diff options
| -rw-r--r-- | config/time_simple_mlp_tgtcls_2_cswdtx.py | 41 | ||||
| -rw-r--r-- | model/time_simple_mlp_tgtcls.py | 67 | ||||
| -rwxr-xr-x | train.py | 6 |
3 files changed, 111 insertions, 3 deletions
diff --git a/config/time_simple_mlp_tgtcls_2_cswdtx.py b/config/time_simple_mlp_tgtcls_2_cswdtx.py new file mode 100644 index 0000000..4579df3 --- /dev/null +++ b/config/time_simple_mlp_tgtcls_2_cswdtx.py @@ -0,0 +1,41 @@ +import model.time_simple_mlp_tgtcls as model + +from blocks.initialization import IsotropicGaussian, Constant + +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 + +# generate target classes as a Fibonacci sequence +tgtcls = [1, 2] +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), + ('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, 100] +dim_output = len(tgtcls) + +embed_weights_init = IsotropicGaussian(0.001) +mlp_weights_init = IsotropicGaussian(0.01) +mlp_biases_init = Constant(0.001) + +exp_base = 1.5 + +learning_rate = 0.0001 +momentum = 0.99 +batch_size = 32 + +valid_set = 'cuts/test_times_0' 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'] @@ -108,7 +108,7 @@ def main(): # Checkpoint('model.pkl', every_n_batches=100), Dump('model_data/' + model_name, every_n_batches=1000), LoadFromDump('model_data/' + model_name), - FinishAfter(after_epoch=42), + # FinishAfter(after_epoch=42), ] main_loop = MainLoop( @@ -124,12 +124,12 @@ def main(): outfile = open("output/test-output-%s.csv" % model_name, "w") outcsv = csv.writer(outfile) - if model.pred_vars == ['time']: + if model.pred_vars == ['travel_time']: outcsv.writerow(["TRIP_ID", "TRAVEL_TIME"]) for out in apply_model.Apply(outputs=outputs, stream=test_stream, return_vars=['trip_id', 'outputs']): time = out['outputs'] for i, trip in enumerate(out['trip_id']): - outcsv.writerow([trip, int(time[i, 0])]) + outcsv.writerow([trip, int(time[i])]) else: outcsv.writerow(["TRIP_ID", "LATITUDE", "LONGITUDE"]) for out in apply_model.Apply(outputs=outputs, stream=test_stream, return_vars=['trip_id', 'outputs']): |