Code Editor for app.py

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

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

st.title('Data Explorer')

# 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')
    
    # Process data based on controls
    if shuffle:
        display_df = df.sample(frac=1).reset_index(drop=True)
    else:
        display_df = df.copy()
    
    # Display dataframe
    st.subheader('Data Preview')
    st.dataframe(display_df.head(n_rows))
    
    # Variable selection for visualization
    st.subheader('Visualization')
    numeric_cols = df.select_dtypes(include=[np.number]).columns.tolist()
    categorical_cols = df.select_dtypes(exclude=[np.number]).columns.tolist()
    all_cols = numeric_cols + categorical_cols
    
    var1 = st.selectbox('Select first variable', all_cols)
    var2 = st.selectbox('Select second variable (optional)', ['None'] + all_cols)
    
    if var2 == 'None':
        # Single variable visualization
        if var1 in numeric_cols:
            fig = px.histogram(df, x=var1, title=f'Distribution of {var1}')
            st.plotly_chart(fig)
        else:
            fig = px.bar(df[var1].value_counts().reset_index(), 
                        x='index', 
                        y=var1,
                        title=f'Count of {var1}')
            st.plotly_chart(fig)
    else:
        # Two variable visualization
        if var1 in numeric_cols and var2 in numeric_cols:
            # Two numeric variables: scatter plot
            fig = px.scatter(df, x=var1, y=var2, 
                           title=f'Scatter plot of {var1} vs {var2}')
            st.plotly_chart(fig)
        
        elif var1 in numeric_cols and var2 in categorical_cols:
            # One numeric, one categorical: box plot
            fig = px.box(df, x=var2, y=var1, 
                        title=f'Distribution of {var1} by {var2}')
            st.plotly_chart(fig)
        
        elif var1 in categorical_cols and var2 in numeric_cols:
            # One categorical, one numeric: box plot
            fig = px.box(df, x=var1, y=var2, 
                        title=f'Distribution of {var2} by {var1}')
            st.plotly_chart(fig)
        
        else:
            # Two categorical variables: heatmap
            contingency = pd.crosstab(df[var1], df[var2])
            fig = px.imshow(contingency, 
                          title=f'Relationship between {var1} and {var2}')
            st.plotly_chart(fig)

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