Code Editor for app.py

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

# Add a title
st.title("CSV Data Viewer and Visualizer")

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

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

try:
    # Load the data
    df = load_data(url)
    
    # Controls
    col1, col2 = st.columns(2)
    
    with col1:
        n_rows = st.number_input("Number of rows to display", min_value=1, 
                                max_value=len(df), value=min(10, len(df)))
    
    with col2:
        shuffle = st.checkbox("Randomly shuffle data")
    
    if shuffle:
        df_display = df.sample(n=len(df))
    else:
        df_display = df.copy()
    
    # Display the dataframe
    st.subheader("Data Preview")
    st.dataframe(df_display.head(n_rows))
    
    # Variable selection for visualization
    st.subheader("Data Visualization")
    
    # Get numerical and categorical columns
    numeric_cols = df.select_dtypes(include=[np.number]).columns.tolist()
    categorical_cols = df.select_dtypes(exclude=[np.number]).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)
    
    # Create visualization based on selected variables
    if var2 == "None":
        # Single variable visualization
        if var1 in numeric_cols:
            # For numeric variables, show histogram
            fig = px.histogram(df, x=var1, title=f"Distribution of {var1}")
            st.plotly_chart(fig)
        else:
            # For categorical variables, show bar chart
            fig = px.bar(df[var1].value_counts().reset_index(), 
                        x='index', y=var1, title=f"Count of {var1}")
            st.plotly_chart(fig)
    else:
        # Two variable visualization
        if var1 in numeric_cols and var2 in numeric_cols:
            # Both numeric: scatter plot
            fig = px.scatter(df, x=var1, y=var2, 
                           title=f"Scatter plot of {var1} vs {var2}")
        elif var1 in numeric_cols and var2 in categorical_cols:
            # Numeric and categorical: box plot
            fig = px.box(df, x=var2, y=var1, 
                        title=f"Distribution of {var1} by {var2}")
        elif var1 in categorical_cols and var2 in numeric_cols:
            # Categorical and numeric: box plot
            fig = px.box(df, x=var1, y=var2, 
                        title=f"Distribution of {var2} by {var1}")
        else:
            # Both categorical: heatmap
            heatmap_data = pd.crosstab(df[var1], df[var2])
            fig = px.imshow(heatmap_data, 
                          title=f"Heatmap of {var1} vs {var2}")
        
        st.plotly_chart(fig)

except Exception as e:
    st.error(f"Error loading or processing data: {str(e)}")