Skip to content

Add docstring examples for Aggregate window functions #1418

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

Merged
kosiew merged 8 commits into from
Mar 19, 2026
Merged

Add docstring examples for Aggregate window functions #1418

Changes from 1 commit
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
548cddb
Add docstring examples for Aggregate window functions
ntjohnson1 Mar 5, 2026
abe668d
Remove for example for example docstring
ntjohnson1 Mar 14, 2026
66f1a04
Actually remove all for example calls in favor of docstrings
ntjohnson1 Mar 14, 2026
401baa7
Remove builtins
ntjohnson1 Mar 14, 2026
b464214
Make google docstyle
ntjohnson1 Mar 14, 2026
f217ddd
Merge branch 'main' of github.com:apache/datafusion-python into nick/…
ntjohnson1 Mar 17, 2026
4b6e351
Fix bad merge leading to duplicate xample
ntjohnson1 Mar 17, 2026
7871f12
Merge branch 'main' of github.com:apache/datafusion-python into nick/…
ntjohnson1 Mar 18, 2026
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
104 changes: 104 additions & 0 deletions python/datafusion/functions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2516,6 +2516,14 @@ def first_value(
For example::

df.aggregate([], first_value(col("a"), order_by="ts"))

Examples:
---------
>>> ctx = dfn.SessionContext()
>>> df = ctx.from_pydict({"a": [10, 20, 30]})
>>> result = df.aggregate([], [dfn.functions.first_value(dfn.col("a")).alias("v")])
Copy link
Copy Markdown
Contributor

@kosiew kosiew Mar 13, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

2518: df.aggregate([], expr)

2524: ...df.aggregate([], [expr])

Mixing both forms inside the same docstring makes the API shape feel less crisp than it could be.

Same observation for first_value, last_value, and nth_value

>>> result.collect_column("v")[0].as_py()
10
"""
order_by_raw = sort_list_to_raw_sort_list(order_by)
filter_raw = filter.expr if filter is not None else None
Expand Down Expand Up @@ -2553,6 +2561,14 @@ def last_value(
For example::

df.aggregate([], last_value(col("a"), order_by="ts"))

Examples:
---------
>>> ctx = dfn.SessionContext()
>>> df = ctx.from_pydict({"a": [10, 20, 30]})
>>> result = df.aggregate([], [dfn.functions.last_value(dfn.col("a")).alias("v")])
>>> result.collect_column("v")[0].as_py()
30
"""
order_by_raw = sort_list_to_raw_sort_list(order_by)
filter_raw = filter.expr if filter is not None else None
Expand Down Expand Up @@ -2592,6 +2608,14 @@ def nth_value(
For example::

df.aggregate([], nth_value(col("a"), 2, order_by="ts"))

Examples:
---------
>>> ctx = dfn.SessionContext()
>>> df = ctx.from_pydict({"a": [10, 20, 30]})
>>> result = df.aggregate([], [dfn.functions.nth_value(dfn.col("a"), 2).alias("v")])
>>> result.collect_column("v")[0].as_py()
20
"""
order_by_raw = sort_list_to_raw_sort_list(order_by)
filter_raw = filter.expr if filter is not None else None
Expand Down Expand Up @@ -2732,6 +2756,16 @@ def lead(
For example::

lead(col("b"), order_by="ts")

Examples:
---------
>>> ctx = dfn.SessionContext()
>>> df = ctx.from_pydict({"a": [1, 2, 3]})
>>> result = df.select(
... dfn.col("a"), dfn.functions.lead(dfn.col("a"), shift_offset=1,
... default_value=0, order_by="a").alias("lead"))
>>> result.sort(dfn.col("a")).collect_column("lead").to_pylist()
[2, 3, 0]
"""
if not isinstance(default_value, pa.Scalar) and default_value is not None:
default_value = pa.scalar(default_value)
Expand Down Expand Up @@ -2787,6 +2821,16 @@ def lag(
For example::

lag(col("b"), order_by="ts")

Examples:
---------
>>> ctx = dfn.SessionContext()
>>> df = ctx.from_pydict({"a": [1, 2, 3]})
>>> result = df.select(
... dfn.col("a"), dfn.functions.lag(dfn.col("a"), shift_offset=1,
... default_value=0, order_by="a").alias("lag"))
>>> result.sort(dfn.col("a")).collect_column("lag").to_pylist()
[0, 1, 2]
"""
if not isinstance(default_value, pa.Scalar):
default_value = pa.scalar(default_value)
Expand Down Expand Up @@ -2832,6 +2876,15 @@ def row_number(
For example::

row_number(order_by="points")

Examples:
---------
>>> ctx = dfn.SessionContext()
>>> df = ctx.from_pydict({"a": [10, 20, 30]})
>>> result = df.select(
... dfn.col("a"), dfn.functions.row_number(order_by="a").alias("rn"))
>>> result.sort(dfn.col("a")).collect_column("rn").to_pylist()
[1, 2, 3]
"""
partition_by_raw = expr_list_to_raw_expr_list(partition_by)
order_by_raw = sort_list_to_raw_sort_list(order_by)
Expand Down Expand Up @@ -2876,6 +2929,14 @@ def rank(
For example::

rank(order_by="points")

Examples:
---------
>>> ctx = dfn.SessionContext()
>>> df = ctx.from_pydict({"a": [10, 10, 20]})
>>> result = df.select(dfn.col("a"), dfn.functions.rank(order_by="a").alias("rnk"))
>>> result.sort(dfn.col("a")).collect_column("rnk").to_pylist()
[1, 1, 3]
"""
partition_by_raw = expr_list_to_raw_expr_list(partition_by)
order_by_raw = sort_list_to_raw_sort_list(order_by)
Expand Down Expand Up @@ -2915,6 +2976,15 @@ def dense_rank(
For example::

dense_rank(order_by="points")

Examples:
---------
>>> ctx = dfn.SessionContext()
>>> df = ctx.from_pydict({"a": [10, 10, 20]})
>>> result = df.select(
... dfn.col("a"), dfn.functions.dense_rank(order_by="a").alias("dr"))
>>> result.sort(dfn.col("a")).collect_column("dr").to_pylist()
[1, 1, 2]
"""
partition_by_raw = expr_list_to_raw_expr_list(partition_by)
order_by_raw = sort_list_to_raw_sort_list(order_by)
Expand Down Expand Up @@ -2955,6 +3025,15 @@ def percent_rank(
For example::

percent_rank(order_by="points")

Examples:
---------
>>> ctx = dfn.SessionContext()
>>> df = ctx.from_pydict({"a": [10, 20, 30]})
>>> result = df.select(
... dfn.col("a"), dfn.functions.percent_rank(order_by="a").alias("pr"))
>>> result.sort(dfn.col("a")).collect_column("pr").to_pylist()
[0.0, 0.5, 1.0]
"""
partition_by_raw = expr_list_to_raw_expr_list(partition_by)
order_by_raw = sort_list_to_raw_sort_list(order_by)
Expand Down Expand Up @@ -2995,6 +3074,22 @@ def cume_dist(
For example::

cume_dist(order_by="points")

Examples:
---------
>>> ctx = dfn.SessionContext()
>>> df = ctx.from_pydict({"a": [10, 10, 20]})
>>> import builtins
>>> result = df.select(
... dfn.col("a"),
... dfn.functions.cume_dist(
... order_by="a"
... ).alias("cd")
... )
>>> [builtins.round(x, 4) for x in
... result.sort(dfn.col("a")
... ).collect_column("cd").to_pylist()]
[0.6667, 0.6667, 1.0]
Copy link
Copy Markdown
Contributor

@kosiew kosiew Mar 13, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think this would be a simpler example without builtin:

>>> ctx = dfn.SessionContext()
>>> df = ctx.from_pydict({"a": [1, 2, 2, 3]})
>>> result = df.select(cume_dist(col("a"))).collect()[0]
>>> rounded = [round(x, 2) for x in result.column(0)]
>>> rounded
[0.25, 0.75, 0.75, 1.0]

"""
partition_by_raw = expr_list_to_raw_expr_list(partition_by)
order_by_raw = sort_list_to_raw_sort_list(order_by)
Expand Down Expand Up @@ -3039,6 +3134,15 @@ def ntile(
For example::

ntile(3, order_by="points")

Examples:
---------
>>> ctx = dfn.SessionContext()
>>> df = ctx.from_pydict({"a": [10, 20, 30, 40]})
>>> result = df.select(
... dfn.col("a"), dfn.functions.ntile(2, order_by="a").alias("nt"))
>>> result.sort(dfn.col("a")).collect_column("nt").to_pylist()
[1, 1, 2, 2]
"""
partition_by_raw = expr_list_to_raw_expr_list(partition_by)
order_by_raw = sort_list_to_raw_sort_list(order_by)
Expand Down
Loading