Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix(python): Preserve Expr name in is_between #6661

Merged
merged 1 commit into from
Feb 3, 2023
Merged

fix(python): Preserve Expr name in is_between #6661

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 12 additions & 8 deletions py-polars/polars/internals/expr/expr.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3414,7 +3414,7 @@ def is_between(
Examples
--------
>>> df = pl.DataFrame({"num": [1, 2, 3, 4, 5]})
>>> df.with_columns(pl.col("num").is_between(2, 4))
>>> df.with_columns(pl.col("num").is_between(2, 4).alias("is_between"))
shape: (5, 2)
┌─────┬────────────┐
│ num ┆ is_between │
Expand All @@ -3430,7 +3430,9 @@ def is_between(

Use the ``closed`` argument to include or exclude the values at the bounds:

>>> df.with_columns(pl.col("num").is_between(2, 4, closed="left"))
>>> df.with_columns(
... pl.col("num").is_between(2, 4, closed="left").alias("is_between")
... )
shape: (5, 2)
┌─────┬────────────┐
│ num ┆ is_between │
Expand All @@ -3444,13 +3446,15 @@ def is_between(
│ 5 ┆ false │
└─────┴────────────┘

Can also use strings as well as numeric/temporal values (note: ensure that
You can also use strings as well as numeric/temporal values (note: ensure that
string literals are wrapped with ``lit`` so as not to conflate them with
column names):

>>> df = pl.DataFrame({"a": ["a", "b", "c", "d", "e"]})
>>> df.with_columns(
... pl.col("a").is_between(pl.lit("a"), pl.lit("c"), closed="both")
... pl.col("a")
... .is_between(pl.lit("a"), pl.lit("c"), closed="both")
... .alias("is_between")
... )
shape: (5, 2)
┌─────┬────────────┐
Expand All @@ -3469,13 +3473,13 @@ def is_between(
end = expr_to_lit_or_expr(end, str_to_lit=False)

if closed == "none":
return ((self > start) & (self < end)).alias("is_between")
return (self > start) & (self < end)
elif closed == "both":
return ((self >= start) & (self <= end)).alias("is_between")
return (self >= start) & (self <= end)
elif closed == "right":
return ((self > start) & (self <= end)).alias("is_between")
return (self > start) & (self <= end)
elif closed == "left":
return ((self >= start) & (self < end)).alias("is_between")
return (self >= start) & (self < end)
else:
raise ValueError(
"closed must be one of {'left', 'right', 'both', 'none'},"
Expand Down
50 changes: 17 additions & 33 deletions py-polars/tests/unit/test_lazy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1178,38 +1178,22 @@ def test_quantile(fruits_cars: pl.DataFrame) -> None:


def test_is_between(fruits_cars: pl.DataFrame) -> None:
result = fruits_cars.select(pl.col("A").is_between(2, 4))["is_between"]
assert_series_equal(
result, pl.Series("is_between", [False, True, True, True, False])
)
result = fruits_cars.select(pl.col("A").is_between(2, 4)).to_series()
assert_series_equal(result, pl.Series("A", [False, True, True, True, False]))

result = fruits_cars.select(pl.col("A").is_between(2, 4, closed="none"))[
"is_between"
]
assert_series_equal(
result, pl.Series("is_between", [False, False, True, False, False])
)
result = fruits_cars.select(pl.col("A").is_between(2, 4, closed="none")).to_series()
assert_series_equal(result, pl.Series("A", [False, False, True, False, False]))

result = fruits_cars.select(pl.col("A").is_between(2, 4, closed="both"))[
"is_between"
]
assert_series_equal(
result, pl.Series("is_between", [False, True, True, True, False])
)
result = fruits_cars.select(pl.col("A").is_between(2, 4, closed="both")).to_series()
assert_series_equal(result, pl.Series("A", [False, True, True, True, False]))

result = fruits_cars.select(pl.col("A").is_between(2, 4, closed="right"))[
"is_between"
]
assert_series_equal(
result, pl.Series("is_between", [False, False, True, True, False])
)
result = fruits_cars.select(
pl.col("A").is_between(2, 4, closed="right")
).to_series()
assert_series_equal(result, pl.Series("A", [False, False, True, True, False]))

result = fruits_cars.select(pl.col("A").is_between(2, 4, closed="left"))[
"is_between"
]
assert_series_equal(
result, pl.Series("is_between", [False, True, True, False, False])
)
result = fruits_cars.select(pl.col("A").is_between(2, 4, closed="left")).to_series()
assert_series_equal(result, pl.Series("A", [False, True, True, False, False]))


def test_is_between_data_types() -> None:
Expand All @@ -1231,29 +1215,29 @@ def test_is_between_data_types() -> None:
# on purpose, for float and int, we pass in a mixture of bound data types
assert_series_equal(
df.select(pl.col("flt").is_between(1, 2.3))[:, 0],
pl.Series("is_between", [True, True, False]),
pl.Series("flt", [True, True, False]),
)
assert_series_equal(
df.select(pl.col("int").is_between(1.5, 3))[:, 0],
pl.Series("is_between", [True, True, False]),
pl.Series("int", [True, True, False]),
)
assert_series_equal(
df.select(pl.col("date").is_between(date(2019, 1, 1), date(2020, 2, 5)))[:, 0],
pl.Series("is_between", [True, True, False]),
pl.Series("date", [True, True, False]),
)
assert_series_equal(
df.select(
pl.col("datetime").is_between(
datetime(2020, 1, 1, 5, 0, 0), datetime(2020, 1, 1, 11, 0, 0)
)
)[:, 0],
pl.Series("is_between", [False, True, False]),
pl.Series("datetime", [False, True, False]),
)
assert_series_equal(
df.select(
pl.col("str").is_between(pl.lit("str"), pl.lit("zzz"), closed="left")
)[:, 0],
pl.Series("is_between", [True, True, False]),
pl.Series("str", [True, True, False]),
)
assert_series_equal(
df.select(
Expand Down
4 changes: 2 additions & 2 deletions py-polars/tests/unit/test_series.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2053,8 +2053,8 @@ def test_is_between_datetime() -> None:
expected = pl.Series("a", [False, True])

# only on the expression api
result = s.to_frame().with_columns(pl.col("*").is_between(start, end))["is_between"]
assert_series_equal(result.rename("a"), expected)
result = s.to_frame().with_columns(pl.col("*").is_between(start, end)).to_series()
assert_series_equal(result, expected)


@pytest.mark.parametrize(
Expand Down