def test_compound_ungroup():
assert ungroup(1) == 1
g = Series([1, 2, 3]).groupby([1, 1, 2])
assert ungroup(g) is g.obj
with pytest.raises(ValueError):
ungroup(g, "abc")
df = tibble(x=1, y=2) >> group_by(f.x, f.y)
out = ungroup(df)
assert group_vars(out) == []
out = ungroup(df, f.x)
assert group_vars(out) == ["y"]
out = ungroup(df, f.y)
assert group_vars(out) == ["x"]
out = group_by(df, f.y, _add=True)
assert group_vars(out) == ["x", "y"]
rf = df >> rowwise()
with pytest.raises(ValueError):
ungroup(rf, f.x)
with pytest.raises(KeyError):
group_by(df, f.w)
def test_can_re_rowwise():
rf1 = rowwise(tibble(x=range(1, 6), y=range(1, 6)), "x")
rf2 = rowwise(rf1, f.y)
assert group_vars(rf2) == ["y"]
rf3 = rowwise(rf2)
assert group_vars(rf3) == []
def test__groups_is_defused_with_context():
# test_that(".groups is defused with context", {
local_fn = identity
out = with_groups(mtcars, local_fn(2), mutate, disp=f.disp / sd(f.disp))
exp = with_groups(mtcars, 2, mutate, disp=f.disp / sd(f.disp))
assert out.equals(exp)
assert group_vars(out) == group_vars(exp)
def test_add(df):
tbl = df >> group_by(f.x, f.y, _add=True)
gvars = group_vars(tbl)
assert gvars == ["x", "y"]
tbl = df >> group_by(f.x, _add=True) >> group_by(f.y, _add=True)
gvars = group_vars(tbl)
assert gvars == ["x", "y"]
def test_peels_off_a_single_layer_of_grouping():
df = tibble(
x=rep([1, 2, 3, 4], each=4), y=rep([1, 2], each=8), z=runif(16)
)
gf = df >> group_by(f.x, f.y)
assert group_vars(summarise(gf)) == ["x"]
assert group_vars(summarise(summarise(gf))) == []
def test_empty_returns_self():
df = tibble(x=range(1, 11), y=range(1, 11))
gf = df >> group_by(f.x)
assert arrange(df).equals(df)
out = arrange(gf)
assert out.equals(gf)
assert group_vars(out) == group_vars(gf)
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_preserves_grouping():
gf = tibble(x=c(1, 1, 2, 2), y=f.x) >> group_by(f.x)
out = gf >> distinct()
gvars = group_vars(out)
assert gvars == ["x"]
out = gf >> distinct(x=f.x + 2)
gvars = group_vars(out)
assert gvars == ["x"]
def test_deals_with_0_groups():
df = tibble(x=[]) >> group_by(f.x)
out = mutate(df, y=f.x + 1)
exp = tibble(x=[], y=[]) >> group_by(f.x)
assert_iterable_equal(out, exp)
assert group_vars(out) == group_vars(exp)
out = mutate(df, y=max(f.x))
assert out.shape == (0, 2)
assert group_vars(out) == ["x"]
def test_preserve_grouping():
df = tibble(g=c(1, 2, 2, 2))
exp = tibble(g=c(1, 2), n=c(1, 3))
out = df >> count(f.g)
assert out.equals(exp)
df1 = df >> group_by(f.g) >> count()
df2 = exp >> group_by(f.g)
assert df1.equals(df2)
assert group_vars(df1) == group_vars(df2)
def test_output_preserves_grouping():
df = tibble(g=c(1, 2, 2, 2))
exp = tibble(g=c(1, 2, 2, 2), n=c(1, 3, 3, 3))
out = df >> add_count(f.g)
assert out.equals(exp)
out = df >> group_by(f.g) >> add_count()
exp >>= group_by(f.g)
assert out.equals(exp)
assert group_vars(out) == group_vars(exp)
def test_can_add_tallies_of_a_variable():
df = tibble(a=c(2, 1, 1))
out = df >> group_by(f.a) >> add_tally()
exp = tibble(a=c(2, 1, 1), n=c(1, 2, 2)) >> group_by(f.a)
assert_frame_equal(out, exp)
assert group_vars(out) == group_vars(exp)
# sort
out = df >> group_by(f.a) >> add_tally(sort=True)
exp = tibble(a=c(1, 1, 2), n=c(2, 2, 1)) >> group_by(f.a)
assert out.equals(exp)
# assert_frame_equal(out, exp)
assert group_vars(out) == group_vars(exp)
def test_joins_preserve_groups():
gf1 = tibble(a=[1, 2, 3]) >> group_by(f.a)
gf2 = tibble(a=rep([1, 2, 3, 4], 2), b=1) >> group_by(f.b)
out = inner_join(gf1, gf2, by="a")
assert group_vars(out) == ["a"]
out = semi_join(gf1, gf2, by="a")
assert group_vars(out) == ["a"]
# See comment in nest_join
out = nest_join(gf1, gf2, by="a")
assert group_vars(out) == ["a"]
def test_rowwise_preserved_by_subsetting():
rf = rowwise(tibble(x=range(1, 6), y=range(5, 0, -1)), f.x)
# out = get(rf, [1])
# assert isinstance(out, TibbleRowwise)
# assert group_vars(out) == ["x"]
out = mutate(rf, z=f.y)
assert isinstance(out, TibbleRowwise)
assert group_vars(out) == ["x"]
out = rename_with(rf, str.upper)
assert isinstance(out, TibbleRowwise)
assert group_vars(out) == ["X"]
def test_group_column_names_reflect_renamed_duplicate_columns():
# test_that("group column names reflect renamed duplicate columns (#2330)", {
df1 = tibble(x=range(1, 6), y=range(1, 6)) >> group_by(f.x, f.y)
df2 = tibble(x=range(1, 6), y=range(1, 6))
out = inner_join(df1, df2, by="x")
assert group_vars(out) == ["x"]
def test_preserves_grouping():
gf = group_by(tibble(x=[1, 2], y=2), f.x)
out = mutate(gf, x=1)
assert group_vars(out) == ["x"]
assert nrow(group_data(out)) == 1
out = mutate(gf, z=1)
assert group_data(out).equals(group_data(gf))
def test_rowwise_captures_group_vars():
df = group_by(tibble(g=[1, 2], x=[1, 2]), f.g)
rw = rowwise(df)
assert group_vars(rw) == ["g"]
with pytest.raises(ValueError):
rowwise(df, f.x)
def test_rowwise_preserved_by_major_verbs():
rf = rowwise(tibble(x=range(1, 6), y=range(5, 0, -1)), f.x)
out = arrange(rf, f.y)
assert isinstance(out, TibbleRowwise)
assert group_vars(out) == ["x"]
out = filter(rf, f.x < 3)
assert isinstance(out, TibbleRowwise)
assert group_vars(out) == ["x"]
out = mutate(rf, x=f.x + 1)
assert isinstance(out, TibbleRowwise)
assert group_vars(out) == ["x"]
out = rename(rf, X=f.x)
assert isinstance(out, TibbleRowwise)
assert group_vars(out) == ["X"]
out = select(rf, "x")
assert isinstance(out, TibbleRowwise)
assert group_vars(out) == ["x"]
out = slice(rf, c(0, 0))
assert isinstance(out, TibbleRowwise)
assert group_vars(out) == ["x"]
# Except for summarise
out = summarise(rf, z=mean(f.x, f.y))
assert isinstance(out, TibbleGrouped)
assert group_vars(out) == ["x"]
def test_join_preserve_grouping(df):
g = df >> group_by(f.x)
tbl = g >> inner_join(g, by=["x", "y"])
gvars = tbl >> group_vars()
assert gvars == ["x"]
tbl = g >> left_join(g, by=["x", "y"])
gvars = tbl >> group_vars()
assert gvars == ["x"]
tbl = g >> semi_join(g, by=["x", "y"])
gvars = tbl >> group_vars()
assert gvars == ["x"]
tbl = g >> anti_join(g, by=["x", "y"])
gvars = tbl >> group_vars()
assert gvars == ["x"]
def test_no_expressions():
df = tibble(x=[1, 2], y=[1, 2])
gf = group_by(df, f.x)
out = summarise(df)
assert dim(out) == (1, 0)
out = summarise(gf)
assert group_vars(out) == []
exp = tibble(x=[1, 2])
assert_tibble_equal(out, exp)
out = summarise(df, tibble())
assert dim(out) == (1, 0)
out = summarise(gf, tibble())
assert group_vars(out) == []
exp = tibble(x=[1, 2])
assert out.equals(exp)
def test_works_with_grouped_empty_data_frames():
df = tibble(x=[])
df1 = df >> group_by(f.x) >> summarise(y=1)
assert dim(df1) == (0, 2)
assert df1.columns.tolist() == ["x", "y"]
df1 = df >> rowwise(f.x) >> summarise(y=1)
assert group_vars(df1) == ["x"]
assert dim(df1) == (0, 2)
assert df1.columns.tolist() == ["x", "y"]
def test_empty_mutate_returns_input():
df = tibble(x=1)
gf = group_by(df, f.x)
out = mutate(df)
assert out.equals(df)
out = mutate(gf)
assert_tibble_equal(out, gf)
assert isinstance(gf, TibbleGrouped)
assert group_vars(out) == ["x"]
def test_zero_row_dfs():
df = tibble(a=[], b=[], g=[])
dfg = group_by(df, f.g, _drop=False)
assert dfg.shape == (0, 3)
assert group_vars(dfg) == ["g"]
assert group_size(dfg) == []
