Create app.py

app.py

@@ -0,0 +1,78 @@
+import gradio as gr
+import pandas as pd
+import requests
+from pathlib import Path
+from zipfile import ZipFile
+
+# ------------------
+# Download Resources
+# ------------------
+def download_file(url: str, output_path: Path):
+    if output_path.exists():
+        print(f"Skipping {output_path.name}, already exists.")
+        return
+    print(f"Downloading {url}")
+    response = requests.get(url)
+    response.raise_for_status()
+    output_path.write_bytes(response.content)
+    print(f"Saved to {output_path}")
+
+# Download files
+download_file("https://raw.githubusercontent.com/BradyStephenson/bible-data/refs/heads/main/BibleData-Person.csv", Path("BibleData-Person.csv"))
+download_file("https://www.ssa.gov/oact/babynames/names.zip", Path("names.zip"))
+download_file("https://raw.githubusercontent.com/BradyStephenson/bible-data/refs/heads/main/BibleData-PersonLabel.csv", Path("BibleData-PersonLabel.csv"))
+
+# Unzip names.zip
+with ZipFile("names.zip", 'r') as zip_ref:
+    zip_ref.extractall(".")
+    print("Unzipped names.zip")
+
+# ------------------
+# Load Data
+# ------------------
+ssa_name_txt_files = list(Path(".").glob("yob*.txt"))
+
+def load_ssa_names():
+    ssa_dfs = []
+    for names_file in ssa_name_txt_files:
+        yob = int(names_file.name.split(".")[0].replace("yob", ""))
+        df = pd.read_csv(names_file, names=["name", "sex", "count"])
+        df["year"] = yob
+        ssa_dfs.append(df)
+    ssa_names_df = pd.concat(ssa_dfs)
+    ssa_names_aggregated_df = (
+        ssa_names_df
+        .groupby(["name", "sex"], as_index=False)["count"]
+        .sum()
+        .sort_values(by="count", ascending=False)
+    )
+    return ssa_names_df, ssa_names_aggregated_df
+
+def load_bible_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"
+    )
+    return bible_names_df
+
+# Load on startup
+ssa_names_df, ssa_names_aggregated_df = load_ssa_names()
+bible_names_df = load_bible_names()
+
+# ------------------
+# Gradio Interface
+# ------------------
+
+with gr.Blocks() as demo:
+    gr.Markdown("## Bible Names & SSA Names Datasets")
+
+    with gr.Tab("Bible Names"):
+        gr.Dataframe(bible_names_df.head(100), label="Bible Names (first 100 rows)")
+
+    with gr.Tab("SSA Names (Aggregated)"):
+        gr.Dataframe(ssa_names_aggregated_df.head(100), label="Top SSA Names (first 100 rows)")
+
+demo.launch()