言語処理100本ノック

"".join([i+j for i,j in zip(str1,str2)])

re.sub(`[,\.]`,``,str) # sub(a,b,str) でstrからaをbに置き換える

import re

str = 'Hi He Lied Because Boron Could Not Oxidize Fluorine. New Nations Might Also Sign Peace Security Clause. Arthur King Can.'
str = re.sub("[,\.]", "", str)
lis = str.split()
one_ch = [1, 5, 6, 7, 8, 9, 15, 16, 19]
ans = {}
idx = 0
for i, word in enumerate(lis):#enumerate でindexとenumerate型の要素を順番に取得する
    if idx < len(one_ch) and i+1 == one_ch[idx]:
        idx += 1
        ans[word[:1]] = i+1
    else:
        ans[word[:2]] = i+1
print(ans)

def ngram(n, iter):
    res = []
    for i in range(len(iter)-n+1):
        tmp = []
        for j in range(n):
            tmp.append(iter[j+i])
        res.append(tuple(tmp))
    return res


str = 'I am an NLPer'
chars_bi_gram = ngram(2, str)
words_bi_gram = ngram(2, str.split())
print(chars_bi_gram)
print(words_bi_gram)

def ngram_(n, lst):
    # ex.
    # [str[i:] for i in range(2)] -> ['I am an NLPer', ' am an NLPer']
    # zip(*[str[i:] for i in range(2)]) -> zip('I am an NLPer', ' am an NLPer')
    return list(zip(*[lst[i:] for i in range(n)]))

str1 = 'paraparaparadise'
str2 = 'paragraph'


def ngram(n, iter):
    res = []
    for i in range(len(iter)-n+1):
        tmp = []
        for j in range(n):
            tmp.append(iter[j+i])
        res.append(tuple(tmp))
    return res


x = set(ngram(2, str1))
y = set(ngram(2, str2))
union = x | y
intersection = x & y
difference = x - y

print("x:", x)
print("y:", y)
print("和集合：", union)
print("積集合：", intersection)
print("差集合：", difference)
print("xにseが含まれるか：", {("s", "e")} <= x)
print("yにseが含まれるか：", {("s", "e")} <= y)

def generate_template(a, b, c):
    print(f'{a}時のとき{b}は{c}')


generate_template(12, "気温", 22.4)

def cipher(s):
    res = ""
    for c in s:
        if ord(c) < 123 and ord(c) > 96:
            res += chr(219-ord(c))
        else:
            res += c
    return res


message = 'the quick brown fox jumps over the lazy dog'
message = cipher(message)
print('暗号化:', message)
message = cipher(message)
print('復号化:', message)

from random import sample


def word_shuffle(str_):
    word_list = str_.split()
    res = ""
    for i in word_list:
        if len(i) <= 4:
            res += i + " "
        else:
            res += i[0] + "".join(sample(i[1:-1], len(i[1:-1]))) + i[-1] + " "
    return res[:-1]


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

tmp = df.reset_indez(drop=False)
df_cut = pd.qcut(tmp.index,N,labels=[i for i in range(N)])
df_cut = pd.concat([df,pd.Series(df_cut,name="sep")],axis=1)

import re

pattern = r'^(.*\[\[Category:.*\]\].*)$'
result = '\n'.join(re.findall(pattern, text_uk, re.MULTILINE))
print(result)

pattern = r'^.*\[\[Category:(.*?)(?:\|.*)?\]\].*$'
result = '\n'.join(re.findall(pattern, text_uk, re.MULTILINE))
print(result)