自然言語100本ノック 2025 をやってみる（00-09）

str1 = 'パトカー'
str2 = 'タクシー'

def linked_alternately(str1 , str2):
    str1_len = len(str1)
    str2_len = len(str2)
    maxlen = max(str1_len , str2_len)
    return ''.join( 
        (str1[i] if str1_len > i else '') + 
        (str2[i] if str2_len > i else '')
        for i in range(maxlen))

linked_alternately(str1 , str2)

from itertools import zip_longest

def linked_alternately(str1 , str2):
    return ''.join(
        a + b for a , b in zip_longest(str1 , str2 , fillvalue=''))

linked_alternately(str1 , str2)

text = 'パタトクカシーー'
''.join(text[i] for i in range(len(text)) if i % 2 == 0)

text = 'パタトクカシーー'
''.join(c for i , c in enumerate(text) if i % 2 == 0)

text = 'パタトクカシーー'
text[::2]

text = "stressed"
text[::-1]

text = "Now I need a drink, alcoholic of course, after the heavy lectures involving quantum mechanics."

omit_symbol_list = [',' , '.']     # 除外したい記号を定義
text_without_symbol = text      # 記号除外後の文字列
# 文字列除外
for omit_symbol in omit_symbol_list:
    text_without_symbol = text_without_symbol.replace(omit_symbol , '')
    
[len(x) for x in text_without_symbol.split(' ')]

text = "Now I need a drink, alcoholic of course, after the heavy lectures involving quantum mechanics."
omit_symbols = ',.'

omit_table = str.maketrans('' , '' , omit_symbols)
text_without_symbol = text.translate(omit_table)

[len(x) for x in text_without_symbol.split(' ')]

text = "Hi He Lied Because Boron Could Not Oxidize Fluorine. New Nations Might Also Sign Peace Security Clause. Arthur King Can."
one_char_word_num = [1, 5, 6, 7, 8, 9, 15, 16, 19]

word_list = text.split(" ")
element_symbol_map = {}

for i , word in enumerate(word_list):
    if i + 1 in one_char_word_num:
        element_symbol_map[i + 1] = word[:1]
    else:
        element_symbol_map[i + 1] = word[:2]

print(element_symbol_map)        

text = "Hi He Lied Because Boron Could Not Oxidize Fluorine. New Nations Might Also Sign Peace Security Clause. Arthur King Can."
one_char_word_num = [1, 5, 6, 7, 8, 9, 15, 16, 19]

element_symbol_map = {
    i + 1 : word[:1] if i + 1 in one_char_word_num else word[:2] for i , word in enumerate(word_list)
}

print(element_symbol_map)

text = "I am an NLPer"

def ngram(n , text , is_char_ngram=False):
    if is_char_ngram:
        return [ text[i:i+n] for i ,_ in enumerate(text) ]
    else:
        word_list = text.split(" ")
        return [ word_list[i:i+n] for i ,_ in enumerate(word_list) ]

# 文字tri-gram
print(ngram(3, text , is_char_ngram=True))
# 単語bi-gram
print(ngram(2, text))

['I a', ' am', 'am ', 'm a', ' an', 'an ', 'n N', ' NL', 'NLP', 'LPe', 'Per', 'er', 'r']
[['I', 'am'], ['am', 'an'], ['an', 'NLPer'], ['NLPer']]

['I a', ' am', 'am ', 'm a', ' an', 'an ', 'n N', ' NL', 'NLP', 'LPe', 'Per', 'er', 'r']
[['I', 'am'], ['am', 'an'], ['an', 'NLPer'], ['NLPer']]

['I a', ' am', 'am ', 'm a', ' an', 'an ', 'n N', ' NL', 'NLP', 'LPe', 'Per']
[['I', 'am'], ['am', 'an'], ['an', 'NLPer']]

text = "I am an NLPer"

def ngram(n , text , is_char_ngram=False):
    if is_char_ngram:
        return [ text[i:i+n] for i in range(len(text) - n + 1) ]
    else:
        word_list = text.split(" ")
        return [ tuple(word_list[i:i+n]) for i in range(len(word_list) - n + 1) ]

# 文字tri-gram
print(ngram(3, text , is_char_ngram=True))
# 単語bi-gram
print(ngram(2, text))

['I a', ' am', 'am ', 'm a', ' an', 'an ', 'n N', ' NL', 'NLP', 'LPe', 'Per']
[('I', 'am'), ('am', 'an'), ('an', 'NLPer')]

# n-gramを求める関数を定義
def ngram(n , text):
    return set([ text[i:i+n] for i in range(len(text) - n + 1) ])

# それぞれの文字bi-gramをX,Yとして取得
X = ngram(2 , "paraparaparadise")
Y = ngram(2 , "paragraph")

# 和集合
print(X | Y)
# 積集合
print(X & Y)
# 差集合
print(X - Y)

# "se"というbi-gramが含まれるか
print("X:" , "se" in X)
print("Y:" , "se" in Y)

{'pa', 'se', 'ra', 'di', 'ar', 'ag', 'gr', 'ad', 'ph', 'ap', 'is'}
{'pa', 'ap', 'ar', 'ra'}
{'se', 'ad', 'is', 'di'}
X: True
Y: False

def ngram(n , text):
    return set([ text[i:i+n] for i in range(len(text) - n + 1) ])

def ngram(n , text):
    return { text[i:i+n] for i in range(len(text) - n + 1) }

# これはジェネレータ式！
(el for el in range(1,5))
# タプルにするならこう！
tuple(el for el in range(1,5))

def gen_str(x , y , z):
    return "{}時の{}は{}".format(x , y , z)
print(gen_str(x=12, y="気温", z=22.4))

def gen_str(x , y , z):
    return f"{x}時の{y}は{z}"
print(gen_str(x=12, y="気温", z=22.4))

# 暗号化
def cipher(text):
    return "".join([chr(219 - ord(charcter)) if charcter.islower() else charcter
        for _ , charcter in enumerate(text)])

print(cipher("Hello! 私の名前はMikeです。"))
print(cipher(cipher("Hello! 私の名前はMikeです。")))

Hvool! 私の名前はMrpvです。
Hello! 私の名前はMikeです。

import random

def typo_word_generator(word):
    # 単語の中間部分
    word_middle_part = []
    # 単語の中間部分のインデックス値の集合。割り当てたらこの集合から引いていく
    unassigned_char_index = { i for i in range(1 , len(word) -1)}
    for _ in range(len(word) -2):
        while True:
            index = random.randint(1 , (len(word) -2))
            if index in unassigned_char_index:
                word_middle_part.append(word[index])
                unassigned_char_index.remove(index)
                break
    return word[:1] + "".join(word_middle_part) + word[-1:]

def converter(text):
    after_conversion = []
    for i , word in enumerate(text.split(" ")):
        if len(word) > 4:
            after_conversion.append(typo_word_generator(word))
        else:
            after_conversion.append(word)
    return " ".join(after_conversion)

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

"I cud'nolt bvieele that I cuold atclauly unnetasrdd what I was raeidng : the ponmeenhal poewr of the hmuan mind ."

import random
word = "abcde"
char_list = list(word)
random.shuffle(char_list)
print("".join(char_list))

import random

def typo_word_generator(word):
    middle = list(word[1:-1])
    random.shuffle(middle)
    return word[:1] + "".join(middle) + word[-1:]

def converter(text):
    after_conversion = []
    for i , word in enumerate(text.split(" ")):
        if len(word) > 4:
            after_conversion.append(typo_word_generator(word))
        else:
            after_conversion.append(word)
    return " ".join(after_conversion)

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