taxi

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

commit bfda3532ea58a48533ceaa417b1bd5c3f5137be3
parent aa605460eb5891b64b4e795cbeff9cab474dee0d
Author: Étienne Simon <esimon@esimon.eu>
Date:   Mon, 11 May 2015 21:20:11 +0000

Add method to TaxiDataset to easily extract a dictionary

Diffstat:
Mdata/hdf5.py | 5+++++
1 file changed, 5 insertions(+), 0 deletions(-)

diff --git a/data/hdf5.py b/data/hdf5.py @@ -19,6 +19,11 @@ class TaxiDataset(H5PYDataset): def data_path(self): return os.path.join(data.path, self.filename) + def extract(self, request): + if not self.load_in_memory: + raise ValueError('extract called on a dataset not loaded in memory') + return dict(zip(self.sources, self.get_data(None, request))) + class TaxiStream(DataStream): def __init__(self, which_set, filename='data.hdf5', iteration_scheme=None, **kwargs): dataset = TaxiDataset(which_set, filename, **kwargs)