def test_dataset_init(self): # From text files dataset = Dataset(join(tdp(), 'items.txt'), join(tdp(), 'scales.txt')) self.assertEqual(len(dataset.X), len(dataset.y)) # From pandas DFs dataset = Dataset(self.X, self.y) self.assertEqual(len(dataset.X), len(dataset.y))
def test_measure_save(self): measure = Measure(X=join(tdp(), 'items.txt'), y=join(tdp(), 'scales.txt'), key=join(tdp(), 'key.txt'), missing='drop') t = tempfile.mkdtemp() measure.save(key=True, summary=True, pickle=True, path=t) self.assertTrue(exists(t + '/key.txt')) self.assertTrue(exists(t + '/data.pkl')) self.assertTrue(exists(t + '/summary.txt')) shutil.rmtree(t)
def setUpClass(cls): measure = Measure(X=join(tdp(), 'items.txt'), y=join(tdp(), 'scales.txt'), key=join(tdp(), 'key.txt'), missing='drop') abb = abbreviate.TopNAbbreviator(max_items=8, min_r=0.3) gen = Generator(abbreviator=abb) gen.run(measure, n_gens=3) cls.generator = gen
def setUp(self): self.dataset = Dataset(join(tdp(), 'items.txt'), join(tdp(), 'scales.txt'), missing='drop')
def test_abbreviator(self): measure = Measure(X=join(tdp(), 'items.txt'), y=join(tdp(), 'scales.txt'), key=join(tdp(), 'key.txt'), missing='drop') gen = Generator() am = gen.run(measure, n_gens=3)