def main():
'''
INPUT: None
OUTPUT: Recommendations sorted in order of relevance
Uses the TextParser and Recommender classes to generate resource recommendations given a user's Quora data
'''
read = TextParser()
read.assemble_df()
pickle.dump(read.df, open("data/master_df.pkl", "wb"))
quora_user = open('data/quora_data.pkl')
quora = pickle.load(quora_user)
filtered = read.preprocess_quora(quora)
clean_quora = read.clean_up(filtered)
pickle.dump(clean_quora, open("data/clean_quora.pkl", "wb"))
# Make recommendations
rec = Recommender()
test = rec.vectorize()
top_ten_ind = rec.recommend()
recs = read.df.ix[top_ten_ind]
recs = recs.reset_index()
recs['img_link'] = map(get_image, recs['title'])
recs.loc[recs['type']=='course', 'img_link'] = 'http://www.michaellenox.com/wp-content/uploads/2014/07/coursera_square_logo.jpg'
pickle.dump(recs[0:5], open("data/recs.pkl", "wb"))
print "These are your recommendations: \n"
print recs[['title', 'type', 'img_link']]
return recs[['title', 'type', 'img_link']]
def index_documents(options, args):
for arg in args:
mime_type = TikaParser.get_mime_type(arg)
(text, meta) = TikaParser.parse(arg)
if not text.keys():
if 'text/plain' in meta['content_type']:
(text, txt_meta) = TextParser.parse(arg)
meta.update(txt_meta)
elif 'vnd.oasis.opendocument' in meta['content_type']:
(text, od_meta) = OpenDocumentParser.parse(arg)
meta.update(od_meta)
(mpty, fs_meta) = FsMetaParser.parse(arg)
meta.update(fs_meta)
meta['content_type'] = mime_type
for field in meta:
print("{}: {}".format(field, meta.get(field)))
# if meta.get('content_type', '') == 'application/pdf':
# es_index(text, meta, doctype='pdf', options=options)
print(text)
exit()
def recommend():
user_data = str(request.form['user_input'].encode('utf-8'))
# --- Drive to the given URL, scrape and generate recs -- #
scraped = profile_crawl(user_data)
quora = scraped['text']
# Read and clean Quora dump recommendations
read = TextParser()
read.df = master_df
filtered = read.preprocess_quora(quora)
clean_quora = read.clean_up(filtered)
pickle.dump(clean_quora, open("data/clean_quora.pkl", "wb"))
rec = Recommender()
test = rec.vectorize()
top_ten_ind = rec.recommend()
recs = read.df.ix[top_ten_ind]
recs = recs.reset_index()
recs['img_link'] = map(get_image, recs['title'])
recs.loc[recs['type']=='course', 'img_link'] = 'http://www.michaellenox.com/wp-content/uploads/2014/07/coursera_square_logo.jpg'
recs = recs[0:20] # Get the top twenty recommendations
return render_template('testing.html', data = recs[['title', 'img_link']].values)
def get_terms(self, query_text):
query_terms = TextParser.parse(query_text)
query_term_ids = [self.term_store.get_id_for_term(term) for term in
query_terms]
return query_term_ids