생능출판사 (가칭)"데이터과학 파이썬" 코드 9장¶
9.2 문자열에서 개별 문자들을 뽑아보자¶
In [1]:
s = 'Monty Python'
s[0]
Out[1]:
In [2]:
s[6:10]
Out[2]:
In [3]:
s[-12:-7]
Out[3]:
In [4]:
t = s[:-2]
t
Out[4]:
In [5]:
t = s[-2:]
t
Out[5]:
In [6]:
s[:-2] + s[-2:]
Out[6]:
9.3 문자열을 분해해 보자¶
In [7]:
s = 'Welcome to Python'
s.split()
Out[7]:
In [8]:
s = '2021.8.15'
s.split('.')
Out[8]:
In [9]:
s = 'Hello, World!'
s.split(",")
Out[9]:
In [10]:
s = 'Hello, World!'
s.split(', ')
Out[10]:
In [11]:
s = 'Welcome, to, Python, and , bla, bla '
[x.strip() for x in s.split(',')]
Out[11]:
In [12]:
list('Hello, World!')
Out[12]:
9.4 문자열을 이어붙이는 것은 파이썬한테는 쉬운 일¶
In [13]:
','.join(['apple', 'grape', 'banana'])
Out[13]:
In [14]:
'-'.join('010.1234.5678'.split('.')) # .À¸·Î ±¸ºÐµÈ ÀüȹøÈ£¸¦ ÇÏÀÌÇÂÀ¸·Î °íÄ¡±â
Out[14]:
In [15]:
'010.1234.5678'.replace('.','-')
Out[15]:
In [16]:
s = 'hello world'
clist = list(s)
clist
Out[16]:
In [17]:
''.join(clist)
Out[17]:
In [18]:
a_string = 'Actions \n\t speak louder than words'
a_string
Out[18]:
In [19]:
print(a_string)
In [20]:
word_list = a_string.split()
word_list
Out[20]:
In [21]:
refined_string = " ".join(word_list) # a_string¿¡ ÀÖ´Â ÁٹٲÞ, Åǹ®ÀÚ°¡ ¾ø¾îÁø´Ù
print(refined_string)
9.5 대문자와 소문자 변환, 그리고 문자열 삭제¶
In [22]:
s = 'Hello, World!'
s.lower()
Out[22]:
In [23]:
s.upper()
Out[23]:
In [24]:
s = " Hello, World! "
s.strip()
Out[24]:
In [25]:
s.lstrip()
Out[25]:
In [26]:
s.rstrip()
Out[26]:
In [27]:
s = "########this is an example#####"
s.strip('#')
Out[27]:
In [28]:
s = "########this is an example#####"
s.lstrip('#')
Out[28]:
In [29]:
s.rstrip('#')
Out[29]:
In [30]:
s.strip('#').capitalize()
Out[30]:
In [31]:
s = "www.booksr.co.kr"
s.find(".kr")
Out[31]:
In [32]:
s.find("x") # 'x' ¹®ÀÚ¿ÀÌ ¾øÀ» °æ¿ì -1À» ¹ÝȯÇÔ
Out[32]:
9.6 다양한 문자열 처리 함수와 string 모듈¶
In [33]:
s = 'www.booksr.co.kr' # »ý´ÉÃâÆÇ»çÀÇ È¨ÆäÀÌÁö
s.count('.') # . ÀÌ ¸î¹ø ³ªÅ¸³ª´Â°¡¸¦ ¾Ë·ÁÁØ´Ù
Out[33]:
In [34]:
s = 'www.booksr.co.kr'
ord(max(s)) # s¹®ÀÚ¿ ³»¿¡¼ À¯´ÏÄÚµå °ªÀÌ °¡Àå Å« °ªÀÇ À¯´ÏÄÚµå °ªÀ» ¹Ýȯ
