Code Editor for app.py

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

# Caching the CSV data
@st.cache_data
def load_data(url):
    return pd.read_csv(url)

# App title
st.title('Penguins Data Viewer')

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

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

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

# Checkbox to shuffle the DataFrame
shuffle = st.checkbox('Shuffle the DataFrame')
if shuffle:
    data = data.sample(frac=1).reset_index(drop=True)

# Display selected number of rows
st.write(data.head(num_rows))

# Variables selection for plotting
st.subheader('Plotting Variables')
variables = data.columns.tolist()
selected_vars = st.multiselect('Select one or two variables for plotting:', variables)

# Plotting logic
if len(selected_vars) > 0:
    if len(selected_vars) == 1:
        # Plotting single variable histogram
        plt.figure(figsize=(8,6))
        plt.hist(data[selected_vars[0]].dropna(), 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:
        # Plotting scatter plot for two variables
        plt.figure(figsize=(8,6))
        plt.scatter(data[selected_vars[0]], data[selected_vars[1]], alpha=0.6)
        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)