def test_read_vec(self): module=VECLoader(get_dataset('warlogs'), id='test_read_vec') self.assertTrue(module.df() is None) module.run(0) s = module.trace_stats(max_runs=1) df = module.df() self.assertFalse(df is None) l = len(df) self.assertEqual(l, len(df[df[module.UPDATE_COLUMN]==module.last_update()])) cnt = 1 while not module.is_zombie(): module.run(cnt) cnt += 1 s = module.trace_stats(max_runs=1) df = module.df() ln = len(df) print "Run time: %gs, loaded %d rows" % (s['duration'].irow(-1), ln) self.assertEqual(ln-l, len(df[df[module.UPDATE_COLUMN]==module.last_update()])) l = ln s = module.trace_stats(max_runs=1) print "Done. Run time: %gs, loaded %d rows" % (s['duration'].irow(-1), len(module.df())) df2 = module.df().groupby([Module.UPDATE_COLUMN]) self.assertEqual(cnt, len(df2))
def NOtest_vec_distances(self): s=Scheduler() vec=VECLoader(get_dataset('warlogs'),scheduler=s) dis=PairwiseDistances(metric='cosine',scheduler=s) dis.input.df = vec.output.df dis.input.array = vec.output.array cnt = Every(proc=print_len,constant_time=True,scheduler=s) cnt.input.df = dis.output.dist global times times = 0 s.start() df = vec.df() computed = dis.dist() self.assertEquals(computed.shape[0], len(df)) truth = pairwise_distances(vec.toarray(), metric=dis._metric) self.assertTrue(np.allclose(truth, computed))