def test_join_with_index(self):
"""
Test Join operation with index
"""
R = Table.inputfromfile('test_csv/real_sales1.csv')
S = Table.inputfromfile('test_csv/real_sales1.csv')
start = time.time()
R1 = Table.join(R, S, 'R', 'S', 'R.pricerange = S.pricerange')
end = time.time()
self.assertIsNotNone(R1.table)
for row in R1.table:
self.assertEqual(row['R_pricerange'], row['S_pricerange'])
without_index = end - start
Table.Hash(R, 'pricerange')
Table.Hash(S, 'pricerange')
start = time.time()
R1 = Table.join(R, S, 'R', 'S', 'R.pricerange = S.pricerange')
end = time.time()
with_index = end - start
self.assertIsNotNone(R1.table)
for row in R1.table:
self.assertEqual(row['R_pricerange'], row['S_pricerange'])
self.assertLess(with_index, without_index*0.9)
start = time.time()
R1 = Table.join(R, S, 'R', 'S', 'S.pricerange = R.pricerange')
end = time.time()
with_index = end - start
self.assertIsNotNone(R1.table)
for row in R1.table:
self.assertEqual(row['R_pricerange'], row['S_pricerange'])
self.assertLess(with_index, without_index*0.9)
def test_join_with_greater(self):
'''Test join wtih condition: R.qty > S.Q'''
R = Table.inputfromfile('test_csv/sales1.csv')
S = Table.inputfromfile('test_csv/sales2.csv')
R1 = Table.join(R, S, 'R', 'S', 'R.qty >S.Q')
self.assertIsNotNone(R1.table)
for row in R1.table:
self.assertIsNotNone(row['R_qty'], row['S_Q'])
self.assertGreater(row['R_qty'], row['S_Q'])
def test_join_with_same_customerid(self):
"""Test join wtih condition: R.customerid = S.C"""
R = Table.inputfromfile('test_csv/sales1.csv')
S = Table.inputfromfile('test_csv/sales2.csv')
R1 = Table.join(R, S, 'R', 'S', 'R.customerid=S.C')
self.assertIsNotNone(R1.table)
for row in R1.table:
self.assertIsNotNone(row['R_customerid'], row['S_C'])
self.assertEqual(row['R_customerid'], row['S_C'])
def test_join_with_same_princerage(self):
'''Test join wtih condition: R.pricerange = S.P'''
R = Table.inputfromfile('test_csv/sales1.csv')
S = Table.inputfromfile('test_csv/sales2.csv')
R1 = Table.join(R, S, 'R', 'S', 'R.pricerange = S.P')
self.assertIsNotNone(R1.table)
for row in R1.table:
self.assertIsNotNone(row['R_pricerange'], row['S_P'])
self.assertEqual(row['R_pricerange'], row['S_P'])
def test_join_with_multiple_condtion(self):
'''Test join wtih condition: (R.qty >= S.Q) and (R.pricerange = S.P)'''
R = Table.inputfromfile('test_csv/sales1.csv')
S = Table.inputfromfile('test_csv/sales2.csv')
R1 = Table.join(R, S, 'R', 'S', '(R.qty >= S.Q) and (R.pricerange = S.P)')
self.assertIsNotNone(R1.table)
for row in R1.table:
self.assertIsNotNone(row['R_qty'], row['S_Q'])
self.assertGreaterEqual(row['R_qty'], row['S_Q'])
self.assertIsNotNone(row['R_pricerange'], row['S_P'])
self.assertEqual(row['R_pricerange'], row['S_P'])
def test_join_column_name(self):
'''Test join wtih the output column name'''
R = Table.inputfromfile('test_csv/sales1.csv')
S = Table.inputfromfile('test_csv/sales2.csv')
R1 = Table.join(R, S, 'R1', 'S1', 'True')
self.assertIsNotNone(R1.table)
keyset = R1.table[0].keys()
for key in R.table[0].keys():
new_key = 'R1_{}'.format(key)
self.assertTrue(new_key in keyset)
for key in S.table[0].keys():
new_key = 'S1_{}'.format(key)
self.assertTrue(new_key in keyset)
