def test2_5_hits(self):
input_ = pd.DataFrame(
{'test_col': ['berlin and paris are both capitals',
'Angela M. plans to buy a flat in Hamburg',
'The BASF is located in Ludwigshafen, Rhineland-Palatine',
'Crist. Ronaldo plays in Madrid for Real Madrid']})
expected = pd.read_csv("test/data/linking/5hits_expected.csv")
output = dbpedia_spotlight_linker(input_, 'test_col', max_hits=5)
pd.testing.assert_frame_equal(
output, expected, check_like=True)
def test8_all_nan(self):
input_ = pd.DataFrame(
{'test_col': [np.nan, np.nan,
np.nan, np.nan]})
expected = pd.DataFrame(
{'test_col': [np.nan, np.nan, np.nan, np.nan],
'new_link': [np.nan, np.nan, np.nan, np.nan]})
output = dbpedia_spotlight_linker(input_, 'test_col')
pd.testing.assert_frame_equal(
output, expected, check_like=True)
def transform(self, X, y=None):
X = dbpedia_spotlight_linker(
X,
column=self.column,
new_attribute_name=self.new_attribute_name,
progress=self.progress,
max_hits=self.max_hits,
language=self.language,
selection=self.selection,
confidence=self.confidence,
support=self.support,
min_similarity_score=self.min_similarity_score,
caching=self.caching)
return X
def test3_nan(self):
input_ = pd.DataFrame(
{'test_col': ['Dakar', 'Horse Racing in Uruguay',
np.nan, 'Ukulele']})
expected = pd.DataFrame(
{'test_col': ['Dakar', 'Horse Racing in Uruguay',
np.nan, 'Ukulele'],
'new_link': ['http://dbpedia.org/resource/Dakar',
'http://dbpedia.org/resource/Horse_racing',
np.nan,
'http://dbpedia.org/resource/Ukulele']})
output = dbpedia_spotlight_linker(input_, 'test_col')
pd.testing.assert_frame_equal(
output, expected, check_like=True)
def test1_default(self):
input_ = pd.DataFrame(
{'test_col': ['berlin', 'darmstadt',
'london', 'munich']})
expected = pd.DataFrame(
{'test_col': ['berlin', 'darmstadt',
'london', 'munich'],
'new_link': ['http://dbpedia.org/resource/Berlin',
'http://dbpedia.org/resource/Darmstadt',
'http://dbpedia.org/resource/London',
'http://dbpedia.org/resource/Munich']})
output = dbpedia_spotlight_linker(input_, 'test_col')
pd.testing.assert_frame_equal(
output, expected, check_like=True)
def test7_no_match(self):
input_ = pd.DataFrame(
{'test_col': ['B. Obama', 'Barrrack Obbama',
'President B. Obama', 'B. Obama']})
expected = pd.DataFrame(
{'test_col': ['B. Obama', 'Barrrack Obbama',
'President B. Obama', 'B. Obama'],
'new_link': [np.nan, np.nan, np.nan, np.nan]})
output = dbpedia_spotlight_linker(input_, 'test_col',
confidence=0.99)
pd.testing.assert_frame_equal(
output, expected, check_like=True)
def test6_high_confidence(self):
input_ = pd.DataFrame(
{'test_col': ['Barack Hussein Obama', 'Barrrack Obbama',
'President B. Obama', 'B. Obama']})
expected = pd.DataFrame(
{'test_col': ['Barack Hussein Obama', 'Barrrack Obbama',
'President B. Obama', 'B. Obama'],
'new_link': ['http://dbpedia.org/resource/Barack_Obama',
np.nan, np.nan, np.nan]})
output = dbpedia_spotlight_linker(input_, 'test_col',
confidence=0.99)
pd.testing.assert_frame_equal(
output, expected, check_like=True)
def test9_wrong_input_type(self):
input_ = pd.DataFrame(
{'test_col': ['B. Obama', 666,
'President B. Obama', 'B. Obama']})
expected = pd.DataFrame(
{'test_col': ['B. Obama', 666,
'President B. Obama', 'B. Obama'],
'new_link': ['http://dbpedia.org/resource/Barack_Obama',
np.nan, 'http://dbpedia.org/resource/President_of_the_United_States',
'http://dbpedia.org/resource/Barack_Obama']})
output = dbpedia_spotlight_linker(input_, 'test_col')
pd.testing.assert_frame_equal(
output, expected, check_like=True)
def test4_selection_support(self):
input_ = pd.DataFrame(
{'test_col': ['Berlin and Paris are both capitals but Paris is rich and Paris is in France',
'Rather Rome or Madrid? Definitely Rome!',
'Hamburg? Hamburg is not a city in Rhineland-Palatine',
"If I had to choose between Spaghetti or Linguine I'd always choose Spaghetti"]})
expected = pd.DataFrame(
{'test_col': ['Berlin and Paris are both capitals but Paris is rich and Paris is in France',
'Rather Rome or Madrid? Definitely Rome!',
'Hamburg? Hamburg is not a city in Rhineland-Palatine',
"If I had to choose between Spaghetti or Linguine I'd always choose Spaghetti"],
'new_link': ['http://dbpedia.org/resource/France',
'http://dbpedia.org/resource/Rome',
'http://dbpedia.org/resource/Hamburg',
'http://dbpedia.org/resource/Spaghetti']})
output = dbpedia_spotlight_linker(input_, 'test_col', selection='support')
pd.testing.assert_frame_equal(
output, expected, check_like=True)
def test5_selection_similarityScore(self):
input_ = pd.DataFrame(
{'test_col': ['Berlin and Paaris? Berlin and Pariss!',
'Foooootball or Rugbyy?',
'How to write New Yorrk? or is it Neew York',
"Hopelessly trying to spell Emannuel Makrone"]})
expected = pd.DataFrame(
{'test_col': ['Berlin and Paaris? Berlin and Pariss!',
'Foooootball or Rugbyy?',
'How to write New Yorrk? or is it Neew York',
"Hopelessly trying to spell Emannuel Makrone"],
'new_link': ['http://dbpedia.org/resource/Berlin',
np.nan,
'http://dbpedia.org/resource/How_(TV_series)',
'http://dbpedia.org/resource/Hopelessly']})
output = dbpedia_spotlight_linker(input_, 'test_col',
selection='similarityScore')
pd.testing.assert_frame_equal(
output, expected, check_like=True)
