Code Editor for app.py

import streamlit as st
import pandas as pd
import seaborn as sns
import numpy as np

# Cache the data loading
@st.cache_data
def load_data(url):
    try:
        df = pd.read_csv(url)
        return df, None
    except Exception as e:
        return None, str(e)

# Main app
st.title("CSV Viewer & Plotter")

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

# Load data
df, error = load_data(url)

if error:
    st.error(f"Error loading data: {error}")
else:
    # 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")
    
    # Process DataFrame
    display_df = df.copy()
    if shuffle:
        display_df = display_df.sample(frac=1, random_state=42)
    
    # Display DataFrame
    st.subheader("Data Preview")
    st.dataframe(display_df.head(n_rows))
    
    # Variable selection for plotting
    st.subheader("Data Visualization")
    numeric_cols = display_df.select_dtypes(include=[np.number]).columns
    categorical_cols = display_df.select_dtypes(exclude=[np.number]).columns
    all_cols = list(numeric_cols) + list(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:
            st.subheader(f"Distribution of {var1}")
            fig = sns.displot(data=display_df, x=var1, kde=True)
            st.pyplot(fig)
        else:
            st.subheader(f"Count plot of {var1}")
            fig = sns.countplot(data=display_df, x=var1)
            st.pyplot(fig.figure)
    else:
        # Two variable visualization
        if var1 in numeric_cols and var2 in numeric_cols:
            # Scatter plot for two numeric variables
            st.subheader(f"Scatter plot: {var1} vs {var2}")
            fig = sns.scatterplot(data=display_df, x=var1, y=var2)
            st.pyplot(fig.figure)
        elif var1 in numeric_cols and var2 in categorical_cols:
            # Box plot for numeric vs categorical
            st.subheader(f"Box plot: {var1} by {var2}")
            fig = sns.boxplot(data=display_df, x=var2, y=var1)
            st.pyplot(fig.figure)
        elif var1 in categorical_cols and var2 in numeric_cols:
            # Box plot for categorical vs numeric
            st.subheader(f"Box plot: {var2} by {var1}")
            fig = sns.boxplot(data=display_df, x=var1, y=var2)
            st.pyplot(fig.figure)
        else:
            # Heatmap for two categorical variables
            st.subheader(f"Heatmap: {var1} vs {var2}")
            crosstab = pd.crosstab(display_df[var1], display_df[var2])
            fig = sns.heatmap(crosstab, annot=True, fmt='d', cmap='YlOrRd')
            st.pyplot(fig.figure)