taxi

Winning entry to the Kaggle taxi competition
git clone https://esimon.eu/repos/taxi.git
Log | Files | Refs | README

commit 01f27c350347607b31c68cf96ae9c781f10582db
parent 294afc20266372ab8d9051ae5a42912be739d01a
Author: Alex Auvolat <alex.auvolat@ens.fr>
Date:   Sun, 21 Jun 2015 15:45:37 -0400

Fix hdf5 generation

Diffstat:
Mdata/init_valid.py | 4+++-
Mdata/make_valid_cut.py | 1+
2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/data/init_valid.py b/data/init_valid.py @@ -38,15 +38,17 @@ def init_valid(path): ('source', 'a', 21), ('start', numpy.int64, 1), ('stop', numpy.int64, 1), + ('indices', h5py.special_dtype(ref=h5py.Reference)), ('available', numpy.bool, 1), ('comment', 'a', 1)])) split_array[:]['split'] = 'dummy'.encode('utf8') for (i, k) in enumerate(_fields.keys()): - split_array[i] = k.encode('utf8') + split_array[i]['source'] = k.encode('utf8') split_array[:]['start'] = 0 split_array[:]['stop'] = 0 split_array[:]['available'] = False + split_array[:]['indices'] = None split_array[:]['comment'] = '.'.encode('utf8') h5file.attrs['split'] = split_array diff --git a/data/make_valid_cut.py b/data/make_valid_cut.py @@ -57,6 +57,7 @@ def make_valid(cutfile, outpath): splits[slen+i]['source'] = field.encode('utf8') splits[slen+i]['start'] = clen splits[slen+i]['stop'] = alen + splits[slen+i]['indices'] = None splits[slen+i]['available'] = True splits[slen+i]['comment'] = '.' file.attrs['split'] = splits