import nltk

from nltk.corpus import stopwords

from nltk.stem import PorterStemmer

from nltk.tokenize import WordPunctTokenizer

from nltk.collocations import BigramCollocationFinder

from nltk.metrics import BigramAssocMeasures

def get_bigrams(myString):

tokenizer = WordPunctTokenizer()

tokens = tokenizer.tokenize(myString)

stemmer = PorterStemmer()

bigram_finder = BigramCollocationFinder.from_words(tokens)

bigrams = bigram_finder.nbest(BigramAssocMeasures.chi_sq, 500)

for bigram_tuple in bigrams:

x = "%s %s" % bigram_tuple

tokens.append(x)

result = [' '.join([stemmer.stem(w).lower() for w in x.split()]) for x in tokens if x.lower() not in stopwords.words('english') and len(x) > 8]

return result