Update app.py

app.py

@@ -64,6 +64,7 @@ ssa_names_df, ssa_names_aggregated_df = load_ssa_names()
 bible_names_df = pd.read_csv("BibleData-Person.csv")
 bible_names_personlabel_df = pd.read_csv("BibleData-PersonLabel.csv")
 bible_names_personlabel_df = bible_names_personlabel_df.merge(bible_names_df[["person_id", "sex"]], on="person_id", how="left")
+bible_names_personlabel_df["sex"] = bible_names_personlabel_df["sex"].replace({"male": "M", "female": "F"})
 
 # --- Name generation logic ---
 import random
@@ -80,14 +81,17 @@ def get_normal_and_bible(
     ssa_popularity_percentile=(0.95, 1.0),
     sex=None,
     forbidden_names=None,
+    ssa_names_col="name",
+    bible_names_col="english_label"
     debug=False,
+    
 ):
     if forbidden_names is None:
         forbidden_names = set()
 
     filtered_ssa = ssa_names_aggregated_df.copy()
     filtered_ssa = filtered_ssa[
-        filtered_ssa["name"].str.len().between(min_length_ssa, max_length_ssa)
+        filtered_ssa[ssa_names_col].str.len().between(min_length_ssa, max_length_ssa)
     ]
     if sex:
         filtered_ssa = filtered_ssa[filtered_ssa["sex"] == sex]
@@ -103,22 +107,22 @@ def get_normal_and_bible(
     if debug:
         print(f"SSA names after popularity percentile slice: {len(filtered_ssa)}")
 
-    ssa_name = filtered_ssa.sample(1)["name"].values[0]
+    ssa_name = filtered_ssa.sample(1)[ssa_names_col].values[0]
 
     filtered_bible = bible_names_df.copy()
     filtered_bible = filtered_bible[
-        filtered_bible["name"].str.len().between(min_length_bible, max_length_bible)
+        filtered_bible[bible_names_col].str.len().between(min_length_bible, max_length_bible)
     ]
     if sex:
         filtered_bible = filtered_bible[filtered_bible["sex"] == sex]
-    filtered_bible = filtered_bible[~filtered_bible["name"].isin(forbidden_names)]
+    filtered_bible = filtered_bible[~filtered_bible[bible_names_col].isin(forbidden_names)]
     if debug:
         print(f"Bible names after filtering: {len(filtered_bible)}")
 
     if len(filtered_bible) == 0 or len(filtered_ssa) == 0:
         raise ValueError("No valid names found after filtering.")
 
-    bible_name = filtered_bible.sample(1)["name"].values[0]
+    bible_name = filtered_bible.sample(1)[bible_names_col].values[0]
 
     return ssa_name, bible_name