Out[34]:
In [35]:
ord(min(s)) # s¹®ÀÚ¿ ³»¿¡¼ À¯´ÏÄÚµå °ªÀÌ °¡Àå ÀÛÀº °ªÀÇ À¯´ÏÄÚµå °ªÀ» ¹Ýȯ
Out[35]:
In [36]:
chr(119), chr(46) # À¯´ÏÄÚµå °ª 119, 46¿¡ ÇØ´çÇÏ´Â ¹®ÀÚ¸¦ ¹Ýȯ
Out[36]:
In [37]:
import string
src_str = string.ascii_uppercase
print('src_str =', src_str)
In [38]:
src_str = string.ascii_uppercase
dst_str = src_str[1:] + src_str[:1]
print('dst_str =', dst_str)
In [39]:
n = src_str.index('A')
print('src_strÀÇ A À妽º =', n)
print('src_strÀÇ A À§Ä¡¿¡ ÀÖ´Â dst_strÀÇ ¹®ÀÚ =', dst_str[n])
LAB 9-1 : 카이사르 암호를 만들어 보자¶
In [40]:
import string
src_str = string.ascii_uppercase
dst_str = src_str[3:] + src_str[:3]
def ciper(a): # ¾ÏÈ£È Äڵ带 ¸¸µå´Â ÇÔ¼Ò
idx = src_str.index(a)
return dst_str[idx]
src = input('¹®ÀåÀ» ÀÔ·ÂÇϽÿÀ: ')
print('¾ÏÈ£ÈµÈ ¹®Àå : ', end='')
for ch in src:
if ch in src_str:
print(ciper(ch), end='')
else:
print(ch, end='')
print()
LAB 9-2 : 트위터 메시지 처리의 단어 추출¶
In [41]:
t = "There's a reason some people are working to make it harder to vote, especially for people of color. It¡¯s because when we show up, things change."
length = len(t.split(" "))
print('word count:', length)
LAB 9-3 : 트위터 메시지의 대문자, 소문자 변환¶
In [42]:
t = "It's Not The Right Time To Conduct Exams. MY DEMAND IN BOLD AND CAPITAL. NO EXAMS IN COVID!!!"
t
Out[42]:
In [43]:
t = "It's Not The Right Time To Conduct Exams. MY DEMAND IN BOLD AND CAPITAL. NO EXAMS IN COVID!!!"
l = t.lower()
l
Out[43]:
도전문제 9.3¶
- Æ®À µ¥ÀÌÅÍ¿¡¼ ´ë¹®ÀÚ³ª ´À³¦Ç¥°¡ ¸¹ÀÌ ³ªÅ¸³ª´Â °ÍÀº ±Û¾²´Â »ç¶÷ÀÇ °¨Á¤ÀÌ ÈïºÐÇϰųª ºÐ³ëÇÑ »óÅÂÀÓÀ» ³ªÅ¸³»´Â °æ¿ì°¡ ¸¹´Ù. ÁÖ¾îÁø ¿øõ Æ®À µ¥ÀÌÅÍ¿¡¼ ´ë¹®ÀÚ¿Í ´À³¦Ç¥°¡ ¸î ¹ø »ç¿ëµÇ¾ú´ÂÁö °è»êÇÏ´Â Äڵ带 ÀÛ¼ºÇØ º¸¶ó. ´À³¦Ç¥°¡ ¸î °³ÀÎÁö Çì¾Æ¸®´Â °ÍÀº count() ÇÔ¼ö¸¦ »ç¿ëÇÏ¸é ½±°Ô ÇÒ ¼ö ÀÖ´Ù. ´ë¹®ÀÚ´Â ¾î¶»°Ô ¼¿ ¼ö ÀÖÀ»±î? ¿ø Æ®ÀÀ» list()¸¦ ÀÌ¿ëÇÏ¿© Çϳª ÇϳªÀÇ ¹®ÀÚ·Î ºÐ¸®ÇÏ¿© ¸®½ºÆ®¸¦ ¸¸µé ¼ö ÀÖ´Ù. ±×¸®°í ÀÌ ¸®½ºÆ®ÀÇ °¢ Ç׸ñ ¹®ÀÚ°¡ ch¶ó°í ÇÒ ¶§, ch.isupper()¸¦ È£ÃâÇÏ¸é ´ë¹®ÀÚÀÎ °æ¿ì True°¡ ¹ÝȯµÈ´Ù.
In [44]:
t_lst = list(t)
print('´À³¦Ç¥ °¹¼ö :', t_lst.count('!'))
In [45]:
count = 0
for ch in t_lst:
if ch.isupper() == True:
count += 1
print('´ë¹®ÀÚ °¹¼ö :', count)
LAB 9-4 : 1회용 패스워드를 만들어 보자¶
In [46]:
import random
n_digits = int(input('¸î ÀÚ¸®ÀÇ ºñ¹Ð¹øÈ£¸¦ ¿øÇϽʴϱî? '))
otp = ''
for i in range(n_digits) :
otp += str(random.randrange(0, 10))
print(otp)
In [47]:
!pip install wordcloud wikipedia
In [48]:
import wikipedia
# Specify the title of the Wikipedia page
wiki = wikipedia.page('Artificial intelligence')
# Extract the plain text content of the page
text = wiki.content
In [49]:
from wordcloud import WordCloud
# Generate word cloud
wordcloud = WordCloud(width = 2000, height = 1500).generate(text)
In [50]:
import matplotlib.pyplot as plt
plt.figure(figsize=(40, 30))
# Display image
plt.imshow(wordcloud)
plt.show()
In [51]:
import wikipedia
import matplotlib.pyplot as plt
from wordcloud import WordCloud, STOPWORDS
# Specify the title of the Wikipedia page
wiki = wikipedia.page('Artificial intelligence')
# Extract the plain text content of the page
text = wiki.content
# Generate word cloud
s_words = STOPWORDS.union( {'one', 'using', 'first', 'two', 'make', 'use'} )
wordcloud = WordCloud(width = 2000, height = 1500,
stopwords = s_words).generate(text)
plt.figure(figsize=(40, 30))
# Display image
plt.imshow(wordcloud)
plt.show()
도전문제 9.4¶
- ÀÌÁ¦ Python°ú Machine LearningÀ» ÀÌ¿ëÇÏ¿© ¿öµå Ŭ¶ó¿ìµå¸¦ °¢°¢ ¸¸µé¾î º¸¾Æ¶ó.
In [52]:
import wikipedia
import matplotlib.pyplot as plt
from wordcloud import WordCloud, STOPWORDS
# Specify the title of the Wikipedia page
wiki = wikipedia.page('Python')
# Extract the plain text content of the page
text = wiki.content
# Generate word cloud
s_words = STOPWORDS.union( {'one', 'using', 'first', 'two', 'make', 'use'} )
wordcloud = WordCloud(width = 2000, height = 1500,
stopwords = s_words).generate(text)
plt.figure(figsize=(40, 30))
# Display image
plt.imshow(wordcloud)
plt.show()
9.9 규칙을 이용해서 문자를 추출하는 멋진 정규식 표현법¶
In [55]:
import re
txt1 = "Life is too short, you need python."
txt2 = "The best moments of my life."
print(re.search('Life', txt1)) # ¹®Àå ¾È¿¡ Life°¡ Àִ°¡ °Ë»çÇÔ
In [56]:
print(re.search('Life', txt2)) # ¹®Àå ¾È¿¡ Life°¡ Àִ°¡ °Ë»çÇÔ
In [57]:
match = re.search('Life', txt1)
match.group()
Out[57]:
In [58]:
match.start()
Out[58]:
In [59]:
match.end()
Out[59]:
In [60]:
match.span()
Out[60]:
In [61]:
print(re.search('Life|life', txt2)) # ¹®Àå ¾È¿¡ Life°¡ Àִ°¡ °Ë»çÇÔ
In [62]:
print(re.search('[Ll]ife', txt2)) # ¹®Àå ¾È¿¡ Life ȤÀº life°¡ Àִ°¡ °Ë»çÇÔ
In [63]:
txt1 = "Life is too short, you need python."
txt2 = "The best moments of my life."
txt3 = "My Life My Choice."
print(re.search('^Life', txt1)) # Á¦ÀÏ Ã¹ ´Ü¾î·Î Life°¡ Àִ°¡ °Ë»çÇÔ
In [64]:
print(re.search('^Life', txt2)) # Á¦ÀÏ Ã¹ ´Ü¾î·Î Life°¡ Àִ°¡ °Ë»çÇÔ
In [65]:
print(re.search('^Life', txt3)) # Á¦ÀÏ Ã¹ ´Ü¾î·Î Life°¡ Àִ°¡ °Ë»çÇÔ
In [66]:
print(re.search('Life', txt3)) # Á¦ÀÏ Ã¹ ´Ü¾î·Î Life°¡ Àִ°¡ °Ë»çÇÔ
In [67]:
re.search('My', txt3)
Out[67]:
In [68]:
txt3 = "Life is like a box of chocolates."
txt4 = "My Life My Choice."
