Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- def add_to_corpus_index(corpus_index,word,next_word):
- for el in corpus_index:
- if el[0]==word:
- el[1].append(next_word)
- return
- corpus_index.append([word,[next_word]])
- def add_all_to_corpus_index(corpus_index,corpus):
- splitted_text=corpus.split()
- for i in range(len(splitted_text)-1):
- current_word,next_word=splitted_text[i],splitted_text[i+1]
- add_to_corpus_index(corpus_index,current_word,next_word)
- corpus="Today is Sunday. I stay at home and keep coding. Today is Monday. I stay at office and keep cleaning. Today I stay awake."
- corpus_index=[]
- add_all_to_corpus_index(corpus_index, corpus)
- print(corpus_index)
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement