Code Editor for app.py

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

# Cache the data loading function
@st.cache_data
def load_data(url):
    try:
        # 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.
        proxied_url = f"https://corsproxy.io/?{url}"
        df = pd.read_csv(proxied_url)
        return df, None
    except Exception as e:
        return None, str(e)

# App title
st.title("Data Visualization Explorer")

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

df, error = load_data(url)

if error:
    st.error(f"Error loading data: {error}")
else:
    # 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) if df is not None else 1,
                                value=min(5, len(df) if df is not None else 1))
    
    with col2:
        shuffle = st.checkbox("Randomly shuffle data")
    
    # Process DataFrame
    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 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
    
    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)
    
    # Create visualization based on selected variables
    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"Distribution of {var1} 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"Distribution of {var2} by {var1}")
            st.plotly_chart(fig)
        
        else:
            # Heatmap for two categorical variables
            contingency = pd.crosstab(df[var1], df[var2])
            fig = px.imshow(contingency,
                           title=f"Relationship between {var1} and {var2}")
            st.plotly_chart(fig)