def test_preserves_grouping():
gf = tibble(g=[1, 1, 1, 2, 2], x=[1, 2, 3, 4, 5]) >> group_by(f.g)
out = gf >> filter(is_element(f.x, [3, 4]))
assert group_vars(out) == ["g"]
assert group_rows(out) == [[0], [1]]
out = gf >> filter(f.x < 3)
assert group_vars(out) == ["g"]
assert group_rows(out) == [[0, 1]]
def test_grouped_filter_handles_indices():
res = iris >> group_by(f.Species) >> filter(f.Sepal_Length > 5)
res2 = res >> mutate(Petal=f.Petal_Width * f.Petal_Length)
assert nrow(res) == nrow(res2)
grows1 = group_rows(res)
grows2 = group_rows(res2)
assert grows1 == grows2
assert all(group_keys(res) == group_keys(res2))
def test_group_rows_group_keys_partition_group_data():
df = tibble(x=[1, 2], y=[1, 2])
rows = group_rows(df)
assert rows == [[0, 1]]
gf = group_by(df, f.x, f.y)
gd = group_data(gf)
assert group_keys(gf).equals(gd.iloc[:, [0, 1]])
assert pull(gd, to="list") == group_rows(gf)
def test_rowwise_group_structure_is_updated_after_a_join():
# test_that("rowwise group structure is updated after a join (#5227)", {
df1 = rowwise(tibble(x=[1, 2]))
df2 = tibble(x=c([1, 2], 2))
x = left_join(df1, df2, by="x")
assert group_rows(x) == [[0], [1], [2]]
def test_group_modify_makes_a_grouped_df():
res = group_by(mtcars, f.cyl) >> group_modify(lambda df: head(df, 2))
assert nrow(res) == 6
assert group_rows(res) == [[0, 1], [2, 3], [4, 5]]
res = (iris >> group_by(f.Species) >> filter(f.Species == "setosa") >>
group_modify(lambda df: tally(df)))
assert nrow(res) == 1
assert group_rows(res) == [[0]]
res = (iris >> group_by(f.Species, _drop=False) >>
filter(f.Species == "setosa") >> group_modify(lambda df: tally(df)))
# assert nrow(res) == 3
assert nrow(res) == 1
# assert group_rows(res) == [[0], [1], [2]]
assert group_rows(res) == [[0]]
def test_correctly_reconstructs_groups():
d = (
tibble(x=[1, 2, 3, 4], g1=rep([1, 2], 2), g2=[1, 2, 3, 4])
>> group_by(f.g1, f.g2)
>> summarise(x=f.x + 1)
)
# Different from dplyr, original df does not reorder.
assert group_rows(d) == [[0, 2], [1, 3]]
def test_filter_false_handles_indices(caplog):
out = mtcars >> group_by(f.cyl) >> filter(False, _preserve=True)
assert "support" in caplog.text
# out = group_rows(out)
# assert out == [[], [], []]
out = mtcars >> group_by(f.cyl) >> filter(False, _preserve=False)
out = group_rows(out)
assert out == []
def test_removes_vars_with_None():
df = tibble(x=range(1, 4), y=range(1, 4))
gf = group_by(df, f.x)
out = df >> mutate(y=None)
assert out.columns.tolist() == ["x"]
out = gf >> mutate(y=None)
assert out.columns.tolist() == ["x"]
assert isinstance(out, TibbleGrouped)
assert group_vars(out) == ["x"]
assert group_rows(out) == [[0], [1], [2]]
# even if it doesn't exist
out = df >> mutate(z=None)
assert out.equals(df)
z = Series(1, name="z")
out = df >> mutate(z, z=None)
assert out.equals(df)
df = tibble(x=1, y=1)
out = mutate(df, z=1, x=None, y=None)
assert out.equals(tibble(z=1))
def test_update_grouping():
df = tibble(g=[2, 2, 1, 1], x=[1, 3, 2, 4])
res = df >> group_by(f.g) >> arrange(f.x)
assert isinstance(res, TibbleGrouped)
assert group_rows(res) == [[0, 2], [1, 3]]
def test_slice_strips_grouped_indices():
res = mtcars >> group_by(f.cyl) >> slice(1) >> mutate(mpgplus=f.mpg + 1)
assert nrow(res) == 3
assert group_rows(res) == [[0], [1], [2]]