def test_assemble_topk_table_2(self):
A = read_csv_metadata(path_a, key='ID')
B = read_csv_metadata(path_b, key='ID')
A_key = em.get_key(A)
B_key = em.get_key(B)
topk_heap = [(0.2727272727272727, 1, 0), (0.23076923076923078, 0, 4),
(0.16666666666666666, 0, 3)]
ret_dataframe = db._assemble_topk_table(topk_heap, A, B, A_key, B_key)
expected_columns = ['_id', 'ltable_ID', 'rtable_ID',
'ltable_name', 'ltable_birth_year',
'ltable_hourly_wage',
'ltable_address', 'ltable_zipcode', 'rtable_name',
'rtable_birth_year', 'rtable_hourly_wage',
'rtable_address', 'rtable_zipcode']
self.assertEqual(len(ret_dataframe), 3)
self.assertEqual(list(ret_dataframe.columns), expected_columns)
expected_recs = [[0, 'a2', 'b1', 'Michael Franklin',
1988, 27.5, '1652 Stockton St, San Francisco',
94122, 'Mark Levene', 1987, 29.5,
'108 Clement St, San Francisco', 94107],
[1, 'a1', 'b5', 'Kevin Smith',
1989, 30.0, '607 From St, San Francisco', 94107,
'Alfons Kemper', 1984, 35.0,
'170 Post St, Apt 4, San Francisco', 94122],
[2, 'a1', 'b4', 'Kevin Smith',
1989, 30.0, '607 From St, San Francisco', 94107,
'Joseph Kuan', 1982, 26.0,
'108 South Park, San Francisco', 94122]]
self.assertEqual(list(ret_dataframe.ix[0]), expected_recs[0])
self.assertEqual(list(ret_dataframe.ix[1]), expected_recs[1])
self.assertEqual(list(ret_dataframe.ix[2]), expected_recs[2])
def test_assemble_topk_table_2(self):
A = read_csv_metadata(path_a, key='ID')
B = read_csv_metadata(path_b, key='ID')
A_key = em.get_key(A)
B_key = em.get_key(B)
topk_heap = [(0.2727272727272727, 1, 0), (0.23076923076923078, 0, 4),
(0.16666666666666666, 0, 3)]
ret_dataframe = db._assemble_topk_table(topk_heap, A, B, A_key, B_key)
expected_columns = ['_id', 'ltable_ID', 'rtable_ID',
'ltable_name', 'ltable_birth_year',
'ltable_hourly_wage',
'ltable_address', 'ltable_zipcode', 'rtable_name',
'rtable_birth_year', 'rtable_hourly_wage',
'rtable_address', 'rtable_zipcode']
self.assertEqual(len(ret_dataframe), 3)
self.assertEqual(list(ret_dataframe.columns), expected_columns)
expected_recs = [[0, 'a2', 'b1', 'Michael Franklin',
1988, 27.5, '1652 Stockton St, San Francisco',
94122, 'Mark Levene', 1987, 29.5,
'108 Clement St, San Francisco', 94107],
[1, 'a1', 'b5', 'Kevin Smith',
1989, 30.0, '607 From St, San Francisco', 94107,
'Alfons Kemper', 1984, 35.0,
'170 Post St, Apt 4, San Francisco', 94122],
[2, 'a1', 'b4', 'Kevin Smith',
1989, 30.0, '607 From St, San Francisco', 94107,
'Joseph Kuan', 1982, 26.0,
'108 South Park, San Francisco', 94122]]
self.assertEqual(list(ret_dataframe.loc[0]), expected_recs[0])
self.assertEqual(list(ret_dataframe.loc[1]), expected_recs[1])
self.assertEqual(list(ret_dataframe.loc[2]), expected_recs[2])
def test_assemble_topk_table_1(self):
A = read_csv_metadata(path_a, key='ID')
B = read_csv_metadata(path_b, key='ID')
topk_heap = []
ret_dataframe = db._assemble_topk_table(topk_heap, A, B)
self.assertEqual(len(ret_dataframe), 0)
self.assertEqual(list(ret_dataframe.columns), [])
def test_assemble_topk_table_1(self):
A = read_csv_metadata(path_a, key='ID')
B = read_csv_metadata(path_b, key='ID')
A_key = em.get_key(A)
B_key = em.get_key(B)
topk_heap = []
ret_dataframe = db._assemble_topk_table(topk_heap, A, B, A_key, B_key)
self.assertEqual(len(ret_dataframe), 0)
self.assertEqual(list(ret_dataframe.columns), [])