Code Editor for app.py

import streamlit as st
import pandas as pd
import numpy as np
import plotly.express as px
import plotly.graph_objects as go
from plotly.subplots import make_subplots

# Set page config
st.set_page_config(page_title="Data Visualizer", layout="wide")

# App title
st.title("📊 Data Visualizer")
st.markdown("Upload a CSV from URL and explore your data with interactive visualizations!")

# Sidebar controls
st.sidebar.header("Data Controls")

# URL input
url = st.sidebar.text_input(
    "CSV URL", 
    value="https://raw.githubusercontent.com/mwaskom/seaborn-data/master/penguins.csv",
    help="Enter the URL of a CSV file to load"
)

@st.cache_data
def load_data(url):
    """Load and cache CSV data from URL"""
    try:
        df = pd.read_csv(url)
        return df, None
    except Exception as e:
        return None, str(e)

# Load data
if url:
    with st.spinner("Loading data..."):
        df, error = load_data(url)
    
    if error:
        st.error(f"Error loading data: {error}")
        st.stop()
    
    if df is not None:
        # Data controls
        st.sidebar.subheader("Display Options")
        
        # Number of rows control
        max_rows = len(df)
        num_rows = st.sidebar.slider(
            "Number of rows to display", 
            min_value=1, 
            max_value=max_rows, 
            value=min(100, max_rows),
            help="Select how many rows to display"
        )
        
        # Shuffle checkbox
        shuffle_data = st.sidebar.checkbox(
            "Randomly shuffle data", 
            value=False,
            help="Randomly shuffle the DataFrame rows"
        )
        
        # Apply controls to dataframe
        display_df = df.copy()
        if shuffle_data:
            display_df = display_df.sample(frac=1, random_state=42).reset_index(drop=True)
        
        display_df = display_df.head(num_rows)
        
        # Main content
        col1, col2 = st.columns([2, 1])
        
        with col2:
            st.subheader("📈 Visualization Controls")
            
            # Get numeric and categorical columns
            numeric_cols = df.select_dtypes(include=[np.number]).columns.tolist()
            categorical_cols = df.select_dtypes(include=['object', 'category']).columns.tolist()
            all_cols = numeric_cols + categorical_cols
            
            # Variable selection
            st.markdown("**Select Variables:**")
            var1 = st.selectbox(
                "First variable", 
                options=all_cols,
                index=0 if all_cols else None,
                help="Select the first variable for visualization"
            )
            
            var2 = st.selectbox(
                "Second variable (optional)", 
                options=[None] + all_cols,
                index=0,
                help="Select a second variable for bivariate analysis"
            )
            
            # Color variable for enhanced visualizations
            color_var = st.selectbox(
                "Color by (optional)",
                options=[None] + categorical_cols,
                index=0,
                help="Select a categorical variable to color the plot"
            )
        
        with col1:
            st.subheader("📋 Data Preview")
            st.dataframe(display_df, use_container_width=True)
            
            # Data info
            st.markdown(f"**Dataset Info:** {len(df)} rows × {len(df.columns)} columns")
            if shuffle_data:
                st.info("Data has been shuffled randomly")
        
        # Visualization section
        st.subheader("📊 Data Visualization")
        
        if var1:
            # Determine the best visualization based on variable types
            var1_type = 'numeric' if var1 in numeric_cols else 'categorical'
            var2_type = 'numeric' if var2 in numeric_cols else 'categorical' if var2 else None
            
            # Create appropriate visualization
            fig = None
            chart_title = ""
            
            if not var2:  # Single variable
                if var1_type == 'numeric':
                    # Histogram for numeric variable
                    fig = px.histogram(
                        display_df, 
                        x=var1, 
                        color=color_var,
                        title=f"Distribution of {var1}",
                        marginal="box"
                    )
                    chart_title = f"Histogram: {var1}"
                else:
                    # Bar chart for categorical variable
                    value_counts = display_df[var1].value_counts()
                    fig = px.bar(
                        x=value_counts.index, 
                        y=value_counts.values,
                        title=f"Count of {var1}",
                        labels={'x': var1, 'y': 'Count'}
                    )
                    chart_title = f"Bar Chart: {var1}"
            
            else:  # Two variables
                if var1_type == 'numeric' and var2_type == 'numeric':
                    # Scatter plot for two numeric variables
                    fig = px.scatter(
                        display_df, 
                        x=var1, 
                        y=var2, 
                        color=color_var,
                        title=f"{var1} vs {var2}",
                        trendline="ols" if color_var is None else None
                    )
                    chart_title = f"Scatter Plot: {var1} vs {var2}"
                
                elif var1_type == 'categorical' and var2_type == 'numeric':
                    # Box plot for categorical vs numeric
                    fig = px.box(
                        display_df, 
                        x=var1, 
                        y=var2, 
                        color=color_var,
                        title=f"{var2} by {var1}"
                    )
                    chart_title = f"Box Plot: {var2} by {var1}"
                
                elif var1_type == 'numeric' and var2_type == 'categorical':
                    # Box plot for numeric vs categorical (swapped)
                    fig = px.box(
                        display_df, 
                        x=var2, 
                        y=var1, 
                        color=color_var,
                        title=f"{var1} by {var2}"
                    )
                    chart_title = f"Box Plot: {var1} by {var2}"
                
                else:  # Both categorical
                    # Grouped bar chart or heatmap
                    crosstab = pd.crosstab(display_df[var1], display_df[var2])
                    fig = px.imshow(
                        crosstab.values,
                        x=crosstab.columns,
                        y=crosstab.index,
                        aspect="auto",
                        title=f"Heatmap: {var1} vs {var2}",
                        labels={'x': var2, 'y': var1, 'color': 'Count'}
                    )
                    chart_title = f"Heatmap: {var1} vs {var2}"
            
            if fig:
                fig.update_layout(height=500)
                st.plotly_chart(fig, use_container_width=True)
                st.caption(f"📈 {chart_title}")
            
            # Summary statistics
            if var1_type == 'numeric' or (var2 and var2_type == 'numeric'):
                st.subheader("📊 Summary Statistics")
                numeric_vars = [v for v in [var1, var2] if v and v in numeric_cols]
                if numeric_vars:
                    summary_stats = display_df[numeric_vars].describe()
                    st.dataframe(summary_stats, use_container_width=True)
        
        else:
            st.info("👆 Select at least one variable to create a visualization")
    
    else:
        st.warning("No data loaded. Please check your URL.")
else:
    st.info("👆 Please enter a CSV URL to get started")