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

Open
ntjohnson1 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add docstring examples for Aggregate window functions #1418

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
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")])
Comment on lines 2518 to +2524
Copy link
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]
Comment on lines +3082 to +3092
Copy link
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