def test_random_table(self):
s=Scheduler()
module=RandomTable(['a', 'b'], rows=10000, scheduler=s)
self.assertEqual(module.df().columns[0],'a')
self.assertEqual(module.df().columns[1],'b')
self.assertEqual(len(module.df().columns), 3) # add the UPDATE_COLUMN
prlen = Every(proc=print_len, constant_time=True, scheduler=s)
prlen.input.df = module.output.df
s.start()
self.assertEqual(len(module.df()), 10000)
self.assertFalse(module.df()['a'].isnull().any())
self.assertFalse(module.df()['b'].isnull().any())
def test_random_table2(self):
s=Scheduler()
# produces more than 4M rows per second on my laptop
module=RandomTable(10, rows=10000000, force_valid_ids=True, scheduler=s)
self.assertEqual(len(module.df().columns), 11) # add the UPDATE_COLUMN
self.assertEqual(module.df().columns[0],'_1')
self.assertEqual(module.df().columns[1],'_2')
prlen = Every(proc=print_len, constant_time=True, scheduler=s)
prlen.input.df = module.output.df
s.start()
self.assertEqual(len(module.df()), 10000000)
self.assertFalse(module.df()['_1'].isnull().any())
self.assertFalse(module.df()['_2'].isnull().any())
def test_max(self):
s=Scheduler()
random = RandomTable(10, rows=10000, scheduler=s)
max=Max(scheduler=s)
max.input.df = random.output.df
pr=Print(scheduler=s)
pr.input.df = max.output.df
s.start()
res1 = random.df()[random.columns.difference([random.UPDATE_COLUMN])].max()
res2 = last_row(max.df(), remove_update=True)
self.assertTrue(np.allclose(res1, res2))
def test_var(self):
s=Scheduler()
random = RandomTable(1, rows=1000, scheduler=s)
var=Var(scheduler=s)
var.input.df = random.output.df
pr=Print(scheduler=s)
pr.input.df = var.output.df
s.start()
res1 = random.df()[1].var()
res2 = last_row(var.df(), remove_update=True)
#print 'res1:', res1
#print 'res2:', res2
self.assertTrue(np.allclose(res1, res2))