taxi

commit 9adfe767010e23823089b4db94cb4dc53cc3c12a
parent 71bb4d90da2bad933fdca48d1879886fe7aa9bc8
Author: Alex Auvolat <alex.auvolat@ens.fr>
Date:   Mon,  4 May 2015 13:15:42 -0400

Merge branch 'master' of github.com:adbrebs/taxi

Diffstat:
M
convert_data.py
 | 
3
++-
M
hdist.py
 | 
16
+++++++++++-----

2 files changed, 13 insertions(+), 6 deletions(-)
diff --git a/convert_data.py b/convert_data.py
@@ -104,8 +104,9 @@ def convert(input_directory, save_path):
     h5file = h5py.File(save_path, 'w')
     split = {}
     split.update(read_stands(input_directory, h5file))
-    split.update(read_taxis(input_directory, h5file, 'test', 'test_'))
     split.update(read_taxis(input_directory, h5file, 'train', ''))
+    print 'First origin_call not present in training set: ', len(origin_call_dict)
+    split.update(read_taxis(input_directory, h5file, 'test', 'test_'))
     split.update(unique(h5file))
     h5file.attrs['split'] = H5PYDataset.create_split_array(split)
     h5file.flush()
diff --git a/hdist.py b/hdist.py
@@ -2,6 +2,9 @@ from theano import tensor
 import theano
 import numpy
 
+rearth = const(6371)
+deg2rad = const(3.141592653589793 / 180)
+
 def const(v):
     if theano.config.floatX == 'float32':
         return numpy.float32(v)
@@ -9,9 +12,6 @@ def const(v):
         return numpy.float64(v)
 
 def hdist(a, b):
-    rearth = const(6371)
-    deg2rad = const(3.141592653589793 / 180)
-
     lat1 = a[:, 0] * deg2rad
     lon1 = a[:, 1] * deg2rad
     lat2 = b[:, 0] * deg2rad
@@ -27,5 +27,11 @@ def hdist(a, b):
 
     return tensor.switch(tensor.eq(hd, float('nan')), (a-b).norm(2, axis=1), hd)
 
-
-
+def erdist(a, b):
+    lat1 = a[:, 0] * deg2rad
+    lon1 = a[:, 1] * deg2rad
+    lat2 = b[:, 0] * deg2rad
+    lon2 = b[:, 1] * deg2rad
+    x = (lon2-lon1) * tensor.cos((lat1+lat2)/2)
+    y = (lat2-lat1)
+    return tensor.sqrt(tensor.sqr(x) + tensor.sqr(y)) * rearth