Create a Streamlit application that has a text field to enter a URL (default value: https://raw.githubusercontent.com/mwaskom/seaborn-data/master/penguins.csv). The app should read the CSV file (and cache it) from the URL and display a DataFrame. Add controls to do the following: - Control how many rows are displayed - A checkbox to determine to randomly shuffle the DataFrame The app should also allow plotting the entire CSV. Users select one or two variables and you must determine the best way to visualize them.
To upload files, please first save the app
import streamlit as st
import pandas as pd
import plotly.express as px
# Function to load and cache the data
@st.cache_data
def load_data(url):
return pd.read_csv(url)
# Default URL
url = "https://raw.githubusercontent.com/mwaskom/seaborn-data/master/penguins.csv"
# Text input for the URL
url_input = st.text_input("Enter CSV URL:", value=url)
# Load data from the provided URL
try:
data = load_data(url_input)
except Exception as e:
st.error(f"Error loading data: {e}")
st.stop()
# Checkbox to shuffle the data
shuffle = st.checkbox("Shuffle Data")
if shuffle:
data = data.sample(frac=1).reset_index(drop=True)
# Control for number of rows to display
num_rows = st.slider("Select number of rows to display:", 1, len(data), 5)
# Display the DataFrame
st.subheader("DataFrame")
st.dataframe(data.head(num_rows))
# Plotting options
st.subheader("Visualize Data")
variables = data.select_dtypes(include=['float64', 'int64']).columns.tolist()
selected_vars = st.multiselect("Select one or two variables to plot:", variables)
if len(selected_vars) > 0:
if len(selected_vars) == 1:
fig = px.histogram(data, x=selected_vars[0])
st.plotly_chart(fig)
elif len(selected_vars) == 2:
fig = px.scatter(data, x=selected_vars[0], y=selected_vars[1])
st.plotly_chart(fig)
else:
st.info("Please select one or two variables to visualize.")
Hi! I can help you with any questions about Streamlit and Python. What would you like to know?