notebook.community

Edit and run



In [16]:

    
def count_words(sentence):
    """
    Function that takes a string as argument and returns
    a dictionary which has words as the keys and the number
    of times each word was seen in the sentence as the value.
    """
    
    return {word:sentence.count(word) for word in sentence.lower().split()}



In [21]:

    
count_words("oh what a day what a lovely day")   # wrong: 'a' is counted for the whole sentence









    Out[21]:





{'a': 6, 'day': 2, 'lovely': 1, 'oh': 1, 'what': 2}



In [22]:

    
count_words("don't stop believing")









    Out[22]:





{'believing': 1, "don't": 1, 'stop': 1}



In [19]:

    
count_words("Oh what a day what a lovely day")  # wrong: 'oh' does not seem to be counted









    Out[19]:





{'a': 6, 'day': 2, 'lovely': 1, 'oh': 0, 'what': 2}



In [23]:

    
count_words("Oh what a day, what a lovely day!")  # wrong: day! and day, are counted as different









    Out[23]:





{'a': 6, 'day!': 1, 'day,': 1, 'lovely': 1, 'oh': 0, 'what': 2}

Refining #1: Considering mixed case words



In [24]:

    
def count_words(sentence):
    """
    Function that takes a string as argument and returns
    a dictionary which has words as the keys and the number
    of times each word was seen in the sentence as the value.
    """
    
    words = sentence.lower().split()
    return {word:words.count(word) for word in words}



In [25]:

    
count_words("oh what a day what a lovely day")









    Out[25]:





{'a': 2, 'day': 2, 'lovely': 1, 'oh': 1, 'what': 2}



In [26]:

    
count_words("don't stop believing")









    Out[26]:





{'believing': 1, "don't": 1, 'stop': 1}



In [27]:

    
count_words("Oh what a day what a lovely day")









    Out[27]:





{'a': 2, 'day': 2, 'lovely': 1, 'oh': 1, 'what': 2}



In [28]:

    
count_words("Oh what a day, what a lovely day!")  # wrong: day! and day, are counted as different









    Out[28]:





{'a': 2, 'day!': 1, 'day,': 1, 'lovely': 1, 'oh': 1, 'what': 2}

Experiments



In [30]:

    
import string



In [31]:

    
string.punctuation









    Out[31]:





'!"#$%&\'()*+,-./:;<=>?@[\\]^_`{|}~'

Refining #2: Ignoring punctuations outside of words



In [40]:

    
def count_words(sentence):
    """
    Function that takes a string as argument and returns
    a dictionary which has words as the keys and the number
    of times each word was seen in the sentence as the value.
    """
    
    words = sentence.lower().split()
    words = [word.strip(string.punctuation) for word in words]   # Removing punctuations outside of words
    return {word:words.count(word) for word in words}



In [41]:

    
count_words("oh what a day what a lovely day")









    Out[41]:





{'a': 2, 'day': 2, 'lovely': 1, 'oh': 1, 'what': 2}



In [42]:

    
count_words("don't stop believing")









    Out[42]:





{'believing': 1, "don't": 1, 'stop': 1}



In [43]:

    
count_words("Oh what a day what a lovely day")









    Out[43]:





{'a': 2, 'day': 2, 'lovely': 1, 'oh': 1, 'what': 2}



In [44]:

    
count_words("Oh what a day, what a lovely day!")









    Out[44]:





{'a': 2, 'day': 2, 'lovely': 1, 'oh': 1, 'what': 2}



In [45]:

    
import unittest


class CountWordsTests(unittest.TestCase):

    """Tests for count_words."""

    def test_simple_sentence(self):
        actual = count_words("oh what a day what a lovely day")
        expected = {'oh': 1, 'what': 2, 'a': 2, 'day': 2, 'lovely': 1}
        self.assertEqual(actual, expected)

    def test_apostrophe(self):
        actual = count_words("don't stop believing")
        expected = {"don't": 1, 'stop': 1, 'believing': 1}
        self.assertEqual(actual, expected)

    # To test the Bonus part of this exercise, comment out the following line
    #@unittest.expectedFailure
    def test_capitalization(self):
        actual = count_words("Oh what a day what a lovely day")
        expected = {'oh': 1, 'what': 2, 'a': 2, 'day': 2, 'lovely': 1}
        self.assertEqual(actual, expected)

    # To test the Bonus part of this exercise, comment out the following line
    #@unittest.expectedFailure
    def test_symbols(self):
        actual = count_words("Oh what a day, what a lovely day!")
        expected = {'oh': 1, 'what': 2, 'a': 2, 'day': 2, 'lovely': 1}
        self.assertEqual(actual, expected)


if __name__ == "__main__":
    unittest.main(argv=['first-arg-is-ignored'], exit=False)









    



....
----------------------------------------------------------------------
Ran 4 tests in 0.003s

OK



In [ ]: