言語処理100本ノック 第1章 解いてみた

はじめに

• YouTubeでPythonの基礎文法の動画見たことあるくらいのレベル
• 開発経験はほぼありません。業務でJavaを3週間程度触りました
• Google Colaboratoryを使用しています
• 誤りや変なコーディングあればご指摘頂けると幸いです
• 第2章以降も頑張りたいと思っています。

00. 文字列の逆順

str = "stressed"
print(str[::-1])

01. 「パタトクカシーー」

str = "パタトクカシー"
print(str[::2])

02. 「パトカー」+「タクシー」=「パタトクカシーー」

str1 = "パトカー"
str2 = "タクシー"
for c1, c2 in zip(str1, str2):
  print(c1 + c2, end='')

03. 円周率

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

04. 元素記号

s = "Hi He Lied Because Boron Could Not Oxidize Fluorine. New Nations Might Also Sign Peace Security Clause. Arthur King Can."
word_list = s.replace(".", "").split(" ")
num_list = [1, 5, 6, 7, 8, 9, 15, 16, 19]
result = {}
for index, word in enumerate(word_list):
  if (index + 1) in num_list:
    result[word[:1]] = index + 1
  else:
    result[word[:2]] = index + 1
print(result)

05. n-gram

def make_n_gram(n, text_list):
  n_gram = []
  for i in range(len(text_list) - (n - 1)):
    n_gram.append(text_list[i:i+n])
  return n_gram

text = "I am an NLPer"
c_bi_gram = make_n_gram(2, list((text.replace(" ", ""))))
w_bi_gram = make_n_gram(2, text.split(" "))
print(c_bi_gram)
print(w_bi_gram)

06. 集合

text1 = "paraparaparadise"
text2 = "paragraph"
bi_gram1 = make_n_gram(2, list(text1))
bi_gram2 = make_n_gram(2, list(text2))
# listはset(list)でsetに変換できるという記事を読んだができなかったので、list→tuple→setに変換
bi_gram1 = [ tuple(item) for item in bi_gram1]
bi_gram2 = [ tuple(item) for item in bi_gram2]
X = set(bi_gram1)
Y = set(bi_gram2)
# 和集合
print(X | Y)
# 積集合
print(X & Y)
# 差集合
print(X - Y)
print("se is ", "" if ("s", "e") in X else "not ", "in X", sep="")
print("se is ", "" if ("s", "e") in Y else "not ", "in Y", sep="")

07. テンプレートによる文生成

def template(x, y, z):
  return "{}時の{}は{}".format(x, y, z)

print(template(12, "気温", 22.4))

08. 暗号文

def cipher(text):
  result = []
  for c in text:
    if c.islower():
      result.append(chr(219 - ord(c)))
    else:
      result.append(c)
  return "".join(result)

message = "Apple Banana Chocolate"
encoded = cipher(message)
decoded = cipher(encoded)
print("暗号化：{}".format(encoded))
print("複合化：{}".format(decoded))

09. Typoglycemia

import random

def typoglycemia(text):
  l = []
  for w in text.split(" "):
    if len(w) <= 4:
      l.append(w)
    else:
      tmp = list(w[1:-1])
      l.append(w[0:1] + "".join(random.sample(tmp, len(tmp))) + w[-1])
  return " ".join(l)

  text = "I couldn't believe that I could actually understand what I was reading : the phenomenal power of the human mind ."
print(typoglycemia(text))