Rename the aggregate script to aggregate-covid19 #2712

.github/workflows/aggregate-ci.yml

@@ -5,19 +5,19 @@ on:
     branches: [main, '*-stable']
     paths:
     - '.github/workflows/aggregate-ci.yml'
-    - 'data-serving/scripts/aggregate/aggregate/**'
+    - 'data-serving/scripts/aggregate-covid19/aggregate/**'
   pull_request:
     paths:
     - '.github/workflows/aggregate-ci.yml'
-    - 'data-serving/scripts/aggregate/aggregate/**'
+    - 'data-serving/scripts/aggregate-covid19/aggregate/**'
   workflow_dispatch:
 
 jobs:
   ci:
     runs-on: ubuntu-20.04
     defaults:
       run:
-        working-directory: data-serving/scripts/aggregate/aggregate
+        working-directory: data-serving/scripts/aggregate-covid19/aggregate
     steps:
     - uses: actions/checkout@v2
     - name: Set up Python 3.9

.github/workflows/aggregate-deploy.yml

@@ -5,8 +5,8 @@ on:
     branches: [main]
     paths:
     - '.github/workflows/aggregate-deploy.yml'
-    - 'data-serving/scripts/aggregate/**'
-    - '!data-serving/scripts/aggregate/README.md'
+    - 'data-serving/scripts/aggregate-covid19/**'
+    - '!data-serving/scripts/aggregate-covid19/README.md'
   workflow_dispatch:
 
 jobs:
@@ -26,7 +26,7 @@ jobs:
       uses: aws-actions/amazon-ecr-login@v1
 
     - name: Build, tag, and push image to Amazon ECR (latest)
-      working-directory: data-serving/scripts/aggregate/aggregate
+      working-directory: data-serving/scripts/aggregate-covid19/aggregate
       env:
         REGISTRY: ${{ steps.login-ecr.outputs.registry }}
         REPO: gdh-map-aggregator

data-serving/scripts/aggregate/README.md → data-serving/scripts/aggregate-covid19/README.md

@@ -1,9 +1,13 @@
 # Aggregating data
 
-This is a AWS batch script built to aggregate data that is used by Map.
+This is a AWS batch script built to aggregate data that is used by COVID-19 Map.
 Previously Lambda functions were used for data export, that is now handled
 by AWS Batch in [../export-data](../export-data/README.md)
 
 The Batch job (actually two; one for the [dev map](https://dev-map.covid-19.global.health) and one for [prod](https://map.covid-19.global.health)) pulls the code from an image on the Amazon container repo. That image is prepared from the `main` branch by a github action.
 
 **Note for Country level**: Mapbox requires that the lat/long coordinates remain static in order to return the shapes for the choropleth, so this is standardized using the [Google Canonical DSPL countries.csv](https://developers.google.com/public-data/docs/canonical/countries_csv) dataset.
+
+### COVID-19 specific aggregation
+
+This script is only appropriate for aggregating COVID-19 data, as it merges in information from the John Hopkins University to report on completeness.

data-serving/scripts/aggregate/aggregate/app.py → data-serving/scripts/aggregate-covid19/aggregate/app.py

@@ -200,7 +200,7 @@ def transform_counts(
     counts: list[dict[str, Any]], jhu_counts: dict[str, int] = None
 ) -> list[dict[str, Any]]:
     """
-    Transforms aggregated casecount data for map
+    Transforms aggregated COVID-19 casecount data for map
 
     counts -- Case counts as a list of records of the form
               [{"_id": "two-letter country code", "casecount": N}, ... ]