In [69]:
print(re.search('^Life', txt1)) # Á¦ÀÏ Ã¹ ´Ü¾î·Î Life°¡ Àִ°¡ °Ë»çÇÔ
print(re.search('^Life', txt2)) # Á¦ÀÏ Ã¹ ´Ü¾î·Î Life°¡ Àִ°¡ °Ë»çÇÔ
print(re.search('^Life', txt3)) # Á¦ÀÏ Ã¹ ´Ü¾î·Î Life°¡ Àִ°¡ °Ë»çÇÔ
print(re.search('^Life', txt4)) # Á¦ÀÏ Ã¹ ´Ü¾î·Î Life°¡ Àִ°¡ °Ë»çÇÔ
In [70]:
print(re.search('Life|life', txt1)) # Life ȤÀº life°¡ Æ÷ÇԵǾî Àִ°¡ °Ë»çÇÔ
print(re.search('Life|life', txt2)) # Life ȤÀº life°¡ Æ÷ÇԵǾî Àִ°¡ °Ë»çÇÔ
In [71]:
print(re.search('[Ll]ife', txt1)) # Life ȤÀº life°¡ Æ÷ÇԵǾî Àִ°¡ °Ë»çÇÔ
print(re.search('[Ll]ife', txt2)) # Life ȤÀº life°¡ Æ÷ÇԵǾî Àִ°¡ °Ë»çÇÔ
In [72]:
>>> re.findall('My', txt4)
Out[72]:
In [73]:
import re
txt1 = 'Who are you to judge the life I live'
txt2 = 'The best moments of my life'
print(re.search('life$', txt1)) # Life ȤÀº life°¡ Æ÷ÇԵǾî Àִ°¡ °Ë»çÇÔ
In [74]:
print(re.search('life$', txt2)) # Life ȤÀº life°¡ Æ÷ÇԵǾî Àִ°¡ °Ë»çÇÔ
9.9 메타 문자를 좀 더 깊이 알아보자¶
In [75]:
import re
re.search('A..A', 'ABA') # Á¶°Ç¿¡ ¸ÂÁö ¾ÊÀ½
In [76]:
re.search('A..A', 'ABBA') # Á¶°Ç¿¡ ¸ÂÀ½
Out[76]:
In [77]:
re.search('A..A', 'ABBBA') # Á¶°Ç¿¡ ¸ÂÁö ¾ÊÀ½
In [ ]:
* 메타문자¶
In [78]:
re.search('AB*', 'A') # Á¶°Ç¿¡ ¸ÂÀ½
Out[78]:
In [79]:
re.search('AB*', 'AA') # Á¶°Ç¿¡ ¸ÂÀ½
Out[79]:
In [80]:
re.search('AB*', 'J-HOP') # Á¶°Ç¿¡ ¸ÂÁö ¾ÊÀ½
In [81]:
re.search('AB*', 'X-MAN') # Á¶°Ç¿¡ ¸ÂÀ½
Out[81]:
In [82]:
re.search('AB*', 'CABBA') # Á¶°Ç¿¡ ¸ÂÀ½
Out[82]:
In [83]:
re.search('AB*', 'CABBBBBA') # Á¶°Ç¿¡ ¸ÂÀ½
Out[83]:
? 메타문자¶
In [84]:
re.search('AB?', 'A') # Á¶°Ç¿¡ ¸ÂÀ½
Out[84]:
In [85]:
re.search('AB?', 'AA') # Á¶°Ç¿¡ ¸ÂÀ½
Out[85]:
In [86]:
re.search('AB?', 'J-HOP') # Á¶°Ç¿¡ ¸ÂÁö ¾ÊÀ½
In [87]:
re.search('AB?', 'X-MAN') # Á¶°Ç¿¡ ¸ÂÀ½
Out[87]:
In [88]:
re.search('AB?', 'CABBA') # Á¶°Ç¿¡ ¸ÂÀ½
Out[88]:
In [89]:
re.search('AB?', 'CABBBBBA') # Á¶°Ç¿¡ ¸ÂÀ½
Out[89]:
+ 메타문¶
In [90]:
re.search('AB+', 'A') # Á¶°Ç¿¡ ¸ÂÁö ¾ÊÀ½
In [91]:
re.search('AB+', 'AA') # Á¶°Ç¿¡ ¸ÂÁö ¾ÊÀ½
In [92]:
re.search('AB+', 'J-HOP') # Á¶°Ç¿¡ ¸ÂÁö ¾ÊÀ½
In [93]:
re.search('AB+', 'X-MAN') # Á¶°Ç¿¡ ¸ÂÁö ¾ÊÀ½
In [94]:
