commit 8442ba13a442d509a407b5913b95d9f1b00989d2
parent c5187418bc93c34e3fdce4fdc1a3b5316812b69a
Author: Alex Auvolat <alex@adnab.me>
Date: Fri, 10 Jul 2015 19:21:04 -0400
Merge branch 'master' of github.com:adbrebs/taxi
Diffstat:
4 files changed, 33 insertions(+), 15 deletions(-)
diff --git a/README.md b/README.md
@@ -0,0 +1,3 @@
+Winning entry to the Kaggle ECML/PKDD destination competition.
+
+https://www.kaggle.com/c/pkdd-15-predict-taxi-service-trajectory-i
diff --git a/config/dest_mlp_tgtcls_1_cswdtx_batchshuffle.py b/config/dest_mlp_tgtcls_1_cswdtx_batchshuffle.py
@@ -23,14 +23,14 @@ dim_embeddings = [
]
dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
-dim_hidden = [1000]
+dim_hidden = [500]
dim_output = tgtcls.shape[0]
embed_weights_init = IsotropicGaussian(0.01)
mlp_weights_init = IsotropicGaussian(0.1)
mlp_biases_init = Constant(0.01)
-step_rule = Momentum(learning_rate=0.01, momentum=0.9)
+step_rule = Momentum(learning_rate=0.001, momentum=0.99)
batch_size = 200
diff --git a/data_analysis/cluster_arrival.py b/data_analysis/cluster_arrival.py
@@ -1,20 +1,31 @@
-import matplotlib.pyplot as plt
+#!/usr/bin/env python
import numpy
import cPickle
import scipy.misc
+import os
from sklearn.cluster import MeanShift, estimate_bandwidth
from sklearn.datasets.samples_generator import make_blobs
from itertools import cycle
-print "Reading arrival point list"
-with open("arrivals.pkl") as f:
- pts = cPickle.load(f)
+import data
+from data.hdf5 import taxi_it
+from data.transformers import add_destination
+
+print "Generating arrival point list"
+dests = []
+for v in taxi_it("train"):
+ if len(v['latitude']) == 0: continue
+ dests.append([v['latitude'][-1], v['longitude'][-1]])
+pts = numpy.array(dests)
+
+with open(os.path.join(data.path, "arrivals.pkl"), "w") as f:
+ cPickle.dump(pts, f, protocol=cPickle.HIGHEST_PROTOCOL)
print "Doing clustering"
bw = estimate_bandwidth(pts, quantile=.1, n_samples=1000)
print bw
-bw = 0.001
+bw = 0.001 # (
ms = MeanShift(bandwidth=bw, bin_seeding=True, min_bin_freq=5)
ms.fit(pts)
@@ -22,6 +33,6 @@ cluster_centers = ms.cluster_centers_
print "Clusters shape: ", cluster_centers.shape
-with open("arrival-cluters.pkl", "w") as f:
+with open(os.path.join(data.path, "arrival-clusters.pkl"), "w") as f:
cPickle.dump(cluster_centers, f, protocol=cPickle.HIGHEST_PROTOCOL)
diff --git a/model/mlp.py b/model/mlp.py
@@ -52,6 +52,12 @@ class FFMLP(Initializable):
def predict_inputs(self):
return self.inputs
+class UniformGenerator(object):
+ def __init__(self):
+ self.rng = numpy.random.RandomState(123)
+ def __call__(self, *args):
+ return float(self.rng.uniform())
+
class Stream(object):
def __init__(self, config):
self.config = config
@@ -69,17 +75,15 @@ class Stream(object):
stream = transformers.TaxiExcludeTrips(stream, valid_trips_ids)
stream = transformers.TaxiGenerateSplits(stream, max_splits=self.config.max_splits)
- stream = transformers.add_destination(stream)
-
- stream = transformers.taxi_add_datetime(stream)
- stream = transformers.taxi_add_first_last_len(stream, self.config.n_begin_end_pts)
- stream = transformers.Select(stream, tuple(req_vars))
if hasattr(self.config, 'shuffle_batch_size'):
stream = transformers.Batch(stream, iteration_scheme=ConstantScheme(self.config.shuffle_batch_size))
- rng = numpy.random.RandomState(123)
- stream = Mapping(stream, SortMapping(lambda x: float(rng.uniform())))
+ stream = Mapping(stream, SortMapping(key=UniformGenerator()))
stream = Unpack(stream)
+
+ stream = transformers.taxi_add_datetime(stream)
+ stream = transformers.taxi_add_first_last_len(stream, self.config.n_begin_end_pts)
+ stream = transformers.Select(stream, tuple(req_vars))
stream = Batch(stream, iteration_scheme=ConstantScheme(self.config.batch_size))
