def test_pull_nest_df_col():
df = tibble(x=1, y=tibble(a=2))
out = pull(df, 1, to="list")
assert out == [[2]]
out = pull(df, 1)
assert_tibble_equal(out, tibble(a=2))
def test_add_tally_can_be_given_a_weighting_variable():
df = tibble(a=c(1, 1, 2, 2, 2), w=c(1, 1, 2, 3, 4))
out = df >> group_by(f.a) >> add_tally(wt=f.w) >> pull(f.n, to="list")
assert out == [2, 2, 9, 9, 9]
out = df >> group_by(f.a) >> add_tally(wt=f.w + 1) >> pull(f.n, to="list")
assert out == [4, 4, 12, 12, 12]
def test_pull_a_flat_dict():
df = tibble(x=[1, 2], y=[3, 4])
out = df >> pull(f.y, f.x)
assert out == {1: 3, 2: 4}
with pytest.raises(ValueError):
# length mismatches
df >> pull(f.y, name=[3, 4, 5], to="dict")
def test_pull_series_when_to_equals_series():
df = tibble(**{"x$a": 1})
out = df >> pull(f.x, to="series")
assert len(out) == 1
assert out.values.tolist() == [1]
# with name
out = df >> pull(f.x, to="series", name="a")
assert out.name == "a"
def test_cur_group_rows():
df = tibble(x=c("b", "a", "b"), y=[1, 2, 3])
gf = df >> group_by(f.x, _sort=True)
out = gf >> summarise(x=cur_group_rows()) >> pull()
assert out.values.tolist() == [[1], [0, 2]]
# data frame
out = df >> summarise(x=cur_group_rows()) >> pull()
assert out.values.tolist() == [[0, 1, 2]]
def test_cur_group():
df = tibble(g=1, x=1)
gf = df >> group_by(f.g)
out = df >> summarise(key=cur_group()) >> pull(f.key)
assert len(out) == 1
assert_iterable_equal(out, [np.nan])
out = gf >> summarise(key=cur_group()) >> pull(f.key, to="list")
assert len(out) == 1
assert out[0].equals(tibble(g=1))
def test_pull_series_with_name():
df = tibble(x=1)
out = df >> pull(f.x, to="frame", name="a")
assert dim(out) == (1, 1)
assert out.columns.tolist() == ["a"]
with pytest.raises(ValueError):
df >> pull(f.x, to="frame", name=["a", "b"])
# pull array
out = df >> pull(f.x, to="array")
assert isinstance(out, np.ndarray)
def test_pull_df():
df = tibble(**{"x$a": 1, "x$b": 2})
out = df >> pull(f.x, to="series")
assert len(out) == 2
assert out["a"].values.tolist() == [1]
assert out["b"].values.tolist() == [2]
with pytest.raises(ValueError):
df >> pull(f.x, to="series", name=["a"])
out = df >> pull(f.x, to="series", name=["c", "d"])
assert len(out) == 2
assert out["c"].values.tolist() == [1]
assert out["d"].values.tolist() == [2]
def test_n_distinct_handles_in_na_rm():
d = tibble(x=c([1, 2, 3, 4], NA))
yes = True
no = False
out = d >> summarise(n=n_distinct(f.x, na_rm=True)) >> pull(to="list")
assert out == [4]
out = d >> summarise(n=n_distinct(f.x, na_rm=False)) >> pull(to="list")
assert out == [5]
out = d >> summarise(n=n_distinct(f.x, na_rm=yes)) >> pull(to="list")
assert out == [4]
out = d >> summarise(n=n_distinct(f.x, na_rm=no)) >> pull(to="list")
assert out == [5]
out = (d >> summarise(n=n_distinct(f.x, na_rm=True or True)) >>
pull(to="list"))
assert out == [4]
def test_cur_data_all():
df = tibble(x=c("b", "a", "b"), y=[1, 2, 3])
gf = df >> group_by(f.x, _sort=True)
out = df >> summarise(x=cur_data()) >> pull(f.x, to="list")
assert out[0].equals(df)
out = df >> summarise(x=cur_data_all()) >> pull(f.x, to="list")
assert out[0].equals(df)
out = gf >> summarise(x=cur_data()) >> pull(f.x)
assert out.values[0].values.flatten().tolist() == [2]
assert out.values[1].values.flatten().tolist() == [1, 3]
out = gf >> summarise(x=cur_data_all()) >> pull(f.x)
assert out.values[0].values.flatten().tolist() == ["a", 2]
assert out.values[1].values.flatten().tolist() == ["b", 1, "b", 3]
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_inside_mutate():
out = (mtcars >> get(f[:4]) >>
mutate(out=case_when(f.cyl == 4, 1, f["am"] == 1, 2, True, 0)) >>
pull(to="list"))
assert out == [2, 2, 1, 0]
def test_mutate_None_preserves_correct_all_vars():
df = (tibble(x=1, y=2) >> mutate(x=None, vars=cur_data_all()) >> pull(
f.vars))
exp = tibble(y=2)
assert_tibble_equal(df[0], exp)
def test_pull_grouped():
df = tibble(x=1, y=2).group_by('x')
out = pull(df, f.y)
assert isinstance(out, Series)
assert out.tolist() == [2]
def test_ntile_does_not_overflow():
m = int(1e2)
res = tibble(a=range(1, m + 1)) >> mutate(b=ntile(f.a, n=m)) >> count(
f.b) >> pull(to='list')
assert sum(res) == 100
def test_weighted_tally_drops_nas():
df = tibble(x=c(1, 1, NA))
out = tally(df, f.x) >> pull(to="list")
assert out == [2]