re.search('AB+', 'CABBA') # 'ABB'¶ó´Â ¹®ÀÚ¿ÀÌ Á¶°Ç¿¡ ¸ÂÀ½
Out[94]:
In [95]:
re.search('AB+', 'CABBBBBA') # 'ABBBBB'¶ó´Â ¹®ÀÚ¿ÀÌ Á¶°Ç¿¡ ¸ÂÀ½
Out[95]:
In [96]:
txt3 = 'My life my life my life in the sunshine'
re.findall('[Mm]y', txt3)
Out[96]:
In [98]:
import re
f = open('./UNDHR.txt')
for line in f:
line = line.rstrip()
if re.search('^\([0-9]+\)', line) :
print(line)
LAB 9-5 : 학사 코드 추출하기에 도전하자¶
In [99]:
import re
# ¸ÖƼ¶óÀÎ ÅؽºÆ®´Â ¼¼ °³ÀÇ µû¿ÈÇ¥¸¦ »ç¿ëÇÏ¿© Ç¥ÇöÇÑ´Ù
text="""101 COM PythonProgramming
102 MAT LinearAlgebra
103 ENG ComputerEnglish"""
s = re.findall('\d+', text)
print(s)
In [100]:
import re
txt = "abc@facebook.com¿Í bbc@google.com¿¡¼ À̸ÞÀÏÀÌ µµÂøÇÏ¿´½À´Ï´Ù."
output = re.findall('\S+@[a-z.]+', txt)
print('ÃßÃâµÈ À̸ÞÀÏ :', output)
In [101]:
import re
while True:
password = input("Æнº¿öµå¸¦ ÀÔ·ÂÇϼ¼¿ä : ");
if len(password)<8 or not re.search("([a-z])([A-Z])", password) \
or not re.search("[0-9]", password) \
or not re.search("[_@$]", password):
None
else:
print("À¯È¿ÇÑ Æнº¿öµå")
break
In [102]:
import re
while True:
password = input("Æнº¿öµå¸¦ ÀÔ·ÂÇϼ¼¿ä : ");
if len(password)<8 or not re.search("[a-z]", password) or \
not re.search("[A-Z]", password) or \
not re.search("[0-9]", password) or not re.search("[_@$!]", password):
print("À¯È¿ÇÏÁö ¾ÊÀº Æнº¿öµå!")
else:
print("À¯È¿ÇÑ Æнº¿öµå")
break
9.11 정규식에서 특정 문자를 대체하는 함수 : sub()¶
In [103]:
import re
s = 'I like BTS!'
re.sub('BTS', 'Black Pink', s)
Out[103]:
In [104]:
s = 'My lucky number 2 7 99'
re.sub('[0-9]+', '*', s) # ¼ýÀÚ¸¸ ã¾Æ¼ *À¸·Î ¹Ù²Þ
Out[104]:
In [105]:
re.sub('\d+', '*', s) # ¼ýÀÚ¸¸ ã¾Æ¼ *À¸·Î ¹Ù²Þ
Out[105]:
In [106]:
def hash_by_mult_and_modulo(m): # ¸Å°³º¯¼ö·Î ¸ÅÄ¡ °´Ã¼¸¦ ¹ÞÀ½
n = int(m.group()) # ¸ÅĪµÈ ¹®ÀÚ¿À» °¡Á®¿Í¼ Á¤¼ö·Î º¯È¯
return str(n * 23435 % 973) # ¼ýÀÚ¿¡ 10À» °öÇÑ µÚ ¹®ÀÚ¿·Î º¯È¯Çؼ ¹Ýȯ
print(re.sub('[0-9]+', hash_by_mult_and_modulo, s))
LAB 9-8 : 트윗 메시지를 깔끔하게 정제하자¶
In [107]:
import re
tweet = input('Æ®ÀÀ» ÀÔ·ÂÇϽÿÀ: ')
tweet = re.sub('RT', '', tweet)
tweet = re.sub('#\S+', '', tweet)
tweet = re.sub('@\S+', '', tweet)
print(tweet)
In [ ]: