replace code with script in batch_image_correlation.yml

Author: gbrencher

.github/workflows/batch_image_correlation.yml

@@ -65,79 +65,10 @@ jobs:
           cache-environment: true
           environment-file: glacier_image_correlation/environment.yml
 
-      # https://words.yuvi.in/post/python-in-github-actions/
       - name: Search aws for S2 imagery
         id: S2_search
-        shell:  bash -el -c "python -u {0}"
         run: | 
-          import xarray as xr
-          import os
-          import pystac
-          import pystac_client
-          import stackstac
-          from dask.distributed import Client
-          import dask
-          import json
-          import pandas as pd
-
-          # GDAL environment variables for better performance
-          os.environ['AWS_REGION']='us-west-2'
-          os.environ['GDAL_DISABLE_READDIR_ON_OPEN']='EMPTY_DIR' 
-          os.environ['AWS_NO_SIGN_REQUEST']='YES'
-
-          # hardcode bbox for now
-          bbox = {
-          "type": "Polygon",
-          "coordinates": [
-          [[75.42382800808971,36.41082887114753],
-          [75.19442677164156,36.41082887114753],
-          [75.19442677164156,36.201076360872946],
-          [75.42382800808971,36.201076360872946],
-          [75.42382800808971,36.41082887114753]]]
-          }
-
-          # Use the api from element84 to query the data
-          URL = "https://earth-search.aws.element84.com/v1"
-          catalog = pystac_client.Client.open(URL)
-
-          search = catalog.search(
-          collections=["sentinel-2-l2a"],
-          intersects=bbox,
-          query={"eo:cloud_cover": {"lt": ${{ inputs.cloud_cover }}}}
-          )
-
-          # Check how many items were returned
-          items = search.item_collection()
-          print(f"Returned {len(items)} Items")
-
-          # create xarray dataset without loading data
-          sentinel2_stack = stackstac.stack(items)
-          # filter to specified month range
-          sentinel2_stack_snowoff = sentinel2_stack.where((sentinel2_stack.time.dt.month >= ${{ inputs.start_month }}) & (sentinel2_stack.time.dt.month <= ${{ inputs.stop_month }}), drop=True)
-
-          # select first image of each month
-          period_index = pd.PeriodIndex(sentinel2_stack_snowoff['time'].values, freq='M')
-          sentinel2_stack_snowoff.coords['year_month'] = ('time', period_index)
-          first_image_indices = sentinel2_stack_snowoff.groupby('year_month').apply(lambda x: x.isel(time=0))
-          
-          product_names = first_image_indices['s2:product_uri'].values.tolist()
-          print('\n'.join(product_names))
-
-          # Create Matrix Job Mapping (JSON Array)
-          pairs = []
-          for r in range(len(product_names) - ${{ inputs.npairs }}):
-              for s in range(1, ${{ inputs.npairs }} + 1 ):
-                img1_product_name = product_names[r]
-                img2_product_name = product_names[r+s]
-                shortname = f'{img1_product_name[11:19]}_{img2_product_name[11:19]}'
-                pairs.append({'img1_product_name': img1_product_name, 'img2_product_name': img2_product_name, 'name':shortname})
-          matrixJSON = f'{{"include":{json.dumps(pairs)}}}'
-          print(f'number of image pairs: {len(pairs)}')
-          
-          with open(os.environ['GITHUB_OUTPUT'], 'a') as f:
-              print(f'IMAGE_DATES={product_names}', file=f)
-              print(f'MATRIX_PARAMS_COMBINATIONS={matrixJSON}', file=f)
-
+          python glacier_image_correlation/s2_search.py ${{ inputs.cloud_cover }} ${{ inputs.start_month }} ${{ inputs.stop_month }} ${{ inputs.npairs }}
 
   # A matrix job that calls a reuseable workflow
   autoRIFT: