def richrank(cities, names):
candls = ['-', '--']
mks = ['o', '^', '*']
for idx in range(len(cities)):
lms = dict()
test = Dataset()
for pid in cities[idx]:
twtp = loadrows(GEOTWEET, ('place_id', 'text', 'created_at'),
('place_id=\'{0}\''.format(pid),), 'sample',
'order by rand() limit 110')
lms[pid] = LanguageModel(twtp['text'][:100])
for cnt in range(100, 110):
test.append({'label': twtp['place_id'][cnt],
'lm': LanguageModel([twtp['text'][cnt],])})
lmranks = list()
randranks = list()
for twtlm in test:
lmranks.append(ranke(lms, twtlm['lm']))
randranks.append(randranke(cities[idx]))
lmeval = batcheval(lmranks, test['label'])
print names[idx], 'P@1', (lmeval['rate'][1] - 0.1)
plt.plot(lmeval['pos'], lmeval['rate'], ls=candls[idx%2], marker=mks[idx/2],
label='{0}($s=100$)'.format(names[idx]))
plt.plot(lmeval['pos'], [float(r) / max(lmeval['pos']) for r in lmeval['pos']],
ls='-.', marker='s',
label='Random Baseline')
plt.legend(loc='lower right')
plt.ylabel('Rate containing referece POI')
plt.xlabel('Top $p$ places')
plt.show()
def richrank(cities, names):
candls = ['-', '--', '.-']
mks = ['o', '^', '*', 'v', 's']
for idx in range(len(cities)):
lms = dict()
test = Dataset()
for pid in cities[idx]:
twtp = loadrows(GEOTWEET, ('place_id', 'text', 'created_at'),
('place_id=\'{0}\''.format(pid), ),
'sample_switch_place_cate',
'order by rand() limit 110')
lms[pid] = LanguageModel(twtp['text'][:100])
for cnt in range(100, 110):
test.append({
'label': twtp['place_id'][cnt],
'lm': LanguageModel([
twtp['text'][cnt],
])
})
lmranks = list()
for twtlm in test:
lmranks.append(ranke(lms, twtlm['lm']))
lmeval = batcheval(lmranks, test['label'])
plt.plot(lmeval['pos'],
lmeval['rate'],
ls=candls[idx % 2],
marker=mks[idx / 2],
label='{0}($s=100$)'.format(names[idx]))
plt.legend(loc='lower right')
plt.ylabel('Rate containing referece POI')
plt.xlabel('Top $p$ places')
plt.show()
def cmpsparse(cities, numtwts, numtest):
""" Compare the model performance trained with different amount of tweets
"""
lmranks = [list() for i in range(len(numtwts))]
randranks = list()
lmtmranks = [list() for i in range(len(numtwts))]
test = Dataset()
for places in cities:
lms = [dict() for i in range(len(numtwts))]
tst = Dataset()
for pid in places:
twtp = loadrows(
GEOTWEET, ('place_id', 'text', 'created_at'),
('place_id=\'{0}\''.format(pid), ), 'sample',
'order by rand() limit {0}'.format(max(numtwts) + numtest))
for i in range(len(numtwts)):
lms[i][pid] = LanguageModel(twtp['text'][:numtwts[i]])
# test data
for i in range(max(numtwts), max(numtwts) + numtest):
tst.append({
'label': pid,
'lm': LanguageModel([
twtp['text'][i],
]),
})
test.extend(tst)
# rank
for item in tst:
for i in range(len(numtwts)):
lmranks[i].append(ranke(lms[i], item['lm']))
randranks.append(randranke(places))
# plot
candls = ['-', '--']
mks = ['o', '^', '*', 'v', 's']
for i, n in enumerate(numtwts):
lmeval = batcheval(lmranks[i], test['label'])
plt.plot(lmeval['pos'],
lmeval['rate'],
label='tweet(s={0})'.format(n),
marker=mks[i])
plt.plot(lmeval['pos'],
[float(r) / max(lmeval['pos']) for r in lmeval['pos']],
ls='-.',
marker='s',
label='Random Baseline')
plt.legend(loc='lower right')
plt.ylabel('Rate containing Reference POI')
plt.xlabel('Top $p$ places')
plt.show()
def cmpsparse(cities, numtwts, numtest):
""" Compare the model performance trained with different amount of tweets
"""
lmranks = [list() for i in range(len(numtwts))]
randranks = list()
lmtmranks = [list() for i in range(len(numtwts))]
test = Dataset()
for places in cities:
lms = [dict() for i in range(len(numtwts))]
tst = Dataset()
for pid in places:
twtp = loadrows(GEOTWEET, ('place_id', 'text', 'created_at'),
('place_id=\'{0}\''.format(pid),), 'sample',
'order by rand() limit {0}'.format(max(numtwts) + numtest))
for i in range(len(numtwts)):
lms[i][pid] = LanguageModel(twtp['text'][:numtwts[i]])
# test data
for i in range(max(numtwts), max(numtwts) + numtest):
tst.append({'label': pid,
'lm': LanguageModel([twtp['text'][i],]),
})
test.extend(tst)
# rank
for item in tst:
for i in range(len(numtwts)):
lmranks[i].append(ranke(lms[i], item['lm']))
randranks.append(randranke(places))
# plot
candls = ['-', '--']
mks = ['o', '^', '*', 'v', 's']
for i, n in enumerate(numtwts):
lmeval = batcheval(lmranks[i], test['label'])
plt.plot(lmeval['pos'], lmeval['rate'],
label='tweet(s={0})'.format(n),
marker=mks[i])
plt.plot(lmeval['pos'], [float(r) / max(lmeval['pos']) for r in lmeval['pos']],
ls='-.', marker='s',
label='Random Baseline')
plt.legend(loc='lower right')
plt.ylabel('Rate containing Reference POI')
plt.xlabel('Top $p$ places')
plt.show()
def gen_poi_list(dst):
"""Generate POI list for crawling by POI id
"""
fdst = open(dst, "w")
# cur = CONN_POOL.get_cur(GEOTWEET)
# cur.execute('SELECT id, max_tweet_id FROM place_dist')
i = 0
for row in loadrows(GEOTWEET, ("id", "max_tweet_id"), None, "place_dist"):
print >> fdst, "{0}${1}".format(row["id"], row["max_tweet_id"])
i += 1
fdst.close()
# cur.close()
logging.info("Generate PID::{0} POI IDs are generated.".format(i))
logging.info("------------------------------------------")
def gen_usr_list(dst):
"""Generate user list for crawling
"""
fdst = open(dst, "w")
# cur = CONN_POOL.get_cur(GEOTWEET)
# cur.execute('SELECT id, max_tweet_id\
# FROM user_dist')
i = 0
for row in loadrows(GEOTWEET, ("id", "max_tweet_id"), ("cnt>10",), "user_dist"):
print >> fdst, "{0}${1}".format(row["id"], row["max_tweet_id"])
i += 1
fdst.close()
logging.info("Generating user_id::{0} user IDs are generated.".format(i))
logging.info("------------------------------------------")
def gen_geocode_list(dst):
"""Generate geocode
"""
fdst = open(dst, "w")
# cur = CONN_POOL.get_cur(GEOTWEET)
# cur.execute('SELECT id, lat, lng, max_tweet_id\
# FROM place_dist where cnt>100')
i = 0
for row in loadrows(GEOTWEET, ("id", "lat", "lng", "max_tweet_id"), None, "place_dist"):
print >> fdst, "{0},{1},{2}${3}".format(row["lat"], row["lng"], "0.1km", row["max_tweet_id"])
i += 1
fdst.close()
logging.info("Generate geocode::{0} geocodes are generated.".format(i))
logging.info("------------------------------------------")
def gen_poi_list(dst):
"""Generate POI list for crawling by POI id
"""
fdst = open(dst, 'w')
#cur = CONN_POOL.get_cur(GEOTWEET)
#cur.execute('SELECT id, max_tweet_id FROM place_dist')
i = 0
for row in loadrows(GEOTWEET, ('id', 'max_tweet_id'), None, 'place_dist'):
