update US population to use all non-null locations

CDCgov · Feb 5, 2025 · d827559 · d827559
1 parent 6cb4cf9
commit d827559
Show file tree

Hide file tree

Showing 3 changed files with 4 additions and 8 deletions.
diff --git a/README.md b/README.md
@@ -135,7 +135,7 @@ print(loc_table)
     │ ---           ┆ ---        ┆ ---                         ┆ ---        │
     │ str           ┆ str        ┆ str                         ┆ i64        │
     ╞═══════════════╪════════════╪═════════════════════════════╪════════════╡
-    │ US            ┆ US         ┆ United States               ┆ 330759736  │
+    │ US            ┆ US         ┆ United States               ┆ 334735155  │
     │ 01            ┆ AL         ┆ Alabama                     ┆ 5024279    │
     │ 02            ┆ AK         ┆ Alaska                      ┆ 733391     │
     │ 04            ┆ AZ         ┆ Arizona                     ┆ 7151502    │

diff --git a/forecasttools/data.py b/forecasttools/data.py
@@ -7,6 +7,7 @@
 an example FluSight submission.
 """
 
+# %%
 import os
 import pathlib
 from urllib import error, request
@@ -114,13 +115,8 @@ def merge_pop_data_and_loc_data(
     )
     loc_df = pl.read_parquet(locations_path)  # should have "long_name"
     merged_df = loc_df.join(pop_df, on="long_name", how="left")
-    # US total is not included by default; get US total
-    # us_states = make_united_states_dataset(
-    #     file_save_path="united_states.parquet"
-    # )
-    # us_population = merged_df.filter(pl.col("long_name").is_in(us_states))[
-    #     "population"
-    # ].sum()
+    # US total is not included by default; get US total from
+    # non-null territories & states
     us_population = merged_df["population"].sum()
     merged_df = merged_df.with_columns(
         pl.when(pl.col("long_name") == "United States")

diff --git a/forecasttools/location_table.parquet b/forecasttools/location_table.parquet