From c0d24068f6c31de846c98657e7ed96f0a06d2d1d Mon Sep 17 00:00:00 2001 From: Stefan Krawczyk Date: Thu, 23 Feb 2023 14:00:24 -0800 Subject: [PATCH] Migrates links to dagworks Updates appropriate links/wording too. --- CODE_OF_CONDUCT.md | 2 +- README.md | 3 +-- developer_setup.md | 6 +++--- docs/best-practices/loading-data.rst | 2 +- docs/conf.py | 2 +- docs/contributing.rst | 4 ++-- docs/extensions.rst | 12 ++++++------ docs/index.rst | 6 +++--- .../writing-your-first-dataflow.rst | 4 ++-- docs/license.rst | 3 +-- .../overview-of-concepts/the-hamilton-driver.rst | 2 +- .../api-extensions/custom-result-builders.rst | 2 +- docs/reference/api-extensions/index.rst | 2 +- .../api-reference/available-decorators.rst | 4 ++-- .../api-reference/available-drivers.rst | 2 +- .../api-reference/available-graph-adapters.rst | 12 ++++++------ .../api-reference/available-result-builders.rst | 6 +++--- docs/tutorials/dask.rst | 2 +- docs/tutorials/data-quality-checks.rst | 8 ++++---- docs/tutorials/model-training.rst | 2 +- docs/tutorials/ray.rst | 6 +++--- docs/tutorials/spark.rst | 2 +- examples/Dockerfile | 2 +- examples/data_loaders/README.md | 2 +- examples/dbt/README.md | 2 +- examples/polars/README.md | 2 +- hamilton/data_quality/default_validators.py | 2 +- hamilton/dev_utils/deprecation.py | 2 +- hamilton/function_modifiers/expanders.py | 6 +++--- hamilton/telemetry.py | 2 +- setup.py | 8 ++++---- tests/function_modifiers/test_recursive.py | 2 +- tests/resources/multiple_decorators_together.py | 2 +- tests/test_dev_utils.py | 16 ++++++++-------- 34 files changed, 70 insertions(+), 72 deletions(-) diff --git a/CODE_OF_CONDUCT.md b/CODE_OF_CONDUCT.md index 2a8832429..578450784 100644 --- a/CODE_OF_CONDUCT.md +++ b/CODE_OF_CONDUCT.md @@ -61,7 +61,7 @@ representative at an online or offline event. Instances of abusive, harassing, or otherwise unacceptable behavior may be reported to the community leaders responsible for enforcement at -algorithms-opensource@stitchfix.com. +opensource@dagworks.io. All complaints will be reviewed and investigated promptly and fairly. All community leaders are obligated to respect the privacy and security of the diff --git a/README.md b/README.md index c93f8bcfc..0961b596c 100644 --- a/README.md +++ b/README.md @@ -159,8 +159,7 @@ E.g. We have a small but active community on [slack](https://join.slack.com/t/hamilton-opensource/shared_invite/zt-1bjs72asx-wcUTgH7q7QX1igiQ5bbdcg). Come join us! # License -Hamilton is released under the [BSD 3-Clause Clear License](LICENSE). If you need to get in touch about something, -contact us at algorithms-opensource (at) stitchfix.com. +Hamilton is released under the [BSD 3-Clause Clear License](LICENSE). # Used internally by: * [Stitch Fix](https://www.stitchfix.com/) diff --git a/developer_setup.md b/developer_setup.md index 19f9e1fa0..faaef54b6 100644 --- a/developer_setup.md +++ b/developer_setup.md @@ -17,7 +17,7 @@ Fork this repo and clone your fork. ([GitHub docs](https://docs.github.com/en/pu GITHUB_USERNAME="YOUR-GITHUB-USERNAME" \ git clone https://github.com/${GITHUB_USERNAME}/hamilton.git cd ./hamilton -git remote add upstream https://github.com/stitchfix/hamilton.git +git remote add upstream https://github.com/dagworks-inc/hamilton.git ``` Install the project's dependencies in your preferred method for managing python dependencies. For example, run the following to use `venv`. @@ -70,7 +70,7 @@ pre-commit run --all-files ...and by following the steps in ["How to run unit tests"](#how-to-run-unit-tests). -Navigate to https://github.com/stitchfix/hamilton/pulls and open a pull request. +Navigate to https://github.com/dagworks-inc/hamilton/pulls and open a pull request. ## How to run unit tests @@ -152,7 +152,7 @@ These are the steps to push to pypi. This is taken from the [python packaging tu Now that you've pushed to pypi, announce your release! We plan to automate this, but for now... 1. Create a github release (select auto-generate release for painless text generation). Create a tag that's called `sf-hamilton-{version_string}`. -See [1.2.0](https://github.com/stitchfix/hamilton/releases/tag/sf-hamilton-1.2.0) for an example. +See [1.2.0](https://github.com/dagworks-inc/hamilton/releases/tag/sf-hamilton-1.2.0) for an example. 2. Announce on the #announcements channel in slack, following the format presented there. 3. Thanks for contributing! diff --git a/docs/best-practices/loading-data.rst b/docs/best-practices/loading-data.rst index 6b89dcdb2..861ada97f 100644 --- a/docs/best-practices/loading-data.rst +++ b/docs/best-practices/loading-data.rst @@ -111,7 +111,7 @@ Caching Data Load for Rapid Iteration ------------------------------------- Hamilton does not yet have caching built into the framework. That said, we are -`working on `_ introducing this as a feature and deciding on the scope +`working on `_ introducing this as a feature and deciding on the scope of the implementation. For now, however, the following decorator/toolset can allow you to cache data loaders based off of the parameters as well as the code itself. Use this at your own risk though, as it's not a fully functioning cache. This can be used as follows: diff --git a/docs/conf.py b/docs/conf.py index 7d11e8595..0f0a734d5 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -3,7 +3,7 @@ html_theme = "furo" html_title = "Hamilton" html_theme_options = { - "source_repository": "https://github.com/stitchfix/hamilton", + "source_repository": "https://github.com/dagworks-inc/hamilton", "source_branch": "main", "source_directory": "docs/", } diff --git a/docs/contributing.rst b/docs/contributing.rst index da6a1e010..da69e0ea8 100644 --- a/docs/contributing.rst +++ b/docs/contributing.rst @@ -4,7 +4,7 @@ Contributing For contributing guidelines see github. -We open contributions big and small. See our `contributing guidelines `_. +We open contributions big and small. See our `contributing guidelines `_. -We also operate under a `Code of Conduct `_, and +We also operate under a `Code of Conduct `_, and expect contributors to do the same. diff --git a/docs/extensions.rst b/docs/extensions.rst index a178a8f17..dca4f4d53 100644 --- a/docs/extensions.rst +++ b/docs/extensions.rst @@ -19,7 +19,7 @@ if you write Pandas code! All that's needed is to: #. Import system specific code to setup a client/cluster/etc for that distributed/scalable system. -#. Import a `GraphAdapter `_ that implements using that distributed/scalable system. See :doc:`reference/api-reference/available-graph-adapters` for what is available. +#. Import a `GraphAdapter `_ that implements using that distributed/scalable system. See :doc:`reference/api-reference/available-graph-adapters` for what is available. #. You may need to provide a specific module that knows how to load data into the scalable system. #. Pass the modules, and graph adapter to the Hamilton Driver. #. Proceed as you would normally. @@ -58,7 +58,7 @@ Ray - Experimental! `Ray `_ is a system to scale python workloads. Hamilton makes it very easy for you to use Ray. -See `Scaling Hamilton on Ray `_ +See `Scaling Hamilton on Ray `_ for an example of using Ray. Single Machine: @@ -81,7 +81,7 @@ Dask - Experimental! `Ray `_ is a system to scale python workloads. Hamilton makes it very easy for you to use Ray. -See `Scaling Hamilton on Dask `_ +See `Scaling Hamilton on Dask `_ for an example of using Dask to scale Hamilton computation. Single Machine: @@ -104,7 +104,7 @@ Koalas on Spark, a.k.a. Pandas API on Spark - Experimental! was the project code name to implement the `Pandas API on top of Spark `_. Hamilton makes it very easy for you to use Koalas on Spark. -See `Scaling Hamilton on Koalas `_ +See `Scaling Hamilton on Koalas `_ for an example of using Koalas on Spark to scale Hamilton computation. Single Machine: @@ -132,9 +132,9 @@ This means, that the result of ``execute()`` can be any python object type! How do you change the type of the object returned? ================================================== -You need to implement a `ResultMixin `_ if there +You need to implement a `ResultMixin `_ if there isn't one already defined for what you want to do. Then you need to provide that to a -`GraphAdapter `_, similar to what was presented +`GraphAdapter `_, similar to what was presented above. See :doc:`reference/api-reference/available-result-builders` for what is provided with Hamilton, or :doc:`reference/api-extensions/custom-result-builders` diff --git a/docs/index.rst b/docs/index.rst index 5ea5c5cee..55947ee8c 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -51,7 +51,7 @@ Hamilton unorganized-docs/index -The open source framework `Hamilton `_, originally built to manage and run Stitch +The open source framework `Hamilton `_, originally built to manage and run Stitch Fix's data pipelines. .. _getting started: @@ -142,8 +142,8 @@ For more information please see :doc:`less-than-15-minutes-to-mastery/installing License --------------- -Hamilton is released under the `BSD 3-Clause Clear License `_. -If you need to get in touch about something, contact us at algorithms-opensource (at) stitchfix.com. +Hamilton is released under the `BSD 3-Clause Clear License `_. +If you need to get in touch about something, contact us at opensource (at) dagworks.io. .. _contributing: diff --git a/docs/less-than-15-minutes-to-mastery/writing-your-first-dataflow.rst b/docs/less-than-15-minutes-to-mastery/writing-your-first-dataflow.rst index 917dbf8e7..a30e27e46 100644 --- a/docs/less-than-15-minutes-to-mastery/writing-your-first-dataflow.rst +++ b/docs/less-than-15-minutes-to-mastery/writing-your-first-dataflow.rst @@ -10,8 +10,8 @@ We're jumping in head-first. If you want to start with an overview, skip ahead t .. note:: - You can follow along in the `examples directory `_ - of the `hamilton repo `_. We highly recommend forking the repo and playing + You can follow along in the `examples directory `_ + of the `hamilton repo `_. We highly recommend forking the repo and playing around with the code to get comfortable. Writing some Transforms diff --git a/docs/license.rst b/docs/license.rst index a9e3f1199..37474085f 100644 --- a/docs/license.rst +++ b/docs/license.rst @@ -4,5 +4,4 @@ License Hamilton's open source license -Hamilton is released under the `BSD 3-Clause Clear License `_. -If you need to get in touch about something, contact us at algorithms-opensource (at) stitchfix.com. +Hamilton is released under the `BSD 3-Clause Clear License `_. diff --git a/docs/overview-of-concepts/the-hamilton-driver.rst b/docs/overview-of-concepts/the-hamilton-driver.rst index 3e42cf435..90f28cc13 100644 --- a/docs/overview-of-concepts/the-hamilton-driver.rst +++ b/docs/overview-of-concepts/the-hamilton-driver.rst @@ -191,7 +191,7 @@ Scaling Hamilton: Multi-core & Distributed Execution This functionality is currently in an "experimental" state. We think the code is solid, but it hasn't been used in a production environment for long. Thus the API to these GraphAdapters might change. -See the `experimental `_ package for the current +See the `experimental `_ package for the current implementations. We encourage you to give them a spin and provide us with feedback. See :doc:`../reference/api-reference/available-graph-adapters` for more details. diff --git a/docs/reference/api-extensions/custom-result-builders.rst b/docs/reference/api-extensions/custom-result-builders.rst index b98343c2a..b38337f39 100644 --- a/docs/reference/api-extensions/custom-result-builders.rst +++ b/docs/reference/api-extensions/custom-result-builders.rst @@ -14,7 +14,7 @@ through it can help ensure we aren't duplicating effort, and we can help steer y What you need to do ------------------- -You need to implement a class that implements a single function - see `github code `_: +You need to implement a class that implements a single function - see `github code `_: .. code-block:: python diff --git a/docs/reference/api-extensions/index.rst b/docs/reference/api-extensions/index.rst index d7d270645..34851c51f 100644 --- a/docs/reference/api-extensions/index.rst +++ b/docs/reference/api-extensions/index.rst @@ -12,5 +12,5 @@ API Extensions Currently the API extensions are all experimental. Note this doesn't mean they're not well-tested or thought out -- rather that we're actively looking for feedback. More docs upcoming, but for now fish around the -`experimental package `_, and give the +`experimental package `_, and give the extensions a try! diff --git a/docs/reference/api-reference/available-decorators.rst b/docs/reference/api-reference/available-decorators.rst index ba8cd1134..548715919 100644 --- a/docs/reference/api-reference/available-decorators.rst +++ b/docs/reference/api-reference/available-decorators.rst @@ -4,7 +4,7 @@ Available Decorators While the 1:1 mapping of column -> function implementation is powerful, we've implemented a few decorators to promote business-logic reuse. The decorators