class PageData(object):
def __init__(self):
self.region = Locations()
self.brewer = Brewers()
self.style = Styles()
self.beer = Beers()
def __to_dict(self, field_dict, records):
out = []
for r in records:
d = {}
for k,v in field_dict.iteritems():
d[k] = r[v]
out.append(d)
return out
def brewer_regions(self):
return self.__to_dict(
{ 'region_id': 0, 'name': 1},
self.region.top_beer_ct(10))
def styles(self):
return self.__to_dict(
{ 'style_id': 0, 'name': 1 },
self.style.top_reviewed_styles(10))
def brewers_by_region(self, region_id):
return self.__to_dict(
{ 'brewer_id': 0, 'name': 1 },
self.brewer.has_recommended_beers_by_loc(region_id, order_by="name"))
def beers_by_brewer(self, brewer_id):
return self.__to_dict(
{ 'beer_id': 1, 'name': 2 },
self.beer.has_rec_by_brewer(brewer_id))
def recommendations(self, beer_id, style_id):
return self.__to_dict(
{ 'brewer_id': 2, 'brewer_name': 3, 'beer_id': 4, 'name': 5, 'score': 6 },
self.beer.recommendations(beer_id, style_id, 10))
def beer_meta(self, beer_id):
return [self.beer.meta_dict(beer_id)]
def __init__(self):
self.region = Locations()
self.brewer = Brewers()
self.style = Styles()
self.beer = Beers()
# pass transformed data to nb for prediction
return self.style_nb_clf.predict(x_t)
if __name__ == "__main__":
from db.styles import Styles
from db.basewordcts import BaseWordFreq
from sklearn import cross_validation as c_v
from sklearn.metrics import classification_report, confusion_matrix
print 'Load baseline stop words'
baseline = BaseWordFreq()
baseline.load_all()
print 'Get reviews by style'
styles = Styles()
# get top n styles by review count
sty_ids = styles.review_counts(10).keys()
X = styles.beer_reviews_rollup(sty_ids, limit=0)
print 'Styles Retrieved: %s' % len(np.unique(X['style_id'].values))
print 'Beers Retrieved : %s' % len(np.unique(X['beer_id'].values))
print 'Total Rev Docs : %s' % len(X.index)
X_train, X_test, y_train, y_test = c_v.train_test_split(X['review'],
X['style_id'],
test_size=0.2,
random_state=0)
clf = StyleTfidfNB(max_features=None,
ngram_range=(1, 2),
def __init__(self): self.region = Locations() self.brewer = Brewers() self.style = Styles() self.beer = Beers()
return self.style_nb_clf.predict(x_t)
if __name__ == "__main__":
from db.styles import Styles
from db.basewordcts import BaseWordFreq
from sklearn import cross_validation as c_v
from sklearn.metrics import classification_report, confusion_matrix
print 'Load baseline stop words'
baseline = BaseWordFreq()
baseline.load_all()
print 'Get reviews by style'
styles = Styles()
# get top n styles by review count
sty_ids = styles.review_counts(10).keys()
X = styles.beer_reviews_rollup(sty_ids, limit=0)
print 'Styles Retrieved: %s' % len(np.unique(X['style_id'].values))
print 'Beers Retrieved : %s' % len(np.unique(X['beer_id'].values))
print 'Total Rev Docs : %s' % len(X.index)
X_train, X_test, y_train, y_test = c_v.train_test_split(
X['review'], X['style_id'], test_size=0.2, random_state=0)
clf = StyleTfidfNB(
max_features=None,
ngram_range=(1,2),
min_df=0.05,