def tag_count(mongo, city, flickr=True, bbox=None, output='tags_count.dat'):
"""Return ordered {tags: count} dict from `flickr` photos (or Foursquare
venues), in `city` and optionally within `bbox`."""
start = clock()
city_field = 'hint' if flickr else 'city'
collec = mongo.world.photos if flickr else mongo.foursquare.venue
query = [{
"$match": {
city_field: city
}
}, {
"$unwind": "$tags"
}, {
"$group": {
"_id": "$tags",
"count": {
"$sum": 1
}
}
}, {
"$sort": SON([("count", -1), ("_id", -1)])
}]
if bbox:
query[0]['$match'].update({"loc": inside_bbox(bbox)})
tags = collec.aggregate(query)
t = 1000 * (clock() - start)
print('aggregate in {:.3f}ms ({})'.format(t, tags['result'][0]))
name = map(itemgetter('_id'), tags['result'])
count = map(itemgetter('count'), tags['result'])
outplot(output, ['tag', 'count'], name, count)
return OrderedDict(zip(name, count))
def top_metrics(tags):
# pool = Pool(4)
res = map(fixed_tag_metrics, tags)
# pool.close()
outplot('e_grav.dat', ['H', 'tags'], [v[2] for v in res],
[v[4] for v in res])
outplot('e_pair.dat', ['H', 'tags'], [v[3] for v in res],
[v[4] for v in res])
mus = np.array([v[0] for v in res])
sigmas = np.array([v[1] for v in res])
sio.savemat('mu_sigma', {'A': np.vstack([mus, sigmas]).T})
tag_cloud([v[4] for v in res], zip(mus, sigmas), True)
def top_metrics(tags):
# pool = Pool(4)
res = map(fixed_tag_metrics, tags)
# pool.close()
outplot('e_grav.dat', ['H', 'tags'],
[v[2] for v in res], [v[4] for v in res])
outplot('e_pair.dat', ['H', 'tags'],
[v[3] for v in res], [v[4] for v in res])
mus = np.array([v[0] for v in res])
sigmas = np.array([v[1] for v in res])
sio.savemat('mu_sigma', {'A': np.vstack([mus, sigmas]).T})
tag_cloud([v[4] for v in res], zip(mus, sigmas), True)
def tag_count(mongo, city, flickr=True, bbox=None, output='tags_count.dat'):
"""Return ordered {tags: count} dict from `flickr` photos (or Foursquare
venues), in `city` and optionally within `bbox`."""
start = clock()
city_field = 'hint' if flickr else 'city'
collec = mongo.world.photos if flickr else mongo.foursquare.venue
query = [{"$match": {city_field: city}}, {"$unwind": "$tags"},
{"$group": {"_id": "$tags", "count": {"$sum": 1}}},
{"$sort": SON([("count", -1), ("_id", -1)])}]
if bbox:
query[0]['$match'].update({"loc": inside_bbox(bbox)})
tags = collec.aggregate(query)
t = 1000*(clock() - start)
print('aggregate in {:.3f}ms ({})'.format(t, tags['result'][0]))
name = map(itemgetter('_id'), tags['result'])
count = map(itemgetter('count'), tags['result'])
outplot(output, ['tag', 'count'], name, count)
return OrderedDict(zip(name, count))
