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):
    # 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.
    if not url.startswith('https://corsproxy.io/?'):
        url = f'https://corsproxy.io/?{url}'
    return pd.read_csv(url)

# Main app
st.title('Data Visualization')

# 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.slider('Number of rows to display', 1, len(df), 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.subheader('Data Preview')
    st.dataframe(df.head(n_rows))
    
    # Variable selection
    st.subheader('Visualization')
    numeric_cols = df.select_dtypes(include=['float64', 'int64']).columns
    categorical_cols = df.select_dtypes(include=['object']).columns
    all_cols = pd.Index(['None']).append(df.columns)
    
    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)
    
    if var1 != 'None':
        if var2 == 'None':
            # Single variable visualization
            if var1 in numeric_cols:
                # Histogram for numeric variables
                chart = alt.Chart(df).mark_bar().encode(
                    alt.X(var1, bin=True),
                    y='count()'
                ).properties(
                    title=f'Distribution of {var1}'
                )
                st.altair_chart(chart, use_container_width=True)
            else:
                # Bar chart for categorical variables
                chart = alt.Chart(df).mark_bar().encode(
                    x='count()',
                    y=var1
                ).properties(
                    title=f'Distribution of {var1}'
                )
                st.altair_chart(chart, use_container_width=True)
        else:
            # Two variable visualization
            if var1 in numeric_cols and var2 in numeric_cols:
                # Scatter plot for two numeric variables
                chart = alt.Chart(df).mark_circle().encode(
                    x=var1,
                    y=var2,
                    tooltip=[var1, var2]
                ).properties(
                    title=f'{var1} vs {var2}'
                )
                st.altair_chart(chart, use_container_width=True)
            elif var1 in numeric_cols and var2 in categorical_cols:
                # Box plot for numeric vs categorical
                chart = alt.Chart(df).mark_boxplot().encode(
                    x=var2,
                    y=var1
                ).properties(
                    title=f'{var1} by {var2}'
                )
                st.altair_chart(chart, use_container_width=True)
            elif var1 in categorical_cols and var2 in numeric_cols:
                # Box plot for numeric vs categorical
                chart = alt.Chart(df).mark_boxplot().encode(
                    x=var1,
                    y=var2
                ).properties(
                    title=f'{var2} by {var1}'
                )
                st.altair_chart(chart, use_container_width=True)
            else:
                # Heatmap for two categorical variables
                chart = alt.Chart(df).mark_rect().encode(
                    x=var1,
                    y=var2,
                    color='count()'
                ).properties(
                    title=f'{var1} vs {var2}'
                )
                st.altair_chart(chart, use_container_width=True)
    
except Exception as e:
    st.error(f"Error: {str(e)}")