Code Editor for app.py

import streamlit as st
import pandas as pd
import altair as alt
import numpy as np

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

# App layout
st.title("CSV Data Viewer & Visualizer")

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

try:
    # Load 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 = df.sample(frac=1, random_state=42).reset_index(drop=True)
    
    # Display dataframe
    st.subheader("Data Preview")
    st.dataframe(df.head(n_rows))
    
    # Variable selection for visualization
    st.subheader("Data Visualization")
    
    # Get numeric 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, index=0)
    
    with col2:
        var2 = st.selectbox("Select second variable (optional)", 
                           ["None"] + all_cols,
                           index=0)
    
    # Create visualization based on selected variables
    if var2 == "None":
        # Single variable visualization
        if var1 in numeric_cols:
            # For numeric variables, show histogram
            chart = alt.Chart(df).mark_bar().encode(
                alt.X(f"{var1}:Q", bin=True),
                y='count()',
                tooltip=['count()']
            ).properties(
                title=f"Distribution of {var1}"
            )
        else:
            # For categorical variables, show bar chart
            chart = alt.Chart(df).mark_bar().encode(
                x=alt.X(f"{var1}:N"),
                y='count()',
                tooltip=['count()']
            ).properties(
                title=f"Distribution of {var1}"
            )
    else:
        # Two variable visualization
        if var1 in numeric_cols and var2 in numeric_cols:
            # Both numeric: scatter plot
            chart = alt.Chart(df).mark_circle().encode(
                x=f"{var1}:Q",
                y=f"{var2}:Q",
                tooltip=[var1, var2]
            ).properties(
                title=f"{var1} vs {var2}"
            )
        elif var1 in numeric_cols and var2 in categorical_cols:
            # Numeric + Categorical: box plot
            chart = alt.Chart(df).mark_boxplot().encode(
                x=f"{var2}:N",
                y=f"{var1}:Q"
            ).properties(
                title=f"{var1} by {var2}"
            )
        elif var1 in categorical_cols and var2 in numeric_cols:
            # Categorical + Numeric: box plot
            chart = alt.Chart(df).mark_boxplot().encode(
                x=f"{var1}:N",
                y=f"{var2}:Q"
            ).properties(
                title=f"{var2} by {var1}"
            )
        else:
            # Both categorical: heatmap
            chart = alt.Chart(df).mark_rect().encode(
                x=f"{var1}:N",
                y=f"{var2}:N",
                color='count()',
                tooltip=[var1, var2, 'count()']
            ).properties(
                title=f"{var1} vs {var2}"
            )
    
    st.altair_chart(chart, use_container_width=True)

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