Skip to content
TheChatArchiveThe Chat Archive
gpt-4o-2024-08-06· OpenAIAi2 WildChat-4.8M (AI2)

Install required packages !pip install yfinance pandas numpy beautifulsoup4 requests…

  1. User

    Install required packages

    !pip install yfinance pandas numpy beautifulsoup4 requests tqdm deap matplotlib lxml

    Import necessary libraries

    import yfinance as yf import pandas as pd import numpy as np import random from bs4 import BeautifulSoup import requests from tqdm import tqdm import sys import warnings import multiprocessing import matplotlib.pyplot as plt

    from deap import base, creator, tools, algorithms

    Suppress warnings for cleaner output

    warnings.filterwarnings("ignore")

    Set random seed for reproducibility

    RANDOM_SEED = 42 random.seed(RANDOM_SEED) np.random.seed(RANDOM_SEED)

    Function to fetch S&P 500 tickers from Wikipedia

    def get_sp500_tickers(): url = 'https://en.wikipedia.org/wiki/List_of_S%26P_500_companies' response = requests.get(url) if response.status_code != 200: raise Exception("Failed to fetch S&P 500 tickers from Wikipedia.") soup = BeautifulSoup(response.text, "lxml") table = soup.find('table', {'id': 'constituents'}) tickers = [] for row in table.findAll('tr')[1:]: ticker = row.findAll('td')[0].text.strip() # Replace '.' with '-' for tickers like BRK.B ticker = ticker.replace('.', '-') tickers.append(ticker) return tickers

    Function to calculate Maximum Drawdown

    def max_drawdown(series): try: roll_max = series.cummax() drawdown = (series - roll_max) / roll_max return drawdown.min() except: return -0.0

    Function to calculate Sortino Ratio

    def sortino_ratio(returns, target=0): downside = returns[returns < target] if len(downside) == 0: return 0 # No downside risk; assign a neutral value expected_return = returns.mean() * 252 downside_risk = np.sqrt((downside ** 2).mean()) * np.sqrt(252) return (expected_return - target) / downside_risk if downside_risk != 0 else 0

    Function to calculate Conditional Value at Risk (CVaR)

    def conditional_value_at_risk(returns, confidence_level=0.95): if len(returns) == 0: return 0 var = np.percentile(returns, (1 - confidence_level) * 100) cvar = returns[returns <= var].mean() return cvar

    Function to generate portfolio weights within constraints

    def generate_weights(n, lower=0.10, upper=0.20, max_attempts=1000): """ Generates a list of weights that sum to 1.0 with each weight between lower and upper bounds. """ for _ in range(max_attempts): weights = np.random.uniform(lower, upper, n) weights /= weights.sum() if all(lower <= w <= upper for w in weights): return weights raise ValueError("Unable to generate weights within constraints after multiple attempts.")

    Function to label economic cycles

    def label_economic_cycles(dates): recession_periods = [ ('2001-03-01', '2001-11-30'), ('2007-12-01', '2009-06-30'), ('2020-02-01', '2020-04-30') ] labels = [] for date in dates: # Remove timezone information if present if date.tzinfo is not None: date = date.replace(tzinfo=None) label = 'Growth' for start, end in recession_periods: if pd.to_datetime(start) <= date <= pd.to_datetime(end): label = 'Recession' break labels.append(label) return labels

    Parameters

    START_DATE = '2000-01-01' END_DATE = '2024-10-30' NUM_ASSETS = 8 # Number of stocks in the portfolio LOWER_WEIGHT = 0.10 UPPER_WEIGHT = 0.20 RISK_FREE_RATE = 0.017 # Approximate risk-free rate (e.g., 10-year US Treasury yield)

    Step 1: Get S&P 500 tickers

    print("Fetching S&P 500 tickers...") tickers = get_sp500_tickers() print(f"Number of tickers fetched: {len(tickers)}")

    Step 2: Download historical data with dynamic start date

    print("Downloading historical data...") failed_tickers = [] successful_tickers = [] data = pd.DataFrame()

    ticker_first_dates = {}

    for ticker in tqdm(tickers, desc="Downloading tickers"): try: df = yf.download(ticker, start=START_DATE, end=END_DATE, progress=False)['Adj Close'] if df.empty: failed_tickers.append(ticker) else: data[ticker] = df successful_tickers.append(ticker) ticker_first_dates[ticker] = df.first_valid_index() except Exception as e: failed_tickers.append(ticker)

    print(f"\nTotal tickers with successful data download: {len(successful_tickers)}") print(f"Total tickers failed to download: {len(failed_tickers)}") if failed_tickers: print(f"Failed tickers: {failed_tickers}")

    Determine the earliest start date among all successful tickers

    if ticker_first_dates: earliest_date = min(ticker_first_dates.values()) print(f"Earliest available data starts from: {earliest_date.date()}")

    # Adjust the dataset to start from the earliest_date
    data = data.loc[earliest_date:]
    
    # Forward fill to propagate last valid observation
    data.fillna(method='ffill', inplace=True)
    # Backward fill to handle any remaining NaNs at the start
    data.fillna(method='bfill', inplace=True)
    print(f"Data shape after adjusting start date and dropping incomplete data: {data.shape}")
    

    else: print("No data available after processing tickers.") sys.exit()

    If there are not enough tickers, exit

    if len(data.columns) < NUM_ASSETS: print("Not enough tickers with complete data to form a portfolio.") sys.exit()

    Step 3: Calculate daily returns

    returns = data.pct_change().dropna()

    Step 4: Label economic cycles

    print("Labeling economic cycles...") return_dates = returns.index labels = label_economic_cycles(return_dates) labels = pd.Series(labels, index=return_dates) # Convert to Series with matching index

    Step 5: Split data into Training (70%), Validation (15%), Testing (15%)

    split_date_1 = int(len(returns) * 0.70) split_date_2 = int(len(returns) * 0.85)

    train_returns = returns.iloc[:split_date_1] # No 'Economic_Cycle' column train_labels = labels.iloc[:split_date_1] # Use iloc to ensure alignment

    validation_returns = returns.iloc[split_date_1:split_date_2] validation_labels = labels.iloc[split_date_1:split_date_2]

    test_returns = returns.iloc[split_date_2:] test_labels = labels.iloc[split_date_2:]

    print(f"Training set: {train_returns.shape[0]} days") print(f"Validation set: {validation_returns.shape[0]} days") print(f"Testing set: {test_returns.shape[0]} days")

    Calculate compounded multi-year metrics for each set

    def calculate_metrics_multi_year(returns_set, labels_set): metrics = {} # Overall cumulative_return = (1 + returns_set.mean(axis=1)).prod() - 1 metrics['cumulative_return'] = cumulative_return

    # Volatility
    volatility = returns_set.mean(axis=1).std() * np.sqrt(252)
    metrics['volatility'] = volatility
    
    # Sharpe Ratio
    sharpe_ratio = (returns_set.mean(axis=1).mean() * 252 - RISK_FREE_RATE) / (returns_set.mean(axis=1).std() * np.sqrt(252))
    metrics['sharpe_ratio'] = sharpe_ratio
    
    # Sortino Ratio
    sortino = {}
    for cycle in ['Growth', 'Recession']:
        cycle_mask = labels_set == cycle
        cycle_returns = returns_set.loc[cycle_mask].mean(axis=1).dropna()
        sortino_cycle = sortino_ratio(cycle_returns)
        sortino[cycle] = sortino_cycle
    metrics['sortino'] = sortino
    
    # CVaR
    cvar = {}
    for cycle in ['Growth', 'Recession']:
        cycle_mask = labels_set == cycle
        cycle_returns = returns_set.loc[cycle_mask].mean(axis=1).dropna()
        cvar_cycle = conditional_value_at_risk(cycle_returns, confidence_level=0.95)
        cvar[cycle] = cvar_cycle
    metrics['cvar'] = cvar
    
    # Maximum Drawdown
    mdd = {}
    for cycle in ['Growth', 'Recession']:
        cycle_mask = labels_set == cycle
        cycle_returns = returns_set.loc[cycle_mask].mean(axis=1).dropna()
        portfolio_cum_returns = (1 + cycle_returns).cumprod()
        mdd_cycle = max_drawdown(portfolio_cum_returns)
        mdd[cycle] = mdd_cycle
    metrics['max_drawdown'] = mdd
    
    return metrics
    

    train_metrics = calculate_metrics_multi_year(train_returns, train_labels) validation_metrics = calculate_metrics_multi_year(validation_returns, validation_labels) test_metrics = calculate_metrics_multi_year(test_returns, test_labels)

    Define Genetic Algorithm parameters

    POPULATION_SIZE = 500 # Adjusted for memory constraints P_CROSSOVER = 0.8 # Probability for crossover P_MUTATION = 0.2 # Probability for mutating an individual MAX_GENERATIONS = 100 # Increased number of generations for better convergence HALL_OF_FAME_SIZE = 1 # Number of best individuals to keep

    Define the weights for each optimization objective

    WEIGHT_SHARPE = 0.20 WEIGHT_MAX_DRAWDOWN = 0.15 WEIGHT_CUMULATIVE_RETURN = 0.25 WEIGHT_VOLATILITY = 0.10 WEIGHT_SORTINO_GROWTH = 0.10 WEIGHT_SORTINO_RECESSION = 0.05 WEIGHT_CVAR_GROWTH = 0.10 WEIGHT_CVAR_RECESSION = 0.05

