quick bigram gist; You can use the dictVectorizer and the Tfidf transformer to generate your features

bigram_gist.py

from collections import Counter
import re
from sklearn.feature_extraction import DictVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.feature_extraction.text import CountVectorizer
from itertools import islice, tee
from nltk.corpus import stopwords

def tokenize(sentence):
    words = re.findall("[a-zA-Z]+", sentence)
    bigram = []

    for gram in generate_ngrams(words, 2):
        bigram.append('{0} {1}'.format(gram[0], gram[1]))

    # take out stop words
    words = [w for w in words if w not in stopwords.words("english")]
    words.extend(bigram)
    
    return words

def generate_ngrams(lst, n):
    ilst = lst
    while True:
        a, b = tee(ilst)
        l = tuple(islice(a, n))
        if len(l) == n:
            yield l
            next(b)
            ilst = b
        else:
            break
          
print(tokenize('Hello there good guy. I will kill you'))

Sentiment analysis