How to Clean Data with Python

                                

# Matching 'consensus' or variations
import re
pattern = re.compile('con[sc]en[sc]us')
matches = pattern.findall('concensus consensus consencus concencus')
print(matches)  # Output: ['concensus', 'consensus', 'consencus', 'concencus']


                              

                                

# Matching 'humor' or 'humour'
import re
pattern = re.compile('humou?r')
matches = pattern.findall('humor humour')
print(matches)  # Output: ['humor', 'humour']


                              

                                

# Matching 'monkey' in text
import re
pattern = re.compile('monkey')
matches = pattern.findall('The monkey and the monkeys')
print(matches)  # Output: ['monkey', 'monkey']


                              

                                

# Matching 'roaaaar' to 'roaaaaaar'
import re
pattern = re.compile('roa{3,6}r')
matches = pattern.findall('roaaar roaaaar roaaaaar roaaaaaar')
print(matches)  # Output: ['roaaar', 'roaaaar', 'roaaaaar', 'roaaaaaar']


                              

                                

# Matching 'baboons' or 'gorillas'
import re
pattern = re.compile('baboons|gorillas')
matches = pattern.findall('baboons gorillas baboons')
print(matches)  # Output: ['baboons', 'gorillas', 'baboons']


                              

                                

# Matching exact text
import re
pattern = re.compile('^Monkeys: my mortal enemy$')
matches = pattern.findall('Monkeys: my mortal enemy')
print(matches)  # Output: ['Monkeys: my mortal enemy']


                              

                                

# Matching any 6-character string
import re
pattern = re.compile('......')
matches = pattern.findall('orangutan marsupial')
print(matches)  # Output: ['orangutan', 'marsupial']


                              

                                

# Matching uppercase letters and digits
import re
pattern = re.compile('[A-Z0-9]+')  # Modify to match one or more characters
matches = pattern.findall('A B 1 2 C D 3')
print(matches)  # Output: ['A', '1', '2', 'C', 'D', '3']


                              

                                

# Matching word characters and digits
import re
pattern = re.compile('\w\d')
matches = pattern.findall('a1 b2 c3')
print(matches)  # Output: ['a1', 'b2', 'c3']


                              

                                

# Matching various repetitions of 'o'
import re
pattern_star = re.compile('meo*w')
pattern_plus = re.compile('meo+w')
print(pattern_star.findall('mew meow meooow meoooooooooooow'))  # Output: ['mew', 'meow', 'meooow', 'meoooooooooooow']
print(pattern_plus.findall('mew meow meooow meoooooooooooow'))  # Output: ['meow', 'meooow', 'meoooooooooooow']


                              

                                

# Matching with grouping
import re
pattern = re.compile('I love (baboons|gorillas)')
matches = pattern.findall('I love baboons I love gorillas')
print(matches)  # Output: ['baboons', 'gorillas']