we've defined are as follows (source can be found in -`function_modifiers `_): +`function_modifiers `_): @tag ---- @@ -184,7 +184,7 @@ of the series, and one that checks whether the data is in a certain range. Note that you can also specify custom decorators using the ``@check_output_custom`` decorator. -See `data_quality `_ for more information on +See `data_quality `_ for more information on available validators and how to build custom ones. @parameterize diff --git a/docs/reference/api-reference/available-drivers.rst b/docs/reference/api-reference/available-drivers.rst index b23d0f875..f4750f1f9 100644 --- a/docs/reference/api-reference/available-drivers.rst +++ b/docs/reference/api-reference/available-drivers.rst @@ -4,7 +4,7 @@ Available Drivers API docs for using the drivers -Currently, we have a `single driver `_. +Currently, we have a `single driver `_. It's highly parameterizable, allowing you to customize: * The way the DAG is executed (how each node is executed), i.e. either locally, in parallel, or on a cluster! diff --git a/docs/reference/api-reference/available-graph-adapters.rst b/docs/reference/api-reference/available-graph-adapters.rst index 73d7111ce..741c7041a 100644 --- a/docs/reference/api-reference/available-graph-adapters.rst +++ b/docs/reference/api-reference/available-graph-adapters.rst @@ -12,10 +12,10 @@ Use ``from hamilton import base`` to use these Graph Adapters: * - Name - What it does - When you'd use it - * - `base.SimplePythonDataFrameGraphAdapter `_ + * - `base.SimplePythonDataFrameGraphAdapter `_ - This executes the Hamilton dataflow locally on a machine in a single threaded, single process fashion. It assumes a pandas dataframe as a result. - This is the default GraphAdapter that Hamilton uses. Use this when you want to execute on a single machine, without parallelization, and you want a pandas dataframe as output. - * - `base.SimplePythonGraphAdapter `_ + * - `base.SimplePythonGraphAdapter `_ - This executes the Hamilton dataflow locally on a machine in a single threaded, single process fashion. It allows you to specify a ResultBuilder to control the return type of what ``execute()`` returns. - This is the default GraphAdapter that Hamilton uses. Use this when you want to execute on a single machine, without parallelization, and you want to control the return type of the object that ``execute()`` returns. @@ -34,16 +34,16 @@ Use ``from hamilton.experimental import h_[NAME]`` to use these Graph Adapters: * - Name - What it does - When you'd use it - * - `h_dask.DaskGraphAdapter `_ + * - `h_dask.DaskGraphAdapter `_ - | This walks the graph and translates it to run onto `Dask `_. | You have the ability to pass in a ResultMixin object to the constructor to control the return type that gets produce by running on Dask. - Use this if you want to utilize multiple cores on a single machine, or you want to scale to large data set sizes with a Dask cluster that you can connect to. - * - `h_ray.RayGraphAdapter `_ + * - `h_ray.RayGraphAdapter `_ - | This walks the graph and translates it to run onto `Ray `_. | You have the ability to pass in a ResultMixin object to the constructor to control the return type that gets produce by running on Ray. - Use this if you want to utilize multiple cores on a single machine, or you want to scale to larger data set sizes with a Ray cluster that you can connect to. Note: you are still constrained by machine memory size with Ray; you can't just scale to any dataset size. - * - `h_spark.SparkKoalasGraphAdapter `_ + * - `h_spark.SparkKoalasGraphAdapter `_ - | This walks the graph and translates it to run onto `Apache Spark `_ using the `Pandas API on Spark `_ (aka `Koalas `_). - | You only have the ability to return either a Koalas Dataframe or a Pandas Dataframe. To do that you either use the stock `base.PandasDataFrameResult `_ ResultMixin, or you use the `h_spark.KoalasDataframeResult `_. + | You only have the ability to return either a Koalas Dataframe or a Pandas Dataframe. To do that you either use the stock `base.PandasDataFrameResult `_ ResultMixin, or you use the `h_spark.KoalasDataframeResult `_. - | You'd generally use this if you have an existing spark cluster running in your workplace, and you want to scale to very large data set sizes. | Note this GraphAdapter has only been tested to work on Spark 3.2+ when Koalas became part of the standard Spark library. diff --git a/docs/reference/api-reference/available-result-builders.rst b/docs/reference/api-reference/available-result-builders.rst index 313673f3b..752158e55 100644 --- a/docs/reference/api-reference/available-result-builders.rst +++ b/docs/reference/api-reference/available-result-builders.rst @@ -12,15 +12,15 @@ Use ``from hamilton import base`` to use these Result Builders: * - Name - What it does - When you'd use it - * - `base.DictResult `_ + * - `base.DictResult `_ - It returns the results as a dictionary, where the keys map to outputs requested, and values map to what was computed for those values. - | When you want to: | 1. debug dataflows. | 2. have heterogenous return types. | 3. Want to manually create a return type. - * - `base.PandasDataFrameResult `_ + * - `base.PandasDataFrameResult `_ - It returns the results as a Pandas Dataframe, where the columns map to outputs requested, and values map to what was computed for those values. Note: this only works if the computed values are pandas series, or scalar values. - Use this when you want to create a pandas dataframe. - * - `base.NumpyMatrixResult `_ + * - `base.NumpyMatrixResult `_ - It returns the results as a numpy matrix, where the columns map to outputs requested (in order), and values map to what was computed for those values. Note: this only works if the computed values are all numpy arrays of the **same length and type**, or scalar values. Scalar values will be made to fill the entire column. - Use this when you want to create a numpy matrix of results. diff --git a/docs/tutorials/dask.rst b/docs/tutorials/dask.rst index 580d99576..8e5b7593f 100644 --- a/docs/tutorials/dask.rst +++ b/docs/tutorials/dask.rst @@ -4,4 +4,4 @@ Dask 'TODO: complete this tutorial' -See examples directory `here `_. +See examples directory `here `_. diff --git a/docs/tutorials/data-quality-checks.rst b/docs/tutorials/data-quality-checks.rst index c99d4455e..77dc2b359 100644 --- a/docs/tutorials/data-quality-checks.rst +++ b/docs/tutorials/data-quality-checks.rst @@ -53,7 +53,7 @@ This is easy with the ``check_output`` decorator! return avg_3wk_spend / signups It takes in a series of arguments -- you can discover these by exploring the code (more documentation of specific -arguments to follow): `DefaultValidation `_ +arguments to follow): `DefaultValidation `_ You can also utilize ``pandera`` to the same effect, simply by providing a ``schema`` argument: .. code-block:: python @@ -77,7 +77,7 @@ You can also utilize ``pandera`` to the same effect, simply by providing a ``sch return avg_3wk_spend / signups pyt Finally, if you want to implement your own checks, you can explore the -`DataValidator `_ +`DataValidator `_ class and the ``check_output_custom`` decorator. Running your Pipelines and Examining the Results @@ -184,6 +184,6 @@ enabling you to programmatically react to them down the line. This concludes our brief lessons on managing data quality in Hamilton -- we hope you spin it up and give it a try. In the mean time, we have more detailed documentation here - -`data_quality.md `_ +`data_quality.md `_ and some more examples (including distributed systems support) - -`data_quality examples `_. +`data_quality examples `_. diff --git a/docs/tutorials/model-training.rst b/docs/tutorials/model-training.rst index 0abb18930..de792928e 100644 --- a/docs/tutorials/model-training.rst +++ b/docs/tutorials/model-training.rst @@ -4,4 +4,4 @@ Model Training 'TODO: complete this tutorial' -See examples directory `here `_. +See examples directory `here `_. diff --git a/docs/tutorials/ray.rst b/docs/tutorials/ray.rst index 666da0958..ccf214e2c 100644 --- a/docs/tutorials/ray.rst +++ b/docs/tutorials/ray.rst @@ -5,7 +5,7 @@ This describes how one can get started with Ray in 5 minutes. For those eager to just see code, please jump right ahead to a full hello world with Ray -`here `_. +`here `_. .. image:: ../_static/Hamilton_ray_post_image.png @@ -139,7 +139,7 @@ To summarize, the recipe for using Ray with Hamilton doesn’t change much from Since it’s so easy to switch to using Ray or not, we’d love some benchmarks/anecdotes to see how much switching to Ray improves the speed or scale at which you can operate your