🎉 Update long_to_wide functionality and metadata handling in grapher …

…steps
owid · Dec 4, 2024 · 6339162 · 6339162
1 parent efb3477
commit 6339162
Show file tree

Hide file tree

Showing 4 changed files with 9 additions and 6 deletions.
diff --git a/etl/grapher_helpers.py b/etl/grapher_helpers.py
@@ -229,7 +229,7 @@ def long_to_wide(long_tb: catalog.Table) -> catalog.Table:
         short_names.append(short_name)
 
         # Create metadata for the column from dimensions
-        metadatas.append(_metadata_for_dimensions(long_tb[dims[0]].metadata, dim_dict, column))
+        metadatas.append(_metadata_for_dimensions(long_tb[dims[0]].metadata.copy(), dim_dict, column))
 
     # Set column names to new short names and use proper metadata
     wide_tb.columns = short_names

diff --git a/etl/helpers.py b/etl/helpers.py
@@ -283,6 +283,9 @@ def create_dataset(
 
         # Expand long to wide
         if long_to_wide:
+            if ds.metadata.channel != "grapher":
+                log.warning("long_to_wide=True should be only used in grapher channel")
+
             dim_names = set(table.index.names) - {"country", "year", "date"}
             if dim_names:
                 # First pass to update metadata from YAML

diff --git a/etl/steps/data/garden/cancer/2024-08-30/gco_alcohol.py b/etl/steps/data/garden/cancer/2024-08-30/gco_alcohol.py
@@ -15,14 +15,14 @@ def run(dest_dir: str) -> None:
     ds_meadow = paths.load_dataset("gco_alcohol")
 
     # Read table from meadow dataset.
-    tb = ds_meadow.read("gco_alcohol")
+    tb = ds_meadow["gco_alcohol"].reset_index()
 
     #
     # Process data.
     #
     tb = geo.harmonize_countries(df=tb, countries_file=paths.country_mapping_path)
 
-    # To display on grapher we need to replace "<0.1" with "0.05" and set the decimal places to 1 so that it shows up as <0.1 on the chart
+    # To display on grapher we need to replace "<0.1" with "0.05" and set the decimal places to 1 so that it shows up as <0.1 on the chart.
     tb["value"] = tb["value"].replace("<0.1", "0.05")
 
     tb = tb.format(["country", "year", "sex", "cancer", "indicator"])
@@ -31,7 +31,7 @@ def run(dest_dir: str) -> None:
     #
     # Create a new garden dataset with the same metadata as the meadow dataset.
     ds_garden = create_dataset(
-        dest_dir, tables=[tb], long_to_wide=True, check_variables_metadata=True, default_metadata=ds_meadow.metadata
+        dest_dir, tables=[tb], check_variables_metadata=True, default_metadata=ds_meadow.metadata
     )
 
     # Save changes in the new garden dataset.

diff --git a/etl/steps/data/grapher/cancer/2024-08-30/gco_alcohol.py b/etl/steps/data/grapher/cancer/2024-08-30/gco_alcohol.py
@@ -23,9 +23,9 @@ def run(dest_dir: str) -> None:
     #
     # Save outputs.
     #
-    # Create a new grapher dataset with the same metadata as the garden dataset.
+    # 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
+        dest_dir, tables=[tb], long_to_wide=True, check_variables_metadata=True, default_metadata=ds_garden.metadata
     )
 
     # Save changes in the new grapher dataset.