言語処理100本ノック http://www.cl.ecei.tohoku.ac.jp/nlp100/ 第1章: 準備運動

chap1.py

# -*- coding: utf-8 -*- 


def chap1_0():
  targ = "stressed"
  print targ[::-1]

def chap1_1():
  targ = u"パタトクカシーー"
  print targ[0::2]

def chap1_2():
  str1 = u"パトカー"
  str2 = u"タクシー"
  str3 = u""

  for a, b in zip(str1, str2):
    str3 = str3 + a + b

  print str3

def chap1_3():
  targ = "Now I need a drink, alcoholic of course, after the heavy lectures involving quantum mechanics."
  targ = targ.replace(",","")
  targ = targ.replace(".","")
  ls = []
  for s in targ.split():
    ls.append(len(s))

  print ls

def chap1_4():
  targ = "Hi He Lied Because Boron Could Not Oxidize Fluorine. New Nations Might Also Sign Peace Security Clause. Arthur King Can."
  targ = targ.replace(",", "")
  targ = targ.replace(".", "")
  mp = {}
  i = 0
  for s in targ.split():
    i += 1
    if i in [1,5,6,7,8,9,15,16,19]:
      mp[i] = s[0]
    else:
      mp[i] = s[0:2]

  for k, v in mp.items():
      print k, v

def chap1_5():
  sentence = "I am an NLPer"
  
  #Charactor as bi-gram
  charGram = [sentence[i:i+2] for i in range(len(sentence)-1)]

  #Word as bi-gram
  words = [word.strip(".,") for word in sentence.split()]
  wordGram = ["-".join(words[i:i+2]) for i in range(len(words)-1)]

  print charGram
  print wordGram

def chap1_6():
  word1 = "paraparaparadise"
  word2 = "paragraph"
  setX = set([word1[i:i+2] for i in range(len(word1)-1)])
  setY = set([word2[i:i+2] for i in range(len(word2)-1)])

  print "setX", setX
  print "setY", setY
  
  print "和集合", setX|setY
  print "差集合", setX - setY
  print "積集合", setX&setY

  if "se" in setX:
    print "'se' contains setX"
  else:
    print "'se' does not contain setX"

  if "se" in setY:
    print "'se' contains setY"
  else:
    print "'se' does not contain setY"

def chap1_7():
  ret = makeStr("12", "気温", "22.4")
  print ret

def makeStr(x, y, z):
  return "{0}の{1}は{2}".format(x, y, z)


def chap1_8():
  print ciph("hello world")
  print ciph("Hello World")
  print ciph("HELLO WORLD")
  print ciph(ciph("hello world"))

import re
def ciph(word):
  return "".join(chr(219-ord(c)) if re.match(r"[a-z]", c) else c for c in word)

def chap1_9():
  targ = "I couldn't believe that I could actually understand what I was reading : the phenomenal power of the human mind ."
  print " ".join(typo(w) if len(w) > 4 else w for w in targ.split())
  typo(targ)

from random import shuffle
def typo(word):
  targ = list(word[1:-1])
  shuffle(targ)
  return word[0] + ''.join(targ) + word[-1]


chap1_0()
chap1_1()
chap1_2()
chap1_3()
chap1_4()
chap1_5()
chap1_6()
chap1_7()
chap1_8()
chap1_9()