Code Editor for app.py

import streamlit as st
import pandas as pd
import plotly.express as px
import seaborn as sns


@st.cache_data
def load_data(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")
    
    if shuffle:
        df = df.sample(frac=1, random_state=42).reset_index(drop=True)
    
    # Display dataframe
    st.subheader("Data Preview")
    st.dataframe(df.head(n_rows))
    
    # Variable selection
    st.subheader("Visualization")
    
    # Get numeric and categorical columns
    numeric_cols = df.select_dtypes(include=['float64', 'int64']).columns
    categorical_cols = df.select_dtypes(include=['object', 'category']).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)
    
    # Visualization logic
    if var1 != 'None':
        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:
                # Scatter plot for two numeric variables
                fig = px.scatter(df, x=var1, y=var2, 
                               title=f'{var2} vs {var1}')
                st.plotly_chart(fig)
            elif var1 in numeric_cols and var2 in categorical_cols:
                # Box plot for numeric vs categorical
                fig = px.box(df, x=var2, y=var1,
                           title=f'{var1} distribution by {var2}')
                st.plotly_chart(fig)
            elif var1 in categorical_cols and var2 in numeric_cols:
                # Box plot for numeric vs categorical
                fig = px.box(df, x=var1, y=var2,
                           title=f'{var2} distribution by {var1}')
                st.plotly_chart(fig)
            else:
                # Heatmap for two categorical variables
                heatmap_data = pd.crosstab(df[var1], df[var2])
                fig = px.imshow(heatmap_data, 
                              title=f'Heatmap of {var1} vs {var2}')
                st.plotly_chart(fig)

except Exception as e:
    st.error(f"Error: {str(e)}")
    st.write("Please check if the URL is valid and points to a CSV file.")