import streamlit as st
import spacy
from spacy import displacy
from collections import Counter

# Load the English language model
nlp = spacy.load("en_core_web_sm")

def process_text(text):
    # Process the text using the spaCy pipeline
    doc = nlp(text)

    # Extract the named entities
    entities = [(ent.text, ent.label_) for ent in doc.ents]

    # Count the occurrences of each entity type
    entity_counts = Counter([ent[1] for ent in entities])

    # Visualize the named entities using displacy
    ent_html = displacy.render(doc, style="ent")

    return ent_html, dict(entity_counts)

def main():
    st.set_page_config(page_title="Named Entity Extraction")
    st.title("Named Entity Extraction")
    st.write("This app uses spaCy to extract named entities from the given text and visualize them.")

    text = st.text_area("Text to Process", height=200, placeholder="Enter the text you want to analyze")

    if st.button("Process Text"):
        ent_html, entity_counts = process_text(text)
        st.markdown(ent_html, unsafe_allow_html=True)
        st.subheader("Entity Type Counts")
        st.dataframe(entity_counts, use_container_width=True)

if __name__ == "__main__":
    main()