mvp

dag/demography.yml

@@ -263,15 +263,22 @@ steps:
     - data://garden/hmd/2024-12-01/hmd
   data://grapher/hmd/2024-12-03/hmd_country:
     - data://garden/hmd/2024-12-03/hmd_country
-  
+
   # Patternal ages (Kai & Klüssner)
   data://meadow/demography/2024-12-05/paternal_ages:
     - snapshot://demography/2024-12-04/paternal_ages.rdata
   data://garden/demography/2024-12-05/paternal_ages:
     - data://meadow/demography/2024-12-05/paternal_ages
   data://grapher/demography/2024-12-05/paternal_ages:
     - data://garden/demography/2024-12-05/paternal_ages
-
+
+  # Mean Age at childbirth (HFD + UN WPP)
+  data://garden/demography/2024-12-18/mean_age_childbearing:
+    - data://garden/un/2024-07-12/un_wpp
+    - data://garden/hmd/2024-11-19/hfd
+  data://grapher/demography/2024-12-18/mean_age_childbearing:
+    - data://garden/demography/2024-12-18/mean_age_childbearing
+
   ########################################################################
   # OTHERS
   ########################################################################

etl/steps/data/garden/demography/2024-12-18/mean_age_childbearing.meta.yml

@@ -0,0 +1,51 @@
+# NOTE: To learn more about the fields, hover over their names.
+definitions:
+  common:
+    presentation:
+      topic_tags:
+        - Fertility Rate
+
+# Learn more about the available fields:
+# http://docs.owid.io/projects/etl/architecture/metadata/reference/
+dataset:
+  update_period_days: 365
+  title: Mean age at childbearing (HFD; UN WPP)
+
+tables:
+  mean_age_childbearing:
+    variables:
+      mean_age_childbearing:
+        title: Mean age at childbearing
+        unit: years
+        description_short: &cb_description_short |-
+          Mean age of mothers at the birth of their children if women were subject throughout their lives to the age-specific fertility rates observed in a given year. UN Medium projections for 2024-2100.
+        description_processing: |-
+          This indicator is constructed by combining data from multiple sources:
+
+          - Before 1949: Historical estimates by Human Fertility Database (2024).
+
+          - 1950-2023: Population records by the UN World Population Prospects (2024 revision).
+
+          - 2024-2100: Projections based on Medium variant by the UN World Population Prospects (2024 revision).
+        presentation:
+          title_public: |-
+            Mean age at childbearing
+          grapher_config:
+            subtitle: *cb_description_short
+
+      mean_age_childbearing_hist:
+        title: Mean age at childbearing, historical
+        unit: years
+        description_short: &cb_description_short_hist |-
+          Mean age of mothers at the birth of their children if women were subject throughout their lives to the age-specific fertility rates observed in a given year.
+        description_processing: |-
+          This indicator is constructed by combining data from multiple sources:
+
+          - Before 1949: Historical estimates by Human Fertility Database (2024).
+
+          - 1950-2023: Population records by the UN World Population Prospects (2024 revision).
+        presentation:
+          title_public: |-
+            Mean age at childbearing
+          grapher_config:
+            subtitle: *cb_description_short_hist

etl/steps/data/garden/demography/2024-12-18/mean_age_childbearing.py

@@ -0,0 +1,69 @@
+"""Load a meadow dataset and create a garden dataset."""
+
+import pandas as pd
+from owid.catalog import processing as pr
+
+from etl.helpers import PathFinder, create_dataset
+
+# Get paths and naming conventions for current step.
+paths = PathFinder(__file__)
+
+
+# Year constants
+YEAR_WPP_START = 1950
+YEAR_WPP_PROJ_START = 2023
+# Table names
+TABLE_NAME_WPP = "mean_age_childbearing"
+TABLE_NAME_HFD = "period"
+TABLE_NAME_NEW = "mean_age_childbearing"
+# Metric names
+COLUMN_NAME_WPP = "mean_age_childbearing"
+COLUMN_NAME_HFD = "mab"
+COLUMN_NEW_NAME = "mean_age_childbearing"
+
+
+def run(dest_dir: str) -> None:
+    #
+    # Load inputs.
+    #
+    # Load meadow dataset.
+    ds_hfd = paths.load_dataset("hfd")
+    ds_un = paths.load_dataset("un_wpp")
+
+    # Read table from meadow dataset.
+    tb_hfd = ds_hfd.read(TABLE_NAME_HFD)
+    tb_un = ds_un.read(TABLE_NAME_WPP)
+
+    # UN: estimates + medium,
+    tb_un = tb_un.loc[
+        (tb_un["sex"] == "all") & (tb_un["variant"].isin(["medium", "estimates"]) & (tb_un["age"] == "all")),
+        ["country", "year", COLUMN_NAME_WPP],
+    ].rename(columns={COLUMN_NAME_WPP: COLUMN_NEW_NAME})
+
+    # HFD: tfr, birth_order=total,
+    tb_hfd = tb_hfd.loc[
+        ((tb_hfd["birth_order"] == "total") & (tb_hfd["year"] < YEAR_WPP_START)), ["country", "year", COLUMN_NAME_HFD]
+    ].rename(columns={COLUMN_NAME_HFD: COLUMN_NEW_NAME})
+
+    # Concatenate
+    tb = pr.concat([tb_hfd, tb_un], ignore_index=True, short_name=TABLE_NAME_NEW)
+
+    # Add historical variant
+    tb[f"{COLUMN_NEW_NAME}_hist"] = tb[COLUMN_NEW_NAME].copy()
+    tb.loc[tb["year"] > YEAR_WPP_PROJ_START, f"{COLUMN_NEW_NAME}_hist"] = pd.NA
+
+    # Format
+    tb = tb.format(["country", "year"])
+
+    #
+    # Save outputs.
+    #
+    # Create a new garden dataset with the same metadata as the meadow dataset.
+    ds_garden = create_dataset(
+        dest_dir,
+        tables=[tb],
+        check_variables_metadata=True,
+    )
+
+    # Save changes in the new garden dataset.
+    ds_garden.save()

etl/steps/data/grapher/demography/2024-12-18/mean_age_childbearing.py

@@ -0,0 +1,28 @@
+"""Load a garden dataset and create a grapher dataset."""
+
+from etl.helpers import PathFinder, create_dataset
+
+# Get paths and naming conventions for current step.
+paths = PathFinder(__file__)
+
+
+def run(dest_dir: str) -> None:
+    #
+    # Load inputs.
+    #
+    # Load garden dataset.
+    ds_garden = paths.load_dataset("mean_age_childbearing")
+
+    # Read table from garden dataset.
+    tb = ds_garden.read("mean_age_childbearing", reset_index=False)
+
+    #
+    # Save outputs.
+    #
+    # Create a new grapher dataset with the same metadata as the garden dataset.
+    ds_grapher = create_dataset(
+        dest_dir, tables=[tb], check_variables_metadata=True, default_metadata=ds_garden.metadata
+    )
+
+    # Save changes in the new grapher dataset.
+    ds_grapher.save()