def test_errors(caplog):
df = tibble(x=1, y=2)
out = df >> group_by(f.x, f.y) >> summarise()
assert "`summarise()` has grouped output by ['x']" in caplog.text
assert out.equals(df)
caplog.clear()
out = tibble(x=1, y=2) >> group_by(f.x, f.y) >> summarise(z=[2, 2])
assert "`summarise()` has grouped output by ['x', 'y']" in caplog.text
exp = tibble(x=[1, 1], y=[2, 2], z=[2, 2])
assert out.equals(exp)
caplog.clear()
out = df >> rowwise(f.x, f.y) >> summarise()
assert "`summarise()` has grouped output by ['x', 'y']" in caplog.text
assert out.equals(df)
caplog.clear()
out = df >> rowwise() >> summarise()
assert "`summarise()` has ungrouped output" in caplog.text
d = dim(out)
assert d == (1, 0)
caplog.clear()
# unsupported type (but python objects are supported by pandas)
# not testing for types futher
# tibble(x=1, y=c(1, 2, 2), z=runif(3)) >> summarise(a=object())
# incompatible size
with pytest.raises(ValueError):
tibble(z=1) >> summarise(x=[1, 2, 3], y=[1, 2])
with pytest.raises(ValueError):
tibble(z=[1, 2]) >> group_by(f.z) >> summarise(x=[1, 2, 3], y=[1, 2])
with pytest.raises(ValueError):
(
tibble(z=c(1, 3))
>> group_by(f.z)
>> summarise(x=seq_len(f.z), y=[1, 2])
)
# Missing variable
with pytest.raises(KeyError):
summarise(mtcars, a=mean(f.not_there))
with pytest.raises(KeyError):
summarise(group_by(mtcars, f.cyl), a=mean(f.not_there))
# Duplicate column names
x = 1
df = tibble(x, x, _name_repair="minimal")
with pytest.raises(NameNonUniqueError):
df >> summarise(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_can_be_before_group_by():
df = tibble(id=c(1, 1, 2, 2, 2, 3, 3, 4, 4, 5),
year=c(2013, 2013, 2012, 2013, 2013, 2013, 2012, 2012, 2013,
2013),
var1=rnorm(10))
dfagg = df >> group_by(f.id, f.year) >> select(
f.id, f.year, f.var1) >> summarise(var1=mean(f.var1))
assert_iterable_equal(names(dfagg), ["id", "year", "var1"])
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 avg_weights_and_filter(owfiles):
_log("- Averaging bin weights")
ofile = outfile.parent / "_avg_weights_filtered.bed"
df = None
for owfile in owfiles:
tmp = pandas.read_csv(owfile, sep="\t", header=0)
df = df >> bind_rows(tmp)
df = df >> group_by(f.chrom1, f.start1, f.end1) >> summarise(
chrom=f.chrom1,
start=f.start1,
end=f.end1,
name=paste(f.name, collapse=":"),
score=mean(f.weight),
strand="+",
) >> filter_(
f.score >= cutoff
) >> ungroup() >> select(
~f.chrom1, ~f.start1, ~f.end1,
)
df.to_csv(ofile, sep="\t", index=False, header=False)
return ofile, len(df.columns)
def test_dup_keyword_args():
df = tibble(g=[1, 1], a=[1.0, 2.0]) >> group_by(f.g)
out = df >> summarise(_b=mean(f.a), b=f._b * 2)
assert_tibble_equal(out, tibble(g=1, b=3.0))
def test_freshly_create_vars():
df = tibble(x=range(1, 11))
out = summarise(df, y=mean(f.x), z=f.y + 1)
assert out.y.to_list() == [5.5]
assert out.z.to_list() == [6.5]
def test_0_groups():
df = tibble(x=1).loc[[], :] >> group_by(f.x)
res = df >> mutate(y=mean(f.x), z=+mean(f.x), n=n())
assert res.columns.tolist() == ["x", "y", "z", "n"]
rows = res >> nrow()
assert rows == 0
def test_with_groups__groups_eq_null_ungroups():
".groups = NULL ungroups"
gf = group_by(tibble(x=[1.0, 2.0]), f.x)
out = gf >> with_groups(NULL, mutate, y=mean(f.x))
assert out.y.tolist() == [1.5, 1.5]