Code Editor for app.py

import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt
import random

st.title('Penguins Data Viewer')

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

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

# Load data
try:
    df = load_data(url)
    st.write(df)
except Exception as e:
    st.error(f'Error loading data: {e}')

# Control for number of rows to display
num_rows = st.slider('Select number of rows to display:', min_value=1, max_value=len(df), value=10)

# Show the selected number of rows
st.write(df.head(num_rows))

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

# Plotting variables
st.subheader('Plotting Variables')
variables = df.columns.tolist()
selected_vars = st.multiselect('Select one or two variables to plot:', variables)

if len(selected_vars) == 1:
    # If one variable, create a histogram
    plt.figure(figsize=(8, 4))
    plt.hist(df[selected_vars[0]], bins=20, color='skyblue', edgecolor='black')
    plt.title(f'Histogram of {selected_vars[0]}')
    plt.xlabel(selected_vars[0])
    plt.ylabel('Frequency')
    st.pyplot(plt)

elif len(selected_vars) == 2:
    # If two variables, create a scatter plot
    plt.figure(figsize=(8, 4))
    plt.scatter(df[selected_vars[0]], df[selected_vars[1]], color='orange')
    plt.title(f'Scatter Plot of {selected_vars[0]} vs {selected_vars[1]}')
    plt.xlabel(selected_vars[0])
    plt.ylabel(selected_vars[1])
    st.pyplot(plt)