Code Editor for app.py

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

# Function to load data from the URL
@st.cache_data
def load_data(url):
    return pd.read_csv(url)

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

# Load and display the data
if url:
    df = load_data(url)
    st.write("Data from the provided URL:")
    st.dataframe(df)

    # Control for number of rows displayed
    num_rows = st.number_input('Number of rows to display:', min_value=1, max_value=len(df), value=10)
    st.dataframe(df.head(num_rows))

    # Checkbox to shuffle the DataFrame
    shuffle = st.checkbox('Shuffle DataFrame')
    if shuffle:
        df = df.sample(frac=1).reset_index(drop=True)
        st.write('DataFrame has been shuffled.')
        st.dataframe(df.head(num_rows))

    # Variable selection for plotting
    st.write('Select variables for plotting:')
    variables = df.columns.tolist()
    var1 = st.selectbox('Select the first variable:', variables)
    var2 = st.selectbox('Select the second variable (optional):', [None] + variables)

    # Create plots based on selections
    if var2 is None:
        # Univariate plot
        fig, ax = plt.subplots()
        sns.histplot(df[var1], ax=ax, kde=True)
        ax.set_title(f'Histogram of {var1}')
        st.pyplot(fig)
    else:
        # Bivariate plot
        fig, ax = plt.subplots()
        sns.scatterplot(data=df, x=var1, y=var2, ax=ax)
        ax.set_title(f'Scatter plot of {var1} vs {var2}')
        st.pyplot(fig)