Code Editor for app.py

import streamlit as st
import pandas as pd
import plotly.express as px

# Cache the data loading
@st.cache_data
def load_data(url):
    # NOTE: Using corsproxy.io because we're in a WASM environment. If running locally,
    # you can remove the corsproxy.io prefix. Some websites don't work with the proxy,
    # in those cases try removing the proxy prefix.
    if not url.startswith('http'):
        st.error('Please enter a valid URL starting with http:// or https://')
        return None
    
    try:
        df = pd.read_csv(f"https://corsproxy.io/?{url}")
        return df
    except Exception as e:
        st.error(f"Error loading data: {str(e)}")
        return None

st.title("CSV Viewer and Plotter")

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

data = load_data(url)

if data is not None:
    # Controls
    col1, col2 = st.columns(2)
    
    with col1:
        n_rows = st.number_input("Number of rows to display", 
                                min_value=1, 
                                max_value=len(data), 
                                value=min(10, len(data)))
    
    with col2:
        shuffle = st.checkbox("Randomly shuffle data")
    
    # Shuffle if requested
    if shuffle:
        data = data.sample(frac=1).reset_index(drop=True)
    
    # Display data
    st.subheader("Data Preview")
    st.dataframe(data.head(n_rows))
    
    # Variable selection for plotting
    st.subheader("Data Visualization")
    
    # Get numeric and categorical columns
    numeric_cols = data.select_dtypes(include=['float64', 'int64']).columns.tolist()
    categorical_cols = data.select_dtypes(include=['object', 'category']).columns.tolist()
    all_cols = numeric_cols + categorical_cols
    
    col1, col2 = st.columns(2)
    
    with col1:
        var1 = st.selectbox("Select first variable", all_cols)
    
    with col2:
        remaining_cols = [col for col in all_cols if col != var1]
        var2 = st.selectbox("Select second variable (optional)", 
                           ["None"] + remaining_cols)
    
    # Plotting logic
    if var2 == "None":
        # Single variable visualization
        if var1 in numeric_cols:
            # For numeric variables, show histogram
            fig = px.histogram(data, x=var1, 
                             title=f"Distribution of {var1}")
        else:
            # For categorical variables, show bar chart
            counts = data[var1].value_counts()
            fig = px.bar(x=counts.index, y=counts.values,
                        title=f"Distribution of {var1}")
    else:
        # Two variable visualization
        if var1 in numeric_cols and var2 in numeric_cols:
            # Both numeric: scatter plot
            fig = px.scatter(data, x=var1, y=var2,
                           title=f"{var2} vs {var1}")
        
        elif var1 in numeric_cols and var2 in categorical_cols:
            # One numeric, one categorical: box plot
            fig = px.box(data, x=var2, y=var1,
                        title=f"Distribution of {var1} by {var2}")
        
        elif var1 in categorical_cols and var2 in numeric_cols:
            # One categorical, one numeric: box plot
            fig = px.box(data, x=var1, y=var2,
                        title=f"Distribution of {var2} by {var1}")
        
        else:
            # Both categorical: heatmap
            contingency = pd.crosstab(data[var1], data[var2])
            fig = px.imshow(contingency,
                          title=f"Relationship between {var1} and {var2}")
    
    st.plotly_chart(fig)