Fix 2024 population estimates (impute with 2022/2023)

sid-kap · Apr 15, 2024 · 5833a8c · 5833a8c
1 parent c6b1e02
commit 5833a8c
Show file tree

Hide file tree

Showing 5 changed files with 34 additions and 50 deletions.
diff --git a/lib/common_elements.tsx b/lib/common_elements.tsx
@@ -135,7 +135,7 @@ const navItems = [
     name: "States",
   },
   {
-    url: "/metros/Bakersfield_CA",
+    url: "/metros/Abilene_TX",
     name: "Metros",
   },
   {

diff --git a/python/housing_data/build_data_utils.py b/python/housing_data/build_data_utils.py
@@ -290,13 +290,26 @@ def add_current_year_projections(year_to_date_df: pd.DataFrame) -> pd.DataFrame:
     return year_to_date_df
 
 
-def impute_2023_population(df_2020s: pd.DataFrame) -> pd.DataFrame:
+def impute_2023_and_2024_population(df_2020s: pd.DataFrame) -> pd.DataFrame:
     """
-    Impute 2023 with the 2022 population
+    Impute 2023 and 2024 with the 2022 population
     """
     return pd.concat(
         [
             df_2020s,
             df_2020s[df_2020s["year"] == "2022"].assign(year="2023"),
+            df_2020s[df_2020s["year"] == "2022"].assign(year="2024"),
+        ]
+    )
+
+
+def impute_2024_population(df_2020s: pd.DataFrame) -> pd.DataFrame:
+    """
+    Impute 2024 with the 2023 population
+    """
+    return pd.concat(
+        [
+            df_2020s,
+            df_2020s[df_2020s["year"] == "2023"].assign(year="2024"),
         ]
     )
diff --git a/python/housing_data/county_population.py b/python/housing_data/county_population.py
@@ -4,8 +4,8 @@
 
 import pandas as pd
 import us
-from housing_data.build_data_utils import impute_2023_population
-from housing_data.data_loading_helpers import get_path, get_url_text
+from housing_data.build_data_utils import impute_2024_population
+from housing_data.data_loading_helpers import get_url_text
 from housing_data.fips_crosswalk import load_fips_crosswalk
 
 
@@ -21,36 +21,21 @@ def _melt_df(df: pd.DataFrame, years: list[int]) -> pd.DataFrame:
 
 
 def get_county_populations_2020s(data_path: Optional[Path]) -> pd.DataFrame:
-    df = pd.read_csv(
-        get_path(
-            "https://www2.census.gov/programs-surveys/popest/datasets/2020-2022/counties/totals/co-est2022-alldata.csv",
-            data_path,
-        ),
-    )
+    df = pd.read_csv(data_path / "co-est2023-alldata.csv", encoding="latin_1")
 
-    df = _melt_df(df, list(range(2020, 2023)))
-    return impute_2023_population(df)
+    df = _melt_df(df, list(range(2020, 2024)))
+    return impute_2024_population(df)
 
 
 def get_county_populations_2010s(data_path: Optional[Path]) -> pd.DataFrame:
-    df = pd.read_csv(
-        get_path(
-            "https://www2.census.gov/programs-surveys/popest/datasets/2010-2020/counties/totals/co-est2020-alldata.csv",
-            data_path,
-        ),
-        encoding="latin_1",
-    )
+    df = pd.read_csv(data_path / "co-est2020-alldata.csv", encoding="latin_1")
 
     return _melt_df(df, list(range(2010, 2020)))
 
 
 def get_county_populations_2000s(data_path: Path, data_repo_path: Path) -> pd.DataFrame:
-    urls = [
-        (
-            state.fips,
-            f"https://www2.census.gov/programs-surveys/popest/tables/2000-2010/"
-            f"intercensal/county/co-est00int-01-{state.fips}.csv",
-        )
+    paths = [
+        (state.fips, f"co-est00int-01-{state.fips}.csv")
         for state in us.STATES_AND_TERRITORIES + [us.states.DC]
         if state.fips not in ["60", "66", "69", "72", "78"]  # exclude territories
     ]
@@ -73,9 +58,9 @@ def get_county_populations_2000s(data_path: Path, data_repo_path: Path) -> pd.Da
     ]
 
     dfs = []
-    for state_code, url in urls:
+    for state_code, path in paths:
         df = pd.read_csv(
-            get_path(url, data_path),
+            data_path / path,
             names=col_names,
             skiprows=4,
             skipfooter=8,
@@ -190,13 +175,7 @@ def get_county_populations_1990s(data_path: Optional[Path]) -> pd.DataFrame:
 def get_county_populations_1980s(data_path: Optional[Path]) -> pd.DataFrame:
     dfs = []
     for year in range(1980, 1990):
-        df = pd.read_excel(
-            get_path(
-                f"https://www2.census.gov/programs-surveys/popest/tables/1980-1990/counties/asrh/pe-02-{year}.xls",
-                data_path,
-            ),
-            skiprows=5,
-        )
+        df = pd.read_excel(data_path / f"pe-02-{year}.xls", skiprows=5)
         df = df.rename(
             columns={
                 "Year of Estimate": "year",

diff --git a/python/housing_data/place_population.py b/python/housing_data/place_population.py
@@ -4,7 +4,7 @@
 
 import numpy as np
 import pandas as pd
-from housing_data.build_data_utils import impute_2023_population
+from housing_data.build_data_utils import impute_2023_and_2024_population
 from housing_data.data_loading_helpers import get_path, get_url_text
 
 
@@ -432,7 +432,7 @@ def get_place_populations_2020s(data_path: Optional[Path]) -> pd.DataFrame:
         ),
     )
     df = _melt_df(df, years=list(range(2020, 2023)))
-    df = impute_2023_population(df)
+    df = impute_2023_and_2024_population(df)
     return df
 
 

diff --git a/python/housing_data/state_population.py b/python/housing_data/state_population.py
@@ -4,7 +4,7 @@
 
 import pandas as pd
 import us
-from housing_data.build_data_utils import impute_2023_population
+from housing_data.build_data_utils import impute_2024_population
 from housing_data.data_loading_helpers import get_path, get_url_text
 
 DIVISIONS = {
@@ -119,10 +119,7 @@ def _get_counties_population_table_1990s(
     assert 1990 <= year <= 1999
 
     df = pd.read_csv(
-        get_path(
-            f"https://www2.census.gov/programs-surveys/popest/tables/1990-2000/intercensal/st-co/stch-icen{year}.txt",
-            data_path,
-        ),
+        data_path / f"stch-icen{year}.txt",
         delim_whitespace=True,
         names=[
             "year",
@@ -223,15 +220,10 @@ def get_state_populations_2010s(data_path: Optional[Path]) -> pd.DataFrame:
 
 
 def get_state_populations_2020s(data_path: Optional[Path]) -> pd.DataFrame:
-    df = pd.read_csv(
-        get_path(
-            "https://www2.census.gov/programs-surveys/popest/datasets/2020-2022/state/totals/NST-EST2022-ALLDATA.csv",
-            data_path,
-        )
-    )
+    df = pd.read_csv(data_path / "NST-EST2023-ALLDATA.csv")
 
-    df = _melt_df(df, list(range(2020, 2023)))
-    return impute_2023_population(df)
+    df = _melt_df(df, list(range(2020, 2024)))
+    return impute_2024_population(df)
 
 
 def get_state_population_estimates(data_path: Optional[Path]) -> pd.DataFrame: