Code Editor for app.py

import streamlit as st
import pandas as pd
import seaborn as sns

@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. Some websites don't work with the proxy,
    # in those cases try removing the proxy prefix.
    proxy_url = f"https://corsproxy.io/?{url}"
    return pd.read_csv(proxy_url)

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

try:
    # Load data
    df = load_data(url)
    
    # Controls
    col1, col2 = st.columns(2)
    
    with col1:
        n_rows = st.number_input("Number of rows to display", 
                               min_value=1, 
                               max_value=len(df), 
                               value=min(10, len(df)))
    
    with col2:
        shuffle = st.checkbox("Randomly shuffle data")
    
    if shuffle:
        df = df.sample(frac=1).reset_index(drop=True)
    
    # Display dataframe
    st.write("### Data Preview")
    st.dataframe(df.head(n_rows))
    
    # Variable selection
    st.write("### Visualization")
    st.write("Select variables to visualize:")
    
    # Get numeric and categorical columns
    numeric_cols = df.select_dtypes(include=['float64', 'int64']).columns
    all_cols = df.columns
    
    col1, col2 = st.columns(2)
    
    with col1:
        var1 = st.selectbox("Variable 1", all_cols)
    
    with col2:
        var2 = st.selectbox("Variable 2", all_cols, index=1 if len(all_cols) > 1 else 0)
    
    # Determine the best visualization based on variable types
    var1_numeric = df[var1].dtype in ['float64', 'int64']
    var2_numeric = df[var2].dtype in ['float64', 'int64']
    
    fig = sns.jointplot(data=df, x=var1, y=var2)
    st.pyplot(fig)
    
    if var1_numeric and var2_numeric:
        st.write(f"Correlation between {var1} and {var2}: {df[var1].corr(df[var2]):.2f}")

except Exception as e:
    st.error(f"Error: {str(e)}")
    st.write("Please check if the URL is valid and points to a CSV file.")