def test_filter_tables(self, tokenizer, sim_measure_type, threshold,
allow_empty, allow_missing, args, expected_pairs):
position_filter = PositionFilter(tokenizer, sim_measure_type,
threshold, allow_empty, allow_missing)
actual_candset = position_filter.filter_tables(*args)
expected_output_attrs = ['_id']
l_out_prefix = self.default_l_out_prefix
r_out_prefix = self.default_r_out_prefix
# Check for l_out_prefix in args.
if len(args) > 8:
l_out_prefix = args[8]
expected_output_attrs.append(l_out_prefix + args[2])
# Check for r_out_prefix in args.
if len(args) > 9:
r_out_prefix = args[9]
expected_output_attrs.append(r_out_prefix + args[3])
# Check for l_out_attrs in args.
if len(args) > 6:
if args[6]:
l_out_attrs = remove_redundant_attrs(args[6], args[2])
for attr in l_out_attrs:
expected_output_attrs.append(l_out_prefix + attr)
# Check for r_out_attrs in args.
if len(args) > 7:
if args[7]:
r_out_attrs = remove_redundant_attrs(args[7], args[3])
for attr in r_out_attrs:
expected_output_attrs.append(r_out_prefix + attr)
# verify whether the output table has the necessary attributes.
assert_list_equal(list(actual_candset.columns.values),
expected_output_attrs)
actual_pairs = set()
for idx, row in actual_candset.iterrows():
actual_pairs.add(','.join((str(row[l_out_prefix + args[2]]),
str(row[r_out_prefix + args[3]]))))
# verify whether the actual pairs and the expected pairs match.
assert_equal(len(expected_pairs), len(actual_pairs))
common_pairs = actual_pairs.intersection(expected_pairs)
assert_equal(len(common_pairs), len(expected_pairs))
def test_filter_tables(self, tokenizer, sim_measure_type, threshold,
allow_empty, allow_missing, args, expected_pairs):
position_filter = PositionFilter(tokenizer, sim_measure_type, threshold,
allow_empty, allow_missing)
actual_candset = position_filter.filter_tables(*args)
expected_output_attrs = ['_id']
l_out_prefix = self.default_l_out_prefix
r_out_prefix = self.default_r_out_prefix
# Check for l_out_prefix in args.
if len(args) > 8:
l_out_prefix = args[8]
expected_output_attrs.append(l_out_prefix + args[2])
# Check for r_out_prefix in args.
if len(args) > 9:
r_out_prefix = args[9]
expected_output_attrs.append(r_out_prefix + args[3])
# Check for l_out_attrs in args.
if len(args) > 6:
if args[6]:
l_out_attrs = remove_redundant_attrs(args[6], args[2])
for attr in l_out_attrs:
expected_output_attrs.append(l_out_prefix + attr)
# Check for r_out_attrs in args.
if len(args) > 7:
if args[7]:
r_out_attrs = remove_redundant_attrs(args[7], args[3])
for attr in r_out_attrs:
expected_output_attrs.append(r_out_prefix + attr)
# verify whether the output table has the necessary attributes.
assert_list_equal(list(actual_candset.columns.values),
expected_output_attrs)
actual_pairs = set()
for idx, row in actual_candset.iterrows():
actual_pairs.add(','.join((str(row[l_out_prefix + args[2]]),
str(row[r_out_prefix + args[3]]))))
# verify whether the actual pairs and the expected pairs match.
assert_equal(len(expected_pairs), len(actual_pairs))
common_pairs = actual_pairs.intersection(expected_pairs)
assert_equal(len(common_pairs), len(expected_pairs))
def test_invalid_r_out_attr(self):
position_filter = PositionFilter(self.tokenizer, self.sim_measure_type,
self.threshold)
position_filter.filter_tables(self.A, self.B, 'A.id', 'B.id', 'A.attr',
'B.attr', ['A.attr'], ['B.invalid_attr'])
def test_numeric_r_filter_attr(self):
position_filter = PositionFilter(self.tokenizer, self.sim_measure_type,
self.threshold)
position_filter.filter_tables(self.A, self.B, 'A.id', 'B.id', 'A.attr',
'B.int_attr')
def test_invalid_rtable(self):
position_filter = PositionFilter(self.tokenizer, self.sim_measure_type,
self.threshold)
position_filter.filter_tables(self.A, [], 'A.id', 'B.id', 'A.attr',
'B.attr')
def test_invalid_r_out_attr(self):
position_filter = PositionFilter(self.tokenizer, self.sim_measure_type,
self.threshold)
position_filter.filter_tables(self.A, self.B, 'A.id', 'B.id',
'A.attr', 'B.attr',
['A.attr'], ['B.invalid_attr'])
def test_numeric_r_filter_attr(self):
position_filter = PositionFilter(self.tokenizer, self.sim_measure_type,
self.threshold)
position_filter.filter_tables(self.A, self.B, 'A.id', 'B.id',
'A.attr', 'B.int_attr')
def test_invalid_rtable(self):
position_filter = PositionFilter(self.tokenizer, self.sim_measure_type,
self.threshold)
position_filter.filter_tables(self.A, [], 'A.id', 'B.id',
'A.attr', 'B.attr')
