Code Editor for app.py

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

@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)

# App 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(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
    st.subheader('Visualization')
    cols = df.select_dtypes(include=[np.number, 'object']).columns
    
    col1, col2 = st.columns(2)
    with col1:
        var1 = st.selectbox('Select first variable', cols)
    with col2:
        remaining_cols = [col for col in cols if col != var1]
        var2 = st.selectbox('Select second variable (optional)', 
                           ['None'] + list(remaining_cols))

    if var2 == 'None':
        # Single variable visualization
        if df[var1].dtype in ['int64', 'float64']:
            # Numeric variable -> histogram
            fig = px.histogram(df, x=var1, title=f'Distribution of {var1}')
            st.plotly_chart(fig)
            
            # Display summary statistics
            st.write(f"Summary statistics for {var1}:")
            stats_df = pd.DataFrame({
                'Metric': ['Mean', 'Median', 'Std Dev', 'Min', 'Max'],
                'Value': [
                    df[var1].mean(),
                    df[var1].median(),
                    df[var1].std(),
                    df[var1].min(),
                    df[var1].max()
                ]
            })
            st.table(stats_df)
        else:
            # Categorical variable -> bar chart
            value_counts = df[var1].value_counts()
            fig = px.bar(x=value_counts.index, 
                        y=value_counts.values,
                        title=f'Distribution of {var1}')
            st.plotly_chart(fig)
    else:
        # Two variable visualization
        if df[var1].dtype in ['int64', 'float64'] and df[var2].dtype in ['int64', 'float64']:
            # Both numeric -> scatter plot
            fig = px.scatter(df, x=var1, y=var2, 
                           title=f'Scatter plot: {var1} vs {var2}')
            st.plotly_chart(fig)
            
            # Calculate correlation
            correlation = stats.pearsonr(df[var1], df[var2])[0]
            st.write(f"Correlation coefficient: {correlation:.3f}")
            
        elif df[var1].dtype in ['int64', 'float64'] or df[var2].dtype in ['int64', 'float64']:
            # One numeric, one categorical -> box plot
            numeric_var = var1 if df[var1].dtype in ['int64', 'float64'] else var2
            categorical_var = var2 if df[var1].dtype in ['int64', 'float64'] else var1
            
            fig = px.box(df, x=categorical_var, y=numeric_var,
                        title=f'Box plot: {numeric_var} by {categorical_var}')
            st.plotly_chart(fig)
        else:
            # Both categorical -> heatmap
            contingency = pd.crosstab(df[var1], df[var2])
            fig = px.imshow(contingency,
                           title=f'Heatmap: {var1} vs {var2}')
            st.plotly_chart(fig)

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