Code Editor for app.py

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

st.title('Penguin Data Explorer')

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

@st.cache_data
def load_data(url):
    return pd.read_csv(url)

# Load the data
try:
    data = load_data(url)
    st.write(data)
except Exception as e:
    st.error(f'Error loading data: {e}')
    data = pd.DataFrame()  # Fallback to empty DataFrame

# Control for number of rows displayed
num_rows = st.slider('Select the number of rows to display:', 1, data.shape[0], 5)
st.dataframe(data.head(num_rows))

# Checkbox for shuffling data
shuffle = st.checkbox('Shuffle DataFrame')
if shuffle:
    data = data.sample(frac=1).reset_index(drop=True)
    st.write(data.head(num_rows))

# Plotting
if not data.empty:
    st.subheader('Plotting Options')
    variables = data.select_dtypes(include=['float64', 'int64']).columns.tolist()
    x_var = st.selectbox('Select X variable:', variables)
    y_var = st.selectbox('Select Y variable (optional):', ['None'] + variables)

    if y_var == 'None':
        # If only one variable is selected, use a distribution plot
        st.write('Displaying distribution of', x_var)
        sns.histplot(data[x_var], kde=True)
    else:
        # Scatter plot for two variables
        st.write('Displaying scatter plot for', x_var, 'and', y_var)
        sns.scatterplot(data=data, x=x_var, y=y_var)

    plt.title(f'{x_var} vs {y_var}' if y_var != 'None' else f'Distribution of {x_var}')
    st.pyplot()