def test_categories_to_integers_big(self):
data = os.path.join(os.path.abspath(
os.path.dirname(__file__)), "data", "adult_set.txt")
df = pandas.read_csv(data, sep="\t")
trans = CategoriesToIntegers(single=True)
trans.fit(df)
newdf = trans.transform(df)
self.assertEqual(len(newdf.columns), len(df.columns))
self.assertEqual(list(newdf.columns), list(df.columns))
newdf2 = trans.fit_transform(df)
self.assertEqual(newdf, newdf2)
rep = repr(trans)
self.assertEqual("CategoriesToIntegers(columns=None,remove=None,single=True,skip_errors=False)",
rep.replace(" ", "").replace("\n", ""))
def test_categories_to_integers_big(self):
data = os.path.join(os.path.abspath(os.path.dirname(__file__)), "data",
"adult_set.txt")
df = pandas.read_csv(data, sep="\t")
trans = CategoriesToIntegers(single=True)
trans.fit(df)
newdf = trans.transform(df)
self.assertEqual(len(newdf.columns), len(df.columns))
self.assertEqual(list(newdf.columns), list(df.columns)) # pylint: disable=E1101
newdf2 = trans.fit_transform(df)
self.assertEqual(newdf, newdf2)
rep = repr(trans)
self.assertStartsWith("CategoriesToIntegers(",
rep.replace(" ", "").replace("\n", ""))
self.assertIn("single=True", rep.replace(" ", "").replace("\n", ""))