x = summarise(dfg, n=n())
assert x.shape == (0, 2)
assert group_vars(x) == []
x = mutate(dfg, c=f.b + 1)
assert x.shape == (0, 4)
assert group_vars(x) == ["g"]
assert group_size(x) == []
x = filter(dfg, f.a == 100)
assert x.shape == (0, 3)
assert group_vars(x) == ["g"]
assert group_size(x) == []
x = arrange(dfg, f.a, f.g)
assert x.shape == (0, 3)
assert group_vars(x) == ["g"]
assert group_size(x) == []
x = select(dfg, f.a)
assert x.shape == (0, 2)
assert group_vars(x) == ["g"]
assert group_size(x) == []
def test_groups_arg(caplog):
df = tibble(x=1, y=2)
out = df >> group_by(f.x, f.y) >> summarise()
assert out.equals(df)
assert "has grouped output by ['x']" in caplog.text
caplog.clear()
out = df >> rowwise(f.x, f.y) >> summarise()
# assert "[Groups: x, y (n=1)]" in out.attrs["_str_footer"]
df = tibble(x=1, y=2)
df1 = df >> summarise(z=3, _groups="rowwise")
df2 = rowwise(tibble(z=3))
assert isinstance(df1, TibbleRowwise)
assert isinstance(df2, TibbleRowwise)
assert df1.equals(df2)
assert group_vars(df1) == group_vars(df2)
gf = df >> group_by(f.x, f.y)
gvars = gf >> summarise() >> group_vars()
assert gvars == ["x"]
gvars = gf >> summarise(_groups="drop_last") >> group_vars()
assert gvars == ["x"]
gvars = gf >> summarise(_groups="drop") >> group_vars()
assert gvars == []
gvars = gf >> summarise(_groups="keep") >> group_vars()
assert gvars == ["x", "y"]
gvars = gf >> summarise(_groups="rowwise") >> group_vars()
assert gvars == ["x", "y"]
# assert gvars == []
rf = df >> rowwise(f.x, f.y)
gvars = rf >> summarise(_groups="drop") >> group_vars()
assert gvars == []
gvars = rf >> summarise(_groups="keep") >> group_vars()
assert gvars == ["x", "y"]
def test_keep_always_retains_grouping_variables():
df = tibble(x=1, y=2, z=3) >> group_by(f.z)
out = df >> mutate(a=f.x + 1, _keep="none")
exp = tibble(z=3, a=2) >> group_by(f.z)
assert out.equals(exp)
assert group_vars(out) == group_vars(exp)
out = df >> mutate(a=f.x + 1, _keep="all")
exp = tibble(x=1, y=2, z=3, a=2) >> group_by(f.z)
assert out.equals(exp)
assert group_vars(out) == group_vars(exp)
out = df >> mutate(a=f.x + 1, _keep="used")
exp = tibble(x=1, z=3, a=2) >> group_by(f.z)
assert out.equals(exp)
assert group_vars(out) == group_vars(exp)
out = df >> mutate(a=f.x + 1, _keep="unused")
exp = tibble(y=2, z=3, a=2) >> group_by(f.z)
assert out.equals(exp)
assert group_vars(out) == group_vars(exp)
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_arguments_to_select_dont_match_vars_select_arguments():
df = tibble(a=1)
out = select(df, var=f.a)
assert out.equals(tibble(var=1))
out = select(group_by(df, f.a), var=f.a)
exp = group_by(tibble(var=1), f.var)
assert out.equals(exp)
assert group_vars(out) == group_vars(exp)
out = select(df, exclude=f.a)
assert out.equals(tibble(exclude=1))
out = select(df, include=f.a)
assert out.equals(tibble(include=1))
out = select(group_by(df, f.a), exclude=f.a)
exp = group_by(tibble(exclude=1), f.exclude)
assert out.equals(exp)
assert group_vars(out) == group_vars(exp)
out = select(group_by(df, f.a), include=f.a)
exp = group_by(tibble(include=1), f.include)
assert out.equals(exp)
assert group_vars(out) == group_vars(exp)
def test_tibble_keep_grouping(df):
g = df >> group_by(f.x)
tbl = tibble(g)
# with pytest.raises(NotImplementedError):
assert group_vars(tbl) == ["x"]
def test_preserves_grouping():
gf = group_by(tibble(g=[1, 2, 3], x=[3, 2, 1]), f.g)
out = select(gf, h=f.g)
assert group_vars(out), ["h"]
def test_rename_preserve_grouping():
gf = group_by(tibble(g=[1, 2, 3], x=[3, 2, 1]), f.g)
out = rename(gf, h=f.g)
assert group_vars(out) == ["h"]
