Code Editor for app.py

import streamlit as st
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np

@st.cache_data
def load_data(url):
    try:
        return pd.read_csv(url)
    except Exception as e:
        st.error(f"Error loading data: {str(e)}")
        return None

# URL input with default value
url = st.text_input(
    "Enter CSV URL",
    value="https://raw.githubusercontent.com/mwaskom/seaborn-data/master/penguins.csv"
)

# Load the data
df = load_data(url)

if df is not None:
    # Shuffle control
    shuffle = st.checkbox("Randomly shuffle data")
    if shuffle:
        df = df.sample(frac=1, random_state=42).reset_index(drop=True)
    
    # Number of rows to display
    n_rows = st.slider("Number of rows to display", 1, len(df), min(10, len(df)))
    
    # Display the dataframe
    st.write("### Data Preview")
    st.dataframe(df.head(n_rows))
    
    # Variable selection
    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
    
    col1, col2 = st.columns(2)
    
    with col1:
        var1 = st.selectbox("Select first variable", all_cols)
    
    with col2:
        remaining_cols = [col for col in all_cols if col != var1]
        var2 = st.selectbox("Select second variable (optional)", ["None"] + remaining_cols)
    
    st.write("### Visualization")
    
    if var2 == "None":
        # Single variable visualization
        if var1 in numeric_cols:
            fig, ax = plt.subplots()
            sns.histplot(data=df, x=var1, ax=ax)
            st.pyplot(fig)
        else:
            fig, ax = plt.subplots()
            sns.countplot(data=df, x=var1, ax=ax)
            plt.xticks(rotation=45)
            st.pyplot(fig)
    else:
        # Two variable visualization
        fig, ax = plt.subplots()
        
        # Both numeric
        if var1 in numeric_cols and var2 in numeric_cols:
            sns.scatterplot(data=df, x=var1, y=var2, ax=ax)
        
        # Both categorical
        elif var1 in categorical_cols and var2 in categorical_cols:
            cross_tab = pd.crosstab(df[var1], df[var2])
            sns.heatmap(cross_tab, annot=True, cmap="YlGnBu", ax=ax)
            plt.xticks(rotation=45)
            plt.yticks(rotation=0)
        
        # One numeric, one categorical
        else:
            num_var = var1 if var1 in numeric_cols else var2
            cat_var = var2 if var1 in numeric_cols else var1
            sns.boxplot(data=df, x=cat_var, y=num_var, ax=ax)
            plt.xticks(rotation=45)
        
        st.pyplot(fig)