def testWithPhoto():
corpus_all = buildAllCorpus(element_type='photos', debug=True)
for key, corpus in corpus_all.items():
break
ei = EventInterface()
ei.setDB('citybeat')
ei.setCollection('candidate_event_25by25_merged')
event = ei.getDocument()
event = BaseFeatureProduction(event, corpus=corpus)
print event.extractFeatures()
def generateData2():
# if sparse:
#rep = Representor()
all_corpus = buildAllCorpus(time_interval_length=14, debug=True)
true_event_list, false_event_list = loadUnbalancedData()
BaseFeatureProduction.GenerateArffFileHeader()
for event in true_event_list + false_event_list:
r = Region(event['region'])
corpus = all_corpus[r.getKey()]
BaseFeatureProduction(event, corpus, None).printFeatures()
def testWithTweet():
cnt = 0
corpus_all = buildAllCorpus(element_type='tweets', debug=False)
ei = EventInterface()
ei.setDB('citybeat_experiment')
ei.setCollection('twitter_candidate_events')
cur = ei.getAllDocuments()
print TwitterFeature.GenerateArffFileHeader()
for event in cur:
region = Region(event['region'])
event = TwitterFeature(event, corpus=corpus_all[region.getKey()])
if event.getActualValue() < 8:
print '< 8'
continue
cnt += 1
print event.extractFeatures()
print cnt, cur.count()
def testWithTweet():
from corpus import buildAllCorpus
corpus_all = buildAllCorpus(element_type="tweets", debug=True)
for key, corpus in corpus_all.items():
break
ei = EventInterface()
ei.setDB("citybeat")
ei.setCollection("candidate_event_25by25_merged")
event = ei.getDocument()
print event
ti = TweetInterface()
cur = ti.getAllDocuments(limit=30)
tweets = []
for tweet in cur:
tweets.append(tweet)
del event["photos"]
event["tweets"] = tweets
event = BaseFeature(event, corpus=corpus)
print event.printFeatures()
def __init__(self, element_type):
"""Given an event, return a list incices of the photos in 'photos' filed
which are representative to stands for this cluster
Could overwrite TfidfVectorizer as a parameter so that you could customize
your own tfidf parameters.
see http://scikit-learn.org/dev/modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html
"""
assert element_type in ["tweets", "photos"]
self._element_type = element_type
paras = {}
paras["max_df"] = 0.05
paras["min_df"] = 1
paras["strip_accents"] = "ascii"
paras["smooth_idf"] = True
paras["preprocessor"] = self._preProcessor
paras["sublinear_tf"] = True
paras["norm"] = "l2"
paras["analyzer"] = "char_wb"
paras["ngram_range"] = (4, 4)
paras["stop_words"] = "english"
self._corpus_dicts_char = buildAllCorpus(element_type=self._element_type, paras=paras)
