Merge pull request #10 from MAAP-Project/gedi-subset-0.2.1

build.sh

@@ -4,4 +4,45 @@ basedir=$(dirname "$(readlink -f "$0")")
 
 set -xeuo pipefail
 
-mamba env create -f "${basedir}/environment.yml"
+# Make sure conda is up to date
+conda update -y -n base -c conda-forge conda
+
+# Install dependencies from lock file for speed and reproducibility
+case $(uname) in
+Linux)
+    platform="linux"
+    ;;
+Darwin)
+    platform="osx"
+    ;;
+*)
+    echo >&2 "Unsupported platform: $(uname)"
+    exit 1
+    ;;
+esac
+
+conda create -y -n gedi_subset --file "${basedir}/gedi-subset/conda-${platform}-64.lock"
+
+# Install maap-py, since it cannot be specified in the lock file
+conda run --no-capture-output -n gedi_subset pip install "git+https://github.com/MAAP-Project/maap-py.git@1bfa99d#egg=maappy"
+
+# Fail build if finicky mix of fiona and gdal isn't correct, so that we don't
+# have to wait to execute a DPS job to find out.
+conda run --no-capture-output -n gedi_subset python -c '
+import geopandas as gpd
+import tempfile
+import warnings
+from shapely.geometry import Point
+
+# Make sure pip install worked
+from maap.maap import MAAP
+
+warnings.filterwarnings("ignore", message=".*initial implementation of Parquet.*")
+
+d = {"col1": ["name1", "name2"], "geometry": [Point(1, 2), Point(2, 1)]}
+gdf = gpd.GeoDataFrame(d, crs="EPSG:4326")
+
+with tempfile.TemporaryFile() as fp:
+    gdf.to_parquet(fp)
+    assert gdf.equals(gpd.read_parquet(fp))
+'

environment.yml

@@ -1,18 +1,17 @@
 name: gedi_subset
 channels:
-  - defaults
   - conda-forge
+  - defaults
 dependencies:
-  - python=3.10
-  - boto3
-  - cachetools
-  - gdal>=3.4
-  - geopandas
-  - h5py
-  - pyarrow
-  - returns
-  - shapely
-  - typer
+  - python==3.10.4
+  - boto3==1.24.1
+  - cachetools==5.0.0
+  - returns==0.19.0
+  - typer==0.4.1
+  - geopandas==0.10.2
+  - h5py==3.6.0
+  - pyarrow==8.0.0
+  - shapely==1.8.2
   - pip
   - pip:
-      - git+https://github.com/MAAP-Project/maap-py.git#egg=maappy
+      - git+https://github.com/MAAP-Project/maap-py.git@1bfa99d#egg=maappy

gedi-subset/CHANGELOG.md

@@ -7,7 +7,23 @@ variation of [Semantic Versioning], with the following difference: each version
 is prefixed with `gedi-subset-` (e.g., `gedi-subset-0.1.0`) to allow for
 distinct lines of versioning of independent work in sibling directories.
 
-## [gedi-subset-0.2.0] - 2022-06-01
+## [gedi-subset-0.2.1] - 2022-06-07
+
+Hotfix replacement for `gedi-subset-0.2.0`.
+
+### Fixed
+
+- Resolved the following runtime error during DPS job execution that occurs with
+  version `gedi-subset-0.2.0`:
+
+  ```plain
+  ImportError: Missing optional dependency 'pyarrow.parquet'.
+  ```
+
+  This appears to be due to a recent release of one or more unpinned transitive
+  dependencies.  This was resolved with a `conda` lock file.
+
+## [gedi-subset-0.2.0] - 2022-06-01 [YANKED]
 
 ## Added
 

gedi-subset/README.md

@@ -37,13 +37,9 @@ To run a GEDI subsetting DPS job, you must supply the following inputs:
 - `limit`: Maximum number of GEDI granule data files to download (among those
   that intersect the specified AOI).  (**Default:** 10,000)
 
-**IMPORTANT:** When supplying input values via the ADE UI, for convenience, to
-accept _all_ default values, you may leave _all_ optional inputs blank.
-However, if you supply a value for _any_ optional input, you must enter a dash
-(`-`) as the input value for _all other_ optional inputs.  This ensures that
-the input values remain correctly ordered for the underlying script to which the
-inputs are supplied.  Otherwise, your job may fail due to invalid script
-arguments, or might produce unpredictable results.
+**IMPORTANT:** When supplying input values via the ADE UI, to accept a default
+input value, enter a dash (`-`) as the input value, otherwise the UI will show
+an error message if you leave any input blank.
 
 If your AOI is a publicly available geoBoundary, see
 [Getting the GeoJSON URL for a geoBoundary](#getting-the-geojson-url-for-a-geoboundary)
@@ -249,8 +245,8 @@ able to register the new version of the algorithm, as follows, within the ADE:
 1. Pull the latest code from GitHub (to obtain merged PR, if necessary):
 
    ```bash
-   git pull origin main
    git checkout main
+   git pull origin
    ```
 
 1. Push the latest code to GitLab (replace `ade` with the appropriate remote
@@ -268,7 +264,7 @@ able to register the new version of the algorithm, as follows, within the ADE:
 1. Confirm that the value of the **version** field matches the GitHub release
    version you created above.  If not, click **Cancel** and review earlier
    steps.  If so, click **Ok**, which will trigger a build job that will take
-   several minutes.
+   about 30 minutes.
 1. Check the build job status at
    <https://repo.ops.maap-project.org/root/register-job/-/jobs>.  If the job
    fails, you will need to correct the issue (and likely create a patch release,

gedi-subset/algorithm_config.yaml

@@ -1,6 +1,6 @@
 description: Subset GEDI L4A granules within an area of interest (AOI)
 algo_name: gedi-subset
-version: gedi-subset-0.2.0
+version: gedi-subset-0.2.1
 environment: ubuntu
 repository_url: https://repo.ops.maap-project.org/data-team/maap-documentation-examples.git
 docker_url: mas.maap-project.org:5000/root/ade-base-images/r:latest