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):
    return pd.read_csv(url)

# 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")
    
    # Shuffle if requested
    if shuffle:
        df = df.sample(frac=1, random_state=42).reset_index(drop=True)
    
    # Display dataframe
    st.dataframe(df.head(n_rows))
    
    # Variable selection
    st.subheader("Visualization")
    columns = df.columns.tolist()
    col1, col2 = st.columns(2)
    
    with col1:
        var1 = st.selectbox("Select first variable", columns)
    
    with col2:
        var2 = st.selectbox("Select second variable", 
                           [None] + [col for col in columns if col != var1])
    
    # Visualization logic
    if var2 is None:
        # Single variable visualization
        if pd.api.types.is_numeric_dtype(df[var1]):
            # Numeric: show histogram
            fig = px.histogram(df, x=var1, title=f"Distribution of {var1}")
        else:
            # Categorical: show bar chart
            counts = df[var1].value_counts().reset_index()
            fig = px.bar(counts, x='index', y=var1, title=f"Counts of {var1}")
    else:
        # Two variable visualization
        if (pd.api.types.is_numeric_dtype(df[var1]) and 
            pd.api.types.is_numeric_dtype(df[var2])):
            # Both numeric: scatter plot
            fig = px.scatter(df, x=var1, y=var2, 
                           title=f"{var2} vs {var1}")
        elif (pd.api.types.is_numeric_dtype(df[var1]) or 
              pd.api.types.is_numeric_dtype(df[var2])):
            # One numeric, one categorical: box plot
            # Make sure categorical is x and numeric is y
            if pd.api.types.is_numeric_dtype(df[var1]):
                fig = px.box(df, x=var2, y=var1, 
                           title=f"{var1} by {var2}")
            else:
                fig = px.box(df, x=var1, y=var2, 
                           title=f"{var2} by {var1}")
        else:
            # Both categorical: 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)}")