diff options
| -rw-r--r-- | config/joint_simple_mlp_tgtcls_111_cswdtx_bigger.py | 56 | ||||
| -rw-r--r-- | config/joint_simple_mlp_tgtcls_111_cswdtx_bigger_dropout.py | 59 | ||||
| -rw-r--r-- | config/joint_simple_mlp_tgtcls_1_cswdtx_bigger.py | 55 | ||||
| -rw-r--r-- | model/joint_simple_mlp_tgtcls.py | 2 | ||||
| -rwxr-xr-x | train.py | 6 |
5 files changed, 175 insertions, 3 deletions
diff --git a/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger.py b/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger.py new file mode 100644 index 0000000..8adb6e7 --- /dev/null +++ b/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger.py @@ -0,0 +1,56 @@ +import cPickle + +import model.joint_simple_mlp_tgtcls as model + +from blocks.initialization import IsotropicGaussian, Constant + +import data + +n_begin_end_pts = 10 # how many points we consider at the beginning and end of the known trajectory +n_end_pts = 10 + +n_valid = 1000 + +with open("%s/arrival-clusters.pkl" % data.path) as f: + dest_tgtcls = cPickle.load(f) + +# generate target classes for time prediction as a Fibonacci sequence +time_tgtcls = [1, 2] +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), + ('week_of_year', 52, 10), + ('day_of_week', 7, 10), + ('qhour_of_day', 24 * 4, 10), + ('day_type', 3, 10), + ('taxi_id', 448, 10), +] + +# Common network part +dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings) +dim_hidden = [1000] + +# Destination prediction part +dim_hidden_dest = [400] +dim_output_dest = dest_tgtcls.shape[0] + +# Time prediction part +dim_hidden_time = [400] +dim_output_time = len(time_tgtcls) + +# Cost ratio between distance cost and time cost +time_cost_factor = 4 + +embed_weights_init = IsotropicGaussian(0.01) +mlp_weights_init = IsotropicGaussian(0.1) +mlp_biases_init = Constant(0.01) + +learning_rate = 0.000001 +momentum = 0.99 +batch_size = 200 + +valid_set = 'cuts/test_times_0' + diff --git a/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger_dropout.py b/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger_dropout.py new file mode 100644 index 0000000..02c8bd8 --- /dev/null +++ b/config/joint_simple_mlp_tgtcls_111_cswdtx_bigger_dropout.py @@ -0,0 +1,59 @@ +import cPickle + +import model.joint_simple_mlp_tgtcls as model + +from blocks.initialization import IsotropicGaussian, Constant + +import data + +n_begin_end_pts = 10 # how many points we consider at the beginning and end of the known trajectory +n_end_pts = 10 + +n_valid = 1000 + +with open("%s/arrival-clusters.pkl" % data.path) as f: + dest_tgtcls = cPickle.load(f) + +# generate target classes for time prediction as a Fibonacci sequence +time_tgtcls = [1, 2] +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), + ('week_of_year', 52, 10), + ('day_of_week', 7, 10), + ('qhour_of_day', 24 * 4, 10), + ('day_type', 3, 10), + ('taxi_id', 448, 10), +] + +# Common network part +dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings) +dim_hidden = [5000] + +# Destination prediction part +dim_hidden_dest = [1000] +dim_output_dest = dest_tgtcls.shape[0] + +# Time prediction part +dim_hidden_time = [500] +dim_output_time = len(time_tgtcls) + +# Cost ratio between distance cost and time cost +time_cost_factor = 4 + +embed_weights_init = IsotropicGaussian(0.01) +mlp_weights_init = IsotropicGaussian(0.1) +mlp_biases_init = Constant(0.01) + +# apply_dropout = True +# dropout_p = 0.5 + +learning_rate = 0.001 +momentum = 0.9 +batch_size = 200 + +valid_set = 'cuts/test_times_0' + diff --git a/config/joint_simple_mlp_tgtcls_1_cswdtx_bigger.py b/config/joint_simple_mlp_tgtcls_1_cswdtx_bigger.py new file mode 100644 index 0000000..995f858 --- /dev/null +++ b/config/joint_simple_mlp_tgtcls_1_cswdtx_bigger.py @@ -0,0 +1,55 @@ +import cPickle + +import model.joint_simple_mlp_tgtcls as model + +from blocks.initialization import IsotropicGaussian, Constant + +import data + +n_begin_end_pts = 7 # how many points we consider at the beginning and end of the known trajectory +n_end_pts = 7 + +n_valid = 1000 + +with open("%s/arrival-clusters.pkl" % data.path) as f: + dest_tgtcls = cPickle.load(f) + +# generate target classes for time prediction as a Fibonacci sequence +time_tgtcls = [1, 2] +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), + ('week_of_year', 52, 10), + ('day_of_week', 7, 10), + ('qhour_of_day', 24 * 4, 10), + ('day_type', 3, 10), + ('taxi_id', 448, 10), +] + +# Common network part +dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings) +dim_hidden = [5000] + +# Destination prediction part +dim_hidden_dest = [] +dim_output_dest = dest_tgtcls.shape[0] + +# Time prediction part +dim_hidden_time = [] +dim_output_time = len(time_tgtcls) + +# Cost ratio between distance cost and time cost +time_cost_factor = 4 + +embed_weights_init = IsotropicGaussian(0.01) +mlp_weights_init = IsotropicGaussian(0.1) +mlp_biases_init = Constant(0.01) + +learning_rate = 0.0001 +momentum = 0.99 +batch_size = 200 + +valid_set = 'cuts/test_times_0' diff --git a/model/joint_simple_mlp_tgtcls.py b/model/joint_simple_mlp_tgtcls.py index 834afbf..0aaf554 100644 --- a/model/joint_simple_mlp_tgtcls.py +++ b/model/joint_simple_mlp_tgtcls.py @@ -58,10 +58,12 @@ class Model(object): 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' @@ -73,7 +73,7 @@ def setup_test_stream(req_vars): test = transformers.TaxiAddFirstLastLen(config.n_begin_end_pts, test) test = transformers.Select(test, tuple(req_vars)) - test_stream = Batch(test, iteration_scheme=ConstantScheme(1000)) + test_stream = Batch(test, iteration_scheme=ConstantScheme(1)) return test_stream @@ -100,8 +100,8 @@ def main(): cost=cost, step_rule=CompositeRule([ RemoveNotFinite(), - #AdaDelta(decay_rate=0.95), - Momentum(learning_rate=config.learning_rate, momentum=config.momentum), + AdaDelta(), + #Momentum(learning_rate=config.learning_rate, momentum=config.momentum), ]), params=params) |