言語処理100本ノック解いてみた（4,5）毎朝やってますわ

問題４

import re
string = "Hi He Lied Because Boron Could Not Oxidize Fluorine. New Nations Might Also Sign Peace Security Clause. Arthur King Can."
re.sub('[-=+,#/\?:^.@*\"※~ㆍ!』‘|\(\)\[\]`\'…》\”\“\’·]',"",string)
strarr = string.split(" ")
arr = [1, 5, 6, 7, 8, 9, 15, 16, 19]
dict_res = {}
for i in arr:
  dict_res[i] = strarr[i-1][0]
for i in range(len(strarr)):
  if i+1 not in arr:
    dict_res[i+1] = strarr[i][:2]
print(dict_res)
"""　実行結果：{'Al': 15,
 'Ar': 18,
 'B': 1,
 'Be': 11,
 'C': 2,
 'Cl': 17,
 'F': 5,
 'H': 0,
 'He': 9,
 'K': 8,
 'Li': 10,
 'Mi': 14,
 'N': 3,
 'Na': 13,
 'Ne': 12,
 'O': 4,
 'P': 6,
 'S': 7,
 'Si': 16}"""

見た目悪いからordereddict　使おう。

import collections
collections.OrderedDict(sorted(dict_res.items()))

"""実行結果：OrderedDict([(1, 'H'),
             (2, 'He'),
             (3, 'Li'),
             (4, 'Be'),
             (5, 'B'),
             (6, 'C'),
             (7, 'N'),
             (8, 'O'),
             (9, 'F'),
             (10, 'Ne'),
             (11, 'Na'),
             (12, 'Mi'),
             (13, 'Al'),
             (14, 'Si'),
             (15, 'P'),
             (16, 'S'),
             (17, 'Cl'),
             (18, 'Ar'),
             (19, 'K'),
             (20, 'Ca')])"""

問題５

input_str = "I am an NLPer"
def bigram(string):
  alphabet = [string.replace(" ","")[i:i+2] for i in range(len(string)-1)]
  word = [string.split()[i:i+2] for i in range(len(string.split())-1)]
  return alphabet, word
a,w = bigram(input_str)
print(a,w)
#実行結果：['Ia', 'am', 'ma', 'an', 'nN', 'NL', 'LP', 'Pe', 'er', 'r', '', ''] [['I', 'am'], ['am', 'an'], ['an', 'NLPer']]