100_questions_NLP_006

#!/usr/bin/env python
# -*- coding: utf-8 -*-

#Link: http://www.cl.ecei.tohoku.ac.jp/nlp100/

"""
Question 06:
06. 集合
"paraparaparadise"と"paragraph"に含まれる文字bi-gramの集合を，
それぞれ, XとYとして求め，XとYの和集合，積集合，差集合を求めよ．
さらに，'se'というbi-gramがXおよびYに含まれるかどうかを調べよ．
"""

"""***********************************************************
100_questions_NLP_005より同様のn-gramの関数を定義する
***********************************************************"""
import re

def parseSentence(sentence):
  return re.findall(r"[\w,']+|,|\.|!|:", sentence)
  
def nGram(target, n, option="letter"):
  answer = []
  if option == "letter":
    combination = len(target) - int(n) + 1
    if not combination >= 1:
      return answer
    else:
      for i in xrange(0, combination):
        answer.append(tuple(target[i:i + n]))
      return answer
  else:
    parse = parseSentence(target)
    combination = len(parse) - int(n) + 1
    if not combination >= 1:
      return answer
    else:
      for i in xrange(0, combination):
        answer.append(tuple(parse[i:i + n]))
      return answer
"""*********************************************************
link: https://gist.github.com/nutszebra/5e29c345b700498bcc5b
*********************************************************"""

X = set(nGram("paraparaparadise",2))
Y = set(nGram("paragraph", 2))
XPlusY = X.union(Y)
XIntersectY = X.intersection(Y)
XMinusY = X.difference(Y)
YMinusX = Y.difference(X)
se = set([("s","e")])

print(u"X集合: {0}".format(list(X)))
print(u"Y集合: {0}".format(list(Y)))
print(u"和集合: {0}".format(list(XPlusY)))
print(u"X-Y差集合: {0}".format(list(XMinusY)))
print(u"Y-X差集合: {0}".format(list(YMinusX)))
print(u"積集合: {0}".format(list(XIntersectY)))

if len(se.intersection(XPlusY)):
  print("seのバイグラムはX,Yに含まれる")
else:
  print("seのバイグラムはX,Yに含まれない")