diff options
author | Étienne Simon <esimon@esimon.eu> | 2015-05-06 11:54:52 -0400 |
---|---|---|
committer | Étienne Simon <esimon@esimon.eu> | 2015-05-06 11:55:26 -0400 |
commit | 0b4b65cb3d88ac4818e71ccef0bded3ddee0683c (patch) | |
tree | 75c0942dd20e73a6c4a67ab207e916f83c7d4bae /data/csv_to_hdf5.py | |
parent | 35b4503ddd148b0c937468891dd0a7e9ff1c79f4 (diff) | |
download | taxi-0b4b65cb3d88ac4818e71ccef0bded3ddee0683c.tar.gz taxi-0b4b65cb3d88ac4818e71ccef0bded3ddee0683c.zip |
Fix floatX!=float32 in hdf5 creation
Diffstat (limited to 'data/csv_to_hdf5.py')
-rwxr-xr-x | data/csv_to_hdf5.py | 9 |
1 files changed, 4 insertions, 5 deletions
diff --git a/data/csv_to_hdf5.py b/data/csv_to_hdf5.py index 17217f3..97cf428 100755 --- a/data/csv_to_hdf5.py +++ b/data/csv_to_hdf5.py @@ -7,7 +7,6 @@ import sys import h5py import numpy -import theano from fuel.converters.base import fill_hdf5_file import data @@ -32,8 +31,8 @@ def get_unique_origin_call(val): def read_stands(input_directory, h5file): stands_name = numpy.empty(shape=(data.stands_size,), dtype=('a', 24)) - stands_latitude = numpy.empty(shape=(data.stands_size,), dtype=theano.config.floatX) - stands_longitude = numpy.empty(shape=(data.stands_size,), dtype=theano.config.floatX) + stands_latitude = numpy.empty(shape=(data.stands_size,), dtype=numpy.float32) + stands_longitude = numpy.empty(shape=(data.stands_size,), dtype=numpy.float32) stands_name[0] = 'None' stands_latitude[0] = stands_longitude[0] = 0 with open(os.path.join(input_directory, 'metaData_taxistandsID_name_GPSlocation.csv'), 'r') as f: @@ -77,8 +76,8 @@ def read_taxis(input_directory, h5file, dataset): day_type[id] = ord(line[6][0]) - ord('A') missing_data[id] = line[7][0] == 'T' polyline = ast.literal_eval(line[8]) - latitude[id] = numpy.array([point[1] for point in polyline], dtype=theano.config.floatX) - longitude[id] = numpy.array([point[0] for point in polyline], dtype=theano.config.floatX) + latitude[id] = numpy.array([point[1] for point in polyline], dtype=numpy.float32) + longitude[id] = numpy.array([point[0] for point in polyline], dtype=numpy.float32) id+=1 splits = () print >> sys.stderr, 'read %s: writing' % dataset |