def test_slice_any_checks_for_constant_n_and_prop():
df = tibble(x=range(1, 11))
with pytest.raises(TypeError):
slice_head(df, n=f.x) # ok with n()
with pytest.raises(TypeError):
slice_head(df, prop=f.x)
with pytest.raises(TypeError):
slice_tail(df, n=f.x)
with pytest.raises(TypeError):
slice_tail(df, prop=f.x)
with pytest.raises(TypeError):
slice_min(df, f.x, n=f.x)
with pytest.raises(TypeError):
slice_min(df, f.x, prop=f.x)
with pytest.raises(TypeError):
slice_max(df, f.x, n=f.x)
with pytest.raises(TypeError):
slice_max(df, f.x, prop=f.x)
with pytest.raises(TypeError):
slice_sample(df, n=f.x)
with pytest.raises(TypeError):
slice_sample(df, prop=f.x)
def test_arguments_to_sample_are_passed_along():
df = tibble(x=range(1, 101), wt=c(1, rep(0, 99)))
out = df >> slice_sample(n=1, weight_by=f.wt)
assert out.x.tolist() == [1]
out = df >> slice_sample(n=2, weight_by=f.wt, replace=True)
assert out.x.tolist() == [1, 1]
def test_slice_family_on_rowwise_df():
df = tibble(x=f[1:6]) >> rowwise()
out = df >> slice_head(prop=0.1)
assert out.shape[0] == 0
out = df >> slice([0, 1, 2])
assert isinstance(out, TibbleRowwise)
assert nrow(out) == 5
out = df >> slice_head(n=3)
assert isinstance(out, TibbleRowwise)
assert nrow(out) == 5
out = df >> slice_tail(n=3)
assert isinstance(out, TibbleRowwise)
assert nrow(out) == 5
out = df >> slice_min(f.x, n=3)
assert isinstance(out, TibbleRowwise)
assert nrow(out) == 5
out = df >> slice_max(f.x, n=3)
assert isinstance(out, TibbleRowwise)
assert nrow(out) == 5
out = df >> slice_sample(n=3)
assert isinstance(out, TibbleRowwise)
assert nrow(out) == 5
def test_slicex_on_grouped_data():
gf = tibble(g=rep([1, 2], each=3), x=seq(1, 6)) >> group_by(f.g)
out = gf >> slice_min(f.x)
assert out.equals(tibble(g=[1, 2], x=[1, 4]))
out = gf >> slice_max(f.x)
assert out.equals(tibble(g=[1, 2], x=[3, 6]))
out = gf >> slice_sample()
assert dim(out) == (2, 2)
def test_functions_silently_truncate_results():
df = tibble(x=range(1, 6))
out = df >> slice_head(n=6) >> nrow()
assert out == 5
out = df >> slice_tail(n=6) >> nrow()
assert out == 5
out = df >> slice_sample(n=6) >> nrow()
assert out == 5
out = df >> slice_min(f.x, n=6) >> nrow()
assert out == 5
out = df >> slice_max(f.x, n=6) >> nrow()
assert out == 5
def test_preserve_prop_not_support(caplog):
df = tibble(x=f[:5]) >> group_by(f.x)
df >> slice(f.x == 2, _preserve=True)
assert "_preserve" in caplog.text
with pytest.raises(ValueError):
df >> slice_min(f.x, prop=0.5)
with pytest.raises(ValueError):
df >> slice_max(f.x, prop=0.5)
with pytest.raises(ValueError):
df >> slice_sample(f.x, prop=0.5)
def test_proportion_computed_correctly():
df = tibble(x=range(1, 11))
out = df >> slice_head(prop=0.11) >> nrow()
assert out == 1
out = df >> slice_tail(prop=0.11) >> nrow()
assert out == 1
out = df >> slice_sample(prop=0.11) >> nrow()
assert out == 1
out = df >> slice_min(f.x, prop=0.11) >> nrow()
assert out == 1
out = df >> slice_max(f.x, prop=0.11) >> nrow()
assert out == 1
out = df >> slice_max(f.x, prop=0.11, with_ties=False) >> nrow()
assert out == 1
out = df >> slice_min(f.x, prop=0.11, with_ties=False) >> nrow()
assert out == 1
def test_slice_sample_n_defaults_to_1():
df = tibble(g=rep([1, 2], each=3), x=seq(1, 6))
out = df >> slice_sample(n=None)
assert dim(out) == (1, 2)
def test_slice_sample_dose_not_error_on_0rows():
df = tibble(dummy=[], weight=[])
res = slice_sample(df, prop=0.5, weight_by=f.weight)
assert nrow(res) == 0