Code Editor for app.py

import streamlit as st
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px
import numpy as np
import random

# Function to load data with error handling
@st.cache_data
def load_data(url):
    try:
        df = pd.read_csv(url)
        return df
    except Exception as e:
        st.error(f"Error loading data: {e}")
        return None

# App Title
st.title("CSV Data Exploration App")

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

# Load data
if url:
    data = load_data(url)

    if data is not None:
        # Cache data shape
        st.write(f"Data loaded successfully with shape: {data.shape}")

        # Display row control
        rows = st.slider("Select number of rows to display:", 1, min(1000, len(data)), 10)
        st.write(data.head(rows))

        # Shuffle checkbox
        shuffle = st.checkbox("Shuffle data")
        random_seed = st.number_input("Select random seed:", min_value=0, value=42)

        if shuffle:
            random.seed(random_seed)
            data = data.sample(frac=1, random_state=random_seed).reset_index(drop=True)

        # Select variables
        columns = data.columns.tolist()
        x_var = st.selectbox("Select X variable:", columns)
        y_var = st.selectbox("Select Y variable (optional):", [None] + columns)

        # Handle missing data
        if data[x_var].isnull().any():
            st.warning(f"{x_var} has missing values.")
        if y_var and data[y_var].isnull().any():
            st.warning(f"{y_var} has missing values.")

        # Visualization
        if y_var:
            if pd.api.types.is_numeric_dtype(data[x_var]) and pd.api.types.is_numeric_dtype(data[y_var]):
                st.subheader("Scatter Plot")
                sns.scatterplot(x=x_var, y=y_var, data=data)
                st.pyplot()
            else:
                st.subheader("Box Plot")
                sns.boxplot(x=x_var, y=y_var, data=data)
                st.pyplot()
        else:
            st.subheader("Distribution Plot")
            sns.histplot(data[x_var], kde=True)
            st.pyplot()

        # Responsive Design
        st.markdown("\n\n<style>\nbody {font-size: 1em;}\n@media (max-width: 768px) {\nbody {font-size: 0.8em;}\n}\n</style>", unsafe_allow_html=True)