Esempio n. 1
0
    def test_single_step_generalization(self):
        postcode_1 = 'HP2 7PW'
        postcode_2 = 'HP2 7PF'
        generalized_1 = reduce_string(postcode_1)
        generalized_2 = reduce_string(postcode_2)

        self.assertNotEqual(postcode_1, postcode_2)
        self.assertEqual(generalized_1, generalized_2)
Esempio n. 2
0
    def test_multistep_generalization(self):
        postcode_1 = 'HP2 7PW'
        postcode_2 = 'HP2 4DY'

        number_of_generalization_steps = 0

        while (postcode_1 != postcode_2):
            if (len(postcode_1) > len(postcode_2)):
                postcode_1 = reduce_string(postcode_1)
            else:
                postcode_2 = reduce_string(postcode_2)
            number_of_generalization_steps = number_of_generalization_steps + 1
        self.assertEqual(postcode_1, postcode_2)
        self.assertEqual(number_of_generalization_steps, 6)
Esempio n. 3
0
    def test_total_generalization(self):
        postcode_1 = 'HP2 7PW'
        postcode_2 = 'CF470JD'

        number_of_generalization_steps = 0

        while (postcode_1 != postcode_2):
            if (len(postcode_1) > len(postcode_2)):
                postcode_1 = reduce_string(postcode_1)
            else:
                postcode_2 = reduce_string(postcode_2)
            number_of_generalization_steps = number_of_generalization_steps + 1

        self.assertEqual(postcode_1, postcode_2)
        self.assertEqual(number_of_generalization_steps, 14)
        self.assertEqual(postcode_1, '*')
Esempio n. 4
0
def recode_strings(series):
    """
    Generalizes a series of strings by stepwise reduction of strings
    Parameters
    ----------
    series: Series
        Series to be recoded.
    Returns
    -------
    str
        Single value recoded to.
    """
    values = set(series.unique())
    while len(values) > 1:
        longest_element = next_string_to_reduce(values)
        values.remove(longest_element)
        generalized = reduce_string(longest_element)
        values.add(generalized)
    return list(values)[0]
Esempio n. 5
0
 def test_generalization(self):
     postcode = 'NE9 5YE'
     generalized = reduce_string(postcode)
     self.assertNotEqual(postcode, generalized)