-
Notifications
You must be signed in to change notification settings - Fork 151
Add docstring examples for Scalar trigonometric functions #1411
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.
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
Merged
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,30 @@ | ||
| # Licensed to the Apache Software Foundation (ASF) under one | ||
| # or more contributor license agreements. See the NOTICE file | ||
| # distributed with this work for additional information | ||
| # regarding copyright ownership. The ASF licenses this file | ||
| # to you under the Apache License, Version 2.0 (the | ||
| # "License"); you may not use this file except in compliance | ||
| # with the License. You may obtain a copy of the License at | ||
| # | ||
| # http://www.apache.org/licenses/LICENSE-2.0 | ||
| # | ||
| # Unless required by applicable law or agreed to in writing, | ||
| # software distributed under the License is distributed on an | ||
| # "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY | ||
| # KIND, either express or implied. See the License for the | ||
| # specific language governing permissions and limitations | ||
| # under the License. | ||
|
|
||
| """Pytest configuration for doctest namespace injection.""" | ||
|
|
||
| import numpy as np | ||
| import pytest | ||
|
|
||
| import datafusion as dfn | ||
|
|
||
|
|
||
| @pytest.fixture(autouse=True) | ||
| def _doctest_namespace(doctest_namespace: dict) -> None: | ||
| """Add common imports to the doctest namespace.""" | ||
| doctest_namespace["dfn"] = dfn | ||
| doctest_namespace["np"] = np |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -491,16 +491,28 @@ def abs(arg: Expr) -> Expr: | |
| def acos(arg: Expr) -> Expr: | ||
| """Returns the arc cosine or inverse cosine of a number. | ||
|
|
||
| Returns: | ||
| -------- | ||
| Expr | ||
| A new expression representing the arc cosine of the input expression. | ||
| Examples: | ||
| --------- | ||
| >>> ctx = dfn.SessionContext() | ||
| >>> df = ctx.from_pydict({"a": [1.0]}) | ||
| >>> result = df.select(dfn.functions.acos(dfn.col("a")).alias("acos")) | ||
| >>> result.collect_column("acos")[0].as_py() | ||
| 0.0 | ||
| """ | ||
| return Expr(f.acos(arg.expr)) | ||
|
|
||
|
|
||
| def acosh(arg: Expr) -> Expr: | ||
| """Returns inverse hyperbolic cosine.""" | ||
| """Returns inverse hyperbolic cosine. | ||
|
|
||
| Examples: | ||
| --------- | ||
| >>> ctx = dfn.SessionContext() | ||
| >>> df = ctx.from_pydict({"a": [1.0]}) | ||
| >>> result = df.select(dfn.functions.acosh(dfn.col("a")).alias("acosh")) | ||
| >>> result.collect_column("acosh")[0].as_py() | ||
| 0.0 | ||
| """ | ||
| return Expr(f.acosh(arg.expr)) | ||
|
|
||
|
|
||
|
|
@@ -510,27 +522,74 @@ def ascii(arg: Expr) -> Expr: | |
|
|
||
|
|
||
| def asin(arg: Expr) -> Expr: | ||
| """Returns the arc sine or inverse sine of a number.""" | ||
| """Returns the arc sine or inverse sine of a number. | ||
|
|
||
| Examples: | ||
| --------- | ||
| >>> ctx = dfn.SessionContext() | ||
| >>> df = ctx.from_pydict({"a": [0.0]}) | ||
| >>> result = df.select(dfn.functions.asin(dfn.col("a")).alias("asin")) | ||
| >>> result.collect_column("asin")[0].as_py() | ||
| 0.0 | ||
| """ | ||
| return Expr(f.asin(arg.expr)) | ||
|
|
||
|
|
||
| def asinh(arg: Expr) -> Expr: | ||
| """Returns inverse hyperbolic sine.""" | ||
| """Returns inverse hyperbolic sine. | ||
|
|
||
| Examples: | ||
| --------- | ||
| >>> ctx = dfn.SessionContext() | ||
| >>> df = ctx.from_pydict({"a": [0.0]}) | ||
| >>> result = df.select(dfn.functions.asinh(dfn.col("a")).alias("asinh")) | ||
| >>> result.collect_column("asinh")[0].as_py() | ||
| 0.0 | ||
| """ | ||
| return Expr(f.asinh(arg.expr)) | ||
|
|
||
|
|
||
| def atan(arg: Expr) -> Expr: | ||
| """Returns inverse tangent of a number.""" | ||
| """Returns inverse tangent of a number. | ||
|
|
||
| Examples: | ||
| --------- | ||
| >>> ctx = dfn.SessionContext() | ||
| >>> df = ctx.from_pydict({"a": [0.0]}) | ||
