Merge pull request #62 from kthyng/add_test_data

Tons of updates
axiom-data-science · Oct 5, 2023 · 287411a · 287411a
2 parents ef41d1e + 23c7e85
commit 287411a
Show file tree

Hide file tree

Showing 73 changed files with 4,166 additions and 3,377 deletions.
diff --git a/.github/workflows/test.yaml b/.github/workflows/test.yaml
@@ -9,36 +9,51 @@ jobs:
       fail-fast: false
       matrix:
         os: ["macos-latest", "ubuntu-latest", "windows-latest"]
-        python-version: ["3.8", "3.9", "3.10"]
+        python-version: ["3.9", "3.10", "3.11"]
     steps:
       - uses: actions/checkout@v4
-      - name: Cache conda
-        uses: actions/cache@v3
-        env:
-          # Increase this value to reset cache if ci/environment.yml has not changed
-          CACHE_NUMBER: 0
-        with:
-          path: ~/conda_pkgs_dir
-          key: ${{ runner.os }}-conda-${{ env.CACHE_NUMBER }}-${{ hashFiles('ci/environment-py${{ matrix.python-version }}.yml') }}
-      - uses: conda-incubator/setup-miniconda@v2
+      # - name: Cache conda
+      #   uses: actions/cache@v3
+      #   env:
+      #     # Increase this value to reset cache if ci/environment.yml has not changed
+      #     CACHE_NUMBER: 0
+      #   with:
+      #     path: ~/conda_pkgs_dir
+      #     key: ${{ runner.os }}-conda-${{ env.CACHE_NUMBER }}-${{ hashFiles('ci/environment-py${{ matrix.python-version }}.yml') }}
+
+      - name: Setup Micromamba Python ${{ matrix.python-version }}
+        uses: mamba-org/setup-micromamba@v1
         with:
-          # mamba-version: "*" # activate this to build with mamba.
-          python-version: ${{ matrix.python-version }}
-          miniforge-variant: Mambaforge
-          channels: conda-forge, defaults # These need to be specified to use mamba
-          channel-priority: true
+          init-shell: bash
+          create-args: >-
+            python=${{ matrix.python-version }} --channel conda-forge
           environment-file: ci/environment-py${{ matrix.python-version }}.yml
+          cache-environment: true
+          post-cleanup: 'all'
+
+
+      # - name: Set up conda environment
+      #   uses: conda-incubator/setup-miniconda@v2
+      #   with:
+      #     # mamba-version: "*" # activate this to build with mamba.
+      #     python-version: ${{ matrix.python-version }}
+      #     miniforge-variant: Mambaforge
+      #     use-mamba: true
+      #     channels: conda-forge, defaults # These need to be specified to use mamba
+      #     channel-priority: true
+      #     environment-file: ci/environment-py${{ matrix.python-version }}.yml
+
+      #     activate-environment: test_env_model_assessor
+      #     use-only-tar-bz2: true # IMPORTANT: This needs to be set for caching to work properly!
 
-          activate-environment: test_env_model_assessor
-          use-only-tar-bz2: true # IMPORTANT: This needs to be set for caching to work properly!
-      - name: Set up conda environment
+      - name: Install package
         shell: bash -l {0}
         run: |
           python -m pip install -e . --no-deps --force-reinstall
       - name: Run Tests
         shell: bash -l {0}
         run: |
-          pytest --cov=./ --cov-report=xml
+          pytest --mpl --cov=./ --cov-report=xml
       - name: Upload code coverage to Codecov
         uses: codecov/codecov-action@v3
         with:

diff --git a/ci/environment-py3.10.yml b/ci/environment-py3.10.yml
@@ -18,16 +18,18 @@ dependencies:
   - pyproj
   - scipy
   - xarray
+  - xcmocean
+  - alphashape
+  - cf_pandas
+  - intake-axds
+  - intake-erddap
+  - intake>=0.7.0
+  - nested-lookup
+  - xroms  # github actions won't find on conda-forge
   ##############
   - pytest
   - pip:
-    - alphashape
-    - cf_pandas
-    - intake-axds
-    - intake-erddap
-    - intake
-    - nested_lookup
-    - tqdm
     - codecov
     - pytest-cov
+    - pytest-mpl
     - coverage[toml]
diff --git a/ci/environment-py3.8.yml → ci/environment-py3.11.yml b/ci/environment-py3.8.yml → ci/environment-py3.11.yml
@@ -2,7 +2,7 @@ name: test_env_model_assessor
 channels:
   - conda-forge
 dependencies:
-  - python=3.8
+  - python=3.11
   ############## These will have to be adjusted to your specific project
   # - cf_pandas
   - cf_xarray
@@ -18,16 +18,18 @@ dependencies:
   - pyproj
   - scipy
   - xarray
+  - xcmocean
   ##############
+  - alphashape
+  - cf_pandas
+  - intake-axds
+  - intake-erddap
+  - intake>=0.7.0
+  - nested-lookup
+  - xroms  # github actions won't find on conda-forge
   - pytest
   - pip:
-    - alphashape
-    - cf_pandas
-    - intake-axds
-    - intake-erddap
-    - intake
-    - nested_lookup
-    - tqdm
     - codecov
     - pytest-cov
+    - pytest-mpl
     - coverage[toml]
diff --git a/ci/environment-py3.9.yml b/ci/environment-py3.9.yml
@@ -18,16 +18,18 @@ dependencies:
   - pyproj
   - scipy
   - xarray
+  - xcmocean
   ##############
+  - alphashape
+  - cf_pandas
+  - intake-axds
+  - intake-erddap
+  - intake
+  - nested-lookup
+  - xroms  # github actions won't find on conda-forge
   - pytest
   - pip:
-    - alphashape
-    - cf_pandas
-    - intake-axds
-    - intake-erddap
-    - intake
-    - nested_lookup
-    - tqdm
     - codecov
     - pytest-cov
+    - pytest-mpl
     - coverage[toml]
diff --git a/docs/add_vocab.md b/docs/add_vocab.md
@@ -4,14 +4,14 @@ jupytext:
     extension: .md
     format_name: myst
     format_version: 0.13
-    jupytext_version: 1.14.4
+    jupytext_version: 1.15.2
 kernelspec:
-  display_name: Python 3.10.8 ('omsa')
+  display_name: Python 3 (ipykernel)
   language: python
   name: python3
 ---
 
-# How to make and work with vocabularies
+# How to make and work with vocabularies and vocab labels
 
 This page demonstrates the workflow of making a new vocabulary, saving it to the user application cache, and reading it back in to use it. The vocabulary created is the exact same as the "general" vocabulary that is saved with the OMSA package, though here it is given another name to demonstrate that you could be making any new vocabulary you want.
 
@@ -31,6 +31,8 @@ Here is the list of variables of interest (with "nickname"), aimed at a physical
 * sea ice velocity v "sea_ice_v"
 * sea ice area fraction "sea_ice_area_fraction"
 
+Vocab labels are used in model-data comparison plots to support nice labeling. They are a dictionary with the same keys as the vocabularies being used and the value is the string you want to use for that variable key's label in a plot.
+
 ```{code-cell} ipython3
 import cf_pandas as cfp
 import ocean_model_skill_assessor as omsa
@@ -100,19 +102,20 @@ vocab
 This exact vocabulary was previously saved as "general" and is available under that name, but this page demonstrates saving a new vocabulary and so we use the name "general2" to differentiate.
 
 ```{code-cell} ipython3
-vocab.save(omsa.VOCAB_PATH("general2"))
+paths = omsa.paths.Paths()
+vocab.save(paths.VOCAB_PATH("general2"))
 ```
 
 ```{code-cell} ipython3
-omsa.VOCAB_PATH("general2")
+paths.VOCAB_PATH("general2")
 ```
 
 ### Use it later
 
 Read the saved vocabulary back in to use it:
 
