Code Editor for app.py

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

# Cache data loading
@st.cache_data
def load_data(url):
    return pd.read_csv(url)

# 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 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 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("Select first variable", options=all_cols)
    
    with col2:
        var2 = st.selectbox("Select second variable (optional)", 
                           options=['None'] + list(all_cols))
    
    if var2 == 'None':
        # Single variable visualization
        if df[var1].dtype in ['float64', 'int64']:
            # Numeric - show histogram
            chart = alt.Chart(df).mark_bar().encode(
                x=alt.X(f'{var1}:Q', bin=True),
                y='count()'
            ).properties(
                title=f'Distribution of {var1}'
            )
        else:
            # Categorical - show bar chart
            chart = alt.Chart(df).mark_bar().encode(
                x=f'{var1}:N',
                y='count()'
            ).properties(
                title=f'Count of {var1}'
            )
    else:
        # Two variable visualization
        if (df[var1].dtype in ['float64', 'int64']) and (df[var2].dtype in ['float64', 'int64']):
            # Both numeric - scatter plot
            chart = alt.Chart(df).mark_circle().encode(
                x=f'{var1}:Q',
                y=f'{var2}:Q'
            ).properties(
                title=f'{var2} vs {var1}'
            )
        elif (df[var1].dtype in ['float64', 'int64']) or (df[var2].dtype in ['float64', 'int64']):
            # One numeric, one categorical - box plot
            # Put the numeric variable on the y-axis
            if df[var1].dtype in ['float64', 'int64']:
                num_var, cat_var = var1, var2
            else:
                num_var, cat_var = var2, var1
                
            chart = alt.Chart(df).mark_boxplot().encode(
                x=f'{cat_var}:N',
                y=f'{num_var}:Q'
            ).properties(
                title=f'Distribution of {num_var} by {cat_var}'
            )
        else:
            # Both categorical - heatmap
            chart = alt.Chart(df).mark_rect().encode(
                x=f'{var1}:N',
                y=f'{var2}:N',
                color='count()'
            ).properties(
                title=f'Heatmap of {var2} vs {var1}'
            )
    
    st.altair_chart(chart, use_container_width=True)

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