Code Editor for app.py

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

# Cache the data loading
@st.cache_data
def load_data(url):
    # NOTE: Using corsproxy.io because we're in a WASM environment. If running locally,
    # you can remove the corsproxy.io prefix.
    if not url.startswith('https://corsproxy.io/?'):
        url = f'https://corsproxy.io/?{url}'
    return pd.read_csv(url)

# App title
st.title('CSV Data Visualizer')

# URL input
url = st.text_input(
    'Enter CSV URL',
    value='https://raw.githubusercontent.com/mwaskom/seaborn-data/master/penguins.csv'
)

try:
    # Load the data
    df = load_data(url)
    
    # Shuffle control
    if st.checkbox('Randomly shuffle data'):
        df = df.sample(frac=1, random_state=42).reset_index(drop=True)
    
    # Number of rows to display
    n_rows = st.slider('Number of rows to display', 1, len(df), min(10, len(df)))
    
    # Display the dataframe
    st.subheader('Data Preview')
    st.dataframe(df.head(n_rows))
    
    # Variable selection
    st.subheader('Variable Selection')
    cols = df.select_dtypes(include=['float64', 'int64']).columns
    var1 = st.selectbox('Select first variable', cols)
    var2 = st.selectbox('Select second variable (optional)', ['None'] + list(cols))
    
    # Visualization
    st.subheader('Visualization')
    
    if var2 == 'None':
        # Single variable visualization
        fig, ax = plt.subplots()
        sns.histplot(data=df, x=var1, kde=True)
        plt.title(f'Distribution of {var1}')
        st.pyplot(fig)
    else:
        # Two variables visualization
        fig, ax = plt.subplots()
        sns.scatterplot(data=df, x=var1, y=var2)
        plt.title(f'{var1} vs {var2}')
        st.pyplot(fig)
        
        # Show correlation
        correlation = df[var1].corr(df[var2])
        st.write(f'Correlation between {var1} and {var2}: {correlation:.2f}')

except Exception as e:
    st.error(f'Error: {str(e)}')