app.py

import pybase64 as base64
import pandas as pd
import streamlit as st
import seaborn as sns
from data_cleaning import preprocess
from transformers import pipeline
from data_integration import scrape_all_pages

#@st.cache_data
#def get_img_as_base64(file):
#    with open(file, "rb") as f:
#        data = f.read()
#    return base64.b64encode(data).decode()


#img = get_img_as_base64("image.jpg")background-image: url("data:image/png;base64,{img}");


page_bg_img = f"""
<style>
[data-testid="stAppViewContainer"] > .main {{
background-image: url("https://i.pinimg.com/originals/6f/6c/15/6f6c1538b050072b002dbc06bedaaf90.jpg");
background-size: cover;
background-position: center;
background-repeat: no-repeat;
}}

[data-testid="stSidebar"] > div:first-child {{
background-position: center; 
background-repeat: no-repeat;
background-attachment: fixed;
}}

[data-testid="stHeader"] {{
background: rgba(0,0,0,0);
}}

[data-testid="stToolbar"] {{
right: 2rem;
}}
</style>
"""
st.markdown(page_bg_img, unsafe_allow_html=True)
# st.image("logo.png", width=200, height=200)
st.image("logo.png", width=80)
st.subheader(':violet[NLP HUB®]')
st.markdown("")
st.markdown("")
st.markdown("")
st.markdown("")

st.subheader('Amazon Sentiment Analysis using FineTuned :red[GPT-2] Pre-Trained Model')

sentiment_model = pipeline(model="ashok2216/gpt2-amazon-sentiment-classifier")
# Example usage:-
sample_url = 'https://www.amazon.in/Dell-Inspiron-i7-1255U-Processor-Platinum/product-reviews/B0C9F142V6/ref=cm_cr_dp_d_show_all_btm?ie=UTF8&reviewerType=all_reviews'
url = st.text_input("Amazon product link", sample_url)
st.button("Re-run")
st.write("Done")
st.subheader('', divider='rainbow')

try:
    all_reviews = scrape_all_pages(url)
    # Convert to DataFrame for further analysis
    reviews = pd.DataFrame(all_reviews)
    reviews['processed_text'] = reviews['content'].apply(preprocess)
    
    # st.dataframe(reviews, use_container_width=True)
    # st.markdown(sentiment_model(['It is Super!']))
    
    sentiments = []
    for text in reviews['processed_text']:
        if list(sentiment_model(text)[0].values())[0] == 'LABEL_1':
            output = 'Positive'
        else:
            output = 'Negative'
        sentiments.append(output)
    
    reviews['sentiments'] = sentiments
    st.markdown(':white[Output]')
    st.dataframe(reviews, use_container_width=True)
    # sns.countplot(reviews['sentiments'])
except KeyError:
    st.markdown('Please :red[Re-run] the app')