Code Editor for app.py

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

# Title of the app
st.title('Penguins Data Visualization')

# Entry field for URL with a default value
url = st.text_input('Enter the URL to the CSV file:',
                    'https://raw.githubusercontent.com/mwaskom/seaborn-data/master/penguins.csv')

# Load and cache the DataFrame
@st.cache_data
def load_data(url):
    return pd.read_csv(url)

# Read the data
try:
    df = load_data(url)
    st.write('Data successfully loaded!')
except Exception as e:
    st.write('Error loading data:', e)
    df = pd.DataFrame()

# Controls to display number of rows and shuffle the DataFrame
if not df.empty:
    num_rows = st.slider('Select number of rows to display:', 1, len(df), 10)
    shuffle = st.checkbox('Shuffle DataFrame?')

    if shuffle:
        df = df.sample(frac=1).reset_index(drop=True)

    st.dataframe(df.head(num_rows))

    # Visualization options
    st.subheader('Visualize Data')
    variables = df.columns.tolist()
    x_axis = st.selectbox('Select X-axis variable:', variables)
    y_axis = st.selectbox('Select Y-axis variable (leave blank for univariate):', variables + [None])

    if st.button('Plot'):  
        if y_axis:
            # Scatter plot for two variables
            sns.scatterplot(data=df, x=x_axis, y=y_axis)
            plt.title(f'Scatter Plot of {y_axis} vs {x_axis}')
        else:
            # Histogram for single variable
            sns.histplot(df[x_axis], bins=20)
            plt.title(f'Histogram of {x_axis}')
        st.pyplot()