taxi

Winning entry to the Kaggle taxi competition
git clone https://esimon.eu/repos/taxi.git
Log | Files | Refs | README

commit 1137abf0511359df8f468f1d9a4828f3e0cb1b6a
parent 39e549f05e568e4153381f025b3a0f256e9a7b7a
Author: Étienne Simon <esimon@esimon.eu>
Date:   Fri, 22 May 2015 11:23:49 -0400

Fix embeddings sizes.

Diffstat:
Mconfig/joint_simple_mlp_tgtcls_111_cswdtx.py | 4++--
Mconfig/joint_simple_mlp_tgtcls_111_cswdtx_bigger.py | 4++--
Mconfig/joint_simple_mlp_tgtcls_111_cswdtx_bigger_dropout.py | 4++--
Mconfig/joint_simple_mlp_tgtcls_111_cswdtx_noise_dout.py | 4++--
Mconfig/joint_simple_mlp_tgtcls_1_cswdtx.py | 4++--
Mconfig/joint_simple_mlp_tgtcls_1_cswdtx_bigger.py | 4++--
Mconfig/time_simple_mlp_2_cswdtx.py | 4++--
Mconfig/time_simple_mlp_tgtcls_2_cswdtx.py | 4++--
8 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/config/joint_simple_mlp_tgtcls_111_cswdtx.py b/config/joint_simple_mlp_tgtcls_111_cswdtx.py @@ -20,8 +20,8 @@ for i in range(22): time_tgtcls.append(time_tgtcls[-1] + time_tgtcls[-2]) dim_embeddings = [ - ('origin_call', data.origin_call_size+1, 10), - ('origin_stand', data.stands_size+1, 10), + ('origin_call', data.origin_call_size, 10), + ('origin_stand', data.stands_size, 10), ('week_of_year', 52, 10), ('day_of_week', 7, 10), ('qhour_of_day', 24 * 4, 10), diff --git a/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger.py b/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger.py @@ -20,8 +20,8 @@ for i in range(21): time_tgtcls.append(time_tgtcls[-1] + time_tgtcls[-2]) dim_embeddings = [ - ('origin_call', data.origin_call_size+1, 15), - ('origin_stand', data.stands_size+1, 10), + ('origin_call', data.origin_call_size, 15), + ('origin_stand', data.stands_size, 10), ('week_of_year', 52, 10), ('day_of_week', 7, 10), ('qhour_of_day', 24 * 4, 10), diff --git a/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger_dropout.py b/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger_dropout.py @@ -20,8 +20,8 @@ for i in range(21): time_tgtcls.append(time_tgtcls[-1] + time_tgtcls[-2]) dim_embeddings = [ - ('origin_call', data.origin_call_size+1, 15), - ('origin_stand', data.stands_size+1, 10), + ('origin_call', data.origin_call_size, 15), + ('origin_stand', data.stands_size, 10), ('week_of_year', 52, 10), ('day_of_week', 7, 10), ('qhour_of_day', 24 * 4, 10), diff --git a/config/joint_simple_mlp_tgtcls_111_cswdtx_noise_dout.py b/config/joint_simple_mlp_tgtcls_111_cswdtx_noise_dout.py @@ -23,8 +23,8 @@ for i in range(22): time_tgtcls.append(time_tgtcls[-1] + time_tgtcls[-2]) dim_embeddings = [ - ('origin_call', data.origin_call_size+1, 10), - ('origin_stand', data.stands_size+1, 10), + ('origin_call', data.origin_call_size, 10), + ('origin_stand', data.stands_size, 10), ('week_of_year', 52, 10), ('day_of_week', 7, 10), ('qhour_of_day', 24 * 4, 10), diff --git a/config/joint_simple_mlp_tgtcls_1_cswdtx.py b/config/joint_simple_mlp_tgtcls_1_cswdtx.py @@ -20,8 +20,8 @@ for i in range(22): time_tgtcls.append(time_tgtcls[-1] + time_tgtcls[-2]) dim_embeddings = [ - ('origin_call', data.origin_call_size+1, 10), - ('origin_stand', data.stands_size+1, 10), + ('origin_call', data.origin_call_size, 10), + ('origin_stand', data.stands_size, 10), ('week_of_year', 52, 10), ('day_of_week', 7, 10), ('qhour_of_day', 24 * 4, 10), diff --git a/config/joint_simple_mlp_tgtcls_1_cswdtx_bigger.py b/config/joint_simple_mlp_tgtcls_1_cswdtx_bigger.py @@ -20,8 +20,8 @@ for i in range(21): time_tgtcls.append(time_tgtcls[-1] + time_tgtcls[-2]) dim_embeddings = [ - ('origin_call', data.origin_call_size+1, 15), - ('origin_stand', data.stands_size+1, 10), + ('origin_call', data.origin_call_size, 15), + ('origin_stand', data.stands_size, 10), ('week_of_year', 52, 10), ('day_of_week', 7, 10), ('qhour_of_day', 24 * 4, 10), diff --git a/config/time_simple_mlp_2_cswdtx.py b/config/time_simple_mlp_2_cswdtx.py @@ -9,8 +9,8 @@ n_begin_end_pts = 5 # how many points we consider at the beginning and end o n_valid = 1000 dim_embeddings = [ - ('origin_call', data.n_train_clients+1, 10), - ('origin_stand', data.n_stands+1, 10), + ('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), diff --git a/config/time_simple_mlp_tgtcls_2_cswdtx.py b/config/time_simple_mlp_tgtcls_2_cswdtx.py @@ -14,8 +14,8 @@ for i in range(22): tgtcls.append(tgtcls[-1] + tgtcls[-2]) dim_embeddings = [ - ('origin_call', data.origin_call_size+1, 10), - ('origin_stand', data.stands_size+1, 10), + ('origin_call', data.origin_call_size, 10), + ('origin_stand', data.stands_size, 10), ('week_of_year', 52, 10), ('day_of_week', 7, 10), ('qhour_of_day', 24 * 4, 10),