print >> fdst, '{0}${1}'.format(row['id'], row['max_tweet_id'])
i += 1
fdst.close()
#cur.close()
logging.info('Generate PID::{0} POI IDs are generated.'.format(i))
logging.info('------------------------------------------')
def gen_usr_list(dst):
"""Generate user list for crawling
"""
fdst = open(dst, 'w')
#cur = CONN_POOL.get_cur(GEOTWEET)
#cur.execute('SELECT id, max_tweet_id\
#FROM user_dist')
i = 0
for row in loadrows(GEOTWEET, \
('id', 'max_tweet_id'), ('cnt>10',), 'user_dist'):
print >> fdst, '{0}${1}'.format(row['id'], row['max_tweet_id'])
i += 1
fdst.close()
logging.info('Generating user_id::{0} user IDs are generated.'.format(i))
logging.info('------------------------------------------')
def gen_place_info_list(dst):
"""Generate place name and coordinates for retrieving category
"""
fdst = open(dst, "w")
# cur = CONN_POOL.get_cur(GEOTWEET)
# cur.execute('SELECT id, name, lat, lng FROM '
# 'place_dist WHERE category is NULL')
i = 0
for row in loadrows(GEOTWEET, ("id", "name", "lat", "lng"), None, "place"):
if row["name"] == None:
continue
print >> fdst, row["id"] + "$" + row["name"] + "$" + str(row["lat"]) + "," + str(row["lng"])
i += 1
fdst.close()
# cur.close()
logging.info("Generate place_name::{0} place are generated.".format(i))
logging.info("------------------------------------------")
def gen_geocode_list(dst):
"""Generate geocode
"""
fdst = open(dst, 'w')
#cur = CONN_POOL.get_cur(GEOTWEET)
#cur.execute('SELECT id, lat, lng, max_tweet_id\
#FROM place_dist where cnt>100')
i = 0
for row in loadrows(GEOTWEET, \
('id', 'lat', 'lng', 'max_tweet_id'), \
None, 'place_dist'):
print >> fdst, '{0},{1},{2}${3}'.format( \
row['lat'], row['lng'], '0.1km', row['max_tweet_id'])
i += 1
fdst.close()
logging.info('Generate geocode::{0} geocodes are generated.'.format(i))
logging.info('------------------------------------------')
def gen_place_info_list(dst):
"""Generate place name and coordinates for retrieving category
"""
fdst = open(dst, 'w')
#cur = CONN_POOL.get_cur(GEOTWEET)
#cur.execute('SELECT id, name, lat, lng FROM '
# 'place_dist WHERE category is NULL')
i = 0
for row in loadrows(GEOTWEET, ('id', 'name', 'lat', 'lng'), \
None, 'place'):
if row['name'] == None:
continue
print >> fdst, row['id'] + '$' \
+ row['name'] + '$' \
+ str(row['lat']) + ',' + str(row['lng'])
i += 1
fdst.close()
#cur.close()
logging.info('Generate place_name::{0} place are generated.'.format(i))
logging.info('------------------------------------------')
def cmptimeweb(cities, numtwts, numtest):
""" compare the time model + web model to original pure text model
"""
lmranks = [list() for _ in numtwts]
tmranks = [list() for _ in numtwts]
wmranks = list()
randranks = list()
lmtmranks = [list() for _ in numtwts]
wmlmranks = [list() for _ in numtwts]
wmlmtmranks = [list() for _ in numtwts]
test = Dataset()
for city in cities:
lms = [dict() for _ in numtwts]
tms = [dict() for _ in numtwts]
wms = dict()
tst = Dataset()
for pid in city:
twtp = loadrows(
GEOTWEET, ('place_id', 'text', 'created_at'),
('place_id=\'{0}\''.format(pid), ), 'sample_switch_place_cate',
'order by rand() limit {0}'.format(max(numtwts) + numtest))
