Spaces:
Running
Running
File size: 2,195 Bytes
d707455 083533c d707455 083533c d707455 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 |
# 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.
""")
# Predefined LOC collections
collections = {
"American Revolutionary War Maps": "american-revolutionary-war-maps",
"Civil War Maps": "civil-war-maps",
"Women’s Suffrage": "womens-suffrage",
"World War I Posters": "world-war-i-posters"
}
# Sidebar for selecting collection
st.sidebar.markdown("## Settings")
selected = st.sidebar.selectbox("Select a collection", list(collections.keys()))
collection_path = collections[selected]
collection_url = f"https://www.loc.gov/collections/{collection_path}/?fo=json"
# Display selected collection
st.sidebar.write(f"Selected Collection: {selected}")
# 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)
|