| >>> result = df.select(dfn.functions.atan(dfn.col("a")).alias("atan")) | ||
| >>> result.collect_column("atan")[0].as_py() | ||
| 0.0 | ||
| """ | ||
| return Expr(f.atan(arg.expr)) | ||
|
|
||
|
|
||
| def atanh(arg: Expr) -> Expr: | ||
| """Returns inverse hyperbolic tangent.""" | ||
| """Returns inverse hyperbolic tangent. | ||
|
|
||
| Examples: | ||
| --------- | ||
| >>> ctx = dfn.SessionContext() | ||
| >>> df = ctx.from_pydict({"a": [0.0]}) | ||
| >>> result = df.select(dfn.functions.atanh(dfn.col("a")).alias("atanh")) | ||
| >>> result.collect_column("atanh")[0].as_py() | ||
| 0.0 | ||
| """ | ||
| return Expr(f.atanh(arg.expr)) | ||
|
|
||
|
|
||
| def atan2(y: Expr, x: Expr) -> Expr: | ||
| """Returns inverse tangent of a division given in the argument.""" | ||
| """Returns inverse tangent of a division given in the argument. | ||
|
|
||
| Examples: | ||
| --------- | ||
| >>> ctx = dfn.SessionContext() | ||
| >>> df = ctx.from_pydict({"y": [0.0], "x": [1.0]}) | ||
| >>> result = df.select( | ||
| ... dfn.functions.atan2(dfn.col("y"), dfn.col("x")).alias("atan2")) | ||
| >>> result = result | ||
ntjohnson1 marked this conversation as resolved.
Outdated
Show resolved
Hide resolved
|
||
| >>> result.collect_column("atan2")[0].as_py() | ||
| 0.0 | ||
| """ | ||
| return Expr(f.atan2(y.expr, x.expr)) | ||
|
|
||
|
|
||
|
|
@@ -581,22 +640,65 @@ def coalesce(*args: Expr) -> Expr: | |
|
|
||
|
|
||
| def cos(arg: Expr) -> Expr: | ||
| """Returns the cosine of the argument.""" | ||
| """Returns the cosine of the argument. | ||
|
|
||
| Examples: | ||
| --------- | ||
| >>> ctx = dfn.SessionContext() | ||
| >>> df = ctx.from_pydict({"a": [0,-1,1]}) | ||
| >>> cos_df = df.select(dfn.functions.cos(dfn.col("a")).alias("cos")) | ||
| >>> cos_df.collect_column("cos")[0].as_py() | ||
| 1.0 | ||
| """ | ||
| return Expr(f.cos(arg.expr)) | ||
|
|
||
|
|
||
| def cosh(arg: Expr) -> Expr: | ||
| """Returns the hyperbolic cosine of the argument.""" | ||
| """Returns the hyperbolic cosine of the argument. | ||
|
|
||
| Examples: | ||
| --------- | ||
| >>> ctx = dfn.SessionContext() | ||
| >>> df = ctx.from_pydict({"a": [0,-1,1]}) | ||
| >>> cosh_df = df.select(dfn.functions.cosh(dfn.col("a")).alias("cosh")) | ||
| >>> cosh_df.collect_column("cosh")[0].as_py() | ||
| 1.0 | ||
| """ | ||
| return Expr(f.cosh(arg.expr)) | ||
|
|
||
|
|
||
| def cot(arg: Expr) -> Expr: | ||
| """Returns the cotangent of the argument.""" | ||
| """Returns the cotangent of the argument. | ||
|
|
||
| Examples: | ||
| --------- | ||
| >>> from math import pi | ||
| >>> ctx = dfn.SessionContext() | ||
| >>> df = ctx.from_pydict({"a": [pi / 4]}) | ||
| >>> import builtins | ||
|
Contributor
Author
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. If we don't like builtins then doctest has an ellipses notation for the expected returned values as well. |
||
| >>> result = df.select( | ||
| ... dfn.functions.cot(dfn.col("a")).alias("cot") | ||
| ... ) | ||
| >>> builtins.round( | ||
| ... result.collect_column("cot")[0].as_py(), 1 | ||
| ... ) | ||
| 1.0 | ||
| """ | ||
| return Expr(f.cot(arg.expr)) | ||
|
|
||
|
|
||
| def degrees(arg: Expr) -> Expr: | ||
| """Converts the argument from radians to degrees.""" | ||
| """Converts the argument from radians to degrees. | ||
|
|
||
| Examples: | ||
| --------- | ||
| >>> from math import pi | ||
| >>> ctx = dfn.SessionContext() | ||
| >>> df = ctx.from_pydict({"a": [0,pi,2*pi]}) | ||
| >>> deg_df = df.select(dfn.functions.degrees(dfn.col("a")).alias("deg")) | ||
| >>> deg_df.collect_column("deg")[2].as_py() | ||
| 360.0 | ||
| """ | ||
| return Expr(f.degrees(arg.expr)) | ||
|
|
||
|
|
||
|
|
@@ -774,7 +876,22 @@ def pow(base: Expr, exponent: Expr) -> Expr: | |
|
|
||
|
|
||
| def radians(arg: Expr) -> Expr: | ||
| """Converts the argument from degrees to radians.""" | ||
| """Converts the argument from degrees to radians. | ||
|
|
||
| Examples: | ||
| --------- | ||
| >>> 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 | ||
| """ | ||
