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("data:image/jpeg;base64,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");
background-size: 100%;
background-position: top left;
background-repeat: no-repeat;
background-attachment: local;
}}

[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=100)
st.subheader(':blue[NLP HUB®]')
st.header('Amazon Sentiment Analysis using FineTuned :green[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.write("Done")
st.subheader('', divider='rainbow')
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(':rainbow[Output]')
st.dataframe(reviews, use_container_width=True)
# sns.countplot(reviews['sentiments'])