estimate prop ourselves

etl/steps/data/garden/demography/2024-12-06/shared.py

@@ -136,3 +136,12 @@ def add_dim_some_education(tb):
 def get_index_columns(tb):
     cols_index = list(tb.columns.intersection(COLUMNS_INDEX))
     return cols_index
+
+
+def add_prop(tb):
+    # Add
+    tbx = tb[tb["education"] == "total"].drop(columns=["education", "assr"])
+    tb_sex_age_edu = tb.merge(tbx, on=["country", "year", "age", "sex", "scenario"], suffixes=["", "_total"])
+    tb_sex_age_edu["prop"] = 100 * tb_sex_age_edu["pop"] / tb_sex_age_edu["pop_total"]
+
+    return tb

etl/steps/data/garden/demography/2024-12-06/wittgenstein_human_capital.meta.yml

@@ -523,6 +523,8 @@ tables:
            with <%- if (education == "no_education") %>no education<%- elif (education == "some_education") %>some formal education<%- else %><<education>> education<%- endif %>
           <%- endif %>
            in a country or region.
+        description_processing: |-
+          We have estimated this indicator with the population values from this source.
         presentation:
           topic_tags:
             - Global Education

etl/steps/data/garden/demography/2024-12-06/wittgenstein_human_capital_historical.meta.yml

@@ -494,6 +494,8 @@ tables:
            with <%- if (education == "no_education") %>no education<%- if (education == "some_education") %>some formal education<%- else %><<education>> education<%- endif %>
           <%- endif %>
            in a country or region.
+        description_processing: |-
+          We have estimated this indicator with the population values from this source.
         presentation:
           topic_tags:
             - Global Education

etl/steps/data/garden/demography/2024-12-06/wittgenstein_human_capital_historical.py

@@ -2,7 +2,7 @@
 
 from etl.helpers import PathFinder, create_dataset
 
-from .shared import add_dim_some_education, make_table
+from .shared import add_dim_some_education, add_prop, make_table
 
 # Get paths and naming conventions for current step.
 paths = PathFinder(__file__)
@@ -96,7 +96,7 @@ def run(dest_dir: str) -> None:
             "age": "category",
             "education": "category",
         },
-        cols_single=["pop", "prop"],
+        cols_single=["pop"],
         cols_range=["assr"],
         per_1000=["pop"],
         per_100=["assr"],
@@ -105,6 +105,9 @@ def run(dest_dir: str) -> None:
     # Add education="some_education" (only for sex=total and age=total, and indicator 'pop')
     tb_sex_age_edu = add_dim_some_education(tb_sex_age_edu)
 
+    # Add population share
+    tb_sex_age_edu = add_prop(tb_sex_age_edu)
+
     #
     # Save outputs.
     #

etl/steps/data/garden/demography/2024-12-06/wittgenstein_human_capital_proj.meta.yml

@@ -558,6 +558,8 @@ tables:
            with <%- if (education == "no_education") %>no education<%- elif (education == "some_education") %>some formal education<%- else %><<education>> education<%- endif %>
           <%- endif %>
            in a country or region.
+        description_processing: |-
+          We have estimated this indicator with the population values from this source.
         presentation:
           topic_tags:
             - Global Education

etl/steps/data/garden/demography/2024-12-06/wittgenstein_human_capital_proj.py

@@ -2,7 +2,7 @@
 
 from etl.helpers import PathFinder, create_dataset
 
-from .shared import add_dim_some_education, make_table
+from .shared import add_dim_some_education, add_prop, make_table
 
 # Get paths and naming conventions for current step.
 paths = PathFinder(__file__)
@@ -96,7 +96,7 @@ def run(dest_dir: str) -> None:
             "age": "category",
             "education": "category",
         },
-        cols_single=["pop", "prop"],
+        cols_single=["pop"],
         cols_range=["assr"],
         per_1000=["pop"],
         per_100=["assr"],
@@ -105,6 +105,9 @@ def run(dest_dir: str) -> None:
     # Add education="some_education" (only for sex=total and age=total, and indicator 'pop')
     tb_sex_age_edu = add_dim_some_education(tb_sex_age_edu)
 
+    # Add population share
+    tb_sex_age_edu = add_prop(tb_sex_age_edu)
+
     #
     # Save outputs.
     #

etl/steps/data/meadow/demography/2024-12-06/wittgenstein_human_capital_historical.py

@@ -49,7 +49,7 @@
 ]
 
 TABLES_CONCAT = [
-    ("prop", "bprop"),
+    # ("prop", "bprop"),
     ("mys", "bmys"),
 ]
 TABLES_DROP = []
@@ -69,7 +69,7 @@
     # 2/ Age+Education dimensions. NOTE: no age=total, that's fine. We have tfr for all ages actually.
     "by_age_edu": {"asfr"},
     # 3/ Sex+Age+Education dimensions
-    "by_sex_age_edu": {"assr", "pop", "prop"},
+    "by_sex_age_edu": {"assr", "pop"},
 }
 
 

etl/steps/data/meadow/demography/2024-12-06/wittgenstein_human_capital_proj.py

@@ -52,7 +52,7 @@
 ]
 
 TABLES_CONCAT = [
-    ("prop", "bprop"),
+    # ("prop", "bprop"),
     ("mys", "bmys"),
 ]
 TABLES_DROP = [
@@ -81,7 +81,7 @@
     # 2/ Age+Education dimensions. NOTE: no age=total, that's fine. We have tfr for all ages actually.
     "by_age_edu": {"asfr"},
     # 3/ Sex+Age+Education dimensions
-    "by_sex_age_edu": {"assr", "pop", "prop"},
+    "by_sex_age_edu": {"assr", "pop"},
 }