Code Editor for app.py

import streamlit as st
import pandas as pd
import plotly.express as px

# Cache the data loading
@st.cache_data
def load_data(url):
    try:
        return pd.read_csv(url)
    except Exception as e:
        st.error(f"Error loading data: {str(e)}")
        return None

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

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

# Load data
df = load_data(url)

if df is not None:
    # 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")
    
    # Shuffle if requested
    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")
    columns = df.select_dtypes(include=['number', 'float', 'int']).columns.tolist()
    
    col1, col2 = st.columns(2)
    
    with col1:
        var1 = st.selectbox("Select first variable", columns)
    
    with col2:
        remaining_cols = [col for col in columns if col != var1]
        var2 = st.selectbox("Select second variable (optional)", 
                           ["None"] + remaining_cols)
    
    # Visualization logic
    if var2 == "None":
        # Single variable visualization
        fig = px.histogram(df, x=var1, title=f"Distribution of {var1}")
        st.plotly_chart(fig)
    else:
        # Two variable visualization
        fig = px.scatter(df, x=var1, y=var2, 
                        title=f"Relationship between {var1} and {var2}")
        
        # Add trend line
        fig.add_traces(px.scatter(df, x=var1, y=var2, 
                                trendline="ols").data[1])
        
        st.plotly_chart(fig)
        
        # Show correlation
        correlation = df[var1].corr(df[var2])
        st.info(f"Correlation coefficient between {var1} and {var2}: {correlation:.3f}")