for i, n in enumerate(numtwts):
lms[i][pid] = LanguageModel(twtp['text'][:n])
tms[i][pid] = TimeModel(twtp['created_at'][:n])
web = loadrows(GEOTWEET, ('place_id', 'web'),
('place_id=\'{0}\''.format(pid), ), 'web',
'order by rand() limit 30')
try:
wms[pid] = LanguageModel(web['web'])
except KeyError:
wms[pid] = LanguageModel('')
# Prepare test data by the tail part of the data retrieved from db
test_pos = max(numtwts)
for i in range(test_pos, test_pos + numtest):
tst.append({
'label': pid,
'lm': LanguageModel([
twtp['text'][i],
]),
'tm': TimeModel([
twtp['created_at'][i],
])
})
test.extend(tst)
# rank
for item in tst:
for i, _ in enumerate(numtwts):
lmranks[i].append(ranke(lms[i], item['lm']))
tmranks[i].append(ranke(tms[i], item['tm']))
wmranks.append(ranke(wms, item['lm']))
randranks.append(randranke(city))
for i in range(len(numtwts)):
for ranklm, ranktm in zip(lmranks[i], tmranks[i]):
lmtmranks[i].append(linearjoin([ranklm, ranktm], [0.5, 0.5]))
for ranklm, rankwm in zip(lmranks[i], wmranks):
wmlmranks[i].append(linearjoin([ranklm, rankwm], [0.5, 0.5]))
for ranklm, ranktm, rankwm in zip(lmranks[i], tmranks[i], wmranks):
wmlmtmranks[i].append(\
linearjoin([ranklm, ranktm, rankwm], [0.33, 0.33, 0.33]))
# plot
candls = ['-', '--', '-.']
# mks = ['o', '^', '*']
#for i in range(len(numtwts)):
#lmeval = batcheval(lmranks[i], test['label'])
#plt.plot(lmeval['pos'], lmeval['rate'],
#label='tweet(s={0})'.format(numtwts[i]),
#ls=candls[i%2], marker=mks[i/2])
#for i in range(len(numtwts)):
#for plc in placetotalrank(lmranks[i], test)['label'][-10:]:
#print place_name(plc), plc
#print placetotalrank(lmranks[i], test)['totalrank'][-10:]
#print wilcoxontest(lmranks[i], lmranks[i-1], test)
#plt.legend(loc='lower right')
#---------------------------------------------------------------
for i in range(len(numtwts)):
lmeval = batcheval(lmranks[i], test['label'])
plt.plot(lmeval['pos'],
lmeval['rate'],
label='tweet(s={0})'.format(numtwts[i]),
ls=candls[i],
marker='o')
# wmlmeval = batcheval(wmlmranks[i], test['label'])
# plt.plot(wmlmeval['pos'], wmlmeval['rate'],
# label='tweet(s={0})+web'.format(numtwts[i]),
# ls=candls[i], marker='^')
# print 'Wilcoxon (lm vs wmlm):', wilcoxontest(lmranks[i], wmlmranks[i], test)
# print 'Place id -> name:'
# for plc in placetotalrank(wmlmranks[i], test)['label'][-10:]:
# print place_name(plc), plc
# print 'Place Total Rank:'
# print placetotalrank(wmlmranks[i], test)['totalrank'][-10:]
plt.plot(lmeval['pos'],
[float(r) / max(lmeval['pos']) for r in lmeval['pos']],
ls='-.',
marker='s',
label='Random Baseline')
# wmeval = batcheval(wmranks, test['label'])
# print 'Place id -> name:'
# for plc in placetotalrank(wmranks, test)['label'][-10:]:
# print place_name(plc), plc
# print 'Place Total Rank'
# print placetotalrank(wmranks, test)['totalrank'][-10:]
# plt.plot(wmeval['pos'], wmeval['rate'],
# label='web',
# ls=':')
#---------------------------------------------------------------
#for i in range(len(numtwts)):
#plt.subplot(121 + i)
#plt.title('$s={0}$'.format(numtwts[i]))
#lmeval = batcheval(lmranks[i], test['label'])
#plt.plot(lmeval['pos'], lmeval['rate'],
#label='tweet',
#ls=candls[i], marker='o')
