Add target class based model for time prediction (seems to work)

1 files changed, 67 insertions, 0 deletions

diff --git a/model/time_simple_mlp_tgtcls.py b/model/time_simple_mlp_tgtcls.py
new file mode 100644
index 0000000..1f1eab7
--- /dev/null
+++ b/model/time_simple_mlp_tgtcls.py
@@ -0,0 +1,67 @@
+from blocks.bricks import MLP, Rectifier, Linear, Sigmoid, Identity, Softmax
+from blocks.bricks.lookup import LookupTable
+
+import numpy
+import theano
+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.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'
+
+        # Calculate the cost
+        cost = error.rmsle(outputs.flatten(), y.flatten())
+        cost.name = 'cost'
+
+        # 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
+
+        for tbl in embed_tables:
+            tbl.initialize()
+        mlp.initialize()
+
+        self.cost = cost
+        self.monitor = [cost]
+        self.outputs = outputs
+        self.pred_vars = ['travel_time']