pages/22_NLP_Transformer_Prompt_2.py

import torch
from transformers import BertTokenizer, BertForSequenceClassification
from transformers import pipeline
import matplotlib.pyplot as plt
import streamlit as st

# Load pre-trained model and tokenizer
model_name = "nlptown/bert-base-multilingual-uncased-sentiment"
model = BertForSequenceClassification.from_pretrained(model_name)
tokenizer = BertTokenizer.from_pretrained(model_name)

# Function to classify text
def classify_text(text):
    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
    outputs = model(**inputs)
    scores = torch.nn.functional.softmax(outputs.logits, dim=1)
    return scores

# Streamlit interface
st.title("NLP Transformer with PyTorch and Hugging Face")

prompt_text = "Crt n NLP trnsfrmr xmpl sng PyTrch wth Hggng Fc, dd Strmlnt ntrfc fr npts nd tpts, ncld mtlpl grph f ncssry. Cd shld b sy t ct nd pst"
st.write(f"**Prompt:** {prompt_text}")

st.header("Sentiment Analysis")

text = st.text_area("Enter text for sentiment analysis:")

if st.button("Classify"):
    scores = classify_text(text).detach().numpy()[0]
    labels = ["1 star", "2 stars", "3 stars", "4 stars", "5 stars"]
    
    st.write("Classification Scores:")
    for label, score in zip(labels, scores):
        st.write(f"{label}: {score:.4f}")

    fig, ax = plt.subplots()
    ax.bar(labels, scores, color='blue')
    ax.set_xlabel('Sentiment')
    ax.set_ylabel('Score')
    ax.set_title('Sentiment Analysis Scores')
    st.pyplot(fig)