#lmtmeval = batcheval(lmtmranks[i], test['label'])
#plt.plot(lmtmeval['pos'], lmtmeval['rate'],
#label='tweet+time',
#ls=candls[i], marker='^')
#wmlmtmeval = batcheval(wmlmtmranks[i], test['label'])
#plt.plot(wmlmtmeval['pos'], wmlmtmeval['rate'],
#label='tweet+time+web',
#ls=candls[i], marker='*')
#plt.legend(loc='lower right')
#plt.ylabel('Rate containing Reference POI')
#plt.xlabel('Top $p$ places')
#plt.show()
#---------------------------------------------------------------
#i=0
#plt.subplot(121 + i)
#plt.title('$s={0}$'.format(numtwts[i]))
#tmeval = batcheval(tmranks[i], test['label'])
#plt.plot(tmeval['pos'], tmeval['rate'],
#label='time',
#ls=candls[i], marker='o')
#lmeval = batcheval(lmranks[i], test['label'])
#plt.plot(lmeval['pos'], lmeval['rate'],
#label='tweet',
#ls=candls[i], marker='^')
#lmtmeval = batcheval(lmtmranks[i], test['label'])
#plt.plot(lmtmeval['pos'], lmtmeval['rate'],
#label='tweet+time',
#ls=candls[i], marker='*')
#for plc in placetotalrank(tmranks[i], test)['label'][-10:]:
#print place_name(plc), plc
#print placetotalrank(tmranks[i], test)['totalrank'][-10:]
#for plc in placetotalrank(lmtmranks[i], test)['label'][-10:]:
#print place_name(plc), plc
#print placetotalrank(lmtmranks[i], test)['totalrank'][-10:]
#print wilcoxontest(lmranks[i], lmtmranks[i], test)
#plt.legend(loc='lower right')
#plt.ylabel('Rate containing Reference POI')
#plt.xlabel('Top $p$ places')
#i=1
#plt.subplot(121 + i)
#plt.title('$s={0}$'.format(numtwts[i]))
#tmeval = batcheval(tmranks[i], test['label'])
#plt.plot(tmeval['pos'], tmeval['rate'],
#label='time',
#ls=candls[i], marker='o')
#wmlmeval = batcheval(wmlmranks[i], test['label'])
#plt.plot(wmlmeval['pos'], wmlmeval['rate'],
#label='tweet + web',
#ls=candls[i], marker='^')
#wmlmtmeval = batcheval(wmlmtmranks[i], test['label'])
#plt.plot(wmlmtmeval['pos'], wmlmtmeval['rate'],
#label='tweet+time+web',
#ls=candls[i], marker='*')
#for plc in placetotalrank(wmlmranks[i], test)['label'][-10:]:
#print place_name(plc), plc
#print placetotalrank(wmlmranks[i], test)['totalrank'][-10:]
#for plc in placetotalrank(wmlmtmranks[i], test)['label'][-10:]:
#print place_name(plc), plc
#print placetotalrank(wmlmtmranks[i], test)['totalrank'][-10:]
#print wilcoxontest(wmlmranks[i], wmlmtmranks[i], test)
#plt.legend(loc='lower right')
#plt.ylabel('Rate containing Reference POI')
#plt.xlabel('Top $p$ places')
plt.legend(loc='lower right')
plt.tight_layout()
plt.show()
def cmptimeweb(cities, numtwts, numtest):
""" compare the time model + web model to original pure text model
"""
lmranks = [list() for i in range(len(numtwts))]
tmranks = [list() for i in range(len(numtwts))]
wmranks = list()
randranks = list()
lmtmranks = [list() for i in range(len(numtwts))]
wmlmranks = [list() for i in range(len(numtwts))]
wmlmtmranks = [list() for i in range(len(numtwts))]
test = Dataset()
for places in cities:
lms = [dict() for i in range(len(numtwts))]
tms = [dict() for i in range(len(numtwts))]
wms = dict()
tst = Dataset()
for pid in places:
twtp = loadrows(GEOTWEET, ('place_id', 'text', 'created_at'),
('place_id=\'{0}\''.format(pid),), 'sample',
'order by rand() limit {0}'.format(max(numtwts) + numtest))
for i in range(len(numtwts)):
