def test_get_features_for_blocking_valid(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
feat_table = afg.get_features_for_blocking(A, B)
self.assertEqual(isinstance(feat_table, pd.DataFrame), True)
functions = feat_table['function']
for f in functions:
x = f(A.ix[1], B.ix[2])
self.assertEqual(x >= 0, True)
def test_get_features_for_blocking_valid(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
feat_table = afg.get_features_for_blocking(A, B)
self.assertEqual(isinstance(feat_table, pd.DataFrame), True)
functions = feat_table['function']
for f in functions:
x = f(A.ix[1], B.ix[2])
self.assertEqual(x >= 0, True)
def test_valid_object_2(self):
cm.del_catalog()
del_files_in_dir(sndbx_path)
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
feature_table = get_features_for_blocking(A, B)
rb = RuleBasedBlocker()
rb.add_rule('zipcode_zipcode_exm(ltuple, rtuple) != 1', feature_table)
C = rb.block_tables(A, B, show_progress=False)
self.assertEqual(len(C), 15)
p = os.sep.join([sndbx_path, 'C.pkl'])
creat_dir_ifnot_exists(sndbx_path)
save_object(rb, p)
rb1 = load_object(p)
C1 = rb1.block_tables(A, B, show_progress=False)
self.assertEqual(C.equals(C1), True)
def test_get_features_for_blocking_invalid_df2(self):
A = read_csv_metadata(path_a)
# B = read_csv_metadata(path_b, key='ID')
feat_table = afg.get_features_for_blocking(A, None)
def test_get_features_for_blocking_invalid_df1(self):
# A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
feat_table = afg.get_features_for_blocking(None, B)
def test_get_features_for_blocking_invalid_df2(self):
A = read_csv_metadata(path_a)
# B = read_csv_metadata(path_b, key='ID')
feat_table = afg.get_features_for_blocking(A, None)
def test_get_features_for_blocking_invalid_df1(self):
# A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
feat_table = afg.get_features_for_blocking(None, B)