def test_get_attr_corres_valid_1(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
ac = get_attr_corres(A, B)
for c in ac['corres']:
self.assertEqual(c[0], c[1])
self.assertEqual(all(ac['ltable'] == A), True)
self.assertEqual(all(ac['rtable'] == B), True)
def get_features_for_matching(A, B):
if not isinstance(A, pd.DataFrame):
logger.error('Input table A is not of type pandas dataframe')
raise AssertionError('Input table A is not of type pandas dataframe')
if not isinstance(B, pd.DataFrame):
logger.error('Input table B is not of type pandas dataframe')
raise AssertionError('Input table B is not of type pandas dataframe')
sim_funcs = get_sim_funs_for_matching()
tok_funcs = get_tokenizers_for_matching()
t_A = get_attr_types(A)
t_B = get_attr_types(B)
attr_corres = get_attr_corres(A, B)
feat_table = get_features(A, B, t_A, t_B, attr_corres, tok_funcs, sim_funcs)
# export important variables to global name space
mg._match_t = tok_funcs
mg._match_s = sim_funcs
mg._atypes1 = t_A
mg._atypes2 = t_B
mg._match_c = attr_corres
return feat_table
def get_features_for_matching(A, B):
if not isinstance(A, pd.DataFrame):
logger.error('Input table A is not of type pandas dataframe')
raise AssertionError('Input table A is not of type pandas dataframe')
if not isinstance(B, pd.DataFrame):
logger.error('Input table B is not of type pandas dataframe')
raise AssertionError('Input table B is not of type pandas dataframe')
sim_funcs = get_sim_funs_for_matching()
tok_funcs = get_tokenizers_for_matching()
t_A = get_attr_types(A)
t_B = get_attr_types(B)
attr_corres = get_attr_corres(A, B)
feat_table = get_features(A, B, t_A, t_B, attr_corres, tok_funcs,
sim_funcs)
# export important variables to global name space
mg._match_t = tok_funcs
mg._match_s = sim_funcs
mg._atypes1 = t_A
mg._atypes2 = t_B
mg._match_c = attr_corres
return feat_table
def test_get_attr_corres_invalid_df2(self):
ac = get_attr_corres(pd.DataFrame(), None)
def test_get_attr_corres_invalid_df1(self):
ac = get_attr_corres(None, pd.DataFrame())