Add day type and taxi id

3 files changed, 58 insertions, 2 deletions

diff --git a/config/simple_mlp_2_cswdt.py b/config/simple_mlp_2_cswdt.py
new file mode 100644
index 0000000..05c9450
--- /dev/null
+++ b/config/simple_mlp_2_cswdt.py
@@ -0,0 +1,25 @@
+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_tgtcls_1_cswdt.py b/config/simple_mlp_tgtcls_1_cswdt.py
index 9261635..45bd39e 100644
--- a/config/simple_mlp_tgtcls_1_cswdt.py
+++ b/config/simple_mlp_tgtcls_1_cswdt.py
@@ -14,9 +14,10 @@ with open(data.DATA_PATH + "/arrival-clusters.pkl") as f: tgtcls = cPickle.load(
 dim_embeddings = [
     ('origin_call', data.n_train_clients+1, 10),
     ('origin_stand', data.n_stands+1, 10),
-    ('week_of_year', 53, 10),
+    ('week_of_year', 52, 10),
     ('day_of_week', 7, 10),
-    ('qhour_of_day', 24 * 4, 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)
diff --git a/config/simple_mlp_tgtcls_1_cswdtx.py b/config/simple_mlp_tgtcls_1_cswdtx.py
new file mode 100644
index 0000000..d51ddde
--- /dev/null
+++ b/config/simple_mlp_tgtcls_1_cswdtx.py
@@ -0,0 +1,30 @@
+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