 ```{code-cell} ipython3
-vocab = cfp.Vocab(omsa.VOCAB_PATH("general2"))
+vocab = cfp.Vocab(paths.VOCAB_PATH("general2"))
 
 df = pd.DataFrame(columns=["sst", "time", "lon", "lat"], data={"sst": [1,2,3]})
 with cfp.set_options(custom_criteria=vocab.vocab):
@@ -124,8 +127,8 @@ with cfp.set_options(custom_criteria=vocab.vocab):
 A user can add together vocabularies. For example, here we combine the built-in "standard_names" and "general" vocabularies.
 
 ```{code-cell} ipython3
-v1 = cfp.Vocab(omsa.VOCAB_PATH("standard_names"))
-v2 = cfp.Vocab(omsa.VOCAB_PATH("general"))
+v1 = cfp.Vocab(paths.VOCAB_PATH("standard_names"))
+v2 = cfp.Vocab(paths.VOCAB_PATH("general"))
 
 v = v1 + v2
 v
@@ -137,3 +140,20 @@ v
 
 .. raw:: html
    <iframe src="vocab_widget.html" height="500px" width="100%"></iframe>
+
++++
+
+## Vocab labels
+
+There is a default set of labels in the repository available alongside the default vocabs, called "vocab_labels.json".
+
+You can use `cf-pandas` to open up and look at `vocal_labels` like a vocabulary since they are both just dictionaries stored as json.
+
+```{code-cell} ipython3
+vocab_labels = cfp.Vocab(paths.VOCAB_PATH("vocab_labels"))
+vocab_labels
+```
+
+```{code-cell} ipython3
+
+```
diff --git a/docs/api.rst b/docs/api.rst
@@ -11,7 +11,7 @@ API
    main
    utils
    paths
-   accessor
    stats
    plot.map
-   plot.time_series
+   plot.line
+   plot.surface
diff --git a/docs/cli.md b/docs/cli.md
@@ -31,7 +31,7 @@ Make a catalog with known local or remote file(s). Also use a local catalog to r
 
 ##### Basic catalog for single dataset
 
-    omsa make_catalog --project_name test1 --catalog_type local --catalog_name example_local_catalog --description "Example local catalog description" --kwargs filenames="[https://erddap.sensors.axds.co/erddap/tabledap/aoos_204.csvp?time%2Clatitude%2Clongitude%2Cz%2Csea_water_temperature&time%3E=2022-01-01T00%3A00%3A00Z&time%3C=2022-01-06T00%3A00%3A00Z]"  --kwargs_open blocksize=None
+    omsa make_catalog --project_name test1 --catalog_type local --catalog_name example_local_catalog --description "Example local catalog description" --kwargs filenames="[https://erddap.sensors.axds.co/erddap/tabledap/aoos_204.csvp?time%2Clatitude%2Clongitude%2Cz%2Csea_water_temperature&time%3E=2022-01-01T00%3A00%3A00Z&time%3C=2022-01-06T00%3A00%3A00Z]"
 
 ##### Dataset with no lon/lat
 
@@ -175,7 +175,7 @@ The datasets need to all cover the same time periods.
 
 ### Available options
 
-    omsa run --project_name test1 --catalogs CATALOG_NAME1 CATALOG_NAME2 --vocab_names VOCAB1 VOCAB2 --key KEY --model_path PATH_TO_MODEL_OUTPUT --ndatasets NDATASETS --verbose --mode MODE
+    omsa run --project_name test1 --catalogs CATALOG_NAME1 CATALOG_NAME2 --vocab_names VOCAB1 VOCAB2 --key KEY --model_path PATH_TO_MODEL_OUTPUT --ndatasets NDATASETS --verbose --mode MODE --kwargs_map key_fig=value_fig --more_kwargs key=value key2=value2
 
 * `project_name`: Subdirectory in cache dir to store files associated together.
 * `catalog_names`: Catalog name(s). Datasets will be accessed from catalog entries.
@@ -185,6 +185,8 @@ The datasets need to all cover the same time periods.
 * `ndatasets`: Max number of datasets from each input catalog to use.
 * `verbose` Print useful runtime commands to stdout if True as well as save in log, otherwise silently save in log. Log is located in the project directory, which can be checked on the command line with `omsa proj_path --project_name PROJECT_NAME`. Default is True, to turn off use `--no-verbose`.
 * `mode` mode for logging file. Default is to overwrite an existing logfile, but can be changed to other modes, e.g. "a" to instead append to an existing log file.
+* `kwargs_map` are sent to `omsa.plot.map`
+* `more_kwargs` are sent to `omsa.run`
 
 ### Example
 

diff --git a/docs/cli_tutorial.md b/docs/cli_tutorial.md