app.py

import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import transformers

# Define sentiment analysis models
models = {
    "DistilBERT": transformers.pipeline("sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english"),
    "BERT": transformers.pipeline("sentiment-analysis", model="bert-base-uncased-finetuned-sst-2-english"),
    "RoBERTa": transformers.pipeline("sentiment-analysis", model="roberta-base-openai-detector"),
}

# Define function to analyze sentiment using selected model
def analyze_sentiment(text, model_name):
    model = models[model_name]
    result = model(text)[0]
    return result['label'], result['score']

# Define Streamlit app
def app():
    st.title("Sentiment Analysis App")

    # User input
    text = st.text_area("Enter text to analyze", max_chars=1024)

    # Sentiment analysis
    if st.button("Analyze"):
        st.write("Analyzing sentiment...")
        with st.spinner("Wait for it..."):
            results = []
            for model_name in models:
                label, score = analyze_sentiment(text, model_name)
                results.append((model_name, label, score))
        st.success("Sentiment analysis complete!")
        st.write("Results:")
        df = pd.DataFrame(results, columns=["Model", "Sentiment", "Score"])
        st.write(df)

        # Plot results
        sns.set_style("whitegrid")
        fig, ax = plt.subplots()
        sns.barplot(x="Model", y="Score", hue="Sentiment", data=df, ax=ax)
        ax.set_title("Sentiment Analysis Results")
        st.pyplot(fig)

# Run Streamlit app
if __name__ == "__main__":
    app()