Merge pull request #50 from OCHA-DAP/main

HDXDSYS-1301  Simplify operational presence HAPI pipeline to read from global HDX dataset

Author: alexandru-m-g

.github/workflows/publish.yaml

@@ -17,17 +17,17 @@ jobs:
           submodules: true
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v2
+        uses: docker/setup-buildx-action@v3
 
       - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@v1
+        uses: aws-actions/configure-aws-credentials@v4
         with:
           aws-access-key-id: ${{ secrets.ECR_AWS_ACCESS_KEY_ID }}
           aws-secret-access-key: ${{ secrets.ECR_AWS_SECRET_ACCESS_KEY }}
           aws-region: us-east-1
 
       - name: Login to Public ECR
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           registry: public.ecr.aws
           username: ${{ secrets.ECR_AWS_ACCESS_KEY_ID }}
@@ -37,11 +37,11 @@ jobs:
 
       - name: Create prod requirements
         run: |
-          pip install --upgrade pip-tools
-          pip-compile pyproject.toml --resolver=backtracking --upgrade -q -c requirements.txt -o prod-requirements.txt
+          pip install --upgrade uv
+          uv pip compile pyproject.toml --resolver=backtracking --upgrade -q -c requirements.txt -o prod-requirements.txt
 
       - name: Build, tag, and push image to Amazon ECR
-        uses: docker/build-push-action@v4
+        uses: docker/build-push-action@v6
         with:
           context: .
           push: true

CHANGELOG.md

@@ -4,6 +4,20 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
+## [0.10.33] = 2025-01-22
+
+### Fixed
+
+- uv instead of pip-compile for publish GH Actions job
+
+## [0.10.32] = 2025-01-22
+
+### Changed
+
+- 3W from global dataset
+- Remove negative and rounded checks from HNO as are now in scraper
+- Common logic for 3W and HNO
+
 ## [0.10.31] = 2025-01-13
 
 ### Changed

Dockerfile

@@ -1,4 +1,4 @@
-FROM public.ecr.aws/unocha/hdx-scraper-baseimage:stable
+FROM public.ecr.aws/unocha/python:3.12-stable
 
 WORKDIR /srv
 

pyproject.toml

@@ -35,11 +35,11 @@ requires-python = ">=3.8"
 
 dependencies = [
     "hapi-schema>= 0.9.6",
-    "hdx-python-api>= 6.3.6",
-    "hdx-python-country>= 3.8.6",
+    "hdx-python-api>= 6.3.7",
+    "hdx-python-country>= 3.8.7",
     "hdx-python-database[postgresql]>= 1.3.4",
-    "hdx-python-scraper>= 2.5.1",
-    "hdx-python-utilities>= 3.8.0",
+    "hdx-python-scraper>= 2.5.5",
+    "hdx-python-utilities>= 3.8.2",
     "libhxl",
     "sqlalchemy"
 ]

