pandas fixes

sid-kap · Sep 24, 2023 · 2e7288f · 2e7288f
1 parent 70d4685
commit 2e7288f
Show file tree

Hide file tree

Showing 5 changed files with 8 additions and 8 deletions.
diff --git a/python/housing_data/california_hcd_data.py b/python/housing_data/california_hcd_data.py
@@ -36,7 +36,7 @@ def load_california_hcd_data(
     # BPS doesn't include mobile homes, so we shouldn't include them here either
     df = df[df["UNIT_CAT_DESC"] != "Mobile Home Unit"].copy()
 
-    df["units"] = df[BUILDING_PERMIT_COLUMNS].sum(axis="columns")
+    df["units"] = df[BUILDING_PERMIT_COLUMNS].sum(axis="columns", numeric_only=True)
     df = df[
         (df["units"] > 0)
         # Exclude rows with a certificate of occupancy, because it's very unlikely

diff --git a/python/housing_data/canada_bper.py b/python/housing_data/canada_bper.py
@@ -200,7 +200,7 @@ def aggregate_to_metros(df: pd.DataFrame) -> pd.DataFrame:
     df = (
         df.drop(columns=["place_name", "province_abbr", "province"])
         .groupby(["metro", "year", "metro_province_abbr"], as_index=False)
-        .sum()
+        .sum(numeric_only=True)
     )
     add_per_capita_columns(df, [DataSource.CANADA])
 
@@ -226,7 +226,7 @@ def aggregate_to_states(df: pd.DataFrame) -> pd.DataFrame:
     df = (
         df.drop(columns=["path_1", "path_2"])
         .groupby(["province", "year"], as_index=False)
-        .sum()
+        .sum(numeric_only=True)
     )
     add_per_capita_columns(df, [DataSource.CANADA])
 

diff --git a/python/housing_data/county_population.py b/python/housing_data/county_population.py
@@ -203,7 +203,7 @@ def get_county_populations_1980s(data_path: Optional[Path]) -> pd.DataFrame:
         df = (
             df.dropna(subset=["year"])
             .groupby(["year", "combined_fips"])
-            .sum()
+            .sum(numeric_only=True)
             .sum(axis=1)
             .rename("population")
             .reset_index()

diff --git a/python/housing_data/place_population.py b/python/housing_data/place_population.py
@@ -313,7 +313,7 @@ def get_place_populations_1990s(data_path: Optional[Path]) -> pd.DataFrame:
             ["place", "state_abbr", "state_fips", "place_fips", "place_or_county_code"],
             dropna=False,
         )
-        .sum()
+        .sum(numeric_only=True)
         .reset_index()
     )
 

diff --git a/python/housing_data/state_population.py b/python/housing_data/state_population.py
@@ -167,7 +167,7 @@ def get_state_populations_1990s(data_path: Optional[Path]) -> pd.DataFrame:
             ]
         )
         .groupby(["year", "state"])
-        .sum()
+        .sum(numeric_only=True)
         .reset_index()
     )
 
@@ -263,13 +263,13 @@ def get_state_population_estimates(data_path: Optional[Path]) -> pd.DataFrame:
     divisions_df = (
         states_df.assign(state=states_df["state"].map(STATE_TO_DIVISION))
         .groupby(["state", "year"])
-        .sum()
+        .sum(numeric_only=True)
         .reset_index()
     )
     regions_df = (
         states_df.assign(state=states_df["state"].map(STATE_TO_REGION))
         .groupby(["state", "year"])
-        .sum()
+        .sum(numeric_only=True)
         .reset_index()
     )