dataflow! -For a full “Ray Hello World” code sample, we direct you to the `examples directory here `_. +For a full “Ray Hello World” code sample, we direct you to the `examples directory here `_. Caveats ------- @@ -151,7 +151,7 @@ been very stable (hasn’t changed since launch), but to feel good about making think. #. We don’t expose all the functionality of Ray, but we could. E.g. memory aware scheduling, or specifying resources for specific functions. Let us know if you want something exposed — create an issue on github please —  -`stitchfix/hamilton `_. +`dagworks-inc/hamilton `_. To conclude ----------- diff --git a/docs/tutorials/spark.rst b/docs/tutorials/spark.rst index ac92eb900..911bd2854 100644 --- a/docs/tutorials/spark.rst +++ b/docs/tutorials/spark.rst @@ -4,4 +4,4 @@ Spark 'TODO: complete this tutorial' -See examples directory `here `_. +See examples directory `here `_. diff --git a/examples/Dockerfile b/examples/Dockerfile index e971452a0..786f912ed 100644 --- a/examples/Dockerfile +++ b/examples/Dockerfile @@ -2,7 +2,7 @@ FROM python:3.9.14-slim-buster RUN apt update -y &&\ apt install git openjdk-11-jdk -y &&\ - git clone https://github.com/stitchfix/hamilton.git --branch=main &&\ + git clone https://github.com/dagworks-inc/hamilton.git --branch=main &&\ cd hamilton/examples &&\ bash make_python_virtualenv.sh diff --git a/examples/data_loaders/README.md b/examples/data_loaders/README.md index 8cbc13d04..493aab13f 100644 --- a/examples/data_loaders/README.md +++ b/examples/data_loaders/README.md @@ -36,4 +36,4 @@ To load/analyze the data, you can run the script `run.py` - `python run.py mock` creates mock data and runs the pipeline Note that you, as the user, have to manually handle connections/whatnot for duckdb. -We are currently designing the ability to do this natively in hamilton: https://github.com/stitchfix/hamilton/issues/197. +We are currently designing the ability to do this natively in hamilton: https://github.com/dagworks-inc/hamilton/issues/197. diff --git a/examples/dbt/README.md b/examples/dbt/README.md index a5f6f099f..bed21dcfc 100644 --- a/examples/dbt/README.md +++ b/examples/dbt/README.md @@ -73,7 +73,7 @@ We've organized the code into two separate DBT models: This is just a start, and we think that Hamilton + DBT have a long/exciting future together. In particular, we could: -1. Compile Hamilton to DBT for orchestration -- the new [SQL adapter](https://github.com/stitchfix/hamilton/issues/197) we're working on would compile nicely to a dbt task. +1. Compile Hamilton to DBT for orchestration -- the new [SQL adapter](https://github.com/dagworks-inc/hamilton/issues/197) we're working on would compile nicely to a dbt task. 2. Add more natural integration -- including a dbt plugin for a hamilton task. 3. Add more examples with different SQL dialects/different python dialects. _hint_: _we're looking for contributors..._ diff --git a/examples/polars/README.md b/examples/polars/README.md index f2cd5d706..a3d6aefd3 100644 --- a/examples/polars/README.md +++ b/examples/polars/README.md @@ -21,7 +21,7 @@ To run things: There is one major caveat with Polars to be aware of: THERE IS NO INDEX IN POLARS LIKE THERE IS WITH PANDAS. What this means is that when you tell Hamilton to execute and return a polars dataframe if you are using the -[provided results builder](https://github.com/stitchfix/hamilton/blob/sf-hamilton-1.14.1/hamilton/plugins/polars_implementations.py#L8), i.e. `hamilton.plugins.polars_implementations.PolarsResultsBuilder`, then you will have to +[provided results builder](https://github.com/dagworks-inc/hamilton/blob/sf-hamilton-1.14.1/hamilton/plugins/polars_implementations.py#L8), i.e. `hamilton.plugins.polars_implementations.PolarsResultsBuilder`, then you will have to ensure the row order matches the order you expect for all the outputs you request. E.g. if you do a filter, or a sort, or a join, or a groupby, you will have to ensure that when you ask Hamilton to materialize an output that it's in the order you expect. diff --git a/hamilton/data_quality/default_validators.py b/hamilton/data_quality/default_validators.py index 2f598d9ca..ab54bfa79 100644 --- a/hamilton/data_quality/default_validators.py +++ b/hamilton/data_quality/default_validators.py @@ -455,6 +455,6 @@ def resolve_default_validators( f"No