requirements.txt

@@ -8,7 +8,7 @@ attrs==24.3.0
     #   jsonlines
     #   jsonschema
     #   referencing
-cachetools==5.5.0
+cachetools==5.5.1
     # via google-auth
 certifi==2024.12.14
     # via requests
@@ -40,7 +40,7 @@ email-validator==2.2.0
     # via hdx-python-api
 et-xmlfile==2.0.0
     # via openpyxl
-filelock==3.16.1
+filelock==3.17.0
     # via virtualenv
 frictionless==5.18.0
     # via hdx-python-utilities
@@ -56,28 +56,28 @@ gspread==6.1.4
     # via hdx-python-scraper
 hapi-schema==0.9.6
     # via hapi-pipelines (pyproject.toml)
-hdx-python-api==6.3.6
+hdx-python-api==6.3.7
     # via
     #   hapi-pipelines (pyproject.toml)
     #   hdx-python-scraper
-hdx-python-country==3.8.6
+hdx-python-country==3.8.7
     # via
     #   hapi-pipelines (pyproject.toml)
     #   hdx-python-api
     #   hdx-python-scraper
 hdx-python-database==1.3.4
     # via hapi-pipelines (pyproject.toml)
-hdx-python-scraper==2.5.1
+hdx-python-scraper==2.5.5
     # via hapi-pipelines (pyproject.toml)
-hdx-python-utilities==3.8.0
+hdx-python-utilities==3.8.2
     # via
     #   hapi-pipelines (pyproject.toml)
     #   hdx-python-api
     #   hdx-python-country
     #   hdx-python-scraper
 humanize==4.11.0
     # via frictionless
-identify==2.6.5
+identify==2.6.6
     # via pre-commit
 idna==3.10
     # via
@@ -120,7 +120,7 @@ markupsafe==3.0.2
     # via jinja2
 mdurl==0.1.2
     # via markdown-it-py
-more-itertools==10.5.0
+more-itertools==10.6.0
     # via inflect
 nodeenv==1.9.1
     # via pre-commit
@@ -144,11 +144,11 @@ ply==3.11
     #   libhxl
 pockets==0.9.1
     # via sphinxcontrib-napoleon
-pre-commit==4.0.1
+pre-commit==4.1.0
     # via hapi-pipelines (pyproject.toml)
-psycopg==3.2.3
+psycopg==3.2.4
     # via hdx-python-database
-psycopg-binary==3.2.3
+psycopg-binary==3.2.4
     # via psycopg
 pyasn1==0.6.1
     # via
@@ -196,7 +196,7 @@ quantulum3==0.9.2
     # via hdx-python-api
 ratelimit==2.2.1
     # via hdx-python-utilities
-referencing==0.35.1
+referencing==0.36.1
     # via
     #   jsonschema
     #   jsonschema-specifications
@@ -251,7 +251,7 @@ sqlalchemy==2.0.37
     #   hdx-python-database
 stringcase==1.2.0
     # via frictionless
-structlog==24.4.0
+structlog==25.1.0
     # via libhxl
 tableschema-to-template==0.0.13
     # via hdx-python-utilities
@@ -271,6 +271,7 @@ typing-extensions==4.12.2
     #   psycopg
     #   pydantic
     #   pydantic-core
+    #   referencing
     #   sqlalchemy
     #   typeguard
     #   typer
@@ -284,7 +285,7 @@ urllib3==2.3.0
     #   requests
 validators==0.34.0
     # via frictionless
-virtualenv==20.28.1
+virtualenv==20.29.1
     # via pre-commit
 wheel==0.45.1
     # via libhxl

src/hapi/pipelines/app/__main__.py

@@ -79,13 +79,6 @@ def parse_args():
         action="store_true",
         help="Use saved data",
     )
-    parser.add_argument(
-        "-dbg",
-        "--debug",
-        default=False,
-        action="store_true",
-        help="Debug",
-    )
     parser.add_argument(
         "-ehx",
         "--err-to-hdx",
@@ -104,7 +97,6 @@ def main(
     basic_auths: Optional[Dict[str, str]] = None,
     save: bool = False,
     use_saved: bool = False,
-    debug: bool = False,
     err_to_hdx: bool = False,
     **ignore,
 ) -> None:
@@ -121,7 +113,6 @@ def main(
         basic_auths (Optional[Dict[str, str]]): Basic authorisations
         save (bool): Whether to save state for testing. Defaults to False.
         use_saved (bool): Whether to use saved state for testing. Defaults to False.
-        debug (bool): Whether to output debug info. Defaults to False.
         err_to_hdx (bool): Whether to write any errors to HDX metadata. Defaults to False.
 
     Returns:
@@ -142,7 +133,7 @@ def main(
         params["prepare_fn"] = prepare_hapi_views
     logger.info(f"> Database parameters: {params}")
     configuration = Configuration.read()
-    with HDXErrorHandler(should_exit_on_error=False) as error_handler:
+    with HDXErrorHandler(write_to_hdx=err_to_hdx) as error_handler:
         with temp_dir() as temp_folder:
             with Database(**params) as database:
                 session = database.get_session()
@@ -169,9 +160,6 @@ def main(
                 )
                 pipelines.run()
                 pipelines.output()
-                pipelines.output_errors(err_to_hdx)
-                if debug:
-                    pipelines.debug("debug")
     logger.info("HAPI pipelines completed!")
 
 
@@ -216,7 +204,6 @@ def main(
         "food_security.yaml",
         "idps.yaml",
         "national_risk.yaml",
-        "operational_presence.yaml",
         "refugees_and_returnees.yaml",
         "wfp.yaml",
     ]
@@ -235,6 +222,5 @@ def main(
         basic_auths=basic_auths,
         save=args.save,
         use_saved=args.use_saved,
-        debug=args.debug,
         err_to_hdx=ehx,
     )

src/hapi/pipelines/app/pipelines.py

@@ -66,7 +66,11 @@ def __init__(
             url=AdminLevel.formats_url, retriever=reader
         ).cache()
         self.admins = Admins(
-            configuration, session, self.locations, libhxl_dataset
+            configuration,
+            session,
+            self.locations,
+            libhxl_dataset,
+            error_handler,
         )
         admin1_config = configuration["admin1"]
         self.adminone = AdminLevel(admin_config=admin1_config, admin_level=1)
@@ -88,21 +92,13 @@ def __init__(
         logger.info("Admin two name replacements:")
         self.admintwo.output_admin_name_replacements()
 
-        self.org = Org(
-            session=session,
-            datasetinfo=configuration["org"],
-        )
         self.org_type = OrgType(
             session=session,
-            datasetinfo=configuration["org_type"],
-            org_type_map=configuration["org_type_map"],
         )
         self.sector = Sector(
             session=session,
-            datasetinfo=configuration["sector"],
-            sector_map=configuration["sector_map"],
         )
-        self.currency = Currency(configuration=configuration, session=session)
+        self.currency = Currency(session=session, configuration=configuration)
 
         Sources.set_default_source_date_format("%Y-%m-%d")
         self.runner = Runner(
@@ -113,6 +109,7 @@ def __init__(
         )
         self.configurable_scrapers = {}
         self.create_configurable_scrapers()
+
         self.metadata = Metadata(
             runner=self.runner, session=session, today=today
         )
@@ -135,7 +132,7 @@ def setup_configurable_scrapers(
         if countryiso3s:
             configuration = {}
             # This assumes format prefix_iso_.... eg.
-            # population_gtm, operational_presence_afg_total
+            # population_gtm
             iso3_index = len(prefix) + 1
             for key, value in self.configuration[f"{prefix}{suffix}"].items():
                 if len(key) < iso3_index + 3:
@@ -172,13 +169,6 @@ def _create_configurable_scrapers(
                 current_scrapers + scraper_names
             )
 
-        _create_configurable_scrapers(
-            "operational_presence", "admintwo", adminlevel=self.admintwo
-        )
-        _create_configurable_scrapers(
-            "operational_presence", "adminone", adminlevel=self.adminone
-        )
-        _create_configurable_scrapers("operational_presence", "national")
         _create_configurable_scrapers("national_risk", "national")
         _create_configurable_scrapers("refugees_and_returnees", "national")
         _create_configurable_scrapers("idps", "national")
@@ -212,21 +202,17 @@ def output_operational_presence(self):
             not self.themes_to_run
             or "operational_presence" in self.themes_to_run
         ):
-            results = self.runner.get_hapi_results(
-                self.configurable_scrapers["operational_presence"]
+            org = Org(
+                session=self.session,
+                metadata=self.metadata,
+                configuration=self.configuration,
             )
+            org.populate()
             operational_presence = OperationalPresence(
                 session=self.session,
                 metadata=self.metadata,
                 admins=self.admins,
-                adminone=self.adminone,
-                admintwo=self.admintwo,
-                org=self.org,
-                org_type=self.org_type,
-                sector=self.sector,
-                results=results,
-                config=self.configuration,
-                error_handler=self.error_handler,
+                configuration=self.configuration,
             )
             operational_presence.populate()
 
@@ -253,9 +239,7 @@ def output_humanitarian_needs(self):
                 session=self.session,
                 metadata=self.metadata,
                 admins=self.admins,
-                sector=self.sector,
                 configuration=self.configuration,
-                error_handler=self.error_handler,
             )
             humanitarian_needs.populate()
 
@@ -374,7 +358,6 @@ def output(self):
         self.locations.populate()
         self.admins.populate()
         self.metadata.populate()
-        self.org.populate()
         self.org_type.populate()
         self.sector.populate()
         self.currency.populate()
@@ -389,9 +372,3 @@ def output(self):
         self.output_poverty_rate()
         self.output_conflict_event()
         self.output_food_prices()
-
-    def debug(self, folder: str) -> None:
-        self.org.output_org_map(folder)
-
-    def output_errors(self, err_to_hdx: bool) -> None:
-        self.error_handler.output_errors(err_to_hdx)