app.py

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

sentiment_model = pipeline(model="ashok2216/gpt2-amazon-sentiment-classifier")

# Example usage:-
sample_url = 'https://www.amazon.in/s?k=laptop&i=computers&crid=1895I80OXDD8Y&sprefix=lap%2Ccomputers%2C533&ref=nb_sb_ss_ts-doa-p_1_3pe=all_reviews'
url = st.text_input("Amazon product link", sample_url)
st.write("The current movie title is", url)

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.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)

df['sentiments'] = sentiments
sns.countplot(reviews['sentiments'])