File size: 1,366 Bytes
d8b68f2 |
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 |
import streamlit as st
import spacy
from spacy import displacy
import json
# Initialize spaCy
nlp = spacy.load("en_core_web_md")
# Define sample data
data = {
"fruit": ["apple", "pear", "orange"],
"vegetable": ["broccoli", "spinach", "tomato"],
"meat": ['beef', 'pork', 'turkey', 'duck']
}
# Streamlit app
st.title('Named Entity Recognition with spaCy')
user_input = st.text_area("Enter text:", "")
if st.button("Process"):
if user_input:
# Process the text
doc = nlp(user_input)
# Visualization options
options = {
"colors": {"fruit": "darkorange", "vegetable": "limegreen", "meat": "salmon"},
"ents": ["fruit", "vegetable", "meat"],
}
# JSON serialization with only entity and type
result_dict = {'entities': []}
for ent in doc.ents:
ent_data = {
'entity': ent.text,
'type': ent.label_
}
result_dict['entities'].append(ent_data)
result_json = json.dumps(result_dict, indent=4)
# Display results
st.subheader("Named Entities")
html = displacy.render(doc, style="ent", page=True, minify=True)
st.write(html, unsafe_allow_html=True)
st.subheader("Entities in JSON format")
st.json(result_json)
|