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 7 commits 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
7 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
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
141 changes: 91 additions & 50 deletions python/datafusion/functions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -823,14 +823,11 @@ def cot(arg: Expr) -> Expr:
>>> from math import pi
>>> ctx = dfn.SessionContext()
>>> df = ctx.from_pydict({"a": [pi / 4]})
>>> import builtins
>>> result = df.select(
... dfn.functions.cot(dfn.col("a")).alias("cot")
... )
>>> builtins.round(
... result.collect_column("cot")[0].as_py(), 1
... )
1.0
>>> result.collect_column("cot")[0].as_py()
1.0...
"""
return Expr(f.cot(arg.expr))

Expand Down Expand Up @@ -1171,14 +1168,11 @@ def radians(arg: Expr) -> Expr:
>>> from math import pi
>>> ctx = dfn.SessionContext()
>>> df = ctx.from_pydict({"a": [180.0]})
>>> import builtins
>>> result = df.select(
... dfn.functions.radians(dfn.col("a")).alias("rad")
... )
>>> builtins.round(
... result.collect_column("rad")[0].as_py(), 6
... )
3.141593
>>> result.collect_column("rad")[0].as_py()
3.14159...
"""
return Expr(f.radians(arg.expr))

Expand Down Expand Up @@ -2521,10 +2515,6 @@ def array_agg(
distinct: If True, a single entry for each distinct value will be in the result
filter: If provided, only compute against rows for which the filter is True
order_by: Order the resultant array values. Accepts column names or expressions.

For example::

df.aggregate([], array_agg(col("a"), order_by="b"))
"""
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 @@ -3081,9 +3071,14 @@ def first_value(
column names or expressions.
null_treatment: Assign whether to respect or ignore null values.

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")]
... )
>>> 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 @@ -3118,9 +3113,14 @@ def last_value(
column names or expressions.
null_treatment: Assign whether to respect or ignore null values.

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 @@ -3157,9 +3157,14 @@ def nth_value(
column names or expressions.
null_treatment: Assign whether to respect or ignore null values.

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 @@ -3337,9 +3342,14 @@ def lead(
order_by: Set ordering within the window frame. Accepts
column names or expressions.

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 @@ -3392,9 +3402,14 @@ def lag(
order_by: Set ordering within the window frame. Accepts
column names or expressions.

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 @@ -3437,9 +3452,13 @@ def row_number(
order_by: Set ordering within the window frame. Accepts
column names or expressions.

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 @@ -3481,9 +3500,14 @@ def rank(
order_by: Set ordering within the window frame. Accepts
column names or expressions.

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 @@ -3520,9 +3544,13 @@ def dense_rank(
order_by: Set ordering within the window frame. Accepts
column names or expressions.

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 @@ -3560,9 +3588,14 @@ def percent_rank(
order_by: Set ordering within the window frame. Accepts
column names or expressions.

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 @@ -3600,9 +3633,17 @@ def cume_dist(
order_by: Set ordering within the window frame. Accepts
column names or expressions.

For example::

cume_dist(order_by="points")
Examples:
>>> ctx = dfn.SessionContext()
>>> df = ctx.from_pydict({"a": [1., 2., 2., 3.]})
>>> result = df.select(
... dfn.col("a"),
... dfn.functions.cume_dist(
... order_by="a"
... ).alias("cd")
... )
>>> result.collect_column("cd").to_pylist()
[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 @@ -3644,9 +3685,13 @@ def ntile(
order_by: Set ordering within the window frame. Accepts
column names or expressions.

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 Expand Up @@ -3682,10 +3727,6 @@ def string_agg(
order_by: Set the ordering of the expression to evaluate. Accepts
column names or expressions.

For example::

df.aggregate([], string_agg(col("a"), ",", order_by="b"))

Examples:
---------
>>> ctx = dfn.SessionContext()
Expand Down
Loading