    Define the evaluation (fitness) function

    def evaluate_portfolio(individual): selected_tickers = individual[:NUM_ASSETS] weights = individual[NUM_ASSETS:]

    # Ensure all selected tickers are unique
    if len(set(selected_tickers)) != NUM_ASSETS:
        return -np.inf,  # Invalid individual
    
    # Ensure weights sum to 1 and are within constraints
    weights = np.array(weights)
    if not np.isclose(weights.sum(), 1.0):
        return -np.inf,
    if not all(LOWER_WEIGHT <= w <= UPPER_WEIGHT for w in weights):
        return -np.inf,
    
    # Check if all tickers are present in the returns DataFrame
    if not all(ticker in returns.columns for ticker in selected_tickers):
        return -np.inf,  # Invalid individual
    
    # Calculate portfolio metrics using Training Set
    try:
        portfolio_returns_train = train_returns[selected_tickers].dot(weights)
        portfolio_cum_return_train = (1 + portfolio_returns_train).prod() - 1
        portfolio_volatility_train = portfolio_returns_train.std() * np.sqrt(252)
        sharpe_ratio_train = (portfolio_returns_train.mean() * 252 - RISK_FREE_RATE) / portfolio_volatility_train if portfolio_volatility_train != 0 else 0
        sortino_growth_train = sortino_ratio(portfolio_returns_train[train_labels == 'Growth'])
        sortino_recession_train = sortino_ratio(portfolio_returns_train[train_labels == 'Recession'])
        cvar_growth_train = conditional_value_at_risk(portfolio_returns_train[train_labels == 'Growth'], 0.95)
        cvar_recession_train = conditional_value_at_risk(portfolio_returns_train[train_labels == 'Recession'], 0.95)
        portfolio_cum_returns_growth_train = (1 + portfolio_returns_train[train_labels == 'Growth']).cumprod()
        portfolio_cum_returns_recession_train = (1 + portfolio_returns_train[train_labels == 'Recession']).cumprod()
        portfolio_max_drawdown_growth_train = max_drawdown(portfolio_cum_returns_growth_train)
        portfolio_max_drawdown_recession_train = max_drawdown(portfolio_cum_returns_recession_train)
    except:
        return -np.inf,
    
    # Combine the metrics into a single fitness score
    fitness = (
        WEIGHT_SHARPE * sharpe_ratio_train +
        WEIGHT_MAX_DRAWDOWN * (portfolio_max_drawdown_growth_train + portfolio_max_drawdown_recession_train) / 2 +
        WEIGHT_CUMULATIVE_RETURN * portfolio_cum_return_train +
        WEIGHT_VOLATILITY * (-portfolio_volatility_train) +
        WEIGHT_SORTINO_GROWTH * sortino_growth_train +
        WEIGHT_SORTINO_RECESSION * sortino_recession_train +
        WEIGHT_CVAR_GROWTH * cvar_growth_train +
        WEIGHT_CVAR_RECESSION * cvar_recession_train
    )
    
    return fitness,
    

    Create the DEAP framework

    creator.create("FitnessMax", base.Fitness, weights=(1.0,)) # Single objective, maximize creator.create("Individual", list, fitness=creator.FitnessMax)

    toolbox = base.Toolbox()

    Attribute generators

    Selection part: choosing 8 unique tickers

    def select_tickers(): return random.sample(successful_tickers, NUM_ASSETS)

    Allocation part: generating 8 weights between 10% and 20% that sum to 1

    def allocate_weights(): return generate_weights(NUM_ASSETS, LOWER_WEIGHT, UPPER_WEIGHT).tolist()

    Define how each individual is created

    def create_individual(): tickers_selected = select_tickers() weights_allocated = allocate_weights() return creator.Individual(tickers_selected + weights_allocated)

    toolbox.register("individual", create_individual) toolbox.register("population", tools.initRepeat, list, toolbox.individual)

    Custom Crossover: Ensures tickers remain unique and weights are within constraints

    def cxTickersWeights(ind1, ind2): # Separate tickers and weights tickers1, weights1 = ind1[:NUM_ASSETS], ind1[NUM_ASSETS:] tickers2, weights2 = ind2[:NUM_ASSETS], ind2[NUM_ASSETS:]

    # Crossover tickers using one-point crossover
    cx_point = random.randint(1, NUM_ASSETS -1)
    new_tickers1 = tickers1[:cx_point] + [ticker for ticker in tickers2[cx_point:] if ticker not in tickers1[:cx_point]]
    new_tickers2 = tickers2[:cx_point] + [ticker for ticker in tickers1[cx_point:] if ticker not in tickers2[:cx_point]]
    
    # Fill the remaining tickers to maintain NUM_ASSETS
    available_tickers1 = list(set(successful_tickers) - set(new_tickers1))
    available_tickers2 = list(set(successful_tickers) - set(new_tickers2))
    
    while len(new_tickers1) < NUM_ASSETS:
        new_tickers1.append(random.choice(available_tickers1))
        available_tickers1.remove(new_tickers1[-1])
    
    while len(new_tickers2) < NUM_ASSETS:
        new_tickers2.append(random.choice(available_tickers2))
        available_tickers2.remove(new_tickers2[-1])
    
    # Assign the new tickers
    ind1[:NUM_ASSETS] = new_tickers1
    ind2[:NUM_ASSETS] = new_tickers2
    
    # Crossover weights using arithmetic crossover
    new_weights1 = (np.array(weights1) + np.array(weights2)) / 2
    new_weights2 = (np.array(weights1) + np.array(weights2)) / 2
    
    # Enforce weight constraints
    try:
        new_weights1 = generate_weights(NUM_ASSETS, LOWER_WEIGHT, UPPER_WEIGHT)
    except ValueError:
        new_weights1 = allocate_weights()
    
    try:
        new_weights2 = generate_weights(NUM_ASSETS, LOWER_WEIGHT, UPPER_WEIGHT)
    except ValueError:
        new_weights2 = allocate_weights()
    
    ind1[NUM_ASSETS:] = new_weights1.tolist()
    ind2[NUM_ASSETS:] = new_weights2.tolist()
    
    return ind1, ind2
    

    Register the custom crossover

    toolbox.register("mate", cxTickersWeights)

    Genetic operators

    toolbox.register("evaluate", evaluate_portfolio)

    Custom mutation: either swap a ticker or adjust weights

    def mutate_portfolio(individual, indpb=0.2): mutation_type = random.choice(['ticker', 'weight'])

    if mutation_type == 'ticker':
        # Mutation: swap one ticker
        idx = random.randint(0, NUM_ASSETS - 1)
        current_ticker = individual[idx]
        available_tickers = list(set(successful_tickers) - set(individual[:NUM_ASSETS]))
        if available_tickers:
            new_ticker = random.choice(available_tickers)
            individual[idx] = new_ticker
    else:
        # Mutation: adjust weights
        try:
            new_weights = generate_weights(NUM_ASSETS, LOWER_WEIGHT, UPPER_WEIGHT)
            individual[NUM_ASSETS:] = new_weights.tolist()
        except ValueError:
            # If unable to generate, leave weights unchanged
            pass
    
    return (individual,)
    

    toolbox.register("mutate", mutate_portfolio, indpb=0.2) toolbox.register("select", tools.selTournament, tournsize=3)

    Define the callback to print instant best portfolio

    class PrintBestPortfolio: def init(self, hof): self.hof = hof self.best_fitness = -np.inf

    def __call__(self, gen, population, fitnesses):
        current_best = max(fitnesses)
        if current_best > self.best_fitness:
            self.best_fitness = current_best
            best_ind = tools.selBest(population, 1)[0]
            selected = best_ind[:NUM_ASSETS]
            weights = np.array(best_ind[NUM_ASSETS:])
    
            # Initialize portfolio_cum_return_train and portfolio_volatility_train
            portfolio_cum_return_train = 0
            portfolio_volatility_train = 0
            sharpe_ratio_train = 0
            sortino_growth_train = 0
            sortino_recession_train = 0
            cvar_growth_train = 0
            cvar_recession_train = 0
            portfolio_max_drawdown_growth_train = 0
            portfolio_max_drawdown_recession_train = 0
    
            # Initialize portfolio_cum_return_val and portfolio_volatility_val
            portfolio_cum_return_val = 0
            portfolio_volatility_val = 0
            sharpe_ratio_val = 0
            sortino_growth_val = 0
            sortino_recession_val = 0
            cvar_growth_val = 0
            cvar_recession_val = 0
            portfolio_max_drawdown_growth_val = 0
            portfolio_max_drawdown_recession_val = 0
    
            # Training Metrics
            try:
                portfolio_returns_train = train_returns[selected].dot(weights)
                portfolio_cum_return_train = (1 + portfolio_returns_train).prod() - 1
                portfolio_volatility_train = portfolio_returns_train.std() * np.sqrt(252)
                sharpe_ratio_train = (portfolio_returns_train.mean() * 252 - RISK_FREE_RATE) / portfolio_volatility_train if portfolio_volatility_train != 0 else 0
                sortino_growth_train = sortino_ratio(portfolio_returns_train[train_labels == 'Growth'])
                sortino_recession_train = sortino_ratio(portfolio_returns_train[train_labels == 'Recession'])
                cvar_growth_train = conditional_value_at_risk(portfolio_returns_train[train_labels == 'Growth'], 0.95)
                cvar_recession_train = conditional_value_at_risk(portfolio_returns_train[train_labels == 'Recession'], 0.95)
                portfolio_cum_returns_growth_train = (1 + portfolio_returns_train[train_labels == 'Growth']).cumprod()
                portfolio_cum_returns_recession_train = (1 + portfolio_returns_train[train_labels == 'Recession']).cumprod()
                portfolio_max_drawdown_growth_train = max_drawdown(portfolio_cum_returns_growth_train)
                portfolio_max_drawdown_recession_train = max_drawdown(portfolio_cum_returns_recession_train)
            except Exception as e:
                print(f"Error in calculating training metrics: {e}")
                portfolio_cum_return_train = 0
                portfolio_volatility_train = 0
                sharpe_ratio_train = 0
                sortino_growth_train = 0
                sortino_recession_train = 0
                cvar_growth_train = 0
                cvar_recession_train = 0
                portfolio_max_drawdown_growth_train = 0
                portfolio_max_drawdown_recession_train = 0
    
            # Validation Metrics
            try:
                portfolio_returns_val = validation_returns[selected].dot(weights)
                portfolio_cum_return_val = (1 + portfolio_returns_val).prod() - 1
                portfolio_volatility_val = portfolio_returns_val.std() * np.sqrt(252)
                sharpe_ratio_val = (portfolio_returns_val.mean() * 252 - RISK_FREE_RATE) / portfolio_volatility_val if portfolio_volatility_val != 0 else 0
                sortino_growth_val = sortino_ratio(portfolio_returns_val[validation_labels == 'Growth'])
                sortino_recession_val = sortino_ratio(portfolio_returns_val[validation_labels == 'Recession'])
                cvar_growth_val = conditional_value_at_risk(portfolio_returns_val[validation_labels == 'Growth'], 0.95)
                cvar_recession_val = conditional_value_at_risk(portfolio_returns_val[validation_labels == 'Recession'], 0.95)
                portfolio_cum_returns_growth_val = (1 + portfolio_returns_val[validation_labels == 'Growth']).cumprod()
                portfolio_cum_returns_recession_val = (1 + portfolio_returns_val[validation_labels == 'Recession']).cumprod()
                portfolio_max_drawdown_growth_val = max_drawdown(portfolio_cum_returns_growth_val)
                portfolio_max_drawdown_recession_val = max_drawdown(portfolio_cum_returns_recession_val)
            except Exception as e:
                print(f"Error in calculating validation metrics: {e}")
                portfolio_cum_return_val = 0
                portfolio_volatility_val = 0
                sharpe_ratio_val = 0
                sortino_growth_val = 0
                sortino_recession_val = 0
                cvar_growth_val = 0
                cvar_recession_val = 0
                portfolio_max_drawdown_growth_val = 0
                portfolio_max_drawdown_recession_val = 0
    
            # Display the new best portfolio
            portfolio_df = pd.DataFrame({
                'Ticker': selected,
                'Allocation': [f"{w*100:.2f}%" for w in weights]
            })
            
            print(f"\nGeneration {gen}: New Best Portfolio Found!")
            display(portfolio_df)
            print(f"--- Training Set Performance ---")
            print(f"Cumulative Return: {portfolio_cum_return_train*100:.2f}%")
            print(f"Annualized Volatility: {portfolio_volatility_train*100:.2f}%")
            print(f"Sharpe Ratio: {sharpe_ratio_train:.2f}")
            print(f"Sortino Ratio (Growth): {sortino_growth_train:.2f}")
            print(f"Sortino Ratio (Recession): {sortino_recession_train:.2f}")
            print(f"CVaR (Growth): {cvar_growth_train:.2%}")
            print(f"CVaR (Recession): {cvar_recession_train:.2%}")
            print(f"Maximum Drawdown (Growth): {portfolio_max_drawdown_growth_train:.2%}")
            print(f"Maximum Drawdown (Recession): {portfolio_max_drawdown_recession_train:.2%}")
            
            print(f"--- Validation Set Performance ---")
            print(f"Cumulative Return: {portfolio_cum_return_val*100:.2f}%")
            print(f"Annualized Volatility: {portfolio_volatility_val*100:.2f}%")
            print(f"Sharpe Ratio: {sharpe_ratio_val:.2f}")
            print(f"Sortino Ratio (Growth): {sortino_growth_val:.2f}")
            print(f"Sortino Ratio (Recession): {sortino_recession_val:.2f}")
            print(f"CVaR (Growth): {cvar_growth_val:.2%}")
            print(f"CVaR (Recession): {cvar_recession_val:.2%}")
            print(f"Maximum Drawdown (Growth): {portfolio_max_drawdown_growth_val:.2%}")
            print(f"Maximum Drawdown (Recession): {portfolio_max_drawdown_recession_val:.2%}")
            
            print(f"--- Testing Set Performance ---")
            try:
                portfolio_returns_test = test_returns[selected].dot(weights)
                portfolio_cum_return_test = (1 + portfolio_returns_test).prod() - 1
                portfolio_volatility_test = portfolio_returns_test.std() * np.sqrt(252)
                sharpe_ratio_test = (portfolio_returns_test.mean() * 252 - RISK_FREE_RATE) / portfolio_volatility_test if portfolio_volatility_test != 0 else 0
                sortino_test_growth = sortino_ratio(portfolio_returns_test[test_labels == 'Growth'])
                sortino_test_recession = sortino_ratio(portfolio_returns_test[test_labels == 'Recession'])
                cvar_test_growth = conditional_value_at_risk(portfolio_returns_test[test_labels == 'Growth'], 0.95)
                cvar_recession_test = conditional_value_at_risk(portfolio_returns_test[test_labels == 'Recession'], 0.95)
                portfolio_cum_returns_growth_test = (1 + portfolio_returns_test[test_labels == 'Growth']).cumprod()
                portfolio_cum_returns_recession_test = (1 + portfolio_returns_test[test_labels == 'Recession']).cumprod()
                portfolio_max_drawdown_growth_test = max_drawdown(portfolio_cum_returns_growth_test)
                portfolio_max_drawdown_recession_test = max_drawdown(portfolio_cum_returns_recession_test)
                
                print(f"Cumulative Return: {portfolio_cum_return_test*100:.2f}%")
                print(f"Annualized Volatility: {portfolio_volatility_test*100:.2f}%")
                print(f"Sharpe Ratio: {sharpe_ratio_test:.2f}")
                print(f"Sortino Ratio (Growth): {sortino_test_growth:.2f}")
                print(f"Sortino Ratio (Recession): {sortino_test_recession:.2f}")
                print(f"CVaR (Growth): {cvar_test_growth:.2%}")
                print(f"CVaR (Recession): {cvar_recession_test:.2%}")
                print(f"Maximum Drawdown (Growth): {portfolio_max_drawdown_growth_test:.2%}")
                print(f"Maximum Drawdown (Recession): {portfolio_max_drawdown_recession_test:.2%}")
            except:
                print("Testing set performance metrics could not be calculated.")
            
            # Assess overfitting
            print("\n--- Overfitting Assessment ---")
            # Define thresholds for acceptable performance differences
            threshold_return = 0.05  # 5% difference in return
            threshold_volatility = 0.05  # 5% difference in volatility
    
            train_val_return_diff = portfolio_cum_return_train - portfolio_cum_return_val
            train_test_return_diff = portfolio_cum_return_train - portfolio_cum_return_test if 'portfolio_cum_return_test' in locals() else 0
            train_val_vol_diff = portfolio_volatility_train - portfolio_volatility_val
            train_test_vol_diff = portfolio_volatility_train - portfolio_volatility_test if 'portfolio_volatility_test' in locals() else 0
    
            overfitting_return = train_test_return_diff > threshold_return
            overfitting_vol = train_test_vol_diff < -threshold_volatility
    
            if overfitting_return and overfitting_vol:
                print("Warning: Overfitting detected! The portfolio performs significantly better on training and validation data compared to testing data.")
            else:
                print("No significant overfitting detected. The portfolio generalizes well to unseen data.")
            
            # Plot cumulative returns for visual assessment
            plt.figure(figsize=(14, 7))
            
            # Training Cumulative Returns
            plt.subplot(1, 2, 1)
            if not portfolio_cum_returns_growth_train.empty:
                plt.plot(portfolio_cum_returns_growth_train.index, portfolio_cum_returns_growth_train, label='Training Growth')
            if not portfolio_cum_returns_recession_train.empty:
                plt.plot(portfolio_cum_returns_recession_train.index, portfolio_cum_returns_recession_train, label='Training Recession')
            if not portfolio_cum_returns_growth_val.empty:
                plt.plot(portfolio_cum_returns_growth_val.index, portfolio_cum_returns_growth_val, label='Validation Growth')
            if not portfolio_cum_returns_recession_val.empty:
                plt.plot(portfolio_cum_returns_recession_val.index, portfolio_cum_returns_recession_val, label='Validation Recession')
            if 'portfolio_cum_returns_growth_test' in locals() and not portfolio_cum_returns_growth_test.empty:
                plt.plot(portfolio_cum_returns_growth_test.index, portfolio_cum_returns_growth_test, label='Testing Growth')
            if 'portfolio_cum_returns_recession_test' in locals() and not portfolio_cum_returns_recession_test.empty:
                plt.plot(portfolio_cum_returns_recession_test.index, portfolio_cum_returns_recession_test, label='Testing Recession')
            plt.title('Cumulative Returns')
            plt.xlabel('Date')
            plt.ylabel('Cumulative Return')
            plt.legend()
            
            # Drawdowns
            plt.subplot(1, 2, 2)
            if not portfolio_cum_returns_growth_train.empty:
                plt.plot(portfolio_cum_returns_growth_train.index, (portfolio_cum_returns_growth_train / portfolio_cum_returns_growth_train.cummax()) - 1, label='Training Growth Drawdown')
            if not portfolio_cum_returns_recession_train.empty:
                plt.plot(portfolio_cum_returns_recession_train.index, (portfolio_cum_returns_recession_train / portfolio_cum_returns_recession_train.cummax()) - 1, label='Training Recession Drawdown')
            if not portfolio_cum_returns_growth_val.empty:
                plt.plot(portfolio_cum_returns_growth_val.index, (portfolio_cum_returns_growth_val / portfolio_cum_returns_growth_val.cummax()) - 1, label='Validation Growth Drawdown')
            if not portfolio_cum_returns_recession_val.empty:
                plt.plot(portfolio_cum_returns_recession_val.index, (portfolio_cum_returns_recession_val / portfolio_cum_returns_recession_val.cummax()) - 1, label='Validation Recession Drawdown')
            if 'portfolio_cum_returns_growth_test' in locals() and not portfolio_cum_returns_growth_test.empty:
                plt.plot(portfolio_cum_returns_growth_test.index, (portfolio_cum_returns_growth_test / portfolio_cum_returns_growth_test.cummax()) - 1, label='Testing Growth Drawdown')
            if 'portfolio_cum_returns_recession_test' in locals() and not portfolio_cum_returns_recession_test.empty:
                plt.plot(portfolio_cum_returns_recession_test.index, (portfolio_cum_returns_recession_test / portfolio_cum_returns_recession_test.cummax()) - 1, label='Testing Recession Drawdown')
            plt.title('Drawdowns')
            plt.xlabel('Date')
            plt.ylabel('Drawdown')
            plt.legend()
            
            plt.tight_layout()
            plt.show()
    

    Determine the number of processes to use

    num_processes = max(1, multiprocessing.cpu_count() - 1) # Leave one core free

    Set up multiprocessing pool

    pool = multiprocessing.Pool(processes=num_processes) toolbox.register("map", pool.map)

    Initialize population

    print("Initializing population...") population = toolbox.population(n=POPULATION_SIZE)

    Initialize statistics to keep track

    stats = tools.Statistics(lambda ind: ind.fitness.values) stats.register("avg", np.mean) stats.register("std", np.std) stats.register("min", np.min) stats.register("max", np.max)

    Initialize Hall of Fame to store the best individual

    hof = tools.HallOfFame(HALL_OF_FAME_SIZE)

    Instantiate the callback

    callback = PrintBestPortfolio(hof)

    Begin the evolution

    print("\nStarting Genetic Algorithm Evolution...\n") for gen in tqdm(range(1, MAX_GENERATIONS + 1), desc="Generations"): # Select the next generation individuals offspring = toolbox.select(population, len(population)) offspring = list(map(toolbox.clone, offspring))

    # Apply crossover on the offspring
    for child1, child2 in zip(offspring[::2], offspring[1::2]):
        if random.random() < P_CROSSOVER:
            toolbox.mate(child1, child2)
            del child1.fitness.values
            del child2.fitness.values
    
    # Apply mutation on the offspring
    for mutant in offspring:
        if random.random() < P_MUTATION:
            toolbox.mutate(mutant)
            del mutant.fitness.values
    
    # Evaluate the individuals with an invalid fitness
    invalid_ind = [ind for ind in offspring if not ind.fitness.valid]
    fitnesses = toolbox.map(toolbox.evaluate, invalid_ind)
    for ind, fit in zip(invalid_ind, fitnesses):
        ind.fitness.values = fit
    
    # Replace population with offspring
    population[:] = offspring
    
    # Update the hall of fame with the generated individuals
    hof.update(population)
    
    # Gather all the fitnesses in one list
    fits = [ind.fitness.values[0] for ind in population]
    
    # Callback to print instant best portfolio
    callback(gen, population, fits)
    

    print("\nEvolution Complete!\n")

    Retrieve and display the best portfolio found

    if len(hof) > 0: best_ind = hof[0] selected = best_ind[:NUM_ASSETS] weights = np.array(best_ind[NUM_ASSETS:])

    # Training Metrics
    portfolio_returns_train = train_returns[selected].dot(weights)
    portfolio_cum_return_train = (1 + portfolio_returns_train).prod() - 1
    portfolio_volatility_train = portfolio_returns_train.std() * np.sqrt(252)
    sharpe_ratio_train = (portfolio_returns_train.mean() * 252 - RISK_FREE_RATE) / portfolio_volatility_train if portfolio_volatility_train != 0 else 0
    sortino_growth_train = sortino_ratio(portfolio_returns_train[train_labels == 'Growth'])
    sortino_recession_train = sortino_ratio(portfolio_returns_train[train_labels == 'Recession'])
    cvar_growth_train = conditional_value_at_risk(portfolio_returns_train[train_labels == 'Growth'], 0.95)
    cvar_recession_train = conditional_value_at_risk(portfolio_returns_train[train_labels == 'Recession'], 0.95)
    portfolio_cum_returns_growth_train = (1 + portfolio_returns_train[train_labels == 'Growth']).cumprod()
    portfolio_cum_returns_recession_train = (1 + portfolio_returns_train[train_labels == 'Recession']).cumprod()
    portfolio_max_drawdown_growth_train = max_drawdown(portfolio_cum_returns_growth_train)
    portfolio_max_drawdown_recession_train = max_drawdown(portfolio_cum_returns_recession_train)
    
    # Validation Metrics
    try:
        portfolio_returns_val = validation_returns[selected].dot(weights)
        portfolio_cum_return_val = (1 + portfolio_returns_val).prod() - 1
        portfolio_volatility_val = portfolio_returns_val.std() * np.sqrt(252)
        sharpe_ratio_val = (portfolio_returns_val.mean() * 252 - RISK_FREE_RATE) / portfolio_volatility_val if portfolio_volatility_val != 0 else 0
        sortino_growth_val = sortino_ratio(portfolio_returns_val[validation_labels == 'Growth'])
        sortino_recession_val = sortino_ratio(portfolio_returns_val[validation_labels == 'Recession'])
        cvar_growth_val = conditional_value_at_risk(portfolio_returns_val[validation_labels == 'Growth'], 0.95)
        cvar_recession_val = conditional_value_at_risk(portfolio_returns_val[validation_labels == 'Recession'], 0.95)
        portfolio_cum_returns_growth_val = (1 + portfolio_returns_val[validation_labels == 'Growth']).cumprod()
        portfolio_cum_returns_recession_val = (1 + portfolio_returns_val[validation_labels == 'Recession']).cumprod()
        portfolio_max_drawdown_growth_val = max_drawdown(portfolio_cum_returns_growth_val)
        portfolio_max_drawdown_recession_val = max_drawdown(portfolio_cum_returns_recession_val)
    except:
        portfolio_returns_val = 0
        portfolio_cum_return_val = 0
        portfolio_volatility_val = 0
        sharpe_ratio_val = 0
        sortino_growth_val = 0
        sortino_recession_val = 0
        cvar_growth_val = 0
        cvar_recession_val = 0
        portfolio_cum_returns_growth_val = 0
        portfolio_cum_returns_recession_val = 0
        portfolio_max_drawdown_growth_val = 0
        portfolio_max_drawdown_recession_val = 0
    
    # Testing Metrics
    try:
        portfolio_returns_test = test_returns[selected].dot(weights)
        portfolio_cum_return_test = (1 + portfolio_returns_test).prod() - 1
        portfolio_volatility_test = portfolio_returns_test.std() * np.sqrt(252)
        sharpe_ratio_test = (portfolio_returns_test.mean() * 252 - RISK_FREE_RATE) / portfolio_volatility_test if portfolio_volatility_test != 0 else 0
        sortino_test_growth = sortino_ratio(portfolio_returns_test[test_labels == 'Growth'])
        sortino_test_recession = sortino_ratio(portfolio_returns_test[test_labels == 'Recession'])
        cvar_test_growth = conditional_value_at_risk(portfolio_returns_test[test_labels == 'Growth'], 0.95)
        cvar_recession_test = conditional_value_at_risk(portfolio_returns_test[test_labels == 'Recession'], 0.95)
        portfolio_cum_returns_growth_test = (1 + portfolio_returns_test[test_labels == 'Growth']).cumprod()
        portfolio_cum_returns_recession_test = (1 + portfolio_returns_test[test_labels == 'Recession']).cumprod()
        portfolio_max_drawdown_growth_test = max_drawdown(portfolio_cum_returns_growth_test)
        portfolio_max_drawdown_recession_test = max_drawdown(portfolio_cum_returns_recession_test)
    except:
        portfolio_returns_test = 0
        portfolio_cum_return_test = 0
        portfolio_volatility_test = 0
        sharpe_ratio_test = 0
        sortino_test_growth = 0
        sortino_test_recession = 0
        cvar_test_growth = 0
        cvar_recession_test = 0
        portfolio_cum_returns_growth_test = 0
        portfolio_cum_returns_recession_test = 0
        portfolio_max_drawdown_growth_test = 0
        portfolio_max_drawdown_recession_test = 0
    
    # Composite Fitness Score on Training and Validation Sets
    fitness_train = (
        WEIGHT_SHARPE * sharpe_ratio_train +
        WEIGHT_MAX_DRAWDOWN * (portfolio_max_drawdown_growth_train + portfolio_max_drawdown_recession_train) / 2 +
        WEIGHT_CUMULATIVE_RETURN * portfolio_cum_return_train +
        WEIGHT_VOLATILITY * (-portfolio_volatility_train) +
        WEIGHT_SORTINO_GROWTH * sortino_growth_train +
        WEIGHT_SORTINO_RECESSION * sortino_recession_train +
        WEIGHT_CVAR_GROWTH * cvar_growth_train +
        WEIGHT_CVAR_RECESSION * cvar_recession_train
    )
    
    fitness_val = (
        WEIGHT_SHARPE * sharpe_ratio_val +
        WEIGHT_MAX_DRAWDOWN * (portfolio_max_drawdown_growth_val + portfolio_max_drawdown_recession_val) / 2 +
        WEIGHT_CUMULATIVE_RETURN * portfolio_cum_return_val +
        WEIGHT_VOLATILITY * (-portfolio_volatility_val) +
        WEIGHT_SORTINO_GROWTH * sortino_growth_val +
        WEIGHT_SORTINO_RECESSION * sortino_recession_val +
        WEIGHT_CVAR_GROWTH * cvar_growth_val +
        WEIGHT_CVAR_RECESSION * cvar_recession_val
    )
    
    fitness = (fitness_train + fitness_val) / 2
    
    portfolio_df = pd.DataFrame({
        'Ticker': selected,
        'Allocation': [f"{w*100:.2f}%" for w in weights]
    })
    
    print("Optimal Portfolio Found:")
    display(portfolio_df)
    print(f"--- Training Set Performance ---")
    print(f"Cumulative Return: {portfolio_cum_return_train*100:.2f}%")
    print(f"Annualized Volatility: {portfolio_volatility_train*100:.2f}%")
    print(f"Sharpe Ratio: {sharpe_ratio_train:.2f}")
    print(f"Sortino Ratio (Growth): {sortino_growth_train:.2f}")
    print(f"Sortino Ratio (Recession): {sortino_recession_train:.2f}")
    print(f"CVaR (Growth): {cvar_growth_train:.2%}")
    print(f"CVaR (Recession): {cvar_recession_train:.2%}")
    print(f"Maximum Drawdown (Growth): {portfolio_max_drawdown_growth_train:.2%}")
    print(f"Maximum Drawdown (Recession): {portfolio_max_drawdown_recession_train:.2%}")
    
    print(f"--- Validation Set Performance ---")
    print(f"Cumulative Return: {cumulative_return_val*100:.2f}%")
    print(f"Annualized Volatility: {portfolio_volatility_val*100:.2f}%")
    print(f"Sharpe Ratio: {sharpe_ratio_val:.2f}")
    print(f"Sortino Ratio (Growth): {sortino_growth_val:.2f}")
    print(f"Sortino Ratio (Recession): {sortino_recession_val:.2f}")
    print(f"CVaR (Growth): {cvar_growth_val:.2%}")
    print(f"CVaR (Recession): {cvar_recession_val:.2%}")
    print(f"Maximum Drawdown (Growth): {portfolio_max_drawdown_growth_val:.2%}")
    print(f"Maximum Drawdown (Recession): {portfolio_max_drawdown_recession_val:.2%}")
    
    print(f"--- Testing Set Performance ---")
    print(f"Cumulative Return: {portfolio_cum_return_test*100:.2f}%")
    print(f"Annualized Volatility: {portfolio_volatility_test*100:.2f}%")
    print(f"Sharpe Ratio: {sharpe_ratio_test:.2f}")
    print(f"Sortino Ratio (Growth): {sortino_test_growth:.2f}")
    print(f"Sortino Ratio (Recession): {sortino_test_recession:.2f}")
    print(f"CVaR (Growth): {cvar_test_growth:.2%}")
    print(f"CVaR (Recession): {cvar_recession_test:.2%}")
    print(f"Maximum Drawdown (Growth): {portfolio_max_drawdown_growth_test:.2%}")
    print(f"Maximum Drawdown (Recession): {portfolio_max_drawdown_recession_test:.2%}")
    
    # Assess overfitting
    print("\n--- Overfitting Assessment ---")
    # Define thresholds for acceptable performance differences
    threshold_return = 0.05  # 5% difference in return
    threshold_volatility = 0.05  # 5% difference in volatility
    
    train_val_return_diff = cumulative_return_train - cumulative_return_val
    train_test_return_diff = portfolio_cum_return_train - portfolio_cum_return_test if 'portfolio_cum_return_test' in locals() else 0
    train_val_vol_diff = portfolio_volatility_train - portfolio_volatility_val
    train_test_vol_diff = portfolio_volatility_train - portfolio_volatility_test if 'portfolio_volatility_test' in locals() else 0
    
    
    overfitting_return = train_test_return_diff > threshold_return
    overfitting_vol = train_test_vol_diff < -threshold_volatility
    
    if overfitting_return and overfitting_vol:
        print("Warning: Overfitting detected! The portfolio performs significantly better on training and validation data compared to testing data.")
    else:
        print("No significant overfitting detected. The portfolio generalizes well to unseen data.")
    
    # Plot cumulative returns for visual assessment
    plt.figure(figsize=(14, 7))
    
    # Training Cumulative Returns
    plt.subplot(1, 2, 1)
    if not portfolio_cum_returns_growth_train.empty:
        plt.plot(portfolio_cum_returns_growth_train.index, portfolio_cum_returns_growth_train, label='Training Growth')
    if not portfolio_cum_returns_recession_train.empty:
        plt.plot(portfolio_cum_returns_recession_train.index, portfolio_cum_returns_recession_train, label='Training Recession')
    if not portfolio_cum_returns_growth_val.empty:
        plt.plot(portfolio_cum_returns_growth_val.index, portfolio_cum_returns_growth_val, label='Validation Growth')
    if not portfolio_cum_returns_recession_val.empty:
        plt.plot(portfolio_cum_returns_recession_val.index, portfolio_cum_returns_recession_val, label='Validation Recession')
    if 'portfolio_cum_returns_growth_test' in locals() and not portfolio_cum_returns_growth_test.empty:
        plt.plot(portfolio_cum_returns_growth_test.index, portfolio_cum_returns_growth_test, label='Testing Growth')
    if 'portfolio_cum_returns_recession_test' in locals() and not portfolio_cum_returns_recession_test.empty:
        plt.plot(portfolio_cum_returns_recession_test.index, portfolio_cum_returns_recession_test, label='Testing Recession')
    plt.title('Cumulative Returns')
    plt.xlabel('Date')
    plt.ylabel('Cumulative Return')
    plt.legend()
    
    # Drawdowns
    plt.subplot(1, 2, 2)
    if not portfolio_cum_returns_growth_train.empty:
        plt.plot(portfolio_cum_returns_growth_train.index, (portfolio_cum_returns_growth_train / portfolio_cum_returns_growth_train.cummax()) - 1, label='Training Growth Drawdown')
    if not portfolio_cum_returns_recession_train.empty:
        plt.plot(portfolio_cum_returns_recession_train.index, (portfolio_cum_returns_recession_train / portfolio_cum_returns_recession_train.cummax()) - 1, label='Training Recession Drawdown')
    if not portfolio_cum_returns_growth_val.empty:
        plt.plot(portfolio_cum_returns_growth_val.index, (portfolio_cum_returns_growth_val / portfolio_cum_returns_growth_val.cummax()) - 1, label='Validation Growth Drawdown')
    if not portfolio_cum_returns_recession_val.empty:
        plt.plot(portfolio_cum_returns_recession_val.index, (portfolio_cum_returns_recession_val / portfolio_cum_returns_recession_val.cummax()) - 1, label='Validation Recession Drawdown')
    if 'portfolio_cum_returns_growth_test' in locals() and not portfolio_cum_returns_growth_test.empty:
        plt.plot(portfolio_cum_returns_growth_test.index, (portfolio_cum_returns_growth_test / portfolio_cum_returns_growth_test.cummax()) - 1, label='Testing Growth Drawdown')
    if 'portfolio_cum_returns_recession_test' in locals() and not portfolio_cum_returns_recession_test.empty:
        plt.plot(portfolio_cum_returns_recession_test.index, (portfolio_cum_returns_recession_test / portfolio_cum_returns_recession_test.cummax()) - 1, label='Testing Recession Drawdown')
    plt.title('Drawdowns')
    plt.xlabel('Date')
    plt.ylabel('Drawdown')
    plt.legend()
    
    plt.tight_layout()
    plt.show()
    

    Close the multiprocessing pool

    pool.close() pool.join()

    there is some bugs in my code, fix it WEIGHT_SHARPE: 0.35 (Emphasizes risk-adjusted returns)

    WEIGHT_SORTINO_GROWTH: 0.25 (Focuses on downside risk during growth periods)

    WEIGHT_SORTINO_RECESSION: 0.15 (Addresses downside risk during recession periods)

    WEIGHT_VOLATILITY: 0.10 (Encourages lower volatility)

    WEIGHT_ANNUALIZED_RETURN: 0.15 (Prioritizes consistent annual returns)

    WEIGHT_MAX_DRAWDOWN: 0.05 (To manage risk and limit losses)

    change my weight into the above one also use cagr instead of cummulative return no need showing the result everytime, only show the best one at last, same with the graph, refactor the code

  2. Assistant

    Certainly! Let's refactor the code according to your specifications. We'll incorporate the following changes:

    1. Update the objective weights as you specified.
    2. Use CAGR (Compound Annual Growth Rate) instead of cumulative return.
    3. Delay displaying the best portfolio and graphs until the end of the genetic algorithm's run.
    4. Refactor the code for improved readability and efficiency.

    Here’s the refactored code:

    # Import required packages
    !pip install yfinance pandas numpy beautifulsoup4 requests tqdm deap matplotlib lxml
    
    # Import necessary libraries
    import yfinance as yf
    import pandas as pd
    import numpy as np
    import random
    from bs4 import BeautifulSoup
    import requests
    from tqdm import tqdm
    import sys
    import warnings
    import multiprocessing
    import matplotlib.pyplot as plt
    
    from deap import base, creator, tools, algorithms
    
    # Suppress warnings for cleaner output
    warnings.filterwarnings("ignore")
    
    # Set random seed for reproducibility
    RANDOM_SEED = 42
    random.seed(RANDOM_SEED)
    np.random.seed(RANDOM_SEED)
    
    # Function to fetch S&P 500 tickers from Wikipedia
    def get_sp500_tickers():
        url = "https://en.wikipedia.org/wiki/List_of_S%26P_500_companies"
        response = requests.get(url)
        if response.status_code != 200:
            raise Exception("Failed to fetch S&P 500 tickers from Wikipedia.")
        soup = BeautifulSoup(response.text, "lxml")
        table = soup.find("table", {"id": "constituents"})
        tickers = []
        for row in table.findAll("tr")[1:]:
            ticker = row.findAll("td")[0].text.strip()
            # Replace '.' with '-' for tickers like BRK.B
            ticker = ticker.replace(".", "-")
            tickers.append(ticker)
        return tickers
    
    # Function to calculate metrics
    def max_drawdown(series):
        roll_max = series.cummax()
        drawdown = (series - roll_max) / roll_max
        return drawdown.min()
    
    def sortino_ratio(returns, target=0):
        downside = returns[returns < target]
        if len(downside) == 0:
            return 0  # No downside risk; assign a neutral value
        expected_return = returns.mean() * 252
        downside_risk = np.sqrt((downside ** 2).mean()) * np.sqrt(252)
        return (expected_return - target) / downside_risk if downside_risk != 0 else 0
    
    def conditional_value_at_risk(returns, confidence_level=0.95):
        var = np.percentile(returns, (1 - confidence_level) * 100)
        cvar = returns[returns <= var].mean()
        return cvar
    
    def CAGR(returns):
        cumulative_returns = (1 + returns).prod()
        periods = len(returns) / 252  # Assumes 252 trading days per year
        return cumulative_returns ** (1 / periods) - 1
    
    # Function to generate portfolio weights within constraints
    def generate_weights(n, lower=0.10, upper=0.20, max_attempts=1000):
        for _ in range(max_attempts):
            weights = np.random.uniform(lower, upper, n)
            weights /= weights.sum()
            if all(lower <= w <= upper for w in weights):
                return weights
        raise ValueError(
            "Unable to generate weights within constraints after multiple attempts."
        )
    
    # Function to label economic cycles
    def label_economic_cycles(dates):
        recession_periods = [
            ("2001-03-01", "2001-11-30"),
            ("2007-12-01", "2009-06-30"),
            ("2020-02-01", "2020-04-30"),
        ]
        labels = []
        for date in dates:
            # Remove timezone information if present
            if date.tzinfo is not None:
                date = date.replace(tzinfo=None)
            label = "Growth"
            for start, end in recession_periods:
                if pd.to_datetime(start) <= date <= pd.to_datetime(end):
                    label = "Recession"
                    break
            labels.append(label)
        return labels
    
    # Parameters
    START_DATE = "2000-01-01"
    END_DATE = "2024-10-30"
    NUM_ASSETS = 8  # Number of stocks in the portfolio
    LOWER_WEIGHT = 0.10
    UPPER_WEIGHT = 0.20
    RISK_FREE_RATE = 0.017  # Approximate risk-free rate (e.g., 10-year US Treasury yield)
    
    # Step 1: Get S&P 500 tickers
    print("Fetching S&P 500 tickers...")
    tickers = get_sp500_tickers()
    print(f"Number of tickers fetched: {len(tickers)}")
    
    # Step 2: Download historical data with dynamic start date
    print("Downloading historical data...")
    failed_tickers = []
    successful_tickers = []
    data = pd.DataFrame()
    
    ticker_first_dates = {}
    
    for ticker in tqdm(tickers, desc="Downloading tickers"):
        try:
            df = yf.download(
                ticker, start=START_DATE, end=END_DATE, progress=False
            )["Adj Close"]
            if df.empty:
                failed_tickers.append(ticker)
            else:
                data[ticker] = df
                successful_tickers.append(ticker)
                ticker_first_dates[ticker] = df.first_valid_index()
        except Exception as e:
            failed_tickers.append(ticker)
    
    print(f"\nTotal tickers with successful data download: {len(successful_tickers)}")
    print(f"Total tickers failed to download: {len(failed_tickers)}")
    if failed_tickers:
        print(f"Failed tickers: {failed_tickers}")
    
    # Determine the earliest start date among all successful tickers
    if ticker_first_dates:
        earliest_date = min(ticker_first_dates.values())
        print(f"Earliest available data starts from: {earliest_date.date()}")
    
        # Adjust the dataset to start from the earliest_date
        data = data.loc[earliest_date:]
    
        # Forward fill to propagate last valid observation
        data.fillna(method="ffill", inplace=True)
        # Backward fill to handle any remaining NaNs at the start
        data.fillna(method="bfill", inplace=True)
        print(
            f"Data shape after adjusting start date and dropping incomplete data: {data.shape}"
        )
    else:
        print("No data available after processing tickers.")
        sys.exit()
    
    # If there are not enough tickers, exit
    if len(data.columns) < NUM_ASSETS:
        print("Not enough tickers with complete data to form a portfolio.")
        sys.exit()
    
    # Step 3: Calculate daily returns
    returns = data.pct_change().dropna()
    
    # Step 4: Label economic cycles
    print("Labeling economic cycles...")
    return_dates = returns.index
    labels = label_economic_cycles(return_dates)
    labels = pd.Series(labels, index=return_dates)  # Convert to Series with matching index
    
    # Step 5: Split data into Training (70%), Validation (15%), Testing (15%)
    split_date_1 = int(len(returns) * 0.70)
    split_date_2 = int(len(returns) * 0.85)
    
    train_returns = returns.iloc[:split_date_1]  # No 'Economic_Cycle' column
    train_labels = labels.iloc[:split_date_1]  # Use iloc to ensure alignment
    
    validation_returns = returns.iloc[split_date_1:split_date_2]
    validation_labels = labels.iloc[split_date_1:split_date_2]
    
    test_returns = returns.iloc[split_date_2:]
    test_labels = labels.iloc[split_date_2:]
    
    print(f"Training set: {train_returns.shape[0]} days")
    print(f"Validation set: {validation_returns.shape[0]} days")
    print(f"Testing set: {test_returns.shape[0]} days")
    
    # Define Genetic Algorithm parameters
    POPULATION_SIZE = 500  # Adjusted for memory constraints
    P_CROSSOVER = 0.8  # Probability for crossover
    P_MUTATION = 0.2  # Probability for mutating an individual
    MAX_GENERATIONS = 100  # Increased number of generations for better convergence
    HALL_OF_FAME_SIZE = 1  # Number of best individuals to keep
    
    # Define the weights for each optimization objective
    WEIGHT_SHARPE = 0.35
    WEIGHT_SORTINO_GROWTH = 0.25
    WEIGHT_SORTINO_RECESSION = 0.15
    WEIGHT_VOLATILITY = 0.10
    WEIGHT_CAGR = 0.15
    WEIGHT_MAX_DRAWDOWN = 0.05
    
    # Define the evaluation (fitness) function
    def evaluate_portfolio(individual):
        selected_tickers = individual[:NUM_ASSETS]
        weights = individual[NUM_ASSETS:]
    
        # Ensure all selected tickers are unique
        if len(set(selected_tickers)) != NUM_ASSETS:
            return -np.inf,  # Invalid individual
    
        # Ensure weights sum to 1 and are within constraints
        weights = np.array(weights)
        if not np.isclose(weights.sum(), 1.0):
            return -np.inf,
        if not all(LOWER_WEIGHT <= w <= UPPER_WEIGHT for w in weights):
            return -np.inf,
    
        # Check if all tickers are present in the returns DataFrame
        if not all(ticker in returns.columns for ticker in selected_tickers):
            return -np.inf,  # Invalid individual
    
        # Calculate portfolio metrics using Training Set
        try:
            portfolio_returns_train = train_returns[selected_tickers].dot(weights)
            portfolio_CAGR_train = CAGR(portfolio_returns_train)
            portfolio_volatility_train = portfolio_returns_train.std() * np.sqrt(252)
            sharpe_ratio_train = (
                (portfolio_returns_train.mean() * 252 - RISK_FREE_RATE)
                / portfolio_volatility_train
                if portfolio_volatility_train != 0
                else 0
            )
            sortino_growth_train = sortino_ratio(
                portfolio_returns_train[train_labels == "Growth"]
            )
            sortino_recession_train = sortino_ratio(
                portfolio_returns_train[train_labels == "Recession"]
            )
            portfolio_cum_returns_growth_train = (
                1 + portfolio_returns_train[train_labels == "Growth"]
            ).cumprod()
            portfolio_cum_returns_recession_train = (
                1 + portfolio_returns_train[train_labels == "Recession"]
            ).cumprod()
            portfolio_max_drawdown_growth_train = max_drawdown(
                portfolio_cum_returns_growth_train
            )
            portfolio_max_drawdown_recession_train = max_drawdown(
                portfolio_cum_returns_recession_train
            )
        except:
            return -np.inf,
    
        # Combine the metrics into a single fitness score
        fitness = (
            WEIGHT_SHARPE * sharpe_ratio_train
            + WEIGHT_SORTINO_GROWTH * sortino_growth_train
            + WEIGHT_SORTINO_RECESSION * sortino_recession_train
            + WEIGHT_VOLATILITY * (-portfolio_volatility_train)
            + WEIGHT_CAGR * portfolio_CAGR_train
            + WEIGHT_MAX_DRAWDOWN
            * (portfolio_max_drawdown_growth_train + portfolio_max_drawdown_recession_train)
            / 2
        )
    
        return fitness,
    
    
    # Create the DEAP framework
    creator.create("FitnessMax", base.Fitness, weights=(1.0,))  # Single objective, maximize
    creator.create("Individual", list, fitness=creator.FitnessMax)
    
    toolbox = base.Toolbox()
    
    # Attribute generators
    # Selection part: choosing 8 unique tickers
    def select_tickers():
        return random.sample(successful_tickers, NUM_ASSETS)
    
    # Allocation part: generating 8 weights between 10% and 20% that sum to 1
    def allocate_weights():
        return generate_weights(NUM_ASSETS, LOWER_WEIGHT, UPPER_WEIGHT).tolist()
    
    # Define how each individual is created
    def create_individual():
        tickers_selected = select_tickers()
        weights_allocated = allocate_weights()
        return creator.Individual(tickers_selected + weights_allocated)
    
    
    toolbox.register("individual", create_individual)
    toolbox.register("population", tools.initRepeat, list, toolbox.individual)
    
    
    # Custom Crossover: Ensures tickers remain unique and weights are within constraints
    def cxTickersWeights(ind1, ind2):
        # Separate tickers and weights
        tickers1, weights1 = ind1[:NUM_ASSETS], ind1[NUM_ASSETS:]
        tickers2, weights2 = ind2[:NUM_ASSETS], ind2[NUM_ASSETS:]
    
        # Crossover tickers using one-point crossover
        cx_point = random.randint(1, NUM_ASSETS - 1)
        new_tickers1 = tickers1[:cx_point] + [
            ticker for ticker in tickers2[cx_point:] if ticker not in tickers1[:cx_point]
        ]
        new_tickers2 = tickers2[:cx_point] + [
            ticker for ticker in tickers1[cx_point:] if ticker not in tickers2[:cx_point]
        ]
    
        # Fill the remaining tickers to maintain NUM_ASSETS
        available_tickers1 = list(set(successful_tickers) - set(new_tickers1))
        available_tickers2 = list(set(successful_tickers) - set(new_tickers2))
    
        while len(new_tickers1) < NUM_ASSETS:
            new_tickers1.append(random.choice(available_tickers1))
            available_tickers1.remove(new_tickers1[-1])
    
        while len(new_tickers2) < NUM_ASSETS:
            new_tickers2.append(random.choice(available_tickers2))
            available_tickers2.remove(new_tickers2[-1])
    
        # Assign the new tickers
        ind1[:NUM_ASSETS] = new_tickers1
        ind2[:NUM_ASSETS] = new_tickers2
    
        # Crossover weights using arithmetic crossover
        new_weights1 = (np.array(weights1) + np.array(weights2)) / 2
        new_weights2 = (np.array(weights1) + np.array(weights2)) / 2
    
        # Enforce weight constraints
        try:
            new_weights1 = generate_weights(NUM_ASSETS, LOWER_WEIGHT, UPPER_WEIGHT)
        except ValueError:
            new_weights1 = allocate_weights()
    
        try:
            new_weights2 = generate_weights(NUM_ASSETS, LOWER_WEIGHT, UPPER_WEIGHT)
        except ValueError:
            new_weights2 = allocate_weights()
    
        ind1[NUM_ASSETS:] = new_weights1.tolist()
        ind2[NUM_ASSETS:] = new_weights2.tolist()
    
        return ind1, ind2
    
    
    # Register the custom crossover
    toolbox.register("mate", cxTickersWeights)
    
    # Genetic operators
    toolbox.register("evaluate", evaluate_portfolio)
    
    
    # Custom mutation: either swap a ticker or adjust weights
    def mutate_portfolio(individual, indpb=0.2):
        mutation_type = random.choice(["ticker", "weight"])
    
        if mutation_type == "ticker":
            # Mutation: swap one ticker
            idx = random.randint(0, NUM_ASSETS - 1)
            current_ticker = individual[idx]
            available_tickers = list(
                set(successful_tickers) - set(individual[:NUM_ASSETS])
            )
            if available_tickers:
                new_ticker = random.choice(available_tickers)
                individual[idx] = new_ticker
        else:
            # Mutation: adjust weights
            try:
                new_weights = generate_weights(NUM_ASSETS, LOWER_WEIGHT, UPPER_WEIGHT)
                individual[NUM_ASSETS:] = new_weights.tolist()
            except ValueError:
                # If unable to generate, leave weights unchanged
                pass
    
        return (individual,)
    
    
    toolbox.register("mutate", mutate_portfolio, indpb=0.2)
    toolbox.register("select", tools.selTournament, tournsize=3)
    
    # Determine the number of processes to use
    num_processes = max(1, multiprocessing.cpu_count() - 1)  # Leave one core free
    
    # Set up multiprocessing pool
    pool = multiprocessing.Pool(processes=num_processes)
    toolbox.register("map", pool.map)
    
    # Initialize population
    print("Initializing population...")
    population = toolbox.population(n=POPULATION_SIZE)
    
    # Initialize statistics to keep track
    stats = tools.Statistics(lambda ind: ind.fitness.values)
    stats.register("avg", np.mean)
    stats.register("std", np.std)
    stats.register("min", np.min)
    stats.register("max", np.max)
    
    # Initialize Hall of Fame to store the best individual
    hof = tools.HallOfFame(HALL_OF_FAME_SIZE)
    
    # Begin the evolution
    print("\nStarting Genetic Algorithm Evolution...\n")
    for gen in tqdm(range(1, MAX_GENERATIONS + 1), desc="Generations"):
        # Select the next generation individuals
        offspring = toolbox.select(population, len(population))
        offspring = list(map(toolbox.clone, offspring))
    
        # Apply crossover on the offspring
        for child1, child2 in zip(offspring[::2], offspring[1::2]):
            if random.random() < P_CROSSOVER:
                toolbox.mate(child1, child2)
                del child1.fitness.values
                del child2.fitness.values
    
        # Apply mutation on the offspring
        for mutant in offspring:
            if random.random() < P_MUTATION:
                toolbox.mutate(mutant)
                del mutant.fitness.values
    
        # Evaluate the individuals with an invalid fitness
        invalid_ind = [ind for ind in offspring if not ind.fitness.valid]
        fitnesses = toolbox.map(toolbox.evaluate, invalid_ind)
        for ind, fit in zip(invalid_ind, fitnesses):
            ind.fitness.values = fit
    
        # Replace population with offspring
        population[:] = offspring
    
        # Update the hall of fame with the generated individuals
        hof.update(population)
    
    print("\nEvolution Complete!\n")
    
    # Retrieve and display the best portfolio found
    if len(hof) > 0:
        best_ind = hof[0]
        selected = best_ind[:NUM_ASSETS]
        weights = np.array(best_ind[NUM_ASSETS:])
    
        # Training, Validation, and Testing Metrics
        def calculate_metrics(returns_set, labels_set):
            try:
                portfolio_returns = returns_set[selected].dot(weights)
                portfolio_CAGR = CAGR(portfolio_returns)
                volatility = portfolio_returns.std() * np.sqrt(252)
                sharpe_ratio = (
                    (portfolio_returns.mean() * 252 - RISK_FREE_RATE) / volatility
                    if volatility != 0
                    else 0
                )
                sortino_growth = sortino_ratio(portfolio_returns[labels_set == "Growth"])
                sortino_recession = sortino_ratio(
                    portfolio_returns[labels_set == "Recession"]
                )
                cum_returns_growth = (1 + portfolio_returns[labels_set == "Growth"]).cumprod()
                cum_returns_recession = (1 + portfolio_returns[labels_set == "Recession"]).cumprod()
                max_drawdown_growth = max_drawdown(cum_returns_growth)
                max_drawdown_recession = max_drawdown(cum_returns_recession)
            except:
                return {
                    "CAGR": 0,
                    "volatility": 0,
                    "sharpe_ratio": 0,
                    "sortino_growth": 0,
                    "sortino_recession": 0,
                    "max_drawdown_growth": 0,
                    "max_drawdown_recession": 0,
                }
    
            return {
                "CAGR": portfolio_CAGR,
                "volatility": volatility,
                "sharpe_ratio": sharpe_ratio,
                "sortino_growth": sortino_growth,
                "sortino_recession": sortino_recession,
                "max_drawdown_growth": max_drawdown_growth,
                "max_drawdown_recession": max_drawdown_recession,
                "cum_returns_growth": cum_returns_growth,
                "cum_returns_recession": cum_returns_recession,
            }
    
        train_metrics = calculate_metrics(train_returns, train_labels)
        validation_metrics = calculate_metrics(validation_returns, validation_labels)
        test_metrics = calculate_metrics(test_returns, test_labels)
    
        # Display the best portfolio
        portfolio_df = pd.DataFrame(
            {"Ticker": selected, "Allocation": [f"{w*100:.2f}%" for w in weights]}
        )
        print("Optimal Portfolio Found:")
        display(portfolio_df)
    
        # Training, Validation, and Testing Performance Metrics
        print(f"--- Training Set Performance ---")
        print(f"CAGR: {train_metrics['CAGR']*100:.2f}%")
        print(f"Annualized Volatility: {train_metrics['volatility']*100:.2f}%")
        print(f"Sharpe Ratio: {train_metrics['sharpe_ratio']:.2f}")
        print(f"Sortino Ratio (Growth): {train_metrics['sortino_growth']:.2f}")
        print(f"Sortino Ratio (Recession): {train_metrics['sortino_recession']:.2f}")
        print(f"Maximum Drawdown (Growth): {train_metrics['max_drawdown_growth']:.2%}")
        print(f"Maximum Drawdown (Recession): {train_metrics['max_drawdown_recession']:.2%}")
    
        print(f"--- Validation Set Performance ---")
        print(f"CAGR: {validation_metrics['CAGR']*100:.2f}%")
        print(f"Annualized Volatility: {validation_metrics['volatility']*100:.2f}%")
        print(f"Sharpe Ratio: {validation_metrics['sharpe_ratio']:.2f}")
        print(f"Sortino Ratio (Growth): {validation_metrics['sortino_growth']:.2f}")
        print(f"Sortino Ratio (Recession): {validation_metrics['sortino_recession']:.2f}")
        print(
            f"Maximum Drawdown (Growth): {validation_metrics['max_drawdown_growth']:.2%}"
        )
        print(
            f"Maximum Drawdown (Recession): {validation_metrics['max_drawdown_recession']:.2%}"
        )
    
        print(f"--- Testing Set Performance ---")
        print(f"CAGR: {test_metrics['CAGR']*100:.2f}%")
        print(f"Annualized Volatility: {test_metrics['volatility']*100:.2f}%")
        print(f"Sharpe Ratio: {test_metrics['sharpe_ratio']:.2f}")
        print(f"Sortino Ratio (Growth): {test_metrics['sortino_growth']:.2f}")
        print(f"Sortino Ratio (Recession): {test_metrics['sortino_recession']:.2f}")
        print(
            f"Maximum Drawdown (Growth): {test_metrics['max_drawdown_growth']:.2%}"
        )
        print(
            f"Maximum Drawdown (Recession): {test_metrics['max_drawdown_recession']:.2%}"
        )
    
        # Overfitting Assessment
        train_val_return_diff = abs(train_metrics["CAGR"] - validation_metrics["CAGR"])
        train_test_return_diff = abs(train_metrics["CAGR"] - test_metrics["CAGR"])
        train_val_vol_diff = abs(train_metrics["volatility"] - validation_metrics["volatility"])
        train_test_vol_diff = abs(train_metrics["volatility"] - test_metrics["volatility"])
    
        threshold_return = 0.05  # 5% difference in return
        threshold_volatility = 0.05  # 5% difference in volatility
    
        overfitting_return = train_test_return_diff > threshold_return
        overfitting_vol = train_test_vol_diff > threshold_volatility
    
        print("\n--- Overfitting Assessment ---")
        if overfitting_return and overfitting_vol:
            print(
                "Warning: Overfitting detected! The portfolio performs significantly better on training and validation data compared to testing data."
            )
        else:
            print(
                "No significant overfitting detected. The portfolio generalizes well to unseen data."
            )
    
        # Plot cumulative returns for visual assessment
        plt.figure(figsize=(14, 7))
    
        # Training Cumulative Returns
        plt.subplot(1, 2, 1)
        if not train_metrics["cum_returns_growth"].empty:
            plt.plot(
                train_metrics["cum_returns_growth"].index,
                train_metrics["cum_returns_growth"],
                label="Training Growth",
            )
        if not train_metrics["cum_returns_recession"].empty:
            plt.plot(
                train_metrics["cum_returns_recession"].index,
                train_metrics["cum_returns_recession"],
                label="Training Recession",
            )
        if not validation_metrics["cum_returns_growth"].empty:
            plt.plot(
                validation_metrics["cum_returns_growth"].index,
                validation_metrics["cum_returns_growth"],
                label="Validation Growth",
            )
        if not validation_metrics["cum_returns_recession"].empty:
            plt.plot(
                validation_metrics["cum_returns_recession"].index,
                validation_metrics["cum_returns_recession"],
                label="Validation Recession",
            )
        if not test_metrics["cum_returns_growth"].empty:
            plt.plot(
                test_metrics["cum_returns_growth"].index,
                test_metrics["cum_returns_growth"],
                label="Testing Growth",
            )
        if not test_metrics["cum_returns_recession"].empty:
            plt.plot(
                test_metrics["cum_returns_recession"].index,
                test_metrics["cum_returns_recession"],
                label="Testing Recession",
            )
        plt.title("Cumulative Returns")
        plt.xlabel("Date")
        plt.ylabel("Cumulative Return")
        plt.legend()
    
        # Drawdowns
        plt.subplot(1, 2, 2)
        if not train_metrics["cum_returns_growth"].empty:
            plt.plot(
                train_metrics["cum_returns_growth"].index,
                (train_metrics["cum_returns_growth"]
                 / train_metrics["cum_returns_growth"].cummax()) - 1,
                label="Training Growth Drawdown",
            )
        if not train_metrics["cum_returns_recession"].empty:
            plt.plot(
                train_metrics["cum_returns_recession"].index,
                (train_metrics["cum_returns_recession"]
                 / train_metrics["cum_returns_recession"].cummax()) - 1,
                label="Training Recession Drawdown",
            )
        if not validation_metrics["cum_returns_growth"].empty:
            plt.plot(
                validation_metrics["cum_returns_growth"].index,
                (validation_metrics["cum_returns_growth"]
                 / validation_metrics["cum_returns_growth"].cummax()) - 1,
                label="Validation Growth Drawdown",
            )
        if not validation_metrics["cum_returns_recession"].empty:
            plt.plot(
                validation_metrics["cum_returns_recession"].index,
                (validation_metrics["cum_returns_recession"]
                 / validation_metrics["cum_returns_recession"].cummax()) - 1,
                label="Validation Recession Drawdown",
            )
        if not test_metrics["cum_returns_growth"].empty:
            plt.plot(
                test_metrics["cum_returns_growth"].index,
                (test_metrics["cum_returns_growth"]
                 / test_metrics["cum_returns_growth"].cummax()) - 1,
                label="Testing Growth Drawdown",
            )
        if not test_metrics["cum_returns_recession"].empty:
            plt.plot(
                test_metrics["cum_returns_recession"].index,
                (test_metrics["cum_returns_recession"]
                 / test_metrics["cum_returns_recession"].cummax()) - 1,
                label="Testing Recession Drawdown",
            )
        plt.title("Drawdowns")
        plt.xlabel("Date")
        plt.ylabel("Drawdown")
        plt.legend()
    
        plt.tight_layout()
        plt.show()
    
    # Close the multiprocessing pool
    pool.close()
    pool.join()
    

    Key Modifications:

    • Objective Weights: Updated the weights according to your instