widlfires: area burnt by wildfire bug

owid · Nov 25, 2024 · 4ea6d29 · 4ea6d29
1 parent d66931a
commit 4ea6d29
Show file tree

Hide file tree

Showing 4 changed files with 29 additions and 42 deletions.
diff --git a/etl/steps/data/garden/climate/latest/weekly_wildfires.meta.yml b/etl/steps/data/garden/climate/latest/weekly_wildfires.meta.yml
@@ -102,19 +102,3 @@ tables:
           description_key:
             - CO₂ emissions contribute to the greenhouse effect, influencing global warming and climate change.
 
-
-        co2_ha_per_area:
-          title: Carbon dioxide emissions per hectare burnt
-          unit: tonnes
-          short_unit: t
-          description_short: Carbon dioxide emissions per hectare burnt by [wildfires](#dod:wildfires), in tonnes. {definitions.desc_update}
-          description_processing: The carbon dioxide emissions per hectare is calculated by dividing the carbon dioxide emissions by the area burnt by wildfires.
-          description_key: *desc_wildfires
-
-        pm2_5_ha_per_area:
-          title: PM2.5 emissions per hectare burnt
-          unit: tonnes
-          short_unit: t
-          description_short: PM2.5 emissions per hectare burnt by [wildfires](#dod:wildfires), in tonnes. {definitions.desc_update}
-          description_processing: The PM2.5 emissions per hectare is calculated by dividing the PM2.5 emissions by the area burnt by wildfires.
-          description_key: *desc_wildfires
diff --git a/etl/steps/data/garden/climate/latest/weekly_wildfires.py b/etl/steps/data/garden/climate/latest/weekly_wildfires.py
@@ -1,7 +1,6 @@
 """Load a meadow dataset and create a garden dataset."""
 
 
-import numpy as np
 import owid.catalog.processing as pr
 import pandas as pd
 
@@ -87,13 +86,6 @@ def run(dest_dir: str) -> None:
     tb["share_area_ha"] = (tb["area_ha"] / tb["total_area_ha"]) * 100
     tb["share_area_ha_cumulative"] = (tb["area_ha_cumulative"] / tb["total_area_ha"]) * 100
 
-    tb["co2_ha_per_area"] = tb["CO2"] / tb["area_ha"]
-    tb["pm2_5_ha_per_area"] = tb["PM2.5"] / tb["area_ha"]
-
-    tb[["co2_ha_per_area", "pm2_5_ha_per_area"]] = tb[["co2_ha_per_area", "pm2_5_ha_per_area"]].replace(
-        [float("inf"), -float("inf")], np.nan
-    )
-
     tb = tb.drop(columns=["total_area_ha"])
     tb = tb.set_index(["country", "date"], verify_integrity=True)
 

diff --git a/etl/steps/data/grapher/climate/latest/wildfires_by_year.meta.yml b/etl/steps/data/grapher/climate/latest/wildfires_by_year.meta.yml
@@ -56,7 +56,17 @@ tables:
           description_key: *desc_wildfires
 
         co2_ha_per_area:
-          title: Annual carbon dioxide emissions per area burnt
+          title: Carbon dioxide emissions per hectare burnt
+          unit: tonnes
+          short_unit: t
+          description_short: Carbon dioxide emissions per hectare burnt by [wildfires](#dod:wildfires), in tonnes. {definitions.desc_update}
+          description_processing: The carbon dioxide emissions per hectare is calculated by dividing the carbon dioxide emissions by the area burnt by wildfires.
+          description_key: *desc_wildfires
 
         pm2_5_ha_per_area:
-          title: Annual PM2.5 emissions per area burnt
+          title: PM2.5 emissions per hectare burnt
+          unit: tonnes
+          short_unit: t
+          description_short: PM2.5 emissions per hectare burnt by [wildfires](#dod:wildfires), in tonnes. {definitions.desc_update}
+          description_processing: The PM2.5 emissions per hectare is calculated by dividing the PM2.5 emissions by the area burnt by wildfires.
+          description_key: *desc_wildfires
diff --git a/etl/steps/data/grapher/climate/latest/wildfires_by_year.py b/etl/steps/data/grapher/climate/latest/wildfires_by_year.py
@@ -1,8 +1,9 @@
 """Load a garden dataset and create a grapher dataset."""
 
+import numpy as np
 import owid.catalog.processing as pr
 
-from etl.helpers import PathFinder, create_dataset
+from etl.helpers import PathFinder, create_dataset, last_date_accessed
 
 # Get paths and naming conventions for current step.
 paths = PathFinder(__file__)
@@ -22,20 +23,7 @@ def run(dest_dir: str) -> None:
 
     # Get the year
     tb["year"] = tb["date"].astype(str).str[0:4]
-    tb = tb[
-        [
-            "country",
-            "year",
-            "area_ha",
-            "events",
-            "pm2_5",
-            "co2",
-            "share_area_ha",
-            "area_ha_per_wildfire",
-            "co2_ha_per_area",
-            "pm2_5_ha_per_area",
-        ]
-    ]
+    tb = tb[["country", "year", "area_ha", "events", "pm2_5", "co2", "share_area_ha"]]
     # Aggregate the data by year and country (ignore missing values when summing the columns)
     tb_annual_sum = tb.groupby(["country", "year"]).sum(min_count=1).reset_index()
 
@@ -54,12 +42,25 @@ def run(dest_dir: str) -> None:
     # Area per wildfire
     tb["area_ha_per_wildfire"] = tb["area_ha"] / tb["events"]
 
+    tb["co2_ha_per_area"] = tb["co2"] / tb["area_ha"]
+    tb["pm2_5_ha_per_area"] = tb["pm2_5"] / tb["area_ha"]
+
+    tb[["co2_ha_per_area", "pm2_5_ha_per_area"]] = tb[["co2_ha_per_area", "pm2_5_ha_per_area"]].replace(
+        [float("inf"), -float("inf")], np.nan
+    )
+
     tb = tb.set_index(["country", "year"], verify_integrity=True)
 
     # Save outputs.
     #
     # Create a new grapher dataset with the same metadata as the garden dataset.
-    ds_grapher = create_dataset(dest_dir, tables=[tb], default_metadata=ds_garden.metadata)
+    ds_grapher = create_dataset(
+        dest_dir,
+        tables=[tb],
+        default_metadata=ds_garden.metadata,
+        yaml_params={"date_accessed": last_date_accessed(tb)},
+    )
+
     ds_grapher.metadata.title = "Seasonal wildfire trends by year"
 
     ds_grapher.save()