Version 0.10.29

CHANGELOG.md

@@ -4,6 +4,18 @@ 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/).
 
+## [0.10.29] - 2024-12-12
+
+### Fixed
+
+- 3W for NGA
+
+### Changed
+
+- Added ability to read historical humanitarian needs data
+- Replaced missing funding amounts with zeros
+- Updated 3W data for CAF, SSD
+
 ## [0.10.28] - 2024-12-10
 
 ### Changed

src/hapi/pipelines/configs/operational_presence.yaml

@@ -62,35 +62,33 @@ operational_presence_admintwo:
 
   operational_presence_caf:
     dataset: "republique-centrafricaine-presence-operationnelle"
-    resource: "3W_CAR_Mar2024"
+    resource: "3W_CAR_Sep2024"
     format: "xlsx"
     xlsx2csv: True
-    sheet: "OCHA CAR 3W OP T1 2024"
-    headers:
-      - 1
-      - 2
+    sheet: "3W T3 2024"
+    headers: 1
     source_date:
-      start: "01/01/2024"
-      end: "31/03/2024"
+      start: "01/04/2024"
+      end: "30/09/2024"
     use_hxl: False
     admin:
       - ~
-      - "PCODE2 #adm2+code"
+      - "PCODE2"
     admin_exact: True
     input:
-      - "Description_Acteur"
-      - "ACTEUR #org+acronym"
+      - "DESCRIPTION_ACTEUR"
+      - "ACTEUR"
       - "TYPE_ORG"
-      - "SECTEUR #sector"
-      - "PREFECTURE #adm1+name"
-      - "SOUSPREFECTURE #adm2+name"
+      - "SECTEUR"
+      - "PREFECTURE"
+      - "SOUSPREFECTURE"
     list:
-      - "Description_Acteur"
-      - "ACTEUR #org+acronym"
+      - "DESCRIPTION_ACTEUR"
+      - "ACTEUR"
       - "TYPE_ORG"
-      - "SECTEUR #sector"
-      - "PREFECTURE #adm1+name"
-      - "SOUSPREFECTURE #adm2+name"
+      - "SECTEUR"
+      - "PREFECTURE"
+      - "SOUSPREFECTURE"
 
   operational_presence_cmr:
     dataset: "cameroon-5w-operational-presence"
@@ -356,7 +354,7 @@ operational_presence_admintwo:
 
   operational_presence_nga:
     dataset: "nigeria-3w"
-    resource: "who-is-doing-what-and-where_nga_3w_apr_jun_2024.xlsx.csv"
+    resource: "who-is-doing-what-and-where_nga_3w_apr_jun_2024.csv"
     format: "csv"
     headers: 1
     source_date:
@@ -759,14 +757,14 @@ operational_presence_national:
 
   operational_presence_ssd:
     dataset: "south-sudan-operational-presence"
-    resource: "ss_20241106_3w_oerational presence_Jan to Sep_2024.xlsx"
+    resource: "ss_20241212_3w_oerational presence_Jan to Oct_2024.xlsx"
     format: "xlsx"
     xlsx2csv: True
-    sheet: "data"
+    sheet: "Data"
     headers: 1
     source_date:
       start: "01/01/2024"
-      end: "30/09/2024"
+      end: "31/10/2024"
     admin_single: "SSD"
     input:
       - "Name of organization"

src/hapi/pipelines/database/funding.py

@@ -96,16 +96,10 @@ def populate(self) -> None:
                 # This check for a missing funding line has been added due to
                 # an error in the UKR funding requirements data
                 if funding_usd is None:
-                    self._error_manager.add_missing_value_message(
-                        "Funding",
-                        dataset_name,
-                        "funding_usd for appeal code",
-                        appeal_code,
-                        resource_name=resource_name,
-                        err_to_hdx=True,
-                    )
-                    continue
+                    funding_usd = 0
                 funding_pct = row["#value+funding+pct"]
+                if funding_pct is None and funding_usd == 0:
+                    funding_pct = 0
                 reference_period_start = parse_date(row["#date+start"])
                 reference_period_end = parse_date(row["#date+end"])
 

src/hapi/pipelines/database/humanitarian_needs.py

@@ -95,86 +95,87 @@ def populate(self) -> None:
         self._metadata.add_dataset(dataset)
         dataset_id = dataset["id"]
         dataset_name = dataset["name"]
-        resource = dataset.get_resource(0)  # assumes first resource is latest!
-        self._metadata.add_resource(dataset_id, resource)
-        negative_values_by_iso3 = {}
-        rounded_values_by_iso3 = {}
-        resource_id = resource["id"]
-        resource_name = resource["name"]
-        year = int(resource_name[-4:])
-        time_period_start = datetime(year, 1, 1)
-        time_period_end = datetime(year, 12, 31, 23, 59, 59)
-        url = resource["url"]
-        headers, rows = reader.get_tabular_rows(url, dict_form=True)
-        # Admin 1 PCode,Admin 2 PCode,Sector,Gender,Age Group,Disabled,Population Group,Population,In Need,Targeted,Affected,Reached
-        for row in rows:
-            countryiso3 = row["Country ISO3"]
-            admin2_ref = self.get_admin2_ref(row, dataset_name)
-            if not admin2_ref:
-                continue
-            provider_admin1_name = get_provider_name(row, "Admin 1 Name")
-            provider_admin2_name = get_provider_name(row, "Admin 2 Name")
-            sector = row["Sector"]
-            sector_code = self._sector.get_sector_code(sector)
-            if not sector_code:
-                self._error_manager.add_missing_value_message(
-                    "HumanitarianNeeds", dataset_name, "sector", sector
-                )
-                continue
-            category = row["Category"]
-            if category is None:
-                category = ""
-
-            def create_row(in_col, population_status):
-                value = row[in_col]
-                if value is None:
-                    return
-                value = get_numeric_if_possible(value)
-                if value < 0:
-                    dict_of_lists_add(
-                        negative_values_by_iso3, countryiso3, str(value)
+        resources = dataset.get_resources()
+        for resource in resources:
+            self._metadata.add_resource(dataset_id, resource)
+            negative_values_by_iso3 = {}
+            rounded_values_by_iso3 = {}
+            resource_id = resource["id"]
+            resource_name = resource["name"]
+            year = int(resource_name[-4:])
+            time_period_start = datetime(year, 1, 1)
+            time_period_end = datetime(year, 12, 31, 23, 59, 59)
+            url = resource["url"]
+            headers, rows = reader.get_tabular_rows(url, dict_form=True)
+            # Admin 1 PCode,Admin 2 PCode,Sector,Gender,Age Group,Disabled,Population Group,Population,In Need,Targeted,Affected,Reached
+            for row in rows:
+                countryiso3 = row["Country ISO3"]
+                admin2_ref = self.get_admin2_ref(row, dataset_name)
+                if not admin2_ref:
+                    continue
+                provider_admin1_name = get_provider_name(row, "Admin 1 Name")
+                provider_admin2_name = get_provider_name(row, "Admin 2 Name")
+                sector = row["Sector"]
+                sector_code = self._sector.get_sector_code(sector)
+                if not sector_code:
+                    self._error_manager.add_missing_value_message(
+                        "HumanitarianNeeds", dataset_name, "sector", sector
                     )
-                    return
-                if isinstance(value, float):
-                    dict_of_lists_add(
-                        rounded_values_by_iso3, countryiso3, str(value)
+                    continue
+                category = row["Category"]
+                if category is None:
+                    category = ""
+
+                def create_row(in_col, population_status):
+                    value = row[in_col]
+                    if value is None:
+                        return
+                    value = get_numeric_if_possible(value)
+                    if value < 0:
+                        dict_of_lists_add(
+                            negative_values_by_iso3, countryiso3, str(value)
+                        )
+                        return
+                    if isinstance(value, float):
+                        dict_of_lists_add(
+                            rounded_values_by_iso3, countryiso3, str(value)
+                        )
+                        value = round(value)
+                    humanitarian_needs_row = DBHumanitarianNeeds(
+                        resource_hdx_id=resource_id,
+                        admin2_ref=admin2_ref,
+                        provider_admin1_name=provider_admin1_name,
+                        provider_admin2_name=provider_admin2_name,
+                        category=category,
+                        sector_code=sector_code,
+                        population_status=population_status,
+                        population=value,
+                        reference_period_start=time_period_start,
+                        reference_period_end=time_period_end,
                     )
-                    value = round(value)
-                humanitarian_needs_row = DBHumanitarianNeeds(
-                    resource_hdx_id=resource_id,
-                    admin2_ref=admin2_ref,
-                    provider_admin1_name=provider_admin1_name,
-                    provider_admin2_name=provider_admin2_name,
-                    category=category,
-                    sector_code=sector_code,
-                    population_status=population_status,
-                    population=value,
-                    reference_period_start=time_period_start,
-                    reference_period_end=time_period_end,
-                )
-                self._session.add(humanitarian_needs_row)
+                    self._session.add(humanitarian_needs_row)
 
-            create_row("Population", "all")
-            create_row("Affected", "AFF")
-            create_row("In Need", "INN")
-            create_row("Targeted", "TGT")
-            create_row("Reached", "REA")
+                create_row("Population", "all")
+                create_row("Affected", "AFF")
+                create_row("In Need", "INN")
+                create_row("Targeted", "TGT")
+                create_row("Reached", "REA")
 
-        self._session.commit()
-        for countryiso3, values in negative_values_by_iso3.items():
-            self._error_manager.add_multi_valued_message(
-                "HumanitarianNeeds",
-                dataset_name,
-                f"negative population value(s) removed in {countryiso3}",
-                values,
-                resource_name=resource_name,
-                err_to_hdx=True,
-            )
-        for countryiso3, values in rounded_values_by_iso3.items():
-            self._error_manager.add_multi_valued_message(
-                "HumanitarianNeeds",
-                dataset_name,
-                f"population value(s) rounded in {countryiso3}",
-                values,
-                message_type="warning",
-            )
+            self._session.commit()
+            for countryiso3, values in negative_values_by_iso3.items():
+                self._error_manager.add_multi_valued_message(
+                    "HumanitarianNeeds",
+                    dataset_name,
+                    f"negative population value(s) removed in {countryiso3}",
+                    values,
+                    resource_name=resource_name,
+                    err_to_hdx=True,
+                )
+            for countryiso3, values in rounded_values_by_iso3.items():
+                self._error_manager.add_multi_valued_message(
+                    "HumanitarianNeeds",
+                    dataset_name,
+                    f"population value(s) rounded in {countryiso3}",
+                    values,
+                    message_type="warning",
+                )

tests/test_main.py

@@ -230,7 +230,7 @@ def test_funding(self, configuration, folder, pipelines):
         count = session.scalar(select(func.count(DBResource.hdx_id)))
         check.equal(count, 3)
         count = session.scalar(select(func.count(DBFunding.resource_hdx_id)))
-        check.equal(count, 56)
+        check.equal(count, 57)
 
     @pytest.mark.parametrize(
         "themes_to_run", [{"conflict_event": ("BFA", "COL")}]