lms[i][pid] = LanguageModel(twtp['text'][:numtwts[i]])
tms[i][pid] = TimeModel(twtp['created_at'][:numtwts[i]])
web = loadrows(GEOTWEET, ('place_id', 'web'),
('place_id=\'{0}\''.format(pid),), 'web',
'order by rand() limit 30')
wms[pid] = LanguageModel(web['web'])
# test data
for i in range(max(numtwts), max(numtwts) + numtest):
tst.append({'label': pid,
'lm': LanguageModel([twtp['text'][i],]),
'tm': TimeModel([twtp['created_at'][i],])})
test.extend(tst)
# rank
for item in tst:
for i in range(len(numtwts)):
lmranks[i].append(ranke(lms[i], item['lm']))
tmranks[i].append(ranke(tms[i], item['tm']))
wmranks.append(ranke(wms, item['lm']))
randranks.append(randranke(places))
for i in range(len(numtwts)):
for ranklm, ranktm in zip(lmranks[i], tmranks[i]):
lmtmranks[i].append(linearjoin([ranklm, ranktm], [0.5, 0.5]))
for ranklm, rankwm in zip(lmranks[i], wmranks):
wmlmranks[i].append(linearjoin([ranklm, rankwm], [0.5, 0.5]))
for ranklm, ranktm, rankwm in zip(lmranks[i], tmranks[i], wmranks):
wmlmtmranks[i].append(\
linearjoin([ranklm, ranktm, rankwm], [0.33, 0.33, 0.33]))
# plot
candls = ['-', '--']
mks = ['o', '^', '*', 'v', 's']
#for i in range(len(numtwts)):
#lmeval = batcheval(lmranks[i], test['label'])
#plt.plot(lmeval['pos'], lmeval['rate'],
#label='tweet(s={0})'.format(numtwts[i]),
#ls=candls[i%2], marker=mks[i/2])
#for i in range(len(numtwts)):
#for plc in placetotalrank(lmranks[i], test)['label'][-10:]:
#print place_name(plc), plc
#print placetotalrank(lmranks[i], test)['totalrank'][-10:]
#print wilcoxontest(lmranks[i], lmranks[i-1], test)
#plt.legend(loc='lower right')
#---------------------------------------------------------------
for i in range(len(numtwts)):
lmeval = batcheval(lmranks[i], test['label'])
plt.plot(lmeval['pos'], lmeval['rate'],
label='tweet(s={0})'.format(numtwts[i]),
ls=candls[i], marker='o')
wmlmeval = batcheval(wmlmranks[i], test['label'])
plt.plot(wmlmeval['pos'], wmlmeval['rate'],
label='tweet(s={0})+web'.format(numtwts[i]),
ls=candls[i], marker='^')
print wilcoxontest(lmranks[i], wmlmranks[i], test)
for plc in placetotalrank(wmlmranks[i], test)['label'][-10:]:
print place_name(plc), plc
print placetotalrank(wmlmranks[i], test)['totalrank'][-10:]
wmeval = batcheval(wmranks, test['label'])
for plc in placetotalrank(wmranks, test)['label'][-10:]:
print place_name(plc), plc
print placetotalrank(wmranks, test)['totalrank'][-10:]
plt.plot(wmeval['pos'], wmeval['rate'],
label='web',
ls=':')
plt.plot(lmeval['pos'], [float(r) / max(lmeval['pos']) for r in lmeval['pos']],
ls='-.', marker='s',
label='Random Baseline')
#---------------------------------------------------------------
#for i in range(len(numtwts)):
#plt.subplot(121 + i)
#plt.title('$s={0}$'.format(numtwts[i]))
#lmeval = batcheval(lmranks[i], test['label'])
#plt.plot(lmeval['pos'], lmeval['rate'],
#label='tweet',
#ls=candls[i], marker='o')
#lmtmeval = batcheval(lmtmranks[i], test['label'])
#plt.plot(lmtmeval['pos'], lmtmeval['rate'],
#label='tweet+time',
#ls=candls[i], marker='^')
#wmlmtmeval = batcheval(wmlmtmranks[i], test['label'])
#plt.plot(wmlmtmeval['pos'], wmlmtmeval['rate'],
#label='tweet+time+web',
#ls=candls[i], marker='*')
#plt.legend(loc='lower right')
#plt.ylabel('Rate containing Reference POI')
#plt.xlabel('Top $p$ places')
#plt.show()
#---------------------------------------------------------------
#i=0
#plt.subplot(121 + i)
#plt.title('$s={0}$'.format(numtwts[i]))
#tmeval = batcheval(tmranks[i], test['label'])
#plt.plot(tmeval['pos'], tmeval['rate'],
#label='time',
#ls=candls[i], marker='o')
#lmeval = batcheval(lmranks[i], test['label'])
#plt.plot(lmeval['pos'], lmeval['rate'],
#label='tweet',
#ls=candls[i], marker='^')
#lmtmeval = batcheval(lmtmranks[i], test['label'])
#plt.plot(lmtmeval['pos'], lmtmeval['rate'],
#label='tweet+time',
#ls=candls[i], marker='*')
#for plc in placetotalrank(tmranks[i], test)['label'][-10:]:
#print place_name(plc), plc
#print placetotalrank(tmranks[i], test)['totalrank'][-10:]
#for plc in placetotalrank(lmtmranks[i], test)['label'][-10:]:
#print place_name(plc), plc
#print placetotalrank(lmtmranks[i], test)['totalrank'][-10:]
#print wilcoxontest(lmranks[i], lmtmranks[i], test)
#plt.legend(loc='lower right')
#plt.ylabel('Rate containing Reference POI')
#plt.xlabel('Top $p$ places')
#i=1
#plt.subplot(121 + i)
#plt.title('$s={0}$'.format(numtwts[i]))
#tmeval = batcheval(tmranks[i], test['label'])
#plt.plot(tmeval['pos'], tmeval['rate'],
#label='time',
#ls=candls[i], marker='o')
#wmlmeval = batcheval(wmlmranks[i], test['label'])
#plt.plot(wmlmeval['pos'], wmlmeval['rate'],
#label='tweet + web',
#ls=candls[i], marker='^')
#wmlmtmeval = batcheval(wmlmtmranks[i], test['label'])
#plt.plot(wmlmtmeval['pos'], wmlmtmeval['rate'],
#label='tweet+time+web',
#ls=candls[i], marker='*')
#for plc in placetotalrank(wmlmranks[i], test)['label'][-10:]:
#print place_name(plc), plc
#print placetotalrank(wmlmranks[i], test)['totalrank'][-10:]
#for plc in placetotalrank(wmlmtmranks[i], test)['label'][-10:]:
#print place_name(plc), plc
#print placetotalrank(wmlmtmranks[i], test)['totalrank'][-10:]
#print wilcoxontest(wmlmranks[i], wmlmtmranks[i], test)
plt.legend(loc='lower right')
plt.ylabel('Rate containing Reference POI')
plt.xlabel('Top $p$ places')
plt.show()
def cmpsparsecombine(cities, numtwts, numtest):
""" the combined model performance under the influence of sparseness
"""
lmranks = [list() for i in range(len(numtwts))]
tmranks = [list() for i in range(len(numtwts))]
wmranks = list()
randranks = list()
lmtmranks = [list() for i in range(len(numtwts))]
wmlmranks = [list() for i in range(len(numtwts))]
wmlmtmranks = [list() for i in range(len(numtwts))]
test = Dataset()
for places in cities:
lms = [dict() for i in range(len(numtwts))]
tms = [dict() for i in range(len(numtwts))]
wms = dict()
tst = Dataset()
for pid in places:
twtp = loadrows(
GEOTWEET, ('place_id', 'text', 'created_at'),
('place_id=\'{0}\''.format(pid), ), 'sample',
'order by rand() limit {0}'.format(max(numtwts) + numtest))
for i in range(len(numtwts)):
lms[i][pid] = LanguageModel(twtp['text'][:numtwts[i]])
tms[i][pid] = TimeModel(twtp['created_at'][:numtwts[i]])
web = loadrows(GEOTWEET, ('place_id', 'web'),
('place_id=\'{0}\''.format(pid), ), 'web',
'order by rand() limit 30')
wms[pid] = LanguageModel(web['web'])
# test data
for i in range(max(numtwts), max(numtwts) + numtest):
