def test_load_train_and_test_columns_dont_intersect(temp_file_pair):
tmp_train, tmp_test = temp_file_pair
_make_and_write_data(tmp_train,
100,
19,
True,
True,
0,
column_prefix="A")
_make_and_write_data(tmp_test,
20,
11,
True,
True,
0,
column_prefix="B")
with pytest.raises(
ValueError,
match="columns of training and test data do not intersect"):
sdata.load_arff_files_standardized(tmp_train.name,
["event", "time"],
1,
path_testing=tmp_test.name,
survival=True,
standardize_numeric=False,
to_numeric=False)
def test_load_train_and_test_with_different_columns(temp_file_pair):
tmp_train, tmp_test = temp_file_pair
_make_and_write_data(tmp_train, 100, 19, False, True, 0)
_make_and_write_data(tmp_test, 20, 11, False, True, 0)
with pytest.warns(UserWarning,
match="Restricting columns to intersection between "
"training and testing data"):
sdata.load_arff_files_standardized(tmp_train.name, ["event", "time"], 1,
path_testing=tmp_test.name,
survival=True,
standardize_numeric=False, to_numeric=False)
def test_load_with_categorical_index_2(arff_2):
x_train, y_train, x_test, y_test = sdata.load_arff_files_standardized(
arff_2, ["label"], pos_label="yes", survival=False,
standardize_numeric=False, to_numeric=False)
assert x_test is None
assert y_test is None
assert x_train.shape == (5, 2)
assert y_train.shape == (5, 1)
index = pandas.Index(['ASampleOne', 'ASampleTwo', 'ASampleThree', 'ASampleFour', 'ASampleFive'],
name='index', dtype=object)
tm.assert_index_equal(x_train.index, index, exact=True)
label = pandas.Series(pandas.Categorical(["no", "no", "yes", "yes", "no"],
categories=["yes", "no"], ordered=False),
name="label", index=index)
tm.assert_series_equal(y_train["label"], label, check_exact=True)
value = pandas.Series([1.51, 1.38, -20, 245.3, 3.14], name="value", index=index)
tm.assert_series_equal(x_train["value"], value, check_exact=True)
size = pandas.Series(pandas.Categorical(["small", "small", "large", "small", "large"],
categories=["small", "medium", "large"], ordered=False),
name="size", index=index)
tm.assert_series_equal(x_train["size"], size, check_exact=True)
def test_load_with_index(temp_file):
dataset = _make_and_write_data(temp_file, 100, 10, True, True, 0)
x_train, y_train, x_test, y_test = sdata.load_arff_files_standardized(
temp_file.name, ["event", "time"], 1, survival=True,
standardize_numeric=False, to_numeric=False)
assert x_test is None
assert y_test is None
cols = ["event", "time"]
x_true = dataset.drop(cols, axis=1)
assert_x_equal(x_true, x_train)
assert_y_equal(dataset, y_train)
def test_load_train_and_test_no_labels(temp_file_pair):
tmp_train, tmp_test = temp_file_pair
train_dataset = _make_and_write_data(tmp_train, 100, 10, True, True, 0)
test_dataset = _make_and_write_data(tmp_test, 20, 10, True, False, 0)
x_train, y_train, x_test, y_test = sdata.load_arff_files_standardized(
tmp_train.name, ["event", "time"], 1, path_testing=tmp_test.name,
survival=True, standardize_numeric=False, to_numeric=False)
cols = ["event", "time"]
x_true = train_dataset.drop(cols, axis=1)
assert_x_equal(x_true, x_train)
assert_y_equal(train_dataset, y_train)
assert_x_equal(test_dataset, x_test)
assert y_test is None
def test_load_train_and_test_with_categorical_index(arff_1, arff_2):
x_train, y_train, x_test, y_test = sdata.load_arff_files_standardized(
arff_1, ["label"], pos_label="yes", path_testing=arff_2, survival=False,
standardize_numeric=False, to_numeric=False)
assert x_train.shape == (4, 2)
assert x_test.shape == (5, 2)
assert y_train.shape == (4, 1)
assert y_test.shape == (5, 1)
# Check train data
train_index = pandas.Index(['SampleOne', 'SampleTwo', 'SampleThree', 'SampleFour'],
name='index', dtype=object)
tm.assert_index_equal(x_train.index, train_index, exact=True)
train_label = pandas.Series(
pandas.Categorical(["yes", "no", "yes", "yes"], categories=["no", "yes"], ordered=False),
name="label", index=train_index)
tm.assert_series_equal(y_train["label"], train_label, check_exact=True)
train_value = pandas.Series([15.1, 13.8, -0.2, 2.453], name="value", index=train_index)
tm.assert_series_equal(x_train["value"], train_value, check_exact=True)
train_size = pandas.Series(pandas.Categorical(["medium", "large", "small", "large"],
categories=["small", "medium", "large"], ordered=False),
name="size", index=train_index)
tm.assert_series_equal(x_train["size"], train_size, check_exact=True)
# Check test data
test_index = pandas.Index(['ASampleOne', 'ASampleTwo', 'ASampleThree', 'ASampleFour', 'ASampleFive'],
name='index', dtype=object)
tm.assert_index_equal(x_test.index, test_index, exact=True)
test_label = pandas.Series(
pandas.Categorical(["no", "no", "yes", "yes", "no"], categories=["yes", "no"], ordered=False),
name="label", index=test_index)
tm.assert_series_equal(y_test["label"], test_label, check_exact=True)
test_value = pandas.Series([1.51, 1.38, -20, 245.3, 3.14], name="value", index=test_index)
tm.assert_series_equal(x_test["value"], test_value, check_exact=True)
test_size = pandas.Series(pandas.Categorical(["small", "small", "large", "small", "large"],
categories=["small", "medium", "large"], ordered=False),
name="size", index=test_index)
tm.assert_series_equal(x_test["size"], test_size, check_exact=True)
