def keyword_title(title_corpus):
## here we need NLTK stopwords and punkt, will storaged in /usr/share/nltk_data
# uncomment to download
#nltk.download('stopwords')
nltk.download('punkt')
title_dict = {}
for t in title_corpus:
key = (t[3], t[4])
if key in title_dict:
title_dict[key].append(t[1])
else:
title_dict[key] = []
title_dict[key].append(t[1])
# extract keywords with year span
title_years = {}
for k, v in title_dict.items():
key = (k[0], ) # year index
if key in title_years.keys():
title_years[key].append(v)
else:
title_years[key] = []
title_years[key].append(v)
for k, v in title_years.items():
r = Rake()
vs = [item.rstrip('\n') for sublist in v for item in sublist]
# a list of strings where each string is a sentence
#r.extract_keywords_from_sentences(vs)
#print('The keywords for year:{}'.format(str(k[0])))
#print(r.get_ranked_phrases_with_scores()[0:10])
title_txt = '''.'''.join(vs)
title_txt.strip('\n')
r.extract_keywords_from_text(title_txt)
print('The keywords for year:{}'.format(str(k[0])))
# to get keyword phrases ranked from hightest to lowest with scores
print(r.get_ranked_phrases_with_scores()[0:10])