tst.append({
'label': pid,
'lm': LanguageModel([
twtp['text'][i],
]),
'tm': TimeModel([
twtp['created_at'][i],
])
})
test.extend(tst)
# rank
for item in tst:
for i in range(len(numtwts)):
lmranks[i].append(ranke(lms[i], item['lm']))
tmranks[i].append(ranke(tms[i], item['tm']))
wmranks.append(ranke(wms, item['lm']))
randranks.append(randranke(places))
for i in range(len(numtwts)):
for ranklm, ranktm in zip(lmranks[i], tmranks[i]):
lmtmranks[i].append(linearjoin([ranklm, ranktm], [0.5, 0.5]))
for ranklm, rankwm in zip(lmranks[i], wmranks):
wmlmranks[i].append(linearjoin([ranklm, rankwm], [0.5, 0.5]))
for ranklm, ranktm, rankwm in zip(lmranks[i], tmranks[i], wmranks):
wmlmtmranks[i].append(\
linearjoin([ranklm, ranktm, rankwm], [0.33, 0.33, 0.33]))
# plot
candls = ['-', '--']
mks = ['o', '^', '*', 'v', 's']
i = 0
plt.subplot(121 + i)
plt.title('$s={0}$'.format(numtwts[i]))
tmeval = batcheval(tmranks[i], test['label'])
plt.plot(tmeval['pos'],
tmeval['rate'],
label='time',
ls=candls[i],
marker='o')
lmeval = batcheval(lmranks[i], test['label'])
plt.plot(lmeval['pos'],
lmeval['rate'],
label='tweet',
ls=candls[i],
marker='^')
lmtmeval = batcheval(lmtmranks[i], test['label'])
plt.plot(lmtmeval['pos'],
lmtmeval['rate'],
label='tweet+time',
ls=candls[i],
marker='*')
for plc in placetotalrank(tmranks[i], test)['label'][-10:]:
print place_name(plc), plc
print placetotalrank(tmranks[i], test)['totalrank'][-10:]
for plc in placetotalrank(lmtmranks[i], test)['label'][-10:]:
print place_name(plc), plc
print placetotalrank(lmtmranks[i], test)['totalrank'][-10:]
print wilcoxontest(lmranks[i], lmtmranks[i], test)
plt.plot(lmeval['pos'],
[float(r) / max(lmeval['pos']) for r in lmeval['pos']],
ls='-.',
marker='s',
label='Random Baseline')
plt.legend(loc='lower right')
plt.ylabel('Rate containing Reference POI')
plt.xlabel('Top $p$ places')
i = 1
plt.subplot(121 + i)
plt.title('$s={0}$'.format(numtwts[i]))
tmeval = batcheval(tmranks[i], test['label'])
plt.plot(tmeval['pos'],
tmeval['rate'],
label='time',
ls=candls[i],
marker='o')
wmlmeval = batcheval(wmlmranks[i], test['label'])
plt.plot(wmlmeval['pos'],
wmlmeval['rate'],
label='tweet + web',
ls=candls[i],
marker='^')
wmlmtmeval = batcheval(wmlmtmranks[i], test['label'])
plt.plot(wmlmtmeval['pos'],
wmlmtmeval['rate'],
label='tweet+time+web',
ls=candls[i],
marker='*')
for plc in placetotalrank(wmlmranks[i], test)['label'][-10:]:
print place_name(plc), plc
print placetotalrank(wmlmranks[i], test)['totalrank'][-10:]
for plc in placetotalrank(wmlmtmranks[i], test)['label'][-10:]:
print place_name(plc), plc
print placetotalrank(wmlmtmranks[i], test)['totalrank'][-10:]
print wilcoxontest(wmlmranks[i], wmlmtmranks[i], test)
plt.plot(lmeval['pos'],
[float(r) / max(lmeval['pos']) for r in lmeval['pos']],
ls='-.',
marker='s',
label='Random Baseline')
plt.legend(loc='lower right')
plt.ylabel('Rate containing Reference POI')
plt.xlabel('Top $p$ places')
plt.show()
def test():
"""Test this unit"""
twt_lst = loadrows(GEOTWEET, ('place_id', 'text'),
('MBRContains({0}, geo)'.format(\
geo_rect((40.75,-74.02),(40.70,-73.97))),))
gen_arff(twt_lst, 'test.arff', {'text': 'TEXT', 'place_id': 'DISC'})
