# load dataset
import pandas as pd 
df = pd.read_csv('sentiment_data.csv')
texts = df['text'].astype(str)
# Load NER model
import spacy
model = spacy.load('en_core_web_lg')
# Extract entities
result = []
for i in texts:
    doc = model(i)
    entities = [(ent.text,ent.label_) for ent in doc.ents]
    result.append({'Text':i,'Entity':entities})
result_df = pd.DataFrame(result)
# Entity visualization
from spacy import displacy
for t in texts[:5]:
    doc = model(t)
    displacy.render(doc,style='ent')
from collections import Counter
all_entites = [ent for ents in result_df['Entity'] for ent in ents]
print(all_entites)
labels = [label for text, label in all_entites]
Counter(labels).most_common(1)
def ext_ent(sentence):
    doc = model(sentence)
    output = ''
    for i in doc.ents:
        output += f'{i.text} - {i.label_}\n'
    return output
import gradio as gr

demo = gr.Interface(fn=ext_ent,inputs='text',outputs='text',title='Extract Entities')
demo.launch()