Model with only embeddings.

5 files changed, 160 insertions, 1 deletions

diff --git a/config/dest_simple_mlp_emb_only.py b/config/dest_simple_mlp_emb_only.py
new file mode 100644
index 0000000..e5c91b8
--- /dev/null
+++ b/config/dest_simple_mlp_emb_only.py
@@ -0,0 +1,31 @@
+from blocks.initialization import IsotropicGaussian, Constant
+
+import data
+from model.mlp_emb import Model, Stream
+
+use_cuts_for_training = True
+
+dim_embeddings = [
+    ('origin_call', data.origin_call_train_size, 10),
+    ('origin_stand', data.stands_size, 10),
+    ('week_of_year', 52, 10),
+    ('day_of_week', 7, 10),
+    ('qhour_of_day', 24 * 4, 10),
+    ('day_type', 3, 10),
+]
+
+dim_input = sum(x for (_, _, x) in dim_embeddings)
+dim_hidden = [200, 100]
+output_mode = "destination"
+dim_output = 2
+
+embed_weights_init = IsotropicGaussian(0.001)
+mlp_weights_init = IsotropicGaussian(0.01)
+mlp_biases_init = Constant(0.001)
+
+learning_rate = 0.0001
+momentum = 0.99
+batch_size = 32
+
+valid_set = 'cuts/test_times_0'
+max_splits = 100
diff --git a/data/__init__.py b/data/__init__.py
index 2121033..604809c 100644
--- a/data/__init__.py
+++ b/data/__init__.py
@@ -5,6 +5,7 @@ import numpy
 
 
 path = os.environ.get('TAXI_PATH', '/data/lisatmp3/auvolat/taxikaggle')
+path = os.environ.get('TAXI_PATH', '/Users/adeb/data/taxi')
 
 Polyline = h5py.special_dtype(vlen=numpy.float32)
 
diff --git a/data/transformers.py b/data/transformers.py
index 1bed887..e6806cc 100644
--- a/data/transformers.py
+++ b/data/transformers.py
@@ -94,7 +94,7 @@ class TaxiGenerateSplits(Transformer):
 
 
 class _taxi_add_first_last_len_helper(object):
-    def __init__(self, k, latitude, longitude):
+    def __init__(self, k, id_latitude, id_longitude):
         self.k = k
         self.id_latitude = id_latitude
         self.id_longitude = id_longitude
diff --git a/model/mlp.py b/model/mlp.py
index 6abc86f..a6f3991 100644
--- a/model/mlp.py
+++ b/model/mlp.py
@@ -63,6 +63,7 @@ class Stream(object):
 
         stream = transformers.TaxiExcludeTrips(stream, valid_trips_ids)
         stream = transformers.TaxiGenerateSplits(stream, max_splits=self.config.max_splits)
+        stream = transformers.add_destination(stream)
 
         stream = transformers.taxi_add_datetime(stream)
         stream = transformers.taxi_add_first_last_len(stream, self.config.n_begin_end_pts)
diff --git a/model/mlp_emb.py b/model/mlp_emb.py
new file mode 100644
index 0000000..f34541b
--- /dev/null
+++ b/model/mlp_emb.py
@@ -0,0 +1,126 @@
+from theano import tensor
+
+from fuel.transformers import Batch, MultiProcessing
+from fuel.streams import DataStream
+from fuel.schemes import ConstantScheme, ShuffledExampleScheme
+from blocks.bricks import application, MLP, Rectifier, Initializable, Identity
+
+import error
+import data
+from data import transformers
+from data.hdf5 import TaxiDataset, TaxiStream
+from data.cut import TaxiTimeCutScheme
+from model import ContextEmbedder
+
+
+class Model(Initializable):
+    def __init__(self, config, **kwargs):
+        super(Model, self).__init__(**kwargs)
+        self.config = config
+
+        self.context_embedder = ContextEmbedder(config)
+        self.mlp = MLP(activations=[Rectifier() for _ in config.dim_hidden] + [Identity()],
+                       dims=[config.dim_input] + config.dim_hidden + [config.dim_output])
+
+        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=['destination'])
+    def predict(self, **kwargs):
+        embeddings = tuple(self.context_embedder.apply(**{k: kwargs[k] for k in self.context_embedder.inputs }))
+
+        inputs = tensor.concatenate(embeddings, axis=1)
+        outputs = self.mlp.apply(inputs)
+
+        if self.config.output_mode == "destination":
+            return data.train_gps_std * outputs + data.train_gps_mean
+        elif self.config.dim_output == "clusters":
+            return tensor.dot(outputs, self.classes)
+
+    @predict.property('inputs')
+    def predict_inputs(self):
+        return self.inputs
+
+    @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)
+
+        return error.erdist(y_hat, y).mean()
+
+    @cost.property('inputs')
+    def cost_inputs(self):
+        return self.inputs + ['destination_latitude', 'destination_longitude']
+
+
+class Stream(object):
+    def __init__(self, config):
+        self.config = config
+
+    def train(self, req_vars):
+        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 = TaxiDataset('train')
+
+        if hasattr(self.config, 'use_cuts_for_training') and self.config.use_cuts_for_training:
+            stream = DataStream(stream, iteration_scheme=TaxiTimeCutScheme())
+        else:
+            stream = DataStream(stream, iteration_scheme=ShuffledExampleScheme(stream.num_examples))
+
+        stream = transformers.TaxiExcludeTrips(stream, valid_trips_ids)
+        stream = transformers.TaxiGenerateSplits(stream, max_splits=self.config.max_splits)
+
+        stream = transformers.taxi_add_datetime(stream)
+        # stream = transformers.taxi_add_first_last_len(stream, self.config.n_begin_end_pts)
+        stream = transformers.Select(stream, tuple(req_vars))
+        
+        stream = Batch(stream, iteration_scheme=ConstantScheme(self.config.batch_size))
+
+        stream = MultiProcessing(stream)
+
+        return stream
+
+    def valid(self, req_vars):
+        stream = TaxiStream(self.config.valid_set, 'valid.hdf5')
+
+        stream = transformers.taxi_add_datetime(stream)
+        # stream = transformers.taxi_add_first_last_len(stream, self.config.n_begin_end_pts)
+        stream = transformers.Select(stream, tuple(req_vars))
+        return Batch(stream, iteration_scheme=ConstantScheme(1000))
+
+    def test(self, req_vars):
+        stream = TaxiStream('test')
+        
+        stream = transformers.taxi_add_datetime(stream)
+        # stream = transformers.taxi_add_first_last_len(stream, self.config.n_begin_end_pts)
+        stream = transformers.taxi_remove_test_only_clients(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')}