| return Expr(f.radians(arg.expr)) | ||
|
|
||
|
|
||
|
|
@@ -935,12 +1052,30 @@ def signum(arg: Expr) -> Expr: | |
|
|
||
|
|
||
| def sin(arg: Expr) -> Expr: | ||
| """Returns the sine of the argument.""" | ||
| """Returns the sine of the argument. | ||
|
|
||
| Examples: | ||
| --------- | ||
| >>> ctx = dfn.SessionContext() | ||
| >>> df = ctx.from_pydict({"a": [0.0]}) | ||
| >>> result = df.select(dfn.functions.sin(dfn.col("a")).alias("sin")) | ||
| >>> result.collect_column("sin")[0].as_py() | ||
| 0.0 | ||
| """ | ||
| return Expr(f.sin(arg.expr)) | ||
|
|
||
|
|
||
| def sinh(arg: Expr) -> Expr: | ||
| """Returns the hyperbolic sine of the argument.""" | ||
| """Returns the hyperbolic sine of the argument. | ||
|
|
||
| Examples: | ||
| --------- | ||
| >>> ctx = dfn.SessionContext() | ||
| >>> df = ctx.from_pydict({"a": [0.0]}) | ||
| >>> result = df.select(dfn.functions.sinh(dfn.col("a")).alias("sinh")) | ||
| >>> result.collect_column("sinh")[0].as_py() | ||
| 0.0 | ||
| """ | ||
| return Expr(f.sinh(arg.expr)) | ||
|
|
||
|
|
||
|
|
@@ -988,12 +1123,30 @@ def substring(string: Expr, position: Expr, length: Expr) -> Expr: | |
|
|
||
|
|
||
| def tan(arg: Expr) -> Expr: | ||
| """Returns the tangent of the argument.""" | ||
| """Returns the tangent of the argument. | ||
|
|
||
| Examples: | ||
| --------- | ||
| >>> ctx = dfn.SessionContext() | ||
| >>> df = ctx.from_pydict({"a": [0.0]}) | ||
| >>> result = df.select(dfn.functions.tan(dfn.col("a")).alias("tan")) | ||
| >>> result.collect_column("tan")[0].as_py() | ||
| 0.0 | ||
| """ | ||
| return Expr(f.tan(arg.expr)) | ||
|
|
||
|
|
||
| def tanh(arg: Expr) -> Expr: | ||
| """Returns the hyperbolic tangent of the argument.""" | ||
| """Returns the hyperbolic tangent of the argument. | ||
|
|
||
| Examples: | ||
| --------- | ||
| >>> ctx = dfn.SessionContext() | ||
| >>> df = ctx.from_pydict({"a": [0.0]}) | ||
| >>> result = df.select(dfn.functions.tanh(dfn.col("a")).alias("tanh")) | ||
| >>> result.collect_column("tanh")[0].as_py() | ||
| 0.0 | ||
| """ | ||
| return Expr(f.tanh(arg.expr)) | ||
|
|
||
|
|
||
|
|
||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think it would be helpful to extract shared example setup, or align the example style with existing docstrings.
Most of the new examples duplicate the same
SessionContext/from_pydict/select/collect_columnflow with only the function name and literal changing. That is fine for a few functions, but the repetition will get expensive as more scalar helpers gain examples.It would be worth standardizing on a small doctest helper namespace or a more consistent public-facing import style so future additions do not copy-paste boilerplate across dozens of docstrings.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think there is value in the examples being copy pastable/fully stand alone if it's only a few lines of boilerplate. For reference numpy https://numpy.org/doc/2.4/reference/generated/numpy.inner.html#numpy.inner.
Expensive computationally or for maintenance? This is inline with the style from the existing doc examples as far as I can tell https://github.com/rerun-io/datafusion-python/blob/231ed2b1d375fefe9aa01cdc8ae41c620c772f76/python/datafusion/dataframe.py#L324
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I see your point and it is defensible that each example is self-contained.
maintenance.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes, there is definitely a bit of maintenance trade off between the documentation value and pain if there is a large refactor that requires updating the docs examples.
I think there is value to the standalone but am open to opinions on this since I'm not a primary maintainer. My hope is that after the first large landing of these examples this is kind of just a small additional test surface so it's not more cumbersome than updating tests when api changes happen.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think given the rise of LLMs the maintenance is likely easier now