eda.py

import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

def run_eda_app(data):
    st.subheader('Exploratory Data Analysis')
    
    # Display data
    st.write("Here's a glimpse of the dataset:")
    st.write(data.head())
    
    # Show data distribution
    if st.checkbox('Show data distribution'):
        st.write('Data distribution:')
        fig, ax = plt.subplots()
        data.hist(ax=ax, bins=30, figsize=(20,15))
        st.pyplot(fig)
    
    # Correlation heatmap
    if st.checkbox('Show correlation heatmap'):
        st.write('Correlation heatmap:')
        fig, ax = plt.subplots(figsize=(10,8))
        sns.heatmap(data.corr(), annot=True, cmap='coolwarm', ax=ax)
        st.pyplot(fig)

    # Monthly distribution of sessions
    if st.checkbox('Show monthly distribution of sessions'):
        st.write('Monthly distribution of sessions:')
        fig, ax = plt.subplots(figsize=(10,6))
        data['Month'].value_counts().plot(kind='bar', ax=ax)
        ax.set_title('Number of sessions per month')
        ax.set_ylabel('Count')
        st.pyplot(fig)