Code Editor for app.py

import streamlit as st
import pandas as pd
import altair as alt

# Cache the data loading function
@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)

# App title
st.title("Data Visualization App")

# 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)
    
    # 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(5, len(df)))
    
    with col2:
        shuffle = st.checkbox("Randomly shuffle data")
    
    if shuffle:
        df = df.sample(frac=1, random_state=42).reset_index(drop=True)
    
    # Display dataframe
    st.subheader("Data Preview")
    st.dataframe(df.head(n_rows))
    
    # Variable selection
    st.subheader("Visualization")
    
    # Get numerical and categorical columns
    numeric_cols = df.select_dtypes(include=['float64', 'int64']).columns
    categorical_cols = df.select_dtypes(include=['object', 'category']).columns
    all_cols = pd.Index(list(numeric_cols) + list(categorical_cols))
    
    col1, col2 = st.columns(2)
    
    with col1:
        var1 = st.selectbox("Select first variable", all_cols)
    
    with col2:
        var2 = st.selectbox("Select second variable", all_cols)
    
    # Create visualization based on variable types
    if var1 in numeric_cols and var2 in numeric_cols:
        # Scatter plot for two numerical variables
        chart = alt.Chart(df).mark_circle().encode(
            x=var1,
            y=var2,
            tooltip=[var1, var2]
        ).interactive()
        
    elif var1 in numeric_cols and var2 in categorical_cols:
        # Box plot for numerical vs categorical
        chart = alt.Chart(df).mark_boxplot().encode(
            x=var2,
            y=var1
        )
        
    elif var1 in categorical_cols and var2 in numeric_cols:
        # Box plot for categorical vs numerical
        chart = alt.Chart(df).mark_boxplot().encode(
            x=var1,
            y=var2
        )
        
    else:
        # Bar chart for two categorical variables
        chart = alt.Chart(df).mark_bar().encode(
            x=var1,
            y='count()',
            color=var2
        )
    
    st.altair_chart(chart, use_container_width=True)

except Exception as e:
    st.error(f"Error loading or processing data: {str(e)}")