Modularity & Documentation & Automated Testing

pip install pycodestyle

pycodestyle test.py

# Import needed package
import pycodestyle

# Create a StyleGuide instance
style_checker = pycodestyle.StyleGuide()

# Run PEP 8 check on multiple files
result = style_checker.check_files(['nay_pep8.py', 'yay_pep8.py'])

# Print result of PEP 8 style check
print(result.messages)

[__init__.py](<http://init.py>) file let us know that the directory is a package.

from .document import Document 이런식으로 init.py 파일에 추가해줄 수 있음. util.py나 class 함수들을 넣어놓기 유용함.

class Document:
  def __init__(self, text):
    self.text = text
    # Tokenize the document with non-public tokenize method
    self.tokens = self._tokenize()
    # Perform word count with non-public count_words method
    self.word_counts = self._count_words()

  def _tokenize(self):
    return tokenize(self.text)
	
  # non-public method to tally document's word counts with Counter
  def _count_words(self):
    return Counter(self.tokens)

# Define a SocialMedia class that is a child of the `Document class`
class SocialMedia(Document):
		"""Analyze text data from social media
    
    :param text: social media text to analyze

    :ivar hashtag_counts: Counter object containing counts of #hashtags used in text
    :ivar mention_counts: Counter object containing counts of @mentions used in text
    """
    def __init__(self, text):
        Document.__init__(self, text)
        self.hashtag_counts = self._count_hashtags()
        self.mention_counts = self._count_mentions()
        
    def _count_hashtags(self):
        # Filter attribute so only words starting with '#' remain
        return filter_word_counts(self.word_counts, first_char='#')      
    
    def _count_mentions(self):
        # Filter attribute so only words starting with '@' remain
        return filter_word_counts(self.word_counts, first_char='@')

Docstring - reStructuredText

# Complete the function's docstring
def tokenize(text, regex=r'[a-zA-z]+'):
  """Split text into tokens using a regular expression

  :param text: text to be tokenized
  :param regex: regular expression used to match tokens using re.findall 
  :return: a list of resulting tokens

  >>> tokenize('the rain in spain')
  ['the', 'rain', 'in', 'spain']
  """
  return re.findall(regex, text, flags=re.IGNORECASE)

# Print the docstring
help(tokenize)

doctest.testmod()