def get_report(self,time_period,current_period=None,trending_function=biggest_change):
self._group_listings(time_period)
print "\nTrending Items: {}".format(time_period)
if not current_period:
current_period = trunc_date(datetime.datetime.now().date(),time_period)
print "Current Period: {}".format(current_period)
for category, category_listings in self._groups.iteritems():
print "\n{}\n===========".format(category)
trending = self._get_trending(category_listings,current_period,time_period,trending_function)
for rank, index in enumerate(trending):
word_or_phrase = self._lexicon[index]
if type(word_or_phrase) == tuple:
word_or_phrase = " ".join(word_or_phrase)
print "{}. {}".format(rank+1,word_or_phrase.encode('utf-8'))
def _group_listings(self,time_period):#parsed may or may not be an attribute
"""Returns a nested dictionary of grouped, vectorized listings, where the
groups are categories then time periods
Ex:
lexicon = ["big","dog","barks","loudly]
parsed_listings = [([1,2],'business','2012-01-12'), ([1,3],'business',2013-03-01'),
([0,1,2],'marketing','2014-04-01'),([0,2],'marketing','2013-01-01')]
group_listings(parsed_listings,lexicon_size=4,time_period='year')
=> {"business": {datetime.date(2012, 1, 1): [[0,1,1,0]],datetime.date(2013, 1, 1): [[0,1,0,1]]},
"marketing":{datetime.date(2013, 1, 1):[[0,0,1,0]] , datetime.date(2014, 1, 1): [[1,1,1,0]]}}"""
lexicon_size = len(self._lexicon)
for (int_tokens, categories, date) in self._parsed_listings:
date_period = trunc_date(get_date(date),time_period)
vector_listing = get_vectorized_listing(int_tokens,lexicon_size)
for category in categories:
group_listings = self._groups.setdefault(category,{})
category_date_listings = self._groups[category].setdefault(date_period,[])
self._groups[category][date_period].append(vector_listing)
