From d5c679453221c0ca63e12aafa00a93707b575685 Mon Sep 17 00:00:00 2001 From: Work Date: Mon, 11 Aug 2025 20:37:28 -0700 Subject: [PATCH 1/4] DOC: Improve consistency in terminology and fix minor typos in documentation and comments --- README.md | 10 +++++----- pandas/_config/config.py | 4 ++-- pandas/_version.py | 2 +- pandas/core/accessor.py | 4 ++-- pandas/core/base.py | 2 +- pandas/core/indexing.py | 2 +- pandas/io/api.py | 2 +- pandas/io/common.py | 2 +- 8 files changed, 14 insertions(+), 14 deletions(-) diff --git a/README.md b/README.md index ebab2e6016850..a41a57d5e6a3d 100644 --- a/README.md +++ b/README.md @@ -19,7 +19,7 @@ **pandas** is a Python package that provides fast, flexible, and expressive data structures designed to make working with "relational" or "labeled" data both easy and intuitive. It aims to be the fundamental high-level building block for -doing practical, **real world** data analysis in Python. Additionally, it has +doing practical, **real-world** data analysis in Python. Additionally, it has the broader goal of becoming **the most powerful and flexible open source data analysis / manipulation tool available in any language**. It is already well on its way towards this goal. @@ -64,7 +64,7 @@ Here are just a few of the things that pandas does well: data sets - [**Hierarchical**][mi] labeling of axes (possible to have multiple labels per tick) - - Robust IO tools for loading data from [**flat files**][flat-files] + - Robust I/O tools for loading data from [**flat files**][flat-files] (CSV and delimited), [**Excel files**][excel], [**databases**][db], and saving/loading data from the ultrafast [**HDF5 format**][hdfstore] - [**Time series**][timeseries]-specific functionality: date range @@ -115,7 +115,7 @@ details, see the commit logs at https://github.com/pandas-dev/pandas. ## Dependencies - [NumPy - Adds support for large, multi-dimensional arrays, matrices and high-level mathematical functions to operate on these arrays](https://www.numpy.org) - [python-dateutil - Provides powerful extensions to the standard datetime module](https://dateutil.readthedocs.io/en/stable/index.html) -- [pytz - Brings the Olson tz database into Python which allows accurate and cross platform timezone calculations](https://github.com/stub42/pytz) +- [pytz - Brings the Olson tz database into Python which allows accurate and cross-platform timezone calculations](https://github.com/stub42/pytz) See the [full installation instructions](https://pandas.pydata.org/pandas-docs/stable/install.html#dependencies) for minimum supported versions of required, recommended and optional dependencies. @@ -138,7 +138,7 @@ or for installing in [development mode](https://pip.pypa.io/en/latest/cli/pip_in ```sh -python -m pip install -ve . --no-build-isolation -Ceditable-verbose=true +python -m pip install -ve . --no-build-isolation --config-settings editable-verbose=true ``` See the full instructions for [installing from source](https://pandas.pydata.org/docs/dev/development/contributing_environment.html). @@ -155,7 +155,7 @@ has been under active development since then. ## Getting Help -For usage questions, the best place to go to is [StackOverflow](https://stackoverflow.com/questions/tagged/pandas). +For usage questions, the best place to go to is [Stack Overflow](https://stackoverflow.com/questions/tagged/pandas). Further, general questions and discussions can also take place on the [pydata mailing list](https://groups.google.com/forum/?fromgroups#!forum/pydata). ## Discussion and Development diff --git a/pandas/_config/config.py b/pandas/_config/config.py index d42d90d44f82f..50dac1925c936 100644 --- a/pandas/_config/config.py +++ b/pandas/_config/config.py @@ -693,8 +693,8 @@ def _get_registered_option(key: str): def _translate_key(key: str) -> str: """ - if key id deprecated and a replacement key defined, will return the - replacement key, otherwise returns `key` as - is + if `key` is deprecated and a replacement key defined, will return the + replacement key, otherwise returns `key` as-is """ d = _get_deprecated_option(key) if d: diff --git a/pandas/_version.py b/pandas/_version.py index c5e3c16d3f773..54d5bb8c2dc91 100644 --- a/pandas/_version.py +++ b/pandas/_version.py @@ -581,7 +581,7 @@ def render_git_describe(pieces): def render_git_describe_long(pieces): """TAG-DISTANCE-gHEX[-dirty]. - Like 'git describe --tags --dirty --always -long'. + Like 'git describe --tags --dirty --always --long'. The distance/hash is unconditional. Exceptions: diff --git a/pandas/core/accessor.py b/pandas/core/accessor.py index 0331c26c805b6..47cf0452bc32c 100644 --- a/pandas/core/accessor.py +++ b/pandas/core/accessor.py @@ -88,7 +88,7 @@ def _add_delegate_accessors( cls Class to add the methods/properties to. delegate - Class to get methods/properties and doc-strings. + Class to get methods/properties and docstrings. accessors : list of str List of accessors to add. typ : {'property', 'method'} @@ -159,7 +159,7 @@ def delegate_names( Parameters ---------- delegate : object - The class to get methods/properties & doc-strings. + The class to get methods/properties & docstrings. accessors : Sequence[str] List of accessor to add. typ : {'property', 'method'} diff --git a/pandas/core/base.py b/pandas/core/base.py index 6cc28d4e46634..01ca90c96f1db 100644 --- a/pandas/core/base.py +++ b/pandas/core/base.py @@ -90,7 +90,7 @@ class PandasObject(DirNamesMixin): """ - Baseclass for various pandas objects. + Base class for various pandas objects. """ # results from calls to methods decorated with cache_readonly get added to _cache diff --git a/pandas/core/indexing.py b/pandas/core/indexing.py index f1f453cf433cf..9cf2e7b342725 100644 --- a/pandas/core/indexing.py +++ b/pandas/core/indexing.py @@ -1902,7 +1902,7 @@ def _setitem_with_indexer(self, indexer, value, name: str = "iloc") -> None: labels = index.insert(len(index), key) # We are expanding the Series/DataFrame values to match - # the length of thenew index `labels`. GH#40096 ensure + # the length of the new index `labels`. GH#40096 ensure # this is valid even if the index has duplicates. taker = np.arange(len(index) + 1, dtype=np.intp) taker[-1] = -1 diff --git a/pandas/io/api.py b/pandas/io/api.py index 5900c94384384..0d9f38999f787 100644 --- a/pandas/io/api.py +++ b/pandas/io/api.py @@ -1,5 +1,5 @@ """ -Data IO api +Data I/O API """ from pandas.io.clipboards import read_clipboard diff --git a/pandas/io/common.py b/pandas/io/common.py index 1a9e6b472463d..d7aca27aa7643 100644 --- a/pandas/io/common.py +++ b/pandas/io/common.py @@ -1,4 +1,4 @@ -"""Common IO api utilities""" +"""Common I/O API utilities""" from __future__ import annotations From f7883ef0e17e8f7e55ab8ffffa788fa85c1aedea Mon Sep 17 00:00:00 2001 From: Work Date: Mon, 11 Aug 2025 21:15:19 -0700 Subject: [PATCH 2/4] minor changes in README --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index f997d8f1a32a5..ebe37d3cff0e9 100644 --- a/README.md +++ b/README.md @@ -19,7 +19,7 @@ **pandas** is a Python package that provides fast, flexible, and expressive data structures designed to make working with "relational" or "labeled" data both easy and intuitive. It aims to be the fundamental high-level building block for -doing practical, **real world** data analysis in Python. Additionally, it has +doing practical, **real-world** data analysis in Python. Additionally, it has the broader goal of becoming **the most powerful and flexible open source data analysis / manipulation tool available in any language**. It is already well on its way towards this goal. @@ -64,7 +64,7 @@ Here are just a few of the things that pandas does well: data sets - [**Hierarchical**][mi] labeling of axes (possible to have multiple labels per tick) - - Robust IO tools for loading data from [**flat files**][flat-files] + - Robust I/O tools for loading data from [**flat files**][flat-files] (CSV and delimited), [**Excel files**][excel], [**databases**][db], and saving/loading data from the ultrafast [**HDF5 format**][hdfstore] - [**Time series**][timeseries]-specific functionality: date range @@ -155,7 +155,7 @@ has been under active development since then. ## Getting Help -For usage questions, the best place to go to is [StackOverflow](https://stackoverflow.com/questions/tagged/pandas). +For usage questions, the best place to go to is [Stack Overflow](https://stackoverflow.com/questions/tagged/pandas). Further, general questions and discussions can also take place on the [pydata mailing list](https://groups.google.com/forum/?fromgroups#!forum/pydata). ## Discussion and Development From 8e512dd5561f356a7444d9e1eaf62fa408ba15be Mon Sep 17 00:00:00 2001 From: Maitrey Talware Date: Tue, 12 Aug 2025 04:38:53 +0000 Subject: [PATCH 3/4] fix for pre-commit --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index ebe37d3cff0e9..904899d01180a 100644 --- a/README.md +++ b/README.md @@ -187,4 +187,4 @@ As contributors and maintainers to this project, you are expected to abide by pa
-[Go to Top](#table-of-contents) \ No newline at end of file +[Go to Top](#table-of-contents) From c27bc4a09d3118aeef4e9f3932778d5697b8b082 Mon Sep 17 00:00:00 2001 From: Maitrey Talware Date: Tue, 12 Aug 2025 05:58:17 +0000 Subject: [PATCH 4/4] more documentation related fixes --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 904899d01180a..264c2ad40ad31 100644 --- a/README.md +++ b/README.md @@ -20,8 +20,8 @@ structures designed to make working with "relational" or "labeled" data both easy and intuitive. It aims to be the fundamental high-level building block for doing practical, **real-world** data analysis in Python. Additionally, it has -the broader goal of becoming **the most powerful and flexible open source data -analysis / manipulation tool available in any language**. It is already well on +the broader goal of becoming **the most powerful and flexible open-source data +analysis/manipulation tool available in any language**. It is already well on its way towards this goal. ## Table of Contents