') - dest_classes = theano.shared(numpy.array(config.dest_tgtcls, dtype=theano.config.floatX), name='dest_classes') + self.add_auxiliary_variable(dest_cls_probas, name='destination classes ponderations') + self.add_auxiliary_variable(time_cls_probas, name='time classes ponderations') - time_mlp = MLP(activations=[Rectifier() for _ in config.dim_hidden_time] + [Softmax()], - dims=[config.dim_hidden[-1]] + config.dim_hidden_time + [config.dim_output_time], - name='time_mlp') - time_classes = theano.shared(numpy.array(config.time_tgtcls, dtype=theano.config.floatX), name='time_classes') - - # Create the Theano variables - inputs = tensor.concatenate(input_list, axis=1) - # inputs = theano.printing.Print("inputs")(inputs) - hidden = common_mlp.apply(inputs) - - dest_cls_probas = dest_mlp.apply(hidden) - # dest_cls_probas = theano.printing.Print("dest_cls_probas")(dest_cls_probas) - dest_outputs = tensor.dot(dest_cls_probas, dest_classes) - dest_outputs.name = 'dest_outputs' - - time_cls_probas = time_mlp.apply(hidden) - # time_cls_probas = theano.printing.Print("time_cls_probas")(time_cls_probas) - time_outputs = tensor.dot(time_cls_probas, time_classes) + x_input_time - time_outputs.name = 'time_outputs' - - # Calculate the cost - dest_cost = error.erdist(dest_outputs, y_dest).mean() - dest_cost.name = 'dest_cost' - dest_hcost = error.hdist(dest_outputs, y_dest).mean() - dest_hcost.name = 'dest_hcost' - - time_cost = error.rmsle(time_outputs.flatten(), y_time.flatten()) - time_cost.name = 'time_cost' - time_scost = config.time_cost_factor * time_cost - time_scost.name = 'time_scost' - - cost = dest_cost + time_scost - - if hasattr(config, 'dropout_p'): - cg = ComputationGraph(cost) - dropout_inputs = VariableFilter( - bricks=[b for b in list(common_mlp.children) + - list(dest_mlp.children) + - list(time_mlp.children) - if isinstance(b, Rectifier)], - name='output')(cg) - cg = apply_dropout(cg, dropout_inputs, config.dropout_p) - cost = cg.outputs[0] - - cost.name = 'cost' - - # Initialization - for tbl in embed_tables: - tbl.weights_init = config.embed_weights_init - tbl.initialize() - - for mlp in [common_mlp, dest_mlp, time_mlp]: - mlp.weights_init = config.mlp_weights_init - mlp.biases_init = config.mlp_biases_init - mlp.initialize() - - self.cost = cost - self.monitor = [cost, dest_cost, dest_hcost, time_cost, time_scost] - self.outputs = tensor.concatenate([dest_outputs, time_outputs[:, None]], axis=1) - self.outputs.name = 'outputs' - self.pred_vars = ['destination_longitude', 'destination_latitude', 'travel_time'] + return (dest_outputs, time_outputs) + + @predict.property('inputs') + def predict_inputs(self): + return self.inputs + + @application(outputs=['cost']) + def cost(self, **kwargs): + (destination_hat, time_hat) = self.predict(**kwargs) + + destination = tensor.concatenate((kwargs['destination_latitude'][:, None], + kwargs['destination_longitude'][:, None]), axis=1) + time = kwargs['travel_time'] + + destination_cost = error.erdist(destination_hat, destination).mean() + time_cost = error.rmsle(time_hat.flatten(), time.flatten()) + + self.add_auxiliary_variable(destination_cost, [roles.COST], 'destination_cost') + self.add_auxiliary_variable(time_cost, [roles.COST], 'time_cost') + + return destination_cost + self.config.time_cost_factor * time_cost + @cost.property('inputs') + def cost_inputs(self): + return self.inputs + ['destination_latitude', 'destination_longitude', 'travel_time'] diff --git a/model/mlp.py b/model/mlp.py new file mode 100644 index 0000000..9c84ef9 --- /dev/null +++ b/model/mlp.py @@ -0,0 +1,103 @@ +from theano import tensor + +from fuel.transformers import Batch +from fuel.streams import DataStream +from fuel.schemes import ConstantScheme, ShuffledExampleScheme +from blocks.bricks import application, MLP, Rectifier, Initializable + +import data +from data import transformers +from data.hdf5 import TaxiDataset, TaxiStream +from model import ContextEmbedder + + +class FFMLP(Initializable): + def __init__(self, config, output_layer=None, **kwargs): + super(FFMLP, self).__init__(**kwargs) + self.config = config + + self.context_embedder = ContextEmbedder(config) + + output_activation = [] if output_layer is None else [output_layer()] + output_dim = [] if output_layer is None else [config.dim_output] + self.mlp = MLP(activations=[Rectifier() for _ in config.dim_hidden] + output_activation, + dims=[config.dim_input] + config.dim_hidden + output_dim) + + self.extremities = {'%s_k_%s' % (side, ['latitude', 'longitude'][axis]): axis for side in ['first', 'last'] for axis in [0, 1]} + self.inputs = self.context_embedder.inputs + self.extremities.keys() + self.children = [ self.context_embedder, self.mlp ] + + def _push_initialization_config(self): + self.mlp.weights_init = self.config.mlp_weights_init + self.mlp.biases_init = self.config.mlp_biases_init + + @application(outputs=['prediction']) + def predict(self, **kwargs): + embeddings = tuple(self.context_embedder.apply(**{k: kwargs[k] for k in self.context_embedder.inputs })) + extremities = tuple((kwargs[k] - data.train_gps_mean[v]) / data.train_gps_std[v] for k, v in self.extremities.items()) + + inputs = tensor.concatenate(extremities + embeddings, axis=1) + outputs = self.mlp.apply(inputs) + + return outputs + + @predict.property('inputs') + def predict_inputs(self): + return self.inputs + +class Stream(object): + def __init__(self, config): + self.config = config + + def train(self, req_vars): + stream = TaxiDataset('train') + stream = DataStream(stream, iteration_scheme=ShuffledExampleScheme(stream.num_examples)) + + valid = TaxiDataset(self.config.valid_set, 'valid.hdf5', sources=('trip_id',)) + valid_trips_ids = valid.get_data(None, slice(0, valid.num_examples))[0] + + stream = transformers.TaxiExcludeTrips(valid_trips_ids, stream) + stream = transformers.TaxiGenerateSplits(stream, max_splits=100) + + stream = transformers.TaxiAddDateTime(stream) + stream = transformers.TaxiAddFirstLastLen(self.config.n_begin_end_pts, stream) + stream = transformers.Select(stream, tuple(req_vars)) + return Batch(stream, iteration_scheme=ConstantScheme(self.config.batch_size)) + + def valid(self, req_vars): + stream = TaxiStream(self.config.valid_set, 'valid.hdf5') + + stream = transformers.TaxiAddDateTime(stream) + stream = transformers.TaxiAddFirstLastLen(self.config.n_begin_end_pts, stream) + stream = transformers.Select(stream, tuple(req_vars)) + return Batch(stream, iteration_scheme=ConstantScheme(1000)) + + def test(self, req_vars): + stream = TaxiStream('test') + + stream = transformers.TaxiAddDateTime(stream) + stream = transformers.TaxiAddFirstLastLen(self.config.n_begin_end_pts, stream) + + return Batch(stream, iteration_scheme=ConstantScheme(1)) + + def inputs(self): + return {'call_type': tensor.bvector('call_type'), + 'origin_call': tensor.ivector('origin_call'), + 'origin_stand': tensor.bvector('origin_stand'), + 'taxi_id': tensor.wvector('taxi_id'), + 'timestamp': tensor.ivector('timestamp'), + 'day_type': tensor.bvector('day_type'), + 'missing_data': tensor.bvector('missing_data'), + 'latitude': tensor.matrix('latitude'), + 'longitude': tensor.matrix('longitude'), + 'destination_latitude': tensor.vector('destination_latitude'), + 'destination_longitude': tensor.vector('destination_longitude'), + 'travel_time': tensor.ivector('travel_time'), + 'first_k_latitude': tensor.matrix('first_k_latitude'), + 'first_k_longitude': tensor.matrix('first_k_longitude'), + 'last_k_latitude': tensor.matrix('last_k_latitude'), + 'last_k_longitude': tensor.matrix('last_k_longitude'), + 'input_time': tensor.ivector('input_time'), + 'week_of_year': tensor.bvector('week_of_year'), + 'day_of_week': tensor.bvector('day_of_week'), + 'qhour_of_day': tensor.bvector('qhour_of_day')} diff --git a/model/time_simple_mlp.py b/model/time_simple_mlp.py index 9e1b10a..0ce6b29 100644 --- a/model/time_simple_mlp.py +++ b/model/time_simple_mlp.py @@ -1,63 +1,29 @@ -from blocks.bricks import MLP, Rectifier, Linear, Sigmoid, Identity -from blocks.bricks.lookup import LookupTable +from blocks.bricks import application, Identity -from theano import tensor - -import data import error +from model.mlp import FFMLP, Stream -class Model(object): - def __init__(self, config): - # The input and the targets - x_firstk_latitude = (tensor.matrix('first_k_latitude') - data.train_gps_mean[0]) / data.train_gps_std[0] - x_firstk_longitude = (tensor.matrix('first_k_longitude') - data.train_gps_mean[1]) / data.train_gps_std[1] - - x_lastk_latitude = (tensor.matrix('last_k_latitude') - data.train_gps_mean[0]) / data.train_gps_std[0] - x_lastk_longitude = (tensor.matrix('last_k_longitude') - data.train_gps_mean[1]) / data.train_gps_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('travel_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 = config.exp_base ** mlp.apply(inputs) - - # outputs = theano.printing.Print("outputs")(outputs) - # y = theano.printing.Print("y")(y) - outputs.name = 'outputs' +class Model(FFMLP): + def __init__(self, config, **kwargs): + super(Model, self).__init__(config, output_layer=Identity, **kwargs) + self.inputs.append('input_time') - # Calculate the cost - cost = error.rmsle(outputs.flatten(), y.flatten()) - cost.name = 'cost' + @application(outputs=['duration']) + def predict(self, **kwargs): + outputs = super(Model, self).predict(**kwargs) + return kwargs['input_time'] + self.config.exp_base ** outputs - # Initialization - for tbl in embed_tables: - tbl.weights_init = config.embed_weights_init - mlp.weights_init = config.mlp_weights_init - mlp.biases_init = config.mlp_biases_init + @predict.property('inputs') + def predict_inputs(self): + return self.inputs - for tbl in embed_tables: - tbl.initialize() - mlp.initialize() + @application(outputs=['cost']) + def cost(self, **kwargs): + y_hat = self.predict(**kwargs) + y = kwargs['travel_time'] + return error.rmsle(y_hat.flatten(), y.flatten()) - self.cost = cost - self.monitor = [cost] - self.outputs = outputs - self.pred_vars = ['travel_time'] + @cost.property('inputs') + def cost_inputs(self): + return self.inputs + ['travel_time'] diff --git a/model/time_simple_mlp_tgtcls.py b/model/time_simple_mlp_tgtcls.py index 1f1eab7..35c8d8a 100644 --- a/model/time_simple_mlp_tgtcls.py +++ b/model/time_simple_mlp_tgtcls.py @@ -1,67 +1,33 @@ -from blocks.bricks import MLP, Rectifier, Linear, Sigmoid, Identity, Softmax -from blocks.bricks.lookup import LookupTable - import numpy import theano from theano import tensor +from blocks.bricks import application, Softmax -import data import error +from model.mlp import FFMLP, Stream -class Model(object): - def __init__(self, config): - # The input and the targets - x_firstk_latitude = (tensor.matrix('first_k_latitude') - data.train_gps_mean[0]) / data.train_gps_std[0] - x_firstk_longitude = (tensor.matrix('first_k_longitude') - data.train_gps_mean[1]) / data.train_gps_std[1] - - x_lastk_latitude = (tensor.matrix('last_k_latitude') - data.train_gps_mean[0]) / data.train_gps_std[0] - x_lastk_longitude = (tensor.matrix('last_k_longitude') - data.train_gps_mean[1]) / data.train_gps_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('travel_time') - - # 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' +class Model(FFMLP): + def __init__(self, config, **kwargs): + super(Model, self, output_layer=Softmax).__init__(config, **kwargs) + self.classes = theano.shared(numpy.array(config.tgtcls, dtype=theano.config.floatX), name='classes') + self.inputs.append('input_time') - # Calculate the cost - cost = error.rmsle(outputs.flatten(), y.flatten()) - cost.name = 'cost' + @application(outputs=['duration']) + def predict(self, **kwargs): + cls_probas = super(Model, self).predict(**kwargs) + return kwargs['input_time'] + tensor.dot(cls_probas, self.classes) - # Initialization - for tbl in embed_tables: - tbl.weights_init = config.embed_weights_init - mlp.weights_init = config.mlp_weights_init - mlp.biases_init = config.mlp_biases_init + @predict.property('inputs') + def predict_inputs(self): + return self.inputs - for tbl in embed_tables: - tbl.initialize() - mlp.initialize() + @application(outputs=['cost']) + def cost(self, **kwargs): + y_hat = self.predict(**kwargs) + y = kwargs['travel_time'] + return error.rmsle(y_hat.flatten(), y.flatten()) - self.cost = cost - self.monitor = [cost] - self.outputs = outputs - self.pred_vars = ['travel_time'] + @cost.property('inputs') + def cost_inputs(self): + return self.inputs + ['travel_time'] |