eda.py

import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt
from wordcloud import WordCloud

def display_eda(data):
    # Distribution of sentiments
    st.subheader("Distribution of Sentiments")
    sentiment_counts = data['sentiment'].value_counts()
    st.bar_chart(sentiment_counts)
    
    # Word cloud for each sentiment
    st.subheader("Word Clouds for Sentiments")
    sentiments = data['sentiment'].unique()
    for sentiment in sentiments:
        st.write(f"Word Cloud for {sentiment}")
        subset = data[data['sentiment'] == sentiment]
        text = " ".join(review for review in subset['processed_review'])
        wordcloud = WordCloud(max_words=100, background_color="white").generate(text)
        plt.figure()
        plt.imshow(wordcloud, interpolation="bilinear")
        plt.axis("off")
        st.pyplot()