def test_can_move_blocks_of_vars():
df = tibble(x=1, a="a", y=2, b="a")
out = df >> relocate(where(is_string_dtype))
assert out.columns.tolist() == ["a", "b", "x", "y"]
out = df >> relocate(where(is_string_dtype),
_after=where(is_numeric_dtype))
assert out.columns.tolist() == ["x", "y", "a", "b"]
def test_cache_key():
df = tibble(g=rep([1, 2], each=2), a=range(1, 5)) >> group_by(f.g)
out = df >> mutate(
tibble(
x=across(where(is_numeric), mean).a,
y=across(where(is_numeric), max).a,
))
expect = df >> mutate(x=mean(f.a), y=max(f.a))
assert_frame_equal(out, expect)
def test_works_sequentially():
df = tibble(a=1)
out = df >> mutate(x=ncol(across(where(is_numeric))),
y=ncol(across(where(is_numeric))))
expect = tibble(a=1, x=1, y=2)
assert out.equals(expect)
out = df >> mutate(a="x", y=ncol(across(where(is_numeric))))
expect = tibble(a="x", y=0)
assert out.equals(expect)
def test_error_messages():
with pytest.raises(ValueError, match="Argument `_fns` of across must be"):
tibble(x=1) >> summarise(res=across(where(is_numeric), 42))
with pytest.raises(ValueError, match="must only be used inside verbs"):
across()
with pytest.raises(ValueError, match="must only be used inside verbs"):
c_across()
def test_nb_fail():
from datar.datasets import iris
out = iris >> mutate(
across(
where(is_double) & ~c(f["Petal_Length"], f["Petal_Width"]), round))
rows = out >> nrow()
assert rows == 150
def test_tidyselect_funs():
# tidyselect.where
def isupper(ser):
return ser.name.isupper()
df = tibble(x=1, X=2, y=3, Y=4)
out = df >> select(where(isupper))
assert out.columns.tolist() == ["X", "Y"]
@register_verb
def islower(_data, series):
return [series.name.islower(), True]
out = df >> select(where(islower))
assert out.columns.tolist() == ["x", "y"]
out = df >> select(where(lambda x: False))
assert out.shape == (1, 0)
out = df >> select(ends_with("y"))
assert out.columns.tolist() == ["y", "Y"]
out = df >> select(contains("y"))
assert out.columns.tolist() == ["y", "Y"]
with pytest.raises(KeyError):
df >> select(all_of(["x", "a"]))
out = df >> select(any_of(["x", "y"]))
assert out.columns.tolist() == ["x", "y"]
out = df >> select(any_of(["x", "a"]))
assert out.columns.tolist() == ["x"]
out = num_range("a", 3, width=2)
assert out == ["a00", "a01", "a02"]
df = tibble(tibble(X=1), X=2, _name_repair="minimal")
out = df >> select(contains("X"))
assert out.columns.tolist() == ["X"]
def test_names_output():
gf = tibble(x=1, y=2, z=3, s="") >> group_by(f.x)
out = gf >> summarise(across())
assert out.columns.tolist() == ["x", "y", "z", "s"]
out = gf >> summarise(across(_names="id_{_col}"))
assert out.columns.tolist() == ["x", "id_y", "id_z", "id_s"]
out = gf >> summarise(across(where(is_numeric), mean))
assert out.columns.tolist() == ["x", "y", "z"]
out = gf >> summarise(across(where(is_numeric), mean,
_names="mean_{_col}"))
assert out.columns.tolist() == ["x", "mean_y", "mean_z"]
out = gf >> summarise(across(where(is_numeric), {
"mean": mean,
"sum": sum
}))
assert out.columns.tolist() == ["x", "y_mean", "y_sum", "z_mean", "z_sum"]
# Different from R's list
out = gf >> summarise(across(where(is_numeric), {"mean": mean, 1: sum}))
assert out.columns.tolist() == ["x", "y_mean", "y_1", "z_mean", "z_1"]
# Different from R's list
out = gf >> summarise(across(where(is_numeric), {0: mean, "sum": sum}))
assert out.columns.tolist() == ["x", "y_0", "y_sum", "z_0", "z_sum"]
out = gf >> summarise(across(where(is_numeric), [mean, sum]))
assert out.columns.tolist() == ["x", "y_0", "y_1", "z_0", "z_1"]
out = gf >> summarise(
across(where(is_numeric), [mean, sum], _names="{_col}_{_fn1}"))
assert out.columns.tolist() == ["x", "y_1", "y_2", "z_1", "z_2"]
out = gf >> summarise(
across(
where(is_numeric),
{
"mean": mean,
"sum": sum
},
_names="{_fn}_{_col}",
))
assert out.columns.tolist() == ["x", "mean_y", "sum_y", "mean_z", "sum_z"]
def test_reject_non_vectors():
with pytest.raises(ValueError, match="Argument `_fns` of across must be"):
tibble(x=1) >> summarise(across(where(is_numeric), object()))
def test_used_separately():
df = tibble(a=1, b=2)
out = df >> mutate(x=ncol(across(where(is_numeric))), y=ncol(across(f.a)))
expect = tibble(a=1, b=2, x=2, y=1)
assert out.equals(expect)
def test_used_twice():
df = tibble(a=1, b=2)
out = df >> mutate(x=ncol(across(where(is_numeric))) + ncol(across(f.a)))
expect = tibble(a=1, b=2, x=3)
assert out.equals(expect)
def test_keep_used_not_affected_by_across():
df = tibble(x=1, y=2, z=3, a="a", b="b", c="c")
out = df >> mutate(across(where(is_numeric), identity), _keep="unused")
assert out.columns.tolist() == df.columns.tolist()