registered subclass of BaseDefaultValidator is available " f"for arg: {key} and type {output_type}. This either means (a) this arg-type " f"contribution isn't supported or (b) this has not been added yet (but should be). " - f"In the case of (b), we welcome contributions. Get started at github.com/stitchfix/hamilton" + f"In the case of (b), we welcome contributions. Get started at github.com/dagworks-inc/hamilton" ) return validators diff --git a/hamilton/dev_utils/deprecation.py b/hamilton/dev_utils/deprecation.py index bfa19fc75..456430dfc 100644 --- a/hamilton/dev_utils/deprecation.py +++ b/hamilton/dev_utils/deprecation.py @@ -50,7 +50,7 @@ class deprecated: fail_starting=(2,0,0), use_instead=parameterize_values, reason='We have redefined the parameterization decorators to consist of `parametrize`, `parametrize_inputs`, and `parametrize_values` - migration_guide="https://github.com/stitchfix/hamilton/..." + migration_guide="https://github.com/dagworks-inc/hamilton/..." ) class parameterized(...): ... diff --git a/hamilton/function_modifiers/expanders.py b/hamilton/function_modifiers/expanders.py index dba174c1c..ee626e54f 100644 --- a/hamilton/function_modifiers/expanders.py +++ b/hamilton/function_modifiers/expanders.py @@ -215,7 +215,7 @@ def __init__(self, parameter: str, assigned_output: Dict[Tuple[str, str], Any]): fail_starting=(2, 0, 0), use_this=parameterize_values, explanation="We now support three parametrize decorators. @parameterize, @parameterize_values, and @parameterize_inputs", - migration_guide="https://github.com/stitchfix/hamilton/blob/main/decorators.md#migrating-parameterized", + migration_guide="https://github.com/dagworks-inc/hamilton/blob/main/decorators.md#migrating-parameterized", ) class parametrized(parameterize_values): pass @@ -263,7 +263,7 @@ def __init__(self, **parameterization: Dict[str, Dict[str, str]]): fail_starting=(2, 0, 0), use_this=parameterize_sources, explanation="We now support three parametrize decorators. @parameterize, @parameterize_values, and @parameterize_inputs", - migration_guide="https://github.com/stitchfix/hamilton/blob/main/decorators.md#migrating-parameterized", + migration_guide="https://github.com/dagworks-inc/hamilton/blob/main/decorators.md#migrating-parameterized", ) class parametrized_input(parameterize): def __init__(self, parameter: str, variable_inputs: Dict[str, Tuple[str, str]]): @@ -301,7 +301,7 @@ def __init__(self, parameter: str, variable_inputs: Dict[str, Tuple[str, str]]): fail_starting=(2, 0, 0), use_this=parameterize_sources, explanation="We now support three parametrize decorators. @parameterize, @parameterize_values, and @parameterize_inputs", - migration_guide="https://github.com/stitchfix/hamilton/blob/main/decorators.md#migrating-parameterized", + migration_guide="https://github.com/dagworks-inc/hamilton/blob/main/decorators.md#migrating-parameterized", ) class parameterized_inputs(parameterize_sources): pass diff --git a/hamilton/telemetry.py b/hamilton/telemetry.py index 5b8571b3f..c10a1c290 100644 --- a/hamilton/telemetry.py +++ b/hamilton/telemetry.py @@ -126,7 +126,7 @@ def is_telemetry_enabled() -> bool: # Log only the first time someone calls this function; don't want to spam them. logger.warning( "FYI: Hamilton telemetry is enabled. " - "See https://github.com/stitchfix/hamilton#usage-analytics--data-privacy for details." + "See https://github.com/dagworks-inc/hamilton#usage-analytics--data-privacy for details." ) call_counter += 1 if call_counter > MAX_COUNT_SESSION: diff --git a/setup.py b/setup.py index d03749cd6..59ceed67e 100644 --- a/setup.py +++ b/setup.py @@ -42,8 +42,8 @@ def load_requirements(): long_description=readme, long_description_content_type="text/markdown", author="Stefan Krawczyk, Elijah ben Izzy", - author_email="skrawczyk@stitchfix.com,elijah.benizzy@stitchfix.com", - url="https://github.com/stitchfix/hamilton", + author_email="stefan@dagworks.io,elijah@dagworks.io", + url="https://github.com/dagworks-inc/hamilton", packages=find_packages(exclude=["tests"]), include_package_data=True, install_requires=load_requirements(), @@ -79,7 +79,7 @@ def load_requirements(): }, # Relevant project URLs project_urls={ # Optional - "Bug Reports": "https://github.com/stitchfix/hamilton/issues", - "Source": "https://github.com/stitchfix/hamilton", + "Bug Reports": "https://github.com/dagworks-inc/hamilton/issues", + "Source": "https://github.com/dagworks-inc/hamilton", }, ) diff --git a/tests/function_modifiers/test_recursive.py b/tests/function_modifiers/test_recursive.py index 386e0f271..be8995c10 100644 --- a/tests/function_modifiers/test_recursive.py +++ b/tests/function_modifiers/test_recursive.py @@ -100,7 +100,7 @@ def baz(foo: int, bar: int) -> int: decorator = recursive.subdag(foo, bar, inputs={"a": source("c"), "b": source("d")}, config={}) nodes = {node_.name: node_ for node_ in decorator.generate_nodes(baz, {})} # These aren't entirely part of the contract, but they're required for the - # way we're currently implementing it. See https://github.com/stitchfix/hamilton/issues/201 + # way we're currently implementing it. See https://github.com/dagworks-inc/hamilton/issues/201 assert "baz.a" in nodes assert nodes["baz.a"](c=1) == 1 assert "baz.b" in nodes diff --git a/tests/resources/multiple_decorators_together.py b/tests/resources/multiple_decorators_together.py index d911d9678..fda64784c 100644 --- a/tests/resources/multiple_decorators_together.py +++ b/tests/resources/multiple_decorators_together.py @@ -31,7 +31,7 @@ def _dummy(**values) -> dict: @extract_fields({"out_value1": int, "out_value2": str}) @tag(test_key="test-value") -# @check_output(data_type=dict, importance="fail") To fix see https://github.com/stitchfix/hamilton/issues/249 +# @check_output(data_type=dict, importance="fail") To fix see https://github.com/dagworks-inc/hamilton/issues/249 @does(_dummy) def uber_decorated_function(in_value1: int, in_value2: str) -> dict: pass diff --git a/tests/test_dev_utils.py b/tests/test_dev_utils.py index 7b686f700..62b86912b 100644 --- a/tests/test_dev_utils.py +++ b/tests/test_dev_utils.py @@ -34,7 +34,7 @@ def test_from_version_tuple(version_tuple, version): fail_starting=(0, 0, 1), use_this=None, explanation="something", - migration_guide="https://github.com/stitchfix/hamilton", + migration_guide="https://github.com/dagworks-inc/hamilton", ), dict( warn_starting=(0, 0, 0), @@ -64,7 +64,7 @@ def test_validate_deprecated_decorator_params_happy(kwargs): fail_starting=(0, 0, 1), use_this=None, explanation="something", - migration_guide="https://github.com/stitchfix/hamilton", + migration_guide="https://github.com/dagworks-inc/hamilton", ), dict( warn_starting=(0, 0, 0), @@ -102,7 +102,7 @@ def replacement_function() -> bool: fail_starting=(1, 0, 0), use_this=replacement_function, explanation="True is the new False", - migration_guide="https://github.com/stitchfix/hamilton", + migration_guide="https://github.com/dagworks-inc/hamilton", current_version=(0, 0, 0), warn_action=warn, ) @@ -128,7 +128,7 @@ def replacement_function() -> bool: fail_starting=(1, 0, 0), use_this=replacement_function, explanation="True is the new False", - migration_guide="https://github.com/stitchfix/hamilton", + migration_guide="https://github.com/dagworks-inc/hamilton", current_version=(0, 6, 0), warn_action=warn, ) @@ -148,7 +148,7 @@ def replacement_function() -> bool: fail_starting=(1, 0, 0), use_this=replacement_function, explanation="True is the new False", - migration_guide="https://github.com/stitchfix/hamilton", + migration_guide="https://github.com/dagworks-inc/hamilton", current_version=(1, 1, 0), ) def deprecated_function(): @@ -173,7 +173,7 @@ def replacement_function() -> bool: fail_starting=(1, 0, 0), use_this=replacement_function, explanation="True is the new False", - migration_guide="https://github.com/stitchfix/hamilton", + migration_guide="https://github.com/dagworks-inc/hamilton", current_version=(0, 0, 0), warn_action=warn, ) @@ -200,7 +200,7 @@ def replacement_function() -> bool: fail_starting=(1, 0, 0), use_this=replacement_function, explanation="True is the new False", - migration_guide="https://github.com/stitchfix/hamilton", + migration_guide="https://github.com/dagworks-inc/hamilton", current_version=(0, 6, 0), warn_action=warn, ) @@ -221,7 +221,7 @@ def replacement_function() -> bool: fail_starting=(1, 0, 0), use_this=replacement_function, explanation="True is the new False", - migration_guide="https://github.com/stitchfix/hamilton", + migration_guide="https://github.com/dagworks-inc/hamilton", current_version=(1, 1, 0), ) class deprecated_function: