def test_recycling():
df = tibble(x=1, y=2)
out = df >> summarise(across(everything(), lambda col: rep(42, col)))
expect = tibble(x=rep(42, 2), y=rep(42, 2))
assert out.equals(expect)
df = tibble(x=2, y=3)
with pytest.raises(ValueError):
df >> summarise(across(everything(), lambda col: rep(42, col)))
def test_to_functions():
df = tibble(x=c(1, NA)) # -> float
out = df >> summarise(across(everything(), mean, na_rm=True))
expect = tibble(x=1.0)
assert_frame_equal(out, expect)
out = df >> summarise(
across(everything(), dict(mean=mean, median=median), na_rm=True))
expect = tibble(x_mean=1.0, x_median=1.0)
assert_frame_equal(out, expect)
def test_errors():
# wrong type
with pytest.raises(ValueError):
iris >> group_by(f.Species) >> filter(range(1, 10))
with pytest.raises(ValueError):
iris >> filter(range(1, 10))
# wrong size
with pytest.raises(ValueError):
iris >> group_by(f.Species) >> filter([True, False])
with pytest.raises(ValueError):
iris >> rowwise(f.Species) >> filter([True, False])
with pytest.raises(ValueError):
iris >> filter([True, False])
# wrong size in column
with pytest.raises(ValueError):
iris >> group_by(f.Species) >> filter(tibble([True, False]))
with pytest.raises(ValueError):
iris >> rowwise() >> filter(tibble([True, False]))
with pytest.raises(ValueError):
iris >> filter(tibble([True, False]))
with pytest.raises(ValueError):
tibble(x=1) >> filter([True, False])
# named inputs
with pytest.raises(TypeError):
mtcars >> filter(x=1)
with pytest.raises(TypeError):
mtcars >> filter(f.y > 2, z=3)
with pytest.raises(TypeError):
mtcars >> filter(True, x=1)
# across() in filter() does not warn yet
tibble(x=1, y=2) >> filter(across(everything(), lambda x: x > 0))
def test_result_locations_aligned_with_column_names():
df = tibble(x=[1, 2], y=["a", "b"])
expect = tibble(x_cls=numpy.int64, x_type=True, y_cls=object, y_type=False)
x = df >> summarise(
across(everything(), {
"cls": lambda x: x.dtype,
"type": is_numeric
}))
assert_frame_equal(x, expect)
def test_summarise_cols_inside_func():
df = tibble(x=2, y=4, z=8)
@register_func(None, context=None)
def data_frame(**kwargs):
return tibble(**kwargs)
out = df >> summarise(data_frame(x=f.x / f.y, y=f.y / f.y, z=f.z / f.y))
expect = df >> summarise(across(everything(), lambda col: col / df.y))
assert out.equals(expect)
def test_mutate_cols_inside_func():
df = tibble(x=2, y=4, z=8)
@register_func(None, context=None)
def data_frame(**kwargs):
return tibble(**kwargs)
out = df >> mutate(data_frame(x=f.x / f.y, y=f.y / f.y, z=f.z / f.y))
# df.y does not work on grouped data
expect = df >> mutate(across(everything(), lambda col: col / df.y))
assert out.equals(expect)
def test_not_selecting_grouping_var():
df = tibble(g=1, x=1)
out = df >> group_by(f.g) >> summarise(x=across(everything()))
expected = tibble(x=1)
assert_frame_equal(out["x"], expected)