def whas500_without_ties():
# naive survival SVM does resolve ties in survival time differently,
# therefore use data without ties
data = loadarff(WHAS500_NOTIES_FILE)
x, y = get_x_y(data, ['fstat', 'lenfol'], '1')
x = encode_categorical(x)
return x, y
def test_dataframe(self):
contents = "".join(EXPECTED_1)
with StringIO(contents) as fp:
actual_df = loadarff(fp)
expected_df = pandas.DataFrame.from_items(
[("attr_nominal",
pandas.Series(["water", "wine", "beer", None, "wine", "water"]).astype("category")),
("attr_nominal_spaces",
pandas.Series(['"red wine"', '"hard liquor"', None, "mate", '"hard liquor"', "mate"]).astype("category"))
]
)
tm.assert_frame_equal(expected_df, actual_df, check_exact=True)
def test_loadarff_dataframe():
contents = "".join(EXPECTED_1)
with StringIO(contents) as fp:
actual_df = loadarff(fp)
expected_df = pandas.DataFrame.from_dict(OrderedDict(
[("attr_nominal",
pandas.Series(pandas.Categorical.from_codes(
[1, 2, 0, -1, 2, 1],
["beer", "water", "wine"]))),
("attr_nominal_spaces",
pandas.Series(pandas.Categorical.from_codes(
[2, 0, -1, 1, 0, 1],
['"hard liquor"', 'mate', '"red wine"'])))
]
))
tm.assert_frame_equal(expected_df, actual_df, check_exact=True)
def setUp(self):
# naive survival SVM does resolve ties in survival time differently,
# therefore use data without ties
data = loadarff(WHAS500_NOTIES_FILE)
x, self.y = get_x_y(data, ['fstat', 'lenfol'], '1')
self.x = encode_categorical(x)
