diff --git a/.readthedocs.yaml b/.readthedocs.yaml index ea2f74d..b551c56 100644 --- a/.readthedocs.yaml +++ b/.readthedocs.yaml @@ -29,6 +29,6 @@ sphinx: # Optional but recommended, declare the Python requirements required # to build your documentation # See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html -# python: -# install: -# - requirements: docs/requirements.txt +python: + install: + - requirements: docs/requirements.txt diff --git a/docs/data_creation.rst b/docs/data_creation.rst new file mode 100644 index 0000000..06714cd --- /dev/null +++ b/docs/data_creation.rst @@ -0,0 +1,36 @@ +================= +Create Training Data +================= + +We use ufs2arco to generate training, validation, and test datasets. + +First, create a recipe.yaml. An example can be found here. Next, run the following: + +``` +ufs2arco recipe.yaml +``` + +For further information see the ufs2arco `github `_ or `documentation `_ + +Helpful quick tips for ufs2arco +------------------ + +Choosing Dates +~~~~~~~~~~~~~~~~~~~~~~ +Update the dates you wish to include in your dataset by changing the below section in your recipe. +These dates will include all data that you plan to use for training, validation, and testing. +The full dataset will be split into these individual sets later on. + + +.. code-block:: yaml + start: 2022-01-01T06 + end: 2022-12-31T18 + freq: 6h + +Then ensure that you have updated the statistics_period section to match: + +.. code-block:: yaml + start: 2022-01-01T06 + end: 2022-10-31T18 + +Note: it is best practice to ensure that your statistics period only includes dates you plan to include in your training dataset. diff --git a/docs/getting_started.rst b/docs/getting_started.rst index 6c339cd..2a5dc95 100644 --- a/docs/getting_started.rst +++ b/docs/getting_started.rst @@ -2,17 +2,14 @@ Getting Started ================= -Learn how to use the full `ufs2arco + Anemoi + wxvx` pipeline. +We have included a few options to learn how to get started with this pipeline. -You will learn how to: +Google Collab +~~~~~~~~~~~~~~~~~~~~~~ -1) Use `ufs2arco` to create training and validation datasets with NOAA Replay reanalysis -2) Use `anemoi-core` modules to train a graph-based model -3) Use `anemoi-inference` to run inference -4) Use `wxvx` to verify a forecast +Insert info about collab and point to it -------------- -Ursa -------------- +Train a Small Model with NOAA-Replay Data +~~~~~~~~~~~~~~~~~~~~~~ -Insert instructions for Ursa \ No newline at end of file +Insert info about replay option and point to it \ No newline at end of file diff --git a/docs/index.rst b/docs/index.rst index 42d78e7..767ee02 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -1,5 +1,25 @@ -================= +################### Welcome to Eagle! -================= +################### -Enter overview of Eagle project....? \ No newline at end of file +Insert overview of Eagle + +################### +Table of Contents +################### + +.. toctree:: + :maxdepth: 1 + :caption: Full Pipeline + + data_creation + train_a_model + inference + verification + +.. toctree:: + :maxdepth: 1 + :caption: Examples + + getting_started + nested_eagle diff --git a/docs/inference.rst b/docs/inference.rst index ee02810..c7c1065 100644 --- a/docs/inference.rst +++ b/docs/inference.rst @@ -4,6 +4,9 @@ Inference We use the anemoi-inference package to create a forecast. +See `anemoi-inference documentation `_ documentation for further information + Helpful quick tips for using anemoi-inference +------------------ -See `anemoi-inference documentation `_ documentation for further information: \ No newline at end of file +Insert tips \ No newline at end of file diff --git a/docs/nested-eagle.rst b/docs/nested_eagle.rst similarity index 100% rename from docs/nested-eagle.rst rename to docs/nested_eagle.rst diff --git a/docs/pipeline_overview.rst b/docs/pipeline_overview.rst new file mode 100644 index 0000000..c2738b4 --- /dev/null +++ b/docs/pipeline_overview.rst @@ -0,0 +1,23 @@ +================= +Overview of Full Pipeline +================= + +You will learn how to complete a full machine learning pipeline for weather prediction! + +The steps of this pipeline include: + +Step 1: Dataset Creation +~~~~~~~~~~~~~~~~~~~~~~ +Use `ufs2arco` to create training and validation datasets with NOAA Replay reanalysis + +Step 2: Train a Graph-Based Model +~~~~~~~~~~~~~~~~~~~~~~ +Use `anemoi-core` modules to train a graph-based model + +Step 3: Create a Forecast +~~~~~~~~~~~~~~~~~~~~~~ +Use `anemoi-inference` to run inference + +Step 4: Verify a Forecast +~~~~~~~~~~~~~~~~~~~~~~ +Use `wxvx` to verify a forecast \ No newline at end of file diff --git a/docs/requirements.txt b/docs/requirements.txt new file mode 100644 index 0000000..bbbe5ac --- /dev/null +++ b/docs/requirements.txt @@ -0,0 +1,2 @@ +sphinx==8.2.3 +sphinx-rtd-theme==3.0.2 \ No newline at end of file diff --git a/docs/training.rst b/docs/train_a_model.rst similarity index 85% rename from docs/training.rst rename to docs/train_a_model.rst index 899f0af..85dcdbb 100644 --- a/docs/training.rst +++ b/docs/train_a_model.rst @@ -4,9 +4,13 @@ Train a Graph-Based Model We use the anemoi-core modules to train a graph-based model. -Helpful quick tips for using Anemoi - See Anemoi documentation for further information: + - `anemoi-graphs `_ - `anemoi-training `_ - `anemoi-models `_ + +Helpful quick tips for using anemoi-core +------------------ + +Insert tips diff --git a/docs/ufs2arco.rst b/docs/ufs2arco.rst deleted file mode 100644 index 21ecceb..0000000 --- a/docs/ufs2arco.rst +++ /dev/null @@ -1,9 +0,0 @@ -================= -Create Training, Validation, and Test Datasets -================= - -We use ufs2arco to generate our datasets. - -Helpful quick tips for ufs2arco - -See `ufs2arco `_ for further information. \ No newline at end of file diff --git a/docs/verification.rst b/docs/verification.rst index fba89d2..d94b8ae 100644 --- a/docs/verification.rst +++ b/docs/verification.rst @@ -4,6 +4,9 @@ Validation We use wxvx for forecast verification. -Helpful quick tips for using wxvx. +See `wxvx `_ for further information. -See `wxvx `_ for further information. \ No newline at end of file +Helpful quick tips for using wxvx +------------------ + +Insert tips \ No newline at end of file