📊 forests: primary forest share

dag/forests.yml

@@ -16,4 +16,10 @@ steps:
     - data://garden/regions/2023-01-01/regions
     - data://garden/wb/2023-04-30/income_groups
   data://grapher/forests/2024-07-10/tree_cover_loss_by_driver:
-    - data://garden/forests/2024-07-10/tree_cover_loss_by_driver
+    - data://garden/forests/2024-07-10/tree_cover_loss_by_driver
+
+  data://garden/forests/2024-09-17/primary_forest:
+    - data://garden/faostat/2024-03-14/faostat_rl
+  data://grapher/forests/2024-09-17/primary_forest:
+    - data://garden/forests/2024-09-17/primary_forest
+

etl/steps/data/garden/forests/2024-09-17/primary_forest.meta.yml

@@ -0,0 +1,34 @@
+# NOTE: To learn more about the fields, hover over their names.
+definitions:
+  common:
+    presentation:
+      topic_tags:
+        - Forests & Deforestation
+    processing_level: major
+
+# Learn more about the available fields:
+# http://docs.owid.io/projects/etl/architecture/metadata/reference/
+dataset:
+  update_period_days: 365
+
+
+tables:
+  primary_forest:
+    variables:
+      value_primary_forest:
+        title: Primary forest area
+        description_short: Primary forest is defined as naturally regenerated forest of native species, where there are no clearly visible indications of human activities and the ecological processes are not significantly disturbed.
+        display:
+          name: Primary forest area
+        unit: 1000 hectares
+      value_land_area:
+        title: Land area
+        unit:   1000 hectares
+      primary_forest_share:
+        title: Primary forest share
+        description_short: The share of primary forest out of total land area. Primary forest is defined as naturally regenerated forest of native species, where there are no clearly visible indications of human activities and the ecological processes are not significantly disturbed.
+        description_processing: This is calculated as the primary forest area divided by the total land area.
+        display:
+          name: Share of land that is primary forest
+        unit: "%"
+        short_unit: "%"

etl/steps/data/garden/forests/2024-09-17/primary_forest.py

@@ -0,0 +1,41 @@
+"""Load a meadow dataset and create a garden dataset."""
+import owid.catalog.processing as pr
+
+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 meadow dataset.
+    ds = paths.load_dataset("faostat_rl")
+    tb = ds["faostat_rl"].reset_index()
+    tb = tb[["country", "year", "element", "item", "unit", "value"]]
+    tb_primary = tb[(tb["item"] == "Primary Forest") & (tb["unit"] == "hectares")]
+    tb_land_area = tb[(tb["item"] == "Land area") & (tb["unit"] == "hectares")]
+
+    tb = pr.merge(
+        tb_primary,
+        tb_land_area,
+        how="left",
+        suffixes=("_primary_forest", "_land_area"),
+        validate="one_to_one",
+        on=["country", "year", "element", "unit"],
+    )
+    tb["primary_forest_share"] = (tb["value_primary_forest"] / tb["value_land_area"]) * 100
+    tb = tb.drop(columns=["item_primary_forest", "item_land_area", "unit", "element"])
+    tb = tb.format(
+        [
+            "country",
+            "year",
+        ],
+        short_name="primary_forest",
+    )
+    # 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/forests/2024-09-17/primary_forest.py

@@ -0,0 +1,32 @@
+"""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("primary_forest")
+
+    # Read table from garden dataset.
+    tb = ds_garden["primary_forest"]
+
+    #
+    # Process data.
+    #
+
+    #
+    # 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()