components/runbacktest.py import streamlit as st import pandas as pd import numpy as np…
- User
components/run_backtest.py
import streamlit as st import pandas as pd import numpy as np import plotly.express as px
Importing all necessary functions from utils, metrics, and plots
from utils import ( download_data, generate_recommendations, backtest,
fetch_fama_french_factors, )from metrics import ( calculate_portfolio_metrics, calculate_final_score, calculate_risk_factor_attribution, get_drawdown_details )
from plots import ( plot_growth_comparison, plot_drawdown_comparison, plot_cagr_over_time, plot_allocation_pie, plot_correlation_heatmap, plot_risk_return_attribution, plot_rolling_metrics, plot_correlation_heatmap_comparison, plot_cagr_comparison, plot_allocation_comparison, plot_rolling_metrics_comparison, plot_risk_return_attribution_comparison, plot_efficient_frontier_comparison )
def run_backtest_ui(): # Initialize portfolios in session state if not already initialized if 'portfolios' not in st.session_state: st.session_state.portfolios = []
if st.session_state.portfolios: with st.form("compare_form"): st.subheader("🔍 Select Portfolios to Compare") comparison_type = st.selectbox( "Comparison Type", ["Portfolio vs Benchmark", "Portfolio vs Portfolio"] ) portfolio_names = [p['name'] for p in st.session_state.portfolios] if comparison_type == "Portfolio vs Benchmark": portfolio1 = st.selectbox("Select Portfolio", portfolio_names) portfolio2 = None else: portfolio1 = st.selectbox("Select First Portfolio", portfolio_names, key="p1") portfolio2 = st.selectbox("Select Second Portfolio", portfolio_names, key="p2") if portfolio1 == portfolio2: st.warning("Please select two different portfolios for comparison.") st.subheader("⚙️ Visualizations Settings") selected_time_frames = st.multiselect( "Select Time Frames for CAGR", options=['Weekly', 'Monthly', 'Quarterly', 'Annually'], default=['Annually'], key="selected_time_frames", help="Choose one or more time frames to view CAGR over different horizons." ) selected_rolling_periods = st.multiselect( "Select Rolling Periods (Days)", options=[30, 90, 180, 252], default=[252], key="selected_rolling_periods", help="Choose one or more periods to view rolling metrics." ) run = st.form_submit_button("Run Backtest") if run: with st.spinner("Running backtest..."): if comparison_type == "Portfolio vs Benchmark": # Handle Portfolio vs Benchmark try: portfolio = next(p for p in st.session_state.portfolios if p['name'] == portfolio1) except StopIteration: st.error("Selected portfolio not found.") return price_data = download_data( portfolio['selected'], portfolio['start_date'], portfolio['end_date'] ) if price_data.empty: st.error("No price data available for the selected portfolio.") else: available_selected = [ticker for ticker in portfolio['selected'] if ticker in price_data.columns] missing_selected = list(set(portfolio['selected']) - set(available_selected)) if missing_selected: st.warning(f"Excluded tickers with no data: {', '.join(missing_selected)}") if not available_selected: st.error( "No selected tickers have available data for the chosen date range. " "Please ensure that the ticker symbols are correct and data is available for the specified period." ) else: # Extract corresponding allocations original_allocations = portfolio.get('allocations', [0.0]*len(portfolio.get('selected', []))) adjusted_allocations = [original_allocations[i] for i, ticker in enumerate(portfolio.get('selected', [])) if ticker in available_selected] # Error Handling for Allocation-Axis if len(adjusted_allocations) != len(available_selected): st.error("Mismatch between allocations and available assets after filtering.") return # Normalize allocations to sum to 1 weights = np.array(adjusted_allocations) / 100 total_alloc = weights.sum() if not np.isclose(total_alloc, 1.0, atol=1e-4): if total_alloc == 0: st.error("Total allocations sum to 0. Cannot adjust allocations.") return st.warning("Allocations do not sum to 100%. Adjusting allocations proportionally.") weights = weights / total_alloc # Final check to ensure weights match the number of assets if len(weights) != len(available_selected): st.error("Final allocation weights do not match the number of available assets.") return # Calculate per-asset returns asset_returns = price_data[available_selected].pct_change().dropna() # Run backtest to get portfolio returns returns, cum_returns = backtest( weights, price_data[available_selected], portfolio['rebalance_freq'], portfolio['broker_fee'], debug=False ) # Align asset returns with portfolio returns common_index = returns.index.intersection(asset_returns.index) asset_returns = asset_returns.loc[common_index] returns = returns.loc[common_index] cum_returns = cum_returns.loc[common_index] if cum_returns.empty: st.error("Cumulative returns are empty. Check the data and allocations.") else: benchmark_symbol = portfolio['benchmark_symbol'] benchmark_data = download_data([benchmark_symbol], portfolio['start_date'], portfolio['end_date']) if benchmark_symbol not in benchmark_data.columns: st.error(f"The selected benchmark symbol '{benchmark_symbol}' does not have available data for the chosen period.") st.stop() else: st.success(f"Benchmark '{benchmark_symbol}' data successfully downloaded and will be used for comparison.") if not benchmark_data.empty: benchmark_returns = benchmark_data[benchmark_symbol].pct_change().dropna() benchmark_returns = benchmark_returns.reindex(returns.index, method='ffill').dropna() common_index_benchmark = returns.index.intersection(benchmark_returns.index) if common_index_benchmark.empty: st.error("No overlapping dates between portfolio returns and benchmark returns after alignment.") st.stop() returns = returns.loc[common_index_benchmark] cum_returns = cum_returns.loc[common_index_benchmark] asset_returns = asset_returns.loc[common_index_benchmark] benchmark_returns = benchmark_returns.loc[common_index_benchmark] benchmark_cum_returns = (1 + benchmark_returns).cumprod() benchmark_metrics = calculate_portfolio_metrics( benchmark_returns, benchmark_cum_returns, portfolio['rf_rate'], None ) else: benchmark_returns = None benchmark_cum_returns = pd.Series(dtype=float) benchmark_metrics = { 'Start Balance': "N/A", 'End Balance': "N/A", 'Annualized Return (CAGR)': "N/A", 'Best Year': "N/A", 'Worst Year': "N/A", 'Arithmetic Mean (Monthly)': "N/A", 'Arithmetic Mean (Annualized)': "N/A", 'Geometric Mean (Monthly)': "N/A", 'Geometric Mean (Annualized)': "N/A", 'Standard Deviation (Monthly)': "N/A", 'Standard Deviation (Annualized)': "N/A", 'Downside Deviation (Monthly)': "N/A", 'Maximum Drawdown': "N/A", 'Sharpe Ratio': "N/A", 'Sortino Ratio': "N/A", 'Gain/Loss Ratio': "N/A", 'Skewness': "N/A", 'Excess Kurtosis': "N/A", 'Safe Withdrawal Rate': "N/A", 'Perpetual Withdrawal Rate': "N/A", 'Positive Periods': "N/A", 'Benchmark Correlation': "N/A", 'Beta': "N/A", 'Alpha (annualized)': "N/A", 'R2': "N/A", 'Treynor Ratio': "N/A", 'Calmar Ratio': "N/A", 'Modigliani–Modigliani Measure': "N/A", 'Information Ratio': "N/A", 'Tracking Error': "N/A", 'Active Return': "N/A", 'Upside Capture Ratio': "N/A", 'Downside Capture Ratio': "N/A" } if not cum_returns.empty: portfolio_metrics = calculate_portfolio_metrics( returns, cum_returns, portfolio['rf_rate'], benchmark_returns ) # Dashboard Header with Key Stats with st.container(): st.markdown("### 🔑 Key Metrics") key_metrics = { 'Annualized Return (CAGR)': portfolio_metrics.get('Annualized Return (CAGR)', "N/A"), 'Sharpe Ratio': portfolio_metrics.get('Sharpe Ratio', "N/A"), 'Maximum Drawdown': portfolio_metrics.get('Maximum Drawdown', "N/A") } cols = st.columns(len(key_metrics)) for col, (metric, value) in zip(cols, key_metrics.items()): with col: st.metric(label=metric, value=value) # Create Tabs for Organized Sections tabs = st.tabs(["Overview", "Performance Statistics", "Advanced Metrics", "Drawdowns", "Visualizations"]) with tabs[0]: st.header("📈 Portfolio Performance Overview") st.write(f"**Portfolio Name:** {portfolio['name']}") st.write(f"**Start Date:** {portfolio['start_date'].strftime('%Y-%m-%d')}") st.write(f"**End Date:** {portfolio['end_date'].strftime('%Y-%m-%d')}") st.write(f"**Benchmark:** {portfolio['benchmark_symbol']}") with tabs[1]: st.header("📊 Performance Statistics") with st.container(): st.subheader("🛠️ Basic Metrics") performance_data_stats = { 'Metric': [ 'Start Balance', 'End Balance', 'Annualized Return (CAGR)', 'Standard Deviation (Annualized)', 'Best Year', 'Worst Year', 'Maximum Drawdown', 'Sharpe Ratio', 'Sortino Ratio', 'Benchmark Correlation' ], 'Portfolio': [ portfolio_metrics['Start Balance'], portfolio_metrics['End Balance'], portfolio_metrics['Annualized Return (CAGR)'], portfolio_metrics['Standard Deviation (Annualized)'], portfolio_metrics['Best Year'], portfolio_metrics['Worst Year'], portfolio_metrics['Maximum Drawdown'], portfolio_metrics['Sharpe Ratio'], portfolio_metrics['Sortino Ratio'], portfolio_metrics['Benchmark Correlation'] ], 'Benchmark': [ benchmark_metrics.get('Start Balance', "N/A"), benchmark_metrics.get('End Balance', "N/A"), benchmark_metrics.get('Annualized Return (CAGR)', "N/A"), benchmark_metrics.get('Standard Deviation (Annualized)', "N/A"), benchmark_metrics.get('Best Year', "N/A"), benchmark_metrics.get('Worst Year', "N/A"), benchmark_metrics.get('Maximum Drawdown', "N/A"), benchmark_metrics.get('Sharpe Ratio', "N/A"), benchmark_metrics.get('Sortino Ratio', "N/A"), benchmark_metrics.get('Benchmark Correlation', "N/A") ] } performance_df_stats = pd.DataFrame(performance_data_stats).set_index('Metric') # Format metrics to two decimal places def format_value(val): if isinstance(val, str): return val elif isinstance(val, float) or isinstance(val, int): return f"{val:.2f}" else: return "N/A" performance_df_stats_formatted = performance_df_stats.applymap(format_value) st.table(performance_df_stats_formatted) with tabs[2]: st.header("📋 Detail Comparisons") with st.container(): st.subheader("🧮 Advanced Metrics") performance_data_advanced = { 'Metric': list(portfolio_metrics.keys()), 'Portfolio': list(portfolio_metrics.values()), 'Benchmark': list(benchmark_metrics.values()) } performance_df_advanced = pd.DataFrame(performance_data_advanced).set_index('Metric') # Replace NaN with empty strings for better visualization performance_df_advanced = performance_df_advanced.replace(np.nan, "") # Drop rows where both Portfolio and Benchmark values are NaN performance_df_advanced_clean = performance_df_advanced.dropna(how='all') # Format metrics to two decimal places performance_df_advanced_clean = performance_df_advanced_clean.applymap(format_value) st.table(performance_df_advanced_clean) st.markdown("---") st.write("**Note:** Some metrics in the benchmark column are empty because they are portfolio-specific measurements that can't be calculated for the benchmark alone...") st.subheader("🔍 Risk Factor Attribution Analysis") # Define date range based on the overlapping index start_date = common_dates.min().strftime('%Y-%m-%d') end_date = common_dates.max().strftime('%Y-%m-%d') # Fetch actual factor data factors = fetch_fama_french_factors(start_date, end_date) # Ensure factors are fetched if factors.empty: st.write("Failed to retrieve factor data.") else: # Align factors frequency with portfolios if isinstance(returns_a.index, pd.DatetimeIndex): if returns_a.index.freq is None: inferred_freq = pd.infer_freq(returns_a.index) if inferred_freq is None: inferred_freq = 'D' # Set default frequency to daily else: inferred_freq = returns_a.index.freq try: factors = factors.asfreq(inferred_freq, method='ffill') except TypeError as e: st.error(f"Error setting frequency for factors: {e}") st.stop() else: st.error("Returns index is not a DatetimeIndex.") st.stop() # Calculate Attribution for Portfolio A attribution_a, error_a = calculate_risk_factor_attribution(returns_a, factors) # Calculate Attribution for Portfolio B attribution_b, error_b = calculate_risk_factor_attribution(returns_b, factors) if error_a or error_b: st.error("Risk factor attribution analysis is unavailable for one or both portfolios.") else: if attribution_a.empty or attribution_b.empty: st.write("Risk factor attribution analysis is unavailable for one or both portfolios.") else: # Combined Attribution Comparison st.write(f"### Risk Factor Attribution for {portfolio_a['name']} vs {portfolio_b['name']}") # Merge both attributions for comparison combined_attribution = attribution_a.set_index('Factor').join( attribution_b.set_index('Factor'), lsuffix=f' ({portfolio_a["name"]})', rsuffix=f' ({portfolio_b["name"]})', how='outer' ).reset_index() st.table(combined_attribution.fillna(0)) # Visualization fig_attribution = px.bar( combined_attribution.melt(id_vars='Factor', var_name='Category', value_name='Contribution (%)'), x='Factor', y='Contribution (%)', color='Category', barmode='group', title='Risk Factor Attribution Comparison', template='plotly_dark' ) st.plotly_chart(fig_attribution, use_container_width=True) with tabs[3]: st.header("📉 Detailed Drawdowns") st.markdown("### 📈 Drawdowns for Portfolio") portfolio_drawdowns = get_drawdown_details(cum_returns) if portfolio_drawdowns: portfolio_drawdowns_df = pd.DataFrame(portfolio_drawdowns) st.table(portfolio_drawdowns_df) else: st.write("No drawdowns detected for the portfolio.") st.markdown("### 📈 Drawdowns for Benchmark") benchmark_drawdowns = get_drawdown_details(benchmark_cum_returns) if benchmark_drawdowns: benchmark_drawdowns_df = pd.DataFrame(benchmark_drawdowns) st.table(benchmark_drawdowns_df) else: st.write("No drawdowns detected for the benchmark.") with tabs[4]: st.header("📊 Visualizations") if not cum_returns.empty and not benchmark_cum_returns.empty: plot_growth_comparison(cum_returns, benchmark_cum_returns, labels=["Portfolio", "Benchmark"]) else: st.warning("Insufficient data to display Growth Comparison. Ensure both portfolio and benchmark have data.") portfolio_drawdown_series = (cum_returns / cum_returns.expanding().max() - 1) * 100 benchmark_drawdown_series = (benchmark_cum_returns / benchmark_cum_returns.expanding().max() - 1) * 100 plot_drawdown_comparison(portfolio_drawdown_series, benchmark_drawdown_series, labels=["Portfolio", "Benchmark"]) st.subheader("📈 Compound Annual Growth Rate (CAGR) Over Time") if selected_time_frames: plot_cagr_over_time(cum_returns, time_frames=selected_time_frames, label="Portfolio") else: st.warning("Please select at least one time frame for CAGR.") # Box Plot for Returns Distribution st.subheader("📦 Returns Distribution Box Plot") if isinstance(asset_returns, pd.DataFrame): # Assuming the index is named 'Date' if asset_returns.index.name != 'Date': asset_returns = asset_returns.copy() asset_returns.index.name = 'Date' melted_returns = asset_returns.reset_index().melt(id_vars='Date', var_name='Asset', value_name='Return') fig_box_plot = px.box( melted_returns, x='Asset', y='Return', title='Returns Distribution Box Plot', labels={'Return': 'Returns', 'Asset': 'Asset'}, points='all', hover_data=['Return'], template='plotly_dark', color='Asset', color_discrete_sequence=px.colors.qualitative.Set3 ) st.plotly_chart(fig_box_plot, use_container_width=True) st.markdown("**Interpretation:** The box plot visualizes the distribution of returns for each asset in the portfolio. The boxes represent the interquartile range (IQR), the line inside the box indicates the median, and the whiskers show the range of the data. Outliers are displayed as individual points.") elif isinstance(asset_returns, pd.Series): # Assuming the index is named 'Date' if asset_returns.index.name != 'Date': asset_returns = asset_returns.copy() asset_returns.index.name = 'Date' melted_returns = asset_returns.reset_index().rename(columns={'Date': 'Date', 0: 'Return'}) fig_box_plot = px.box( melted_returns, y='Return', title='Returns Distribution Box Plot', labels={'Return': 'Returns'}, points='all', hover_data=['Return'], template='plotly_dark' ) st.plotly_chart(fig_box_plot, use_container_width=True) st.markdown("**Interpretation:** The box plot visualizes the distribution of returns for the portfolio. The box represents the interquartile range (IQR), the line inside the box indicates the median, and the whiskers show the range of the data. Outliers are displayed as individual points.") else: st.warning("Returns data is neither a DataFrame nor a Series.") # Heatmap of Correlations Between Assets st.subheader("🔥 Correlation Heatmap of Assets") plot_correlation_heatmap(asset_returns) # Add Risk-Return Attribution Analysis st.subheader("🔍 Risk-Return Attribution Analysis") plot_risk_return_attribution(returns, weights, label='Portfolio') # Cumulative Returns Heatmap st.subheader("🔥 Cumulative Returns Heatmap") try: cum_returns_normalized = cum_returns / cum_returns.expanding().max() fig_cum_heatmap = px.imshow( cum_returns_normalized.to_frame().T, labels=dict(x="Date", y="Portfolio", color="Normalized Cumulative Return"), title="Cumulative Returns Heatmap", aspect="auto", color_continuous_scale='Viridis', template='plotly_dark' ) st.plotly_chart(fig_cum_heatmap, use_container_width=True) st.markdown("**Interpretation:** The heatmap visualizes the normalized cumulative returns over time, allowing for an intuitive comparison of portfolio performance across different periods.") except Exception as e: st.error(f"Error plotting cumulative returns heatmap: {e}") # Portfolio Allocation Pie Chart st.subheader("🥧 Portfolio Allocation Pie Chart") plot_allocation_pie(weights, available_selected, title="Portfolio Allocation", hover_info="percent+name") # Rolling Metrics Chart with User-Defined Periods st.subheader("📉 Rolling Metrics") if selected_rolling_periods: plot_rolling_metrics(returns, windows=selected_rolling_periods, label='Portfolio') else: st.warning("Please select at least one rolling period to display metrics.") # Recommendations st.markdown("### 💡 Recommendations") recommendations = generate_recommendations( allocations=[alloc for alloc in portfolio['allocations'] if alloc > 0], available_selected=[ticker for ticker in available_selected if portfolio['allocations'][available_selected.index(ticker)] > 0] ) if recommendations: for rec in recommendations: st.write(rec) else: st.success("Your portfolio allocations are well-balanced!") # Final Score st.markdown("### 📝 Final Score") skipped_metrics_set = set() portfolio_score = calculate_final_score(portfolio_metrics, benchmark_metrics, global_skipped=skipped_metrics_set) benchmark_score = calculate_final_score(benchmark_metrics, portfolio_metrics, global_skipped=skipped_metrics_set) st.write(f"**Portfolio:** {portfolio_score:.2f} / 100") st.write(f"**Benchmark:** {benchmark_score:.2f} / 100") # Show skipped metrics once if skipped_metrics_set: st.warning(f"Skipped metrics due to invalid values: {', '.join(skipped_metrics_set)}") # Store results st.session_state.backtest_results = { 'returns': returns, 'cum_returns': cum_returns, 'weights_a': weights, 'price_data': price_data[available_selected], 'metrics': portfolio_metrics, 'benchmark_metrics': benchmark_metrics, 'performance_df_stats': performance_df_stats_formatted, 'performance_df_advanced': performance_df_advanced_clean, # Corrected to use the cleaned DataFrame 'benchmark_cum_returns': benchmark_cum_returns } elif comparison_type == "Portfolio vs Portfolio" and portfolio1 and portfolio2 and portfolio1 != portfolio2: # Handle Portfolio vs Portfolio try: portfolio_a = next(p for p in st.session_state.portfolios if p['name'] == portfolio1) portfolio_b = next(p for p in st.session_state.portfolios if p['name'] == portfolio2) except StopIteration: st.error("One or both selected portfolios were not found.") return # Initialize cum_returns_a and cum_returns_b to prevent UnboundLocalError cum_returns_a = pd.Series(dtype=float) cum_returns_b = pd.Series(dtype=float) # Backtest Portfolio A price_data_a = download_data( portfolio_a['selected'], portfolio_a['start_date'], portfolio_a['end_date'] ) # Backtest Portfolio B price_data_b = download_data( portfolio_b['selected'], portfolio_b['start_date'], portfolio_b['end_date'] ) if price_data_a.empty or price_data_b.empty: st.error("No price data available for one or both selected portfolios.") else: # Process Portfolio A available_a = [ticker for ticker in portfolio_a['selected'] if ticker in price_data_a.columns] missing_a = list(set(portfolio_a['selected']) - set(available_a)) if missing_a: st.warning(f"Excluded tickers from {portfolio_a['name']} with no data: {', '.join(missing_a)}") if not available_a: st.error(f"No selected tickers have available data for the portfolio '{portfolio_a['name']}'.") return # Extract corresponding allocations for Portfolio A original_allocations_a = portfolio_a.get('allocations', [0.0]*len(portfolio_a.get('selected', []))) adjusted_allocations_a = [original_allocations_a[i] for i, ticker in enumerate(portfolio_a.get('selected', [])) if ticker in available_a] if len(adjusted_allocations_a) != len(available_a): st.error(f"Mismatch between allocations and available assets after filtering for '{portfolio_a['name']}'.") return # Normalize allocations to sum to 1 weights_a = np.array(adjusted_allocations_a) / 100 total_alloc_a = weights_a.sum() if not np.isclose(total_alloc_a, 1.0, atol=1e-4): if total_alloc_a == 0: st.error(f"Total allocations for '{portfolio_a['name']}' sum to 0. Cannot adjust allocations.") return st.warning(f"Allocations for '{portfolio_a['name']}' do not sum to 100%. Adjusting allocations proportionally.") weights_a = weights_a / total_alloc_a # Calculate per-asset returns for Portfolio A asset_returns_a = price_data_a[available_a].pct_change().dropna() # Run backtest for Portfolio A returns_a, cum_returns_a = backtest( weights_a, price_data_a[available_a], portfolio_a['rebalance_freq'], portfolio_a['broker_fee'], debug=False ) # Process Portfolio B available_b = [ticker for ticker in portfolio_b['selected'] if ticker in price_data_b.columns] missing_b = list(set(portfolio_b['selected']) - set(available_b)) if missing_b: st.warning(f"Excluded tickers from {portfolio_b['name']} with no data: {', '.join(missing_b)}") if not available_b: st.error(f"No selected tickers have available data for the portfolio '{portfolio_b['name']}'.") return # Extract corresponding allocations for Portfolio B original_allocations_b = portfolio_b.get('allocations', [0.0]*len(portfolio_b.get('selected', []))) adjusted_allocations_b = [original_allocations_b[i] for i, ticker in enumerate(portfolio_b.get('selected', [])) if ticker in available_b] if len(adjusted_allocations_b) != len(available_b): st.error(f"Mismatch between allocations and available assets after filtering for '{portfolio_b['name']}'.") return # Normalize allocations to sum to 1 weights_b = np.array(adjusted_allocations_b) / 100 total_alloc_b = weights_b.sum() if not np.isclose(total_alloc_b, 1.0, atol=1e-4): if total_alloc_b == 0: st.error(f"Total allocations for '{portfolio_b['name']}' sum to 0. Cannot adjust allocations.") return st.warning(f"Allocations for '{portfolio_b['name']}' do not sum to 100%. Adjusting allocations proportionally.") weights_b = weights_b / total_alloc_b # Calculate per-asset returns for Portfolio B asset_returns_b = price_data_b[available_b].pct_change().dropna() # Run backtest for Portfolio B returns_b, cum_returns_b = backtest( weights_b, price_data_b[available_b], portfolio_b['rebalance_freq'], portfolio_b['broker_fee'], debug=False ) # Align the data for comparison common_dates = returns_a.index.intersection(returns_b.index) if common_dates.empty: st.error("No overlapping dates between the two portfolios after alignment.") return cum_returns_a = cum_returns_a.loc[common_dates] cum_returns_b = cum_returns_b.loc[common_dates] returns_a = returns_a.loc[common_dates] returns_b = returns_b.loc[common_dates] asset_returns_a = asset_returns_a.loc[common_dates] asset_returns_b = asset_returns_b.loc[common_dates] # Calculate Metrics metrics_a = calculate_portfolio_metrics( returns_a, cum_returns_a, portfolio_a['rf_rate'], None ) metrics_b = calculate_portfolio_metrics( returns_b, cum_returns_b, portfolio_b['rf_rate'], None ) # Dashboard Header with Key Stats with st.container(): st.markdown("### 🔑 Key Metrics") key_metrics = { 'Annualized Return (CAGR)': ('CAGR', metrics_a.get('Annualized Return (CAGR)', "N/A"), metrics_b.get('Annualized Return (CAGR)', "N/A")), 'Sharpe Ratio': ('Sharpe Ratio', metrics_a.get('Sharpe Ratio', "N/A"), metrics_b.get('Sharpe Ratio', "N/A")), 'Maximum Drawdown': ('Maximum Drawdown', metrics_a.get('Maximum Drawdown', "N/A"), metrics_b.get('Maximum Drawdown', "N/A")) } columns = st.columns(len(key_metrics)) for idx, (metric, (label, value_a, value_b)) in enumerate(key_metrics.items()): with columns[idx]: st.metric(label=f"{label} ({portfolio_a['name']})", value=value_a) st.metric(label=f"{label} ({portfolio_b['name']})", value=value_b) # Create Tabs for Organized Sections tabs = st.tabs(["Overview", "Performance Statistics", "Advanced Metrics", "Drawdowns", "Visualizations"]) with tabs[0]: st.header("📈 Portfolios Performance Overview") # Determine the aligned start and end dates aligned_start_date = common_dates.min().strftime('%Y-%m-%d') aligned_end_date = common_dates.max().strftime('%Y-%m-%d') st.write(f"**Aligned Date Range:** {aligned_start_date} to {aligned_end_date}") st.write(f"**Portfolio A:** {portfolio_a['name']}") st.write(f"**Original Start Date:** {portfolio_a['start_date'].strftime('%Y-%m-%d')}") st.write(f"**Portfolio B:** {portfolio_b['name']}") st.write(f"**Original Start Date:** {portfolio_b['start_date'].strftime('%Y-%m-%d')}") with tabs[1]: st.header("📊 Performance Statistics") with st.container(): st.subheader("🛠️ Basic Metrics") performance_data_stats = { 'Metric': [ 'Start Balance', 'End Balance', 'Annualized Return (CAGR)', 'Standard Deviation (Annualized)', 'Best Year', 'Worst Year', 'Maximum Drawdown', 'Sharpe Ratio', 'Sortino Ratio', 'Benchmark Correlation' ], f'{portfolio_a["name"]}': [ metrics_a['Start Balance'], metrics_a['End Balance'], metrics_a['Annualized Return (CAGR)'], metrics_a['Standard Deviation (Annualized)'], metrics_a['Best Year'], metrics_a['Worst Year'], metrics_a['Maximum Drawdown'], metrics_a['Sharpe Ratio'], metrics_a['Sortino Ratio'], metrics_a['Benchmark Correlation'] ], f'{portfolio_b["name"]}': [ metrics_b['Start Balance'], metrics_b['End Balance'], metrics_b['Annualized Return (CAGR)'], metrics_b['Standard Deviation (Annualized)'], metrics_b['Best Year'], metrics_b['Worst Year'], metrics_b['Maximum Drawdown'], metrics_b['Sharpe Ratio'], metrics_b['Sortino Ratio'], metrics_b['Benchmark Correlation'] ] } performance_df_stats = pd.DataFrame(performance_data_stats).set_index('Metric') st.table(performance_df_stats) with tabs[2]: st.header("📋 Detail Comparisons") with st.container(): st.subheader("🧮 Advanced Metrics") performance_data_advanced = { 'Metric': list(metrics_a.keys()), f'{portfolio_a["name"]}': list(metrics_a.values()), f'{portfolio_b["name"]}': list(metrics_b.values()) } performance_df_advanced = pd.DataFrame(performance_data_advanced).set_index('Metric') # Replace NaN with empty strings for better visualization performance_df_advanced = performance_df_advanced.replace(np.nan, "") # Drop rows where both Portfolio A and Portfolio B values are NaN performance_df_advanced_clean = performance_df_advanced.dropna(how='all', subset=[f'{portfolio_a["name"]}', f'{portfolio_b["name"]}']) st.table(performance_df_advanced_clean) st.markdown("---") st.write("**Note:** Some metrics may be specific to certain portfolios or may not be directly comparable. Ensure to interpret the metrics in the context of each portfolio's strategy and objectives.") st.subheader("🔍 Risk Factor Attribution Analysis") # Define date range based on the overlapping index start_date = common_dates.min().strftime('%Y-%m-%d') end_date = common_dates.max().strftime('%Y-%m-%d') # Fetch actual factor data factors = fetch_fama_french_factors(start_date, end_date) # Ensure factors are fetched if factors.empty: st.write("Failed to retrieve factor data.") else: # Align factors frequency with portfolios if isinstance(returns_a.index, pd.DatetimeIndex): if returns_a.index.freq is None: inferred_freq = pd.infer_freq(returns_a.index) if inferred_freq is None: inferred_freq = 'D' # Set default frequency to daily else: inferred_freq = returns_a.index.freq try: factors = factors.asfreq(inferred_freq, method='ffill') except TypeError as e: st.error(f"Error setting frequency for factors: {e}") st.stop() else: st.error("Returns index is not a DatetimeIndex.") st.stop() # Calculate Attribution for Portfolio A attribution_a, error_a = calculate_risk_factor_attribution(returns_a, factors) # Calculate Attribution for Portfolio B attribution_b, error_b = calculate_risk_factor_attribution(returns_b, factors) if error_a or error_b: st.error("Risk factor attribution analysis is unavailable for one or both portfolios.") else: if attribution_a.empty or attribution_b.empty: st.write("Risk factor attribution analysis is unavailable for one or both portfolios.") else: st.write(f"**Risk Factor Attribution for {portfolio_a['name']}:**") st.table(attribution_a) fig_attribution_a = px.bar( attribution_a, x='Factor', y='Contribution (%)', title=f'Risk Factor Attribution for {portfolio_a["name"]}', labels={'Contribution (%)': 'Contribution (%)'}, template='plotly_dark' ) st.plotly_chart(fig_attribution_a, use_container_width=True) st.write(f"**Risk Factor Attribution for {portfolio_b['name']}:**") st.table(attribution_b) fig_attribution_b = px.bar( attribution_b, x='Factor', y='Contribution (%)', title=f'Risk Factor Attribution for {portfolio_b["name"]}', labels={'Contribution (%)': 'Contribution (%)'}, template='plotly_dark' ) st.plotly_chart(fig_attribution_b, use_container_width=True) # Combined Bar Chart for Comparison combined_attribution = pd.concat([ attribution_a.set_index('Factor')['Contribution (%)'], attribution_b.set_index('Factor')['Contribution (%)'] ], axis=1) combined_attribution.columns = [portfolio_a['name'], portfolio_b['name']] combined_attribution = combined_attribution.fillna(0) st.markdown(f"### 📊 Risk Factor Attribution Comparison") fig_combined_attribution = px.bar( combined_attribution, x=combined_attribution.index, y=combined_attribution.columns, title='Risk Factor Attribution Comparison', labels={'value': 'Contribution (%)', 'Factor': 'Risk Factor'}, template='plotly_dark', barmode='group' ) st.plotly_chart(fig_combined_attribution, use_container_width=True) with tabs[3]: st.header("📉 Detailed Drawdowns") st.markdown("### 📈 Drawdowns for Portfolio A") portfolio_drawdowns = get_drawdown_details(cum_returns_a) if portfolio_drawdowns: portfolio_drawdowns_df = pd.DataFrame(portfolio_drawdowns) st.table(portfolio_drawdowns_df) else: st.write("No drawdowns detected for Portfolio A.") st.markdown("### 📈 Drawdowns for Portfolio B") portfolio_b_drawdowns = get_drawdown_details(cum_returns_b) if portfolio_b_drawdowns: portfolio_b_drawdowns_df = pd.DataFrame(portfolio_b_drawdowns) st.table(portfolio_b_drawdowns_df) else: st.write("No drawdowns detected for Portfolio B.") with tabs[4]: st.header("📊 Visualizations") if not cum_returns_a.empty and not cum_returns_b.empty: plot_growth_comparison(cum_returns_a, cum_returns_b, labels=[portfolio_a['name'], portfolio_b['name']]) else: st.warning("Insufficient data to display Growth Comparison. Ensure both portfolios have data.") portfolio_a_drawdown_series = (cum_returns_a / cum_returns_a.expanding().max() - 1) * 100 portfolio_b_drawdown_series = (cum_returns_b / cum_returns_b.expanding().max() - 1) * 100 plot_drawdown_comparison(portfolio_a_drawdown_series, portfolio_b_drawdown_series, labels=[portfolio_a['name'], portfolio_b['name']]) st.subheader("📈 Compound Annual Growth Rate (CAGR) Over Time") if selected_time_frames: plot_cagr_comparison(cum_returns_a, cum_returns_b, time_frames=selected_time_frames) else: st.warning("Please select at least one time frame for CAGR.") # Box Plot for Returns Distribution st.subheader("📦 Returns Distribution Box Plot") # For portfolio A if isinstance(asset_returns_a, pd.DataFrame): # Ensure the index is named 'Date' if asset_returns_a.index.name != 'Date': asset_returns_a = asset_returns_a.copy() asset_returns_a.index.name = 'Date' melted_returns_a = asset_returns_a.reset_index().melt(id_vars='Date', var_name='Asset', value_name='Return') fig_box_plot_a = px.box( melted_returns_a, x='Asset', y='Return', title='Returns Distribution Box Plot - Portfolio A', labels={'Return': 'Returns', 'Asset': 'Asset'}, points='all', hover_data=['Return'], template='plotly_dark', color='Asset', color_discrete_sequence=px.colors.qualitative.Set3 ) st.plotly_chart(fig_box_plot_a, use_container_width=True) st.markdown("**Interpretation:** The box plot visualizes the distribution of returns for each asset in Portfolio A. The boxes represent the interquartile range (IQR), the line inside the box indicates the median, and the whiskers show the range of the data. Outliers are displayed as individual points.") elif isinstance(asset_returns_a, pd.Series): # Ensure the index is named 'Date' if asset_returns_a.index.name != 'Date': asset_returns_a = asset_returns_a.copy() asset_returns_a.index.name = 'Date' melted_returns_a = asset_returns_a.reset_index().rename(columns={'Date': 'Date', 'Return': 'Return'}) fig_box_plot_a = px.box( melted_returns_a, y='Return', title='Returns Distribution Box Plot - Portfolio A', labels={'Return': 'Returns'}, points='all', hover_data=['Return'], template='plotly_dark' ) st.plotly_chart(fig_box_plot_a, use_container_width=True) st.markdown("**Interpretation:** The box plot visualizes the distribution of returns for Portfolio A. The box represents the interquartile range (IQR), the line inside the box indicates the median, and the whiskers show the range of the data. Outliers are displayed as individual points.") else: st.warning("Returns data for Portfolio A is neither a DataFrame nor a Series.") # For portfolio B if isinstance(asset_returns_b, pd.DataFrame): # Ensure the index is named 'Date' if asset_returns_b.index.name != 'Date': asset_returns_b = asset_returns_b.copy() asset_returns_b.index.name = 'Date' melted_returns_b = asset_returns_b.reset_index().melt(id_vars='Date', var_name='Asset', value_name='Return') fig_box_plot_b = px.box( melted_returns_b, x='Asset', y='Return', title='Returns Distribution Box Plot - Portfolio B', labels={'Return': 'Returns', 'Asset': 'Asset'}, points='all', hover_data=['Return'], template='plotly_dark', color='Asset', color_discrete_sequence=px.colors.qualitative.Set3 ) st.plotly_chart(fig_box_plot_b, use_container_width=True) st.markdown("**Interpretation:** The box plot visualizes the distribution of returns for each asset in Portfolio B. The boxes represent the interquartile range (IQR), the line inside the box indicates the median, and the whiskers show the range of the data. Outliers are displayed as individual points.") elif isinstance(asset_returns_b, pd.Series): # Ensure the index is named 'Date' if asset_returns_b.index.name != 'Date': asset_returns_b = asset_returns_b.copy() asset_returns_b.index.name = 'Date' melted_returns_b = asset_returns_b.reset_index().rename(columns={'Date': 'Date', 'Return': 'Return'}) fig_box_plot_b = px.box( melted_returns_b, y='Return', title='Returns Distribution Box Plot - Portfolio B', labels={'Return': 'Returns'}, points='all', hover_data=['Return'], template='plotly_dark' ) st.plotly_chart(fig_box_plot_b, use_container_width=True) st.markdown("**Interpretation:** The box plot visualizes the distribution of returns for Portfolio B. The box represents the interquartile range (IQR), the line inside the box indicates the median, and the whiskers show the range of the data. Outliers are displayed as individual points.") else: st.warning("Returns data for Portfolio B is neither a DataFrame nor a Series.") # Correlation Heatmap Comparison st.subheader("🔥 Correlation Heatmap Comparison") plot_correlation_heatmap_comparison(asset_returns_a, asset_returns_b) # Efficient Frontier Comparison st.subheader("📈 Efficient Frontier Comparison") plot_efficient_frontier_comparison(asset_returns_a, asset_returns_b, num_portfolios=1000, rf=portfolio_a['rf_rate']) # Risk-Return Attribution Comparison st.subheader("🔍 Risk-Return Attribution Comparison") plot_risk_return_attribution_comparison( returns_a, weights_a, returns_b, weights_b, label_a=portfolio_a['name'], label_b=portfolio_b['name'] ) # Recommendations st.markdown("### 💡 Recommendations") recommendations_a = generate_recommendations( allocations=[alloc for alloc in portfolio_a['allocations'] if alloc > 0], available_selected=[ticker for ticker in available_a if portfolio_a['allocations'][available_a.index(ticker)] > 0] ) recommendations_b = generate_recommendations( allocations=[alloc for alloc in portfolio_b['allocations'] if alloc > 0], available_selected=[ticker for ticker in available_b if portfolio_b['allocations'][available_b.index(ticker)] > 0] ) if recommendations_a: st.write(f"**{portfolio_a['name']} Recommendations:**") for rec in recommendations_a: st.write(rec) else: st.success(f"{portfolio_a['name']} allocations are well-balanced!") if recommendations_b: st.write(f"**{portfolio_b['name']} Recommendations:**") for rec in recommendations_b: st.write(rec) else: st.success(f"{portfolio_b['name']} allocations are well-balanced!") # Final Score st.markdown("### 📝 Final Score") portfolio_score_a = calculate_final_score(metrics_a, metrics_b) portfolio_score_b = calculate_final_score(metrics_b, metrics_a) st.write(f"**{portfolio_a['name']}:** {portfolio_score_a:.2f} / 100") st.write(f"**{portfolio_b['name']}:** {portfolio_score_b:.2f} / 100") # Store results st.session_state.backtest_results = { 'returns_a': returns_a, 'cum_returns_a': cum_returns_a, 'weights_a': weights_a, 'price_data_a': price_data_a[available_a], 'metrics_a': metrics_a, 'returns_b': returns_b, 'cum_returns_b': cum_returns_b, 'weights_b': weights_b, 'price_data_b': price_data_b[available_b], 'metrics_b': metrics_b, 'performance_df_stats_a': performance_df_stats.loc[:, portfolio_a['name']], 'performance_df_advanced_a': performance_df_advanced_clean[[f'{portfolio_a["name"]}']], 'performance_df_stats_b': performance_df_stats.loc[:, portfolio_b['name']], 'performance_df_advanced_b': performance_df_advanced_clean[[f'{portfolio_b["name"]}']] } st.success("Backtest completed successfully!") else: st.warning("Please add at least one portfolio to run backtest.")enhance the above code with the below, output full code to me, no need explanation:
components/run_backtest.py
def run_backtest_ui(): # ... [existing code] ...
if run: with st.spinner("Running backtest..."): if comparison_type == "Portfolio vs Benchmark": # ... [existing code for Portfolio vs Benchmark] ... if not benchmark_data.empty: # ... [download benchmark data] ... benchmark_cum_returns = (1 + benchmark_returns).cumprod() benchmark_metrics = calculate_portfolio_metrics( benchmark_returns, benchmark_cum_returns, portfolio['rf_rate'], None ) else: benchmark_returns = None benchmark_cum_returns = pd.Series(dtype=float) # Ensure it's defined benchmark_metrics = { 'Start Balance': "N/A", 'End Balance': "N/A", 'Annualized Return (CAGR)': "N/A", 'Best Year': "N/A", 'Worst Year': "N/A", 'Arithmetic Mean (Monthly)': "N/A", 'Arithmetic Mean (Annualized)': "N/A", 'Geometric Mean (Monthly)': "N/A", 'Geometric Mean (Annualized)': "N/A", 'Standard Deviation (Monthly)': "N/A", 'Standard Deviation (Annualized)': "N/A", 'Downside Deviation (Monthly)': "N/A", 'Maximum Drawdown': "N/A", 'Sharpe Ratio': "N/A", 'Sortino Ratio': "N/A", 'Gain/Loss Ratio': "N/A", 'Skewness': "N/A", 'Excess Kurtosis': "N/A", 'Safe Withdrawal Rate': "N/A", 'Perpetual Withdrawal Rate': "N/A", 'Positive Periods': "N/A", 'Benchmark Correlation': np.nan, 'Beta': np.nan, 'R2': np.nan } portfolio_metrics = calculate_portfolio_metrics( returns, cum_returns, portfolio['rf_rate'], benchmark_returns ) # ... [rest of your code] ... elif comparison_type == "Portfolio vs Portfolio" and portfolio1 and portfolio2 and portfolio1 != portfolio2: # ... [existing code for Portfolio vs Portfolio] ... # Ensure cum_returns_a and cum_returns_b are defined cum_returns_a = cum_returns_a if 'cum_returns_a' in locals() else pd.Series(dtype=float) cum_returns_b = cum_returns_b if 'cum_returns_b' in locals() else pd.Series(dtype=float) # ... [rest of your code] ... else: st.warning("Please add at least one portfolio to run backtest.") - Assistant
# components/run_backtest.py import streamlit as st import pandas as pd import numpy as np import plotly.express as px # Importing all necessary functions from utils, metrics, and plots from utils import ( download_data, generate_recommendations, backtest, fetch_fama_french_factors, ) from metrics import ( calculate_portfolio_metrics, calculate_final_score, calculate_risk_factor_attribution, get_drawdown_details ) from plots import ( plot_growth_comparison, plot_drawdown_comparison, plot_cagr_over_time, plot_allocation_pie, plot_correlation_heatmap, plot_risk_return_attribution, plot_rolling_metrics, plot_correlation_heatmap_comparison, plot_cagr_comparison, plot_allocation_comparison, plot_rolling_metrics_comparison, plot_risk_return_attribution_comparison, plot_efficient_frontier_comparison ) def run_backtest_ui(): # Initialize portfolios in session state if not already initialized if 'portfolios' not in st.session_state: st.session_state.portfolios = [] if st.session_state.portfolios: with st.form("compare_form"): st.subheader("🔍 Select Portfolios to Compare") comparison_type = st.selectbox( "Comparison Type", ["Portfolio vs Benchmark", "Portfolio vs Portfolio"] ) portfolio_names = [p['name'] for p in st.session_state.portfolios] if comparison_type == "Portfolio vs Benchmark": portfolio1 = st.selectbox("Select Portfolio", portfolio_names) portfolio2 = None else: portfolio1 = st.selectbox("Select First Portfolio", portfolio_names, key="p1") portfolio2 = st.selectbox("Select Second Portfolio", portfolio_names, key="p2") if portfolio1 == portfolio2: st.warning("Please select two different portfolios for comparison.") st.subheader("⚙️ Visualizations Settings") selected_time_frames = st.multiselect( "Select Time Frames for CAGR", options=['Weekly', 'Monthly', 'Quarterly', 'Annually'], default=['Annually'], key="selected_time_frames", help="Choose one or more time frames to view CAGR over different horizons." ) selected_rolling_periods = st.multiselect( "Select Rolling Periods (Days)", options=[30, 90, 180, 252], default=[252], key="selected_rolling_periods", help="Choose one or more periods to view rolling metrics." ) run = st.form_submit_button("Run Backtest") if run: with st.spinner("Running backtest..."): if comparison_type == "Portfolio vs Benchmark": # Handle Portfolio vs Benchmark try: portfolio = next(p for p in st.session_state.portfolios if p['name'] == portfolio1) except StopIteration: st.error("Selected portfolio not found.") return price_data = download_data( portfolio['selected'], portfolio['start_date'], portfolio['end_date'] ) if price_data.empty: st.error("No price data available for the selected portfolio.") else: available_selected = [ticker for ticker in portfolio['selected'] if ticker in price_data.columns] missing_selected = list(set(portfolio['selected']) - set(available_selected)) if missing_selected: st.warning(f"Excluded tickers with no data: {', '.join(missing_selected)}") if not available_selected: st.error( "No selected tickers have available data for the chosen date range. " "Please ensure that the ticker symbols are correct and data is available for the specified period." ) else: # Extract corresponding allocations original_allocations = portfolio.get('allocations', [0.0]*len(portfolio.get('selected', []))) adjusted_allocations = [original_allocations[i] for i, ticker in enumerate(portfolio.get('selected', [])) if ticker in available_selected] # Error Handling for Allocation-Axis if len(adjusted_allocations) != len(available_selected): st.error("Mismatch between allocations and available assets after filtering.") return # Normalize allocations to sum to 1 weights = np.array(adjusted_allocations) / 100 total_alloc = weights.sum() if not np.isclose(total_alloc, 1.0, atol=1e-4): if total_alloc == 0: st.error("Total allocations sum to 0. Cannot adjust allocations.") return st.warning("Allocations do not sum to 100%. Adjusting allocations proportionally.") weights = weights / total_alloc # Final check to ensure weights match the number of assets if len(weights) != len(available_selected): st.error("Final allocation weights do not match the number of available assets.") return # Calculate per-asset returns asset_returns = price_data[available_selected].pct_change().dropna() # Run backtest to get portfolio returns returns, cum_returns = backtest( weights, price_data[available_selected], portfolio['rebalance_freq'], portfolio['broker_fee'], debug=False ) # Align asset returns with portfolio returns common_index = returns.index.intersection(asset_returns.index) asset_returns = asset_returns.loc[common_index] returns = returns.loc[common_index] cum_returns = cum_returns.loc[common_index] if cum_returns.empty: st.error("Cumulative returns are empty. Check the data and allocations.") else: benchmark_symbol = portfolio['benchmark_symbol'] benchmark_data = download_data([benchmark_symbol], portfolio['start_date'], portfolio['end_date']) if benchmark_symbol not in benchmark_data.columns: st.error(f"The selected benchmark symbol '{benchmark_symbol}' does not have available data for the chosen period.") st.stop() else: st.success(f"Benchmark '{benchmark_symbol}' data successfully downloaded and will be used for comparison.") if not benchmark_data.empty: benchmark_returns = benchmark_data[benchmark_symbol].pct_change().dropna() benchmark_returns = benchmark_returns.reindex(returns.index, method='ffill').dropna() common_index_benchmark = returns.index.intersection(benchmark_returns.index) if common_index_benchmark.empty: st.error("No overlapping dates between portfolio returns and benchmark returns after alignment.") st.stop() returns = returns.loc[common_index_benchmark] cum_returns = cum_returns.loc[common_index_benchmark] asset_returns = asset_returns.loc[common_index_benchmark] benchmark_returns = benchmark_returns.loc[common_index_benchmark] benchmark_cum_returns = (1 + benchmark_returns).cumprod() benchmark_metrics = calculate_portfolio_metrics( benchmark_returns, benchmark_cum_returns, portfolio['rf_rate'], None ) else: benchmark_returns = None benchmark_cum_returns = pd.Series(dtype=float) # Ensure it's defined benchmark_metrics = { 'Start Balance': "N/A", 'End Balance': "N/A", 'Annualized Return (CAGR)': "N/A", 'Best Year': "N/A", 'Worst Year': "N/A", 'Arithmetic Mean (Monthly)': "N/A", 'Arithmetic Mean (Annualized)': "N/A", 'Geometric Mean (Monthly)': "N/A", 'Geometric Mean (Annualized)': "N/A", 'Standard Deviation (Monthly)': "N/A", 'Standard Deviation (Annualized)': "N/A", 'Downside Deviation (Monthly)': "N/A", 'Maximum Drawdown': "N/A", 'Sharpe Ratio': "N/A", 'Sortino Ratio': "N/A", 'Gain/Loss Ratio': "N/A", 'Skewness': "N/A", 'Excess Kurtosis': "N/A", 'Safe Withdrawal Rate': "N/A", 'Perpetual Withdrawal Rate': "N/A", 'Positive Periods': "N/A", 'Benchmark Correlation': np.nan, 'Beta': np.nan, 'R2': np.nan } portfolio_metrics = calculate_portfolio_metrics( returns, cum_returns, portfolio['rf_rate'], benchmark_returns ) # Dashboard Header with Key Stats with st.container(): st.markdown("### 🔑 Key Metrics") key_metrics = { 'Annualized Return (CAGR)': portfolio_metrics.get('Annualized Return (CAGR)', "N/A"), 'Sharpe Ratio': portfolio_metrics.get('Sharpe Ratio', "N/A"), 'Maximum Drawdown': portfolio_metrics.get('Maximum Drawdown', "N/A") } cols = st.columns(len(key_metrics)) for col, (metric, value) in zip(cols, key_metrics.items()): with col: st.metric(label=metric, value=value) # Create Tabs for Organized Sections tabs = st.tabs(["Overview", "Performance Statistics", "Advanced Metrics", "Drawdowns", "Visualizations"]) with tabs[0]: st.header("📈 Portfolio Performance Overview") st.write(f"**Portfolio Name:** {portfolio['name']}") st.write(f"**Start Date:** {portfolio['start_date'].strftime('%Y-%m-%d')}") st.write(f"**End Date:** {portfolio['end_date'].strftime('%Y-%m-%d')}") st.write(f"**Benchmark:** {portfolio['benchmark_symbol']}") with tabs[1]: st.header("📊 Performance Statistics") with st.container(): st.subheader("🛠️ Basic Metrics") performance_data_stats = { 'Metric': [ 'Start Balance', 'End Balance', 'Annualized Return (CAGR)', 'Standard Deviation (Annualized)', 'Best Year', 'Worst Year', 'Maximum Drawdown', 'Sharpe Ratio', 'Sortino Ratio', 'Benchmark Correlation' ], 'Portfolio': [ portfolio_metrics['Start Balance'], portfolio_metrics['End Balance'], portfolio_metrics['Annualized Return (CAGR)'], portfolio_metrics['Standard Deviation (Annualized)'], portfolio_metrics['Best Year'], portfolio_metrics['Worst Year'], portfolio_metrics['Maximum Drawdown'], portfolio_metrics['Sharpe Ratio'], portfolio_metrics['Sortino Ratio'], portfolio_metrics['Benchmark Correlation'] ], 'Benchmark': [ benchmark_metrics.get('Start Balance', "N/A"), benchmark_metrics.get('End Balance', "N/A"), benchmark_metrics.get('Annualized Return (CAGR)', "N/A"), benchmark_metrics.get('Standard Deviation (Annualized)', "N/A"), benchmark_metrics.get('Best Year', "N/A"), benchmark_metrics.get('Worst Year', "N/A"), benchmark_metrics.get('Maximum Drawdown', "N/A"), benchmark_metrics.get('Sharpe Ratio', "N/A"), benchmark_metrics.get('Sortino Ratio', "N/A"), benchmark_metrics.get('Benchmark Correlation', "N/A") ] } performance_df_stats = pd.DataFrame(performance_data_stats).set_index('Metric') # Format metrics to two decimal places def format_value(val): if isinstance(val, str): return val elif isinstance(val, float) or isinstance(val, int): return f"{val:.2f}" else: return "N/A" performance_df_stats_formatted = performance_df_stats.applymap(format_value) st.table(performance_df_stats_formatted) with tabs[2]: st.header("📋 Detail Comparisons") with st.container(): st.subheader("🧮 Advanced Metrics") performance_data_advanced = { 'Metric': list(portfolio_metrics.keys()), 'Portfolio': list(portfolio_metrics.values()), 'Benchmark': list(benchmark_metrics.values()) } performance_df_advanced = pd.DataFrame(performance_data_advanced).set_index('Metric') # Replace NaN with empty strings for better visualization performance_df_advanced = performance_df_advanced.replace(np.nan, "") # Drop rows where both Portfolio and Benchmark values are NaN performance_df_advanced_clean = performance_df_advanced.dropna(how='all') # Format metrics to two decimal places performance_df_advanced_clean = performance_df_advanced_clean.applymap(format_value) st.table(performance_df_advanced_clean) st.markdown("---") st.write("**Note:** Some metrics in the benchmark column are empty because they are portfolio-specific measurements that can't be calculated for the benchmark alone...") st.subheader("🔍 Risk Factor Attribution Analysis") # Define date range based on the overlapping index start_date = returns.index.min().strftime('%Y-%m-%d') end_date = returns.index.max().strftime('%Y-%m-%d') # Fetch actual factor data factors = fetch_fama_french_factors(start_date, end_date) # Ensure factors are fetched if factors.empty: st.write("Failed to retrieve factor data.") else: # Align factors frequency with portfolios if isinstance(returns.index, pd.DatetimeIndex): if returns.index.freq is None: inferred_freq = pd.infer_freq(returns.index) if inferred_freq is None: inferred_freq = 'D' # Set default frequency to daily else: inferred_freq = returns.index.freq try: factors = factors.asfreq(inferred_freq, method='ffill') except TypeError as e: st.error(f"Error setting frequency for factors: {e}") st.stop() else: st.error("Returns index is not a DatetimeIndex.") st.stop() # Calculate Attribution for Portfolio attribution, error = calculate_risk_factor_attribution(returns, factors) if error: st.error("Risk factor attribution analysis is unavailable for the portfolio.") else: if attribution.empty: st.write("Risk factor attribution analysis is unavailable for the portfolio.") else: st.write(f"### Risk Factor Attribution for {portfolio['name']}") st.table(attribution.fillna(0)) # Visualization fig_attribution = px.bar( attribution, x='Factor', y='Contribution (%)', title='Risk Factor Attribution', template='plotly_dark' ) st.plotly_chart(fig_attribution, use_container_width=True) with tabs[3]: st.header("📉 Detailed Drawdowns") st.markdown("### 📈 Drawdowns for Portfolio") portfolio_drawdowns = get_drawdown_details(cum_returns) if portfolio_drawdowns: portfolio_drawdowns_df = pd.DataFrame(portfolio_drawdowns) st.table(portfolio_drawdowns_df) else: st.write("No drawdowns detected for the portfolio.") st.markdown("### 📈 Drawdowns for Benchmark") benchmark_drawdowns = get_drawdown_details(benchmark_cum_returns) if benchmark_drawdowns: benchmark_drawdowns_df = pd.DataFrame(benchmark_drawdowns) st.table(benchmark_drawdowns_df) else: st.write("No drawdowns detected for the benchmark.") with tabs[4]: st.header("📊 Visualizations") if not cum_returns.empty and not benchmark_cum_returns.empty: plot_growth_comparison(cum_returns, benchmark_cum_returns, labels=["Portfolio", "Benchmark"]) else: st.warning("Insufficient data to display Growth Comparison. Ensure both portfolio and benchmark have data.") portfolio_drawdown_series = (cum_returns / cum_returns.expanding().max() - 1) * 100 benchmark_drawdown_series = (benchmark_cum_returns / benchmark_cum_returns.expanding().max() - 1) * 100 plot_drawdown_comparison(portfolio_drawdown_series, benchmark_drawdown_series, labels=["Portfolio", "Benchmark"]) st.subheader("📈 Compound Annual Growth Rate (CAGR) Over Time") if selected_time_frames: plot_cagr_over_time(cum_returns, time_frames=selected_time_frames, label="Portfolio") else: st.warning("Please select at least one time frame for CAGR.") # Box Plot for Returns Distribution st.subheader("📦 Returns Distribution Box Plot") if isinstance(asset_returns, pd.DataFrame): # Assuming the index is named 'Date' if asset_returns.index.name != 'Date': asset_returns = asset_returns.copy() asset_returns.index.name = 'Date' melted_returns = asset_returns.reset_index().melt(id_vars='Date', var_name='Asset', value_name='Return') fig_box_plot = px.box( melted_returns, x='Asset', y='Return', title='Returns Distribution Box Plot', labels={'Return': 'Returns', 'Asset': 'Asset'}, points='all', hover_data=['Return'], template='plotly_dark', color='Asset', color_discrete_sequence=px.colors.qualitative.Set3 ) st.plotly_chart(fig_box_plot, use_container_width=True) st.markdown("**Interpretation:** The box plot visualizes the distribution of returns for each asset in the portfolio. The boxes represent the interquartile range (IQR), the line inside the box indicates the median, and the whiskers show the range of the data. Outliers are displayed as individual points.") elif isinstance(asset_returns, pd.Series): # Assuming the index is named 'Date' if asset_returns.index.name != 'Date': asset_returns = asset_returns.copy() asset_returns.index.name = 'Date' melted_returns = asset_returns.reset_index().rename(columns={'Date': 'Date', 0: 'Return'}) fig_box_plot = px.box( melted_returns, y='Return', title='Returns Distribution Box Plot', labels={'Return': 'Returns'}, points='all', hover_data=['Return'], template='plotly_dark' ) st.plotly_chart(fig_box_plot, use_container_width=True) st.markdown("**Interpretation:** The box plot visualizes the distribution of returns for the portfolio. The box represents the interquartile range (IQR), the line inside the box indicates the median, and the whiskers show the range of the data. Outliers are displayed as individual points.") else: st.warning("Returns data is neither a DataFrame nor a Series.") # Heatmap of Correlations Between Assets st.subheader("🔥 Correlation Heatmap of Assets") plot_correlation_heatmap(asset_returns) # Add Risk-Return Attribution Analysis st.subheader("🔍 Risk-Return Attribution Analysis") plot_risk_return_attribution(returns, weights, label='Portfolio') # Cumulative Returns Heatmap st.subheader("🔥 Cumulative Returns Heatmap") try: cum_returns_normalized = cum_returns / cum_returns.expanding().max() fig_cum_heatmap = px.imshow( cum_returns_normalized.to_frame().T, labels=dict(x="Date", y="Portfolio", color="Normalized Cumulative Return"), title="Cumulative Returns Heatmap", aspect="auto", color_continuous_scale='Viridis', template='plotly_dark' ) st.plotly_chart(fig_cum_heatmap, use_container_width=True) st.markdown("**Interpretation:** The heatmap visualizes the normalized cumulative returns over time, allowing for an intuitive comparison of portfolio performance across different periods.") except Exception as e: st.error(f"Error plotting cumulative returns heatmap: {e}") # Portfolio Allocation Pie Chart st.subheader("🥧 Portfolio Allocation Pie Chart") plot_allocation_pie(weights, available_selected, title="Portfolio Allocation", hover_info="percent+name") # Rolling Metrics Chart with User-Defined Periods st.subheader("📉 Rolling Metrics") if selected_rolling_periods: plot_rolling_metrics(returns, windows=selected_rolling_periods, label='Portfolio') else: st.warning("Please select at least one rolling period to display metrics.") # Recommendations st.markdown("### 💡 Recommendations") recommendations = generate_recommendations( allocations=[alloc for alloc in portfolio['allocations'] if alloc > 0], available_selected=[ticker for ticker in available_selected if portfolio['allocations'][available_selected.index(ticker)] > 0] ) if recommendations: for rec in recommendations: st.write(rec) else: st.success("Your portfolio allocations are well-balanced!") # Final Score st.markdown("### 📝 Final Score") skipped_metrics_set = set() portfolio_score = calculate_final_score(portfolio_metrics, benchmark_metrics, global_skipped=skipped_metrics_set) benchmark_score = calculate_final_score(benchmark_metrics, portfolio_metrics, global_skipped=skipped_metrics_set) st.write(f"**Portfolio:** {portfolio_score:.2f} / 100") st.write(f"**Benchmark:** {benchmark_score:.2f} / 100") # Show skipped metrics once if skipped_metrics_set: st.warning(f"Skipped metrics due to invalid values: {', '.join(skipped_metrics_set)}") # Store results st.session_state.backtest_results = { 'returns': returns, 'cum_returns': cum_returns, 'weights_a': weights, 'price_data': price_data[available_selected], 'metrics': portfolio_metrics, 'benchmark_metrics': benchmark_metrics, 'performance_df_stats': performance_df_stats_formatted, 'performance_df_advanced': performance_df_advanced_clean, # Corrected to use the cleaned DataFrame 'benchmark_cum_returns': benchmark_cum_returns } elif comparison_type == "Portfolio vs Portfolio" and portfolio1 and portfolio2 and portfolio1 != portfolio2: # Handle Portfolio vs Portfolio try: portfolio_a = next(p for p in st.session_state.portfolios if p['name'] == portfolio1) portfolio_b = next(p for p in st.session_state.portfolios if p['name'] == portfolio2) except StopIteration: st.error("One or both selected portfolios were not found.") return # Initialize cum_returns_a and cum_returns_b to prevent UnboundLocalError cum_returns_a = pd.Series(dtype=float) cum_returns_b = pd.Series(dtype=float) # Backtest Portfolio A price_data_a = download_data( portfolio_a['selected'], portfolio_a['start_date'], portfolio_a['end_date'] ) # Backtest Portfolio B price_data_b = download_data( portfolio_b['selected'], portfolio_b['start_date'], portfolio_b['end_date'] ) if price_data_a.empty or price_data_b.empty: st.error("No price data available for one or both selected portfolios.") else: # Process Portfolio A available_a = [ticker for ticker in portfolio_a['selected'] if ticker in price_data_a.columns] missing_a = list(set(portfolio_a['selected']) - set(available_a)) if missing_a: st.warning(f"Excluded tickers from {portfolio_a['name']} with no data: {', '.join(missing_a)}") if not available_a: st.error(f"No selected tickers have available data for the portfolio '{portfolio_a['name']}'.") return # Extract corresponding allocations for Portfolio A original_allocations_a = portfolio_a.get('allocations', [0.0]*len(portfolio_a.get('selected', []))) adjusted_allocations_a = [original_allocations_a[i] for i, ticker in enumerate(portfolio_a.get('selected', [])) if ticker in available_a] if len(adjusted_allocations_a) != len(available_a): st.error(f"Mismatch between allocations and available assets after filtering for '{portfolio_a['name']}'.") return # Normalize allocations to sum to 1 weights_a = np.array(adjusted_allocations_a) / 100 total_alloc_a = weights_a.sum() if not np.isclose(total_alloc_a, 1.0, atol=1e-4): if total_alloc_a == 0: st.error(f"Total allocations for '{portfolio_a['name']}' sum to 0. Cannot adjust allocations.") return st.warning(f"Allocations for '{portfolio_a['name']}' do not sum to 100%. Adjusting allocations proportionally.") weights_a = weights_a / total_alloc_a # Calculate per-asset returns for Portfolio A asset_returns_a = price_data_a[available_a].pct_change().dropna() # Run backtest for Portfolio A returns_a, cum_returns_a = backtest( weights_a, price_data_a[available_a], portfolio_a['rebalance_freq'], portfolio_a['broker_fee'], debug=False ) # Process Portfolio B available_b = [ticker for ticker in portfolio_b['selected'] if ticker in price_data_b.columns] missing_b = list(set(portfolio_b['selected']) - set(available_b)) if missing_b: st.warning(f"Excluded tickers from {portfolio_b['name']} with no data: {', '.join(missing_b)}") if not available_b: st.error(f"No selected tickers have available data for the portfolio '{portfolio_b['name']}'.") return # Extract corresponding allocations for Portfolio B original_allocations_b = portfolio_b.get('allocations', [0.0]*len(portfolio_b.get('selected', []))) adjusted_allocations_b = [original_allocations_b[i] for i, ticker in enumerate(portfolio_b.get('selected', [])) if ticker in available_b] if len(adjusted_allocations_b) != len(available_b): st.error(f"Mismatch between allocations and available assets after filtering for '{portfolio_b['name']}'.") return # Normalize allocations to sum to 1 weights_b = np.array(adjusted_allocations_b) / 100 total_alloc_b = weights_b.sum() if not np.isclose(total_alloc_b, 1.0, atol=1e-4): if total_alloc_b == 0: st.error(f"Total allocations for '{portfolio_b['name']}' sum to 0. Cannot adjust allocations.") return st.warning(f"Allocations for '{portfolio_b['name']}' do not sum to 100%. Adjusting allocations proportionally.") weights_b = weights_b / total_alloc_b # Calculate per-asset returns for Portfolio B asset_returns_b = price_data_b[available_b].pct_change().dropna() # Run backtest for Portfolio B returns_b, cum_returns_b = backtest( weights_b, price_data_b[available_b], portfolio_b['rebalance_freq'], portfolio_b['broker_fee'], debug=False ) # Align the data for comparison common_dates = returns_a.index.intersection(returns_b.index) if common_dates.empty: st.error("No overlapping dates between the two portfolios after alignment.") return cum_returns_a = cum_returns_a.loc[common_dates] cum_returns_b = cum_returns_b.loc[common_dates] returns_a = returns_a.loc[common_dates] returns_b = returns_b.loc[common_dates] asset_returns_a = asset_returns_a.loc[common_dates] asset_returns_b = asset_returns_b.loc[common_dates] # Calculate Metrics metrics_a = calculate_portfolio_metrics( returns_a, cum_returns_a, portfolio_a['rf_rate'], None ) metrics_b = calculate_portfolio_metrics( returns_b, cum_returns_b, portfolio_b['rf_rate'], None ) # Dashboard Header with Key Stats with st.container(): st.markdown("### 🔑 Key Metrics") key_metrics = { 'Annualized Return (CAGR)': ('CAGR', metrics_a.get('Annualized Return (CAGR)', "N/A"), metrics_b.get('Annualized Return (CAGR)', "N/A")), 'Sharpe Ratio': ('Sharpe Ratio', metrics_a.get('Sharpe Ratio', "N/A"), metrics_b.get('Sharpe Ratio', "N/A")), 'Maximum Drawdown': ('Maximum Drawdown', metrics_a.get('Maximum Drawdown', "N/A"), metrics_b.get('Maximum Drawdown', "N/A")) } columns = st.columns(len(key_metrics)) for idx, (metric, (label, value_a, value_b)) in enumerate(key_metrics.items()): with columns[idx]: st.metric(label=f"{label} ({portfolio_a['name']})", value=value_a) st.metric(label=f"{label} ({portfolio_b['name']})", value=value_b) # Create Tabs for Organized Sections tabs = st.tabs(["Overview", "Performance Statistics", "Advanced Metrics", "Drawdowns", "Visualizations"]) with tabs[0]: st.header("📈 Portfolios Performance Overview") # Determine the aligned start and end dates aligned_start_date = common_dates.min().strftime('%Y-%m-%d') aligned_end_date = common_dates.max().strftime('%Y-%m-%d') st.write(f"**Aligned Date Range:** {aligned_start_date} to {aligned_end_date}") st.write(f"**Portfolio A:** {portfolio_a['name']}") st.write(f"**Original Start Date:** {portfolio_a['start_date'].strftime('%Y-%m-%d')}") st.write(f"**Portfolio B:** {portfolio_b['name']}") st.write(f"**Original Start Date:** {portfolio_b['start_date'].strftime('%Y-%m-%d')}") with tabs[1]: st.header("📊 Performance Statistics") with st.container(): st.subheader("🛠️ Basic Metrics") performance_data_stats = { 'Metric': [ 'Start Balance', 'End Balance', 'Annualized Return (CAGR)', 'Standard Deviation (Annualized)', 'Best Year', 'Worst Year', 'Maximum Drawdown', 'Sharpe Ratio', 'Sortino Ratio', 'Benchmark Correlation' ], f'{portfolio_a["name"]}': [ metrics_a['Start Balance'], metrics_a['End Balance'], metrics_a['Annualized Return (CAGR)'], metrics_a['Standard Deviation (Annualized)'], metrics_a['Best Year'], metrics_a['Worst Year'], metrics_a['Maximum Drawdown'], metrics_a['Sharpe Ratio'], metrics_a['Sortino Ratio'], metrics_a['Benchmark Correlation'] ], f'{portfolio_b["name"]}': [ metrics_b['Start Balance'], metrics_b['End Balance'], metrics_b['Annualized Return (CAGR)'], metrics_b['Standard Deviation (Annualized)'], metrics_b['Best Year'], metrics_b['Worst Year'], metrics_b['Maximum Drawdown'], metrics_b['Sharpe Ratio'], metrics_b['Sortino Ratio'], metrics_b['Benchmark Correlation'] ] } performance_df_stats = pd.DataFrame(performance_data_stats).set_index('Metric') st.table(performance_df_stats) with tabs[2]: st.header("📋 Detail Comparisons") with st.container(): st.subheader("🧮 Advanced Metrics") performance_data_advanced = { 'Metric': list(metrics_a.keys()), f'{portfolio_a["name"]}': list(metrics_a.values()), f'{portfolio_b["name"]}': list(metrics_b.values()) } performance_df_advanced = pd.DataFrame(performance_data_advanced).set_index('Metric') # Replace NaN with empty strings for better visualization performance_df_advanced = performance_df_advanced.replace(np.nan, "") # Drop rows where both Portfolio A and Portfolio B values are NaN performance_df_advanced_clean = performance_df_advanced.dropna(how='all', subset=[f'{portfolio_a["name"]}', f'{portfolio_b["name"]}']) st.table(performance_df_advanced_clean) st.markdown("---") st.write("**Note:** Some metrics may be specific to certain portfolios or may not be directly comparable. Ensure to interpret the metrics in the context of each portfolio's strategy and objectives.") st.subheader("🔍 Risk Factor Attribution Analysis") # Define date range based on the overlapping index start_date = common_dates.min().strftime('%Y-%m-%d') end_date = common_dates.max().strftime('%Y-%m-%d') # Fetch actual factor data factors = fetch_fama_french_factors(start_date, end_date) # Ensure factors are fetched if factors.empty: st.write("Failed to retrieve factor data.") else: # Align factors frequency with portfolios if isinstance(returns_a.index, pd.DatetimeIndex): if returns_a.index.freq is None: inferred_freq = pd.infer_freq(returns_a.index) if inferred_freq is None: inferred_freq = 'D' # Set default frequency to daily else: inferred_freq = returns_a.index.freq try: factors = factors.asfreq(inferred_freq, method='ffill') except TypeError as e: st.error(f"Error setting frequency for factors: {e}") st.stop() else: st.error("Returns index is not a DatetimeIndex.") st.stop() # Calculate Attribution for Portfolio A attribution_a, error_a = calculate_risk_factor_attribution(returns_a, factors) # Calculate Attribution for Portfolio B attribution_b, error_b = calculate_risk_factor_attribution(returns_b, factors) if error_a or error_b: st.error("Risk factor attribution analysis is unavailable for one or both portfolios.") else: if attribution_a.empty or attribution_b.empty: st.write("Risk factor attribution analysis is unavailable for one or both portfolios.") else: st.write(f"**Risk Factor Attribution for {portfolio_a['name']}:**") st.table(attribution_a) fig_attribution_a = px.bar( attribution_a, x='Factor', y='Contribution (%)', title=f'Risk Factor Attribution for {portfolio_a["name"]}', labels={'Contribution (%)': 'Contribution (%)'}, template='plotly_dark' ) st.plotly_chart(fig_attribution_a, use_container_width=True) st.write(f"**Risk Factor Attribution for {portfolio_b['name']}:**") st.table(attribution_b) fig_attribution_b = px.bar( attribution_b, x='Factor', y='Contribution (%)', title=f'Risk Factor Attribution for {portfolio_b["name"]}', labels={'Contribution (%)': 'Contribution (%)'}, template='plotly_dark' ) st.plotly_chart(fig_attribution_b, use_container_width=True) # Combined Bar Chart for Comparison combined_attribution = pd.concat([ attribution_a.set_index('Factor')['Contribution (%)'], attribution_b.set_index('Factor')['Contribution (%)'] ], axis=1) combined_attribution.columns = [portfolio_a['name'], portfolio_b['name']] combined_attribution = combined_attribution.fillna(0) st.markdown(f"### 📊 Risk Factor Attribution Comparison") fig_combined_attribution = px.bar( combined_attribution, x=combined_attribution.index, y=combined_attribution.columns, title='Risk Factor Attribution Comparison', labels={'value': 'Contribution (%)', 'Factor': 'Risk Factor'}, template='plotly_dark', barmode='group' ) st.plotly_chart(fig_combined_attribution, use_container_width=True) with tabs[3]: st.header("📉 Detailed Drawdowns") st.markdown("### 📈 Drawdowns for Portfolio A") portfolio_drawdowns = get_drawdown_details(cum_returns_a) if portfolio_drawdowns: portfolio_drawdowns_df = pd.DataFrame(portfolio_drawdowns) st.table(portfolio_drawdowns_df) else: st.write("No drawdowns detected for Portfolio A.") st.markdown("### 📈 Drawdowns for Portfolio B") portfolio_b_drawdowns = get_drawdown_details(cum_returns_b) if portfolio_b_drawdowns: portfolio_b_drawdowns_df = pd.DataFrame(portfolio_b_drawdowns) st.table(portfolio_b_drawdowns_df) else: st.write("No drawdowns detected for Portfolio B.") with tabs[4]: st.header("📊 Visualizations") if not cum_returns_a.empty and not cum_returns_b.empty: plot_growth_comparison(cum_returns_a, cum_returns_b, labels=[portfolio_a['name'], portfolio_b['name']]) else: st.warning("Insufficient data to display Growth Comparison. Ensure both portfolios have data.") portfolio_a_drawdown_series = (cum_returns_a / cum_returns_a.expanding().max() - 1) * 100 portfolio_b_drawdown_series = (cum_returns_b / cum_returns_b.expanding().max() - 1) * 100 plot_drawdown_comparison(portfolio_a_drawdown_series, portfolio_b_drawdown_series, labels=[portfolio_a['name'], portfolio_b['name']]) st.subheader("📈 Compound Annual Growth Rate (CAGR) Over Time") if selected_time_frames: plot_cagr_comparison(cum_returns_a, cum_returns_b, time_frames=selected_time_frames) else: st.warning("Please select at least one time frame for CAGR.") # Box Plot for Returns Distribution st.subheader("📦 Returns Distribution Box Plot") # For portfolio A if isinstance(asset_returns_a, pd.DataFrame): # Ensure the index is named 'Date' if asset_returns_a.index.name != 'Date': asset_returns_a = asset_returns_a.copy() asset_returns_a.index.name = 'Date' melted_returns_a = asset_returns_a.reset_index().melt(id_vars='Date', var_name='Asset', value_name='Return') fig_box_plot_a = px.box( melted_returns_a, x='Asset', y='Return', title='Returns Distribution Box Plot - Portfolio A', labels={'Return': 'Returns', 'Asset': 'Asset'}, points='all', hover_data=['Return'], template='plotly_dark', color='Asset', color_discrete_sequence=px.colors.qualitative.Set3 ) st.plotly_chart(fig_box_plot_a, use_container_width=True) st.markdown("**Interpretation:** The box plot visualizes the distribution of returns for each asset in Portfolio A. The boxes represent the interquartile range (IQR), the line inside the box indicates the median, and the whiskers show the range of the data. Outliers are displayed as individual points.") elif isinstance(asset_returns_a, pd.Series): # Ensure the index is named 'Date' if asset_returns_a.index.name != 'Date': asset_returns_a = asset_returns_a.copy() asset_returns_a.index.name = 'Date' melted_returns_a = asset_returns_a.reset_index().rename(columns={'Date': 'Date', 'Return': 'Return'}) fig_box_plot_a = px.box( melted_returns_a, y='Return', title='Returns Distribution Box Plot - Portfolio A', labels={'Return': 'Returns'}, points='all', hover_data=['Return'], template='plotly_dark' ) st.plotly_chart(fig_box_plot_a, use_container_width=True) st.markdown("**Interpretation:** The box plot visualizes the distribution of returns for Portfolio A. The box represents the interquartile range (IQR), the line inside the box indicates the median, and the whiskers show the range of the data. Outliers are displayed as individual points.") else: st.warning("Returns data for Portfolio A is neither a DataFrame nor a Series.") # For portfolio B if isinstance(asset_returns_b, pd.DataFrame): # Ensure the index is named 'Date' if asset_returns_b.index.name != 'Date': asset_returns_b = asset_returns_b.copy() asset_returns_b.index.name = 'Date' melted_returns_b = asset_returns_b.reset_index().melt(id_vars='Date', var_name='Asset', value_name='Return') fig_box_plot_b = px.box( melted_returns_b, x='Asset', y='Return', title='Returns Distribution Box Plot - Portfolio B', labels={'Return': 'Returns', 'Asset': 'Asset'}, points='all', hover_data=['Return'], template='plotly_dark', color='Asset', color_discrete_sequence=px.colors.qualitative.Set3 ) st.plotly_chart(fig_box_plot_b, use_container_width=True) st.markdown("**Interpretation:** The box plot visualizes the distribution of returns for each asset in Portfolio B. The boxes represent the interquartile range (IQR), the line inside the box indicates the median, and the whiskers show the range of the data. Outliers are displayed as individual points.") elif isinstance(asset_returns_b, pd.Series): # Ensure the index is named 'Date' if asset_returns_b.index.name != 'Date': asset_returns_b = asset_returns_b.copy() asset_returns_b.index.name = 'Date' melted_returns_b = asset_returns_b.reset_index().rename(columns={'Date': 'Date', 'Return': 'Return'}) fig_box_plot_b = px.box( melted_returns_b, y='Return', title='Returns Distribution Box Plot - Portfolio B', labels={'Return': 'Returns'}, points='all', hover_data=['Return'], template='plotly_dark' ) st.plotly_chart(fig_box_plot_b, use_container_width=True) st.markdown("**Interpretation:** The box plot visualizes the distribution of returns for Portfolio B. The box represents the interquartile range (IQR), the line inside the box indicates the median, and the whiskers show the range of the data. Outliers are displayed as individual points.") else: st.warning("Returns data for Portfolio B is neither a DataFrame nor a Series.") # Correlation Heatmap Comparison st.subheader("🔥 Correlation Heatmap Comparison") plot_correlation_heatmap_comparison(asset_returns_a, asset_returns_b) # Efficient Frontier Comparison st.subheader("📈 Efficient Frontier Comparison") plot_efficient_frontier_comparison(asset_returns_a, asset_returns_b, num_portfolios=1000, rf=portfolio_a['rf_rate']) # Risk-Return Attribution Comparison st.subheader("🔍 Risk-Return Attribution Comparison") plot_risk_return_attribution_comparison( returns_a, weights_a, returns_b, weights_b, label_a=portfolio_a['name'], label_b=portfolio_b['name'] ) # Recommendations st.markdown("### 💡 Recommendations") recommendations_a = generate_recommendations( allocations=[alloc for alloc in portfolio_a['allocations'] if alloc > 0], available_selected=[ticker for ticker in available_a if portfolio_a['allocations'][available_a.index(ticker)] > 0] ) recommendations_b = generate_recommendations( allocations=[alloc for alloc in portfolio_b['allocations'] if alloc > 0], available_selected=[ticker for ticker in available_b if portfolio_b['allocations'][available_b.index(ticker)] > 0] ) if recommendations_a: st.write(f"**{portfolio_a['name']} Recommendations:**") for rec in recommendations_a: st.write(rec) else: st.success(f"{portfolio_a['name']} allocations are well-balanced!") if recommendations_b: st.write(f"**{portfolio_b['name']} Recommendations:**") for rec in recommendations_b: st.write(rec) else: st.success(f"{portfolio_b['name']} allocations are well-balanced!") # Final Score st.markdown("### 📝 Final Score") portfolio_score_a = calculate_final_score(metrics_a, metrics_b) portfolio_score_b = calculate_final_score(metrics_b, metrics_a) st.write(f"**{portfolio_a['name']}:** {portfolio_score_a:.2f} / 100") st.write(f"**{portfolio_b['name']}:** {portfolio_score_b:.2f} / 100") # Store results st.session_state.backtest_results = { 'returns_a': returns_a, 'cum_returns_a': cum_returns_a, 'weights_a': weights_a, 'price_data_a': price_data_a[available_a], 'metrics_a': metrics_a, 'returns_b': returns_b, 'cum_returns_b': cum_returns_b, 'weights_b': weights_b, 'price_data_b': price_data_b[available_b], 'metrics_b': metrics_b, 'performance_df_stats_a': performance_df_stats.loc[:, portfolio_a['name']], 'performance_df_advanced_a': performance_df_advanced_clean[[f'{portfolio_a["name"]}']], 'performance_df_stats_b': performance_df_stats.loc[:, portfolio_b['name']], 'performance_df_advanced_b': performance_df_advanced_clean[[f'{portfolio_b["name"]}']] } st.success("Backtest completed successfully!") else: st.warning("Please add at least one portfolio to run backtest.")