def loadBusinesses(chunk, num_processes=None):
"""
Loads businesses. Specify a chunk to only load subsets of the businesses. Also specify number of procecesses to use.
"""
assert chunk in ['0', '1', '2'], "Chunk must be 0, 1, or 2"
businesses = loader.get_challengeset(int(chunk))
num_processes = int(num_processes) if num_processes else cpu_count()
total = len(businesses)
global featurizer
# late import
from scorers import Featurizer
featurizer = Featurizer()
pool = Pool(processes=num_processes)
print "Loading {} businesseses".format(total)
i = 0
for group in chunker(businesses, num_processes):
i += len(group)
sys.stdout.write('\r')
sys.stdout.write("[%-50s] %d%% (%d/%d) " %
('=' * ((i + 1) * 50 / total),
((i + 1) * 100 / total), i + 1, total))
sys.stdout.flush()
pool.map(concurrent_process, group)
def get_all_business_types():
businesses = loader.get_challengeset()
idtoloc = loader.get_idtoloc()
business_types_dict = loader.get_business_types()
print "Done {} of {}".format(len(business_types_dict), len(businesses))
for business in businesses:
unique_id = business['unique_id']
if unique_id not in business_types_dict.keys():
print business['name']
closest_place, best_sim = None, 0
lat, lon = idtoloc[unique_id]
for place in get_places(lat, lon):
sim = cosine_sim(place['name'], business['name'])
if sim > best_sim:
closest_place = place
best_sim = sim
if closest_place:
types = filter(lambda x: not x in ['point_of_interest', 'establishment', 'sublocality', 'route',
'real', 'political', 'of', 'or', 'local', 'locality', 'intersection',
'1'], closest_place['types'])
types = " ".join(types).replace("_", " ")
else:
types = None
print types
business_types_dict[unique_id] = types
loader.dump_business_dict(business_types_dict)
def get_business_lat_lon():
gapi = GoogleGeocodingApi()
id_to_loc = loader.get_idtoloc()
businesses = loader.get_challengeset()
for business in businesses:
unique_id = business['unique_id']
address = business['address']
if id_to_loc.get(unique_id) is None:
print business['name']
lat, lng = gapi.decode_address(address)
id_to_loc[unique_id] = (lat, lng)
pickle.dump(id_to_loc, open('../../data/id_to_loc.pickle', 'w'))
def loadBusinesses(chunk, num_processes=None):
"""
Loads businesses. Specify a chunk to only load subsets of the businesses. Also specify number of procecesses to use.
"""
assert chunk in ['0', '1', '2'], "Chunk must be 0, 1, or 2"
businesses = loader.get_challengeset(int(chunk))
num_processes = int(num_processes) if num_processes else cpu_count()
total = len(businesses)
global featurizer
# late import
from scorers import Featurizer
featurizer = Featurizer()
pool = Pool(processes=num_processes)
print "Loading {} businesseses".format(total)
i = 0
for group in chunker(businesses, num_processes):
i += len(group)
sys.stdout.write('\r')
sys.stdout.write("[%-50s] %d%% (%d/%d) " % ('=' * ((i + 1) * 50 / total), ((i + 1) * 100 / total), i + 1, total))
sys.stdout.flush()
pool.map(concurrent_process, group)