app.py

# MetaDiscovery Agent - Phase 1: LOC API Integration and Metadata Gap Analysis

import requests
import pandas as pd
import streamlit as st
import plotly.express as px

# Streamlit app header
st.title("MetaDiscovery Agent for Library of Congress Collections")
st.markdown("""
This tool connects to the LOC API, retrieves metadata from a selected collection, and performs
an initial analysis of metadata completeness.
""")

# User selects a collection (predefined for prototype)
collection_url = "https://www.loc.gov/collections/american-revolutionary-war-maps/?fo=json"
st.sidebar.markdown("## Settings")
st.sidebar.write("Collection: American Revolutionary War Maps")

# Fetch data from LOC API
response = requests.get(collection_url)
data = response.json()

# Parse metadata records
records = data.get("results", [])

# Extract selected metadata fields
items = []
for record in records:
    items.append({
        "title": record.get("title"),
        "date": record.get("date"),
        "subject": record.get("subject"),
        "creator": record.get("creator"),
        "description": record.get("description")
    })

# Create DataFrame
metadata_df = pd.DataFrame(items)
st.subheader("📦 Retrieved Metadata Sample")
st.dataframe(metadata_df.head())

# Metadata completeness analysis
st.subheader("🧠 Metadata Completeness Analysis")
completeness = metadata_df.notnull().mean() * 100
completeness_df = pd.DataFrame({"Field": completeness.index, "Completeness (%)": completeness.values})

# Plot completeness
fig = px.bar(completeness_df, x="Field", y="Completeness (%)", title="Metadata Completeness by Field")
st.plotly_chart(fig)

# List records with missing values
st.subheader("⚠️ Records with Incomplete Metadata")
incomplete_records = metadata_df[metadata_df.isnull().any(axis=1)]
st.dataframe(incomplete_records)