def test_phonetic_does_not_exist(self): values = pd.Series([np.nan, u'John', u'Mary Ann', u'billy', u'Jonathan', u'Gretha', u'Micheal', u'Sjors']) with self.assertRaises(ValueError): phonetic(values, 'unknown_algorithm')
def test_phonetic_does_not_exist(self): values = pd.Series([ np.nan, u'John', u'Mary Ann', u'billy', u'Jonathan', u'Gretha', u'Micheal', u'Sjors' ]) with self.assertRaises(ValueError): phonetic(values, 'unknown_algorithm')
def test_encode_nysiis(self): values = pd.Series([np.nan, u'John', u'Mary Ann', u'billy', u'Jonathan', u'Gretha', u'Micheal', u'Sjors']) expected = pd.Series([np.nan, u'JAN', u'MARYAN', u'BALY', u'JANATAN', u'GRAT', u'MACAL', u'SJAR']) phon = phonetic(values, 'nysiis') pdt.assert_series_equal(phon, expected)
def test_encode_soundex(self): values = pd.Series([np.nan, u'John', u'Mary Ann', u'billy', u'Jonathan', u'Gretha', u'Micheal', u'Sjors']) expected = pd.Series([np.nan, u'J500', u'M650', u'B400', u'J535', u'G630', u'M240', u'S620']) phon = phonetic(values, 'soundex') pdt.assert_series_equal(phon, expected)
def test_encode_match_rating(self): values = pd.Series([np.nan, u'John', u'Mary Ann', u'billy', u'Jonathan', u'Gretha', u'Micheal', u'Sjors']) expected = pd.Series( [np.nan, u'JHN', u'MRYNN', u'BLLY', u'JNTHN', u'GRTH', u'MCHL', u'SJRS']) phon = phonetic(values, method='match_rating') pdt.assert_series_equal(phon, expected)
def test_encode_metaphone(self): values = pd.Series([np.nan, u'John', u'Mary Ann', u'billy', u'Jonathan', u'Gretha', u'Micheal', u'Sjors']) expected = pd.Series( [np.nan, u'JN', u'MRYN', u'BL', u'JN0N', u'KR0', u'MXL', u'SJRS']) phon = phonetic(values, method='metaphone') pdt.assert_series_equal(phon, expected)
def test_encode_metaphone(self): values = pd.Series([ np.nan, u'John', u'Mary Ann', u'billy', u'Jonathan', u'Gretha', u'Micheal', u'Sjors' ]) expected = pd.Series( [np.nan, u'JN', u'MRYN', u'BL', u'JN0N', u'KR0', u'MXL', u'SJRS']) phon = phonetic(values, method='metaphone') pdt.assert_series_equal(phon, expected)
def test_encode_match_rating(self): values = pd.Series([ np.nan, u'John', u'Mary Ann', u'billy', u'Jonathan', u'Gretha', u'Micheal', u'Sjors' ]) expected = pd.Series([ np.nan, u'JHN', u'MRYNN', u'BLLY', u'JNTHN', u'GRTH', u'MCHL', u'SJRS' ]) phon = phonetic(values, method='match_rating') pdt.assert_series_equal(phon, expected)
def test_encode_nysiis(self): values = pd.Series([ np.nan, u'John', u'Mary Ann', u'billy', u'Jonathan', u'Gretha', u'Micheal', u'Sjors' ]) expected = pd.Series([ np.nan, u'JAN', u'MARYAN', u'BALY', u'JANATAN', u'GRAT', u'MACAL', u'SJAR' ]) phon = phonetic(values, 'nysiis') pdt.assert_series_equal(phon, expected)
def test_encode_soundex(self): values = pd.Series([ np.nan, u'John', u'Mary Ann', u'billy', u'Jonathan', u'Gretha', u'Micheal', u'Sjors' ]) expected = pd.Series([ np.nan, u'J500', u'M650', u'B400', u'J535', u'G630', u'M240', u'S620' ]) phon = phonetic(values, 'soundex') pdt.assert_series_equal(phon, expected)