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
@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("Data Visualization App")

# 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 the 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=[np.number]).columns
    all_cols = df.columns
    
    # Variable selection
    var1 = st.selectbox("Select first variable", all_cols)
    var2 = st.selectbox("Select second variable (optional)", 
                        ["None"] + list(all_cols),
                        index=0)

    if var2 == "None":
        # Single variable visualization
        if df[var1].dtype in [np.number]:
            # Numeric: show histogram
            fig = px.histogram(df, x=var1, title=f"Distribution of {var1}")
        else:
            # Categorical: show bar chart
            counts = df[var1].value_counts()
            fig = px.bar(x=counts.index, 
                        y=counts.values,
                        title=f"Count of {var1}")
    else:
        # Two variable visualization
        if df[var1].dtype in [np.number] and df[var2].dtype in [np.number]:
            # Both numeric: scatter plot
            fig = px.scatter(df, x=var1, y=var2,
                           title=f"{var2} vs {var1}")
        elif df[var1].dtype in [np.number]:
            # First numeric, second categorical: box plot
            fig = px.box(df, x=var2, y=var1,
                        title=f"Distribution of {var1} by {var2}")
        elif df[var2].dtype in [np.number]:
            # First categorical, second numeric: box plot
            fig = px.box(df, x=var1, y=var2,
                        title=f"Distribution of {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)}")