def test_null_count(df: pl.DataFrame) -> None:
# note: the zero-row and zero-col cases are always passed as explicit examples
null_count, ncols = df.null_count(), len(df.columns)
if ncols == 0:
assert null_count.shape == (0, 0)
else:
assert null_count.shape == (1, ncols)
for idx, count in enumerate(null_count.rows()[0]):
assert count == sum(v is None
for v in df.select_at_idx(idx).to_list())
print(null_count.rows())
def test_strategy_null_probability(
s: pl.Series,
df1: pl.DataFrame,
df2: pl.DataFrame,
df3: pl.DataFrame,
) -> None:
for obj in (s, df1, df2, df3):
assert len(obj) == 50 # type: ignore[arg-type]
assert s.null_count() < df1.null_count().fold(sum).sum()
assert df1.null_count().fold(sum).sum() < df2.null_count().fold(sum).sum()
assert df2.null_count().fold(sum).sum() < df3.null_count().fold(sum).sum()
nulls_col0, nulls_col1 = df2.null_count().rows()[0]
assert nulls_col0 > nulls_col1
assert nulls_col0 < 50
nulls_col0, nulls_colx = df3.null_count().rows()[0]
assert nulls_col0 > nulls_colx
assert nulls_col0 == 50
def test_null_count():
df = DataFrame({"a": [2, 1, 3], "b": ["a", "b", None]})
assert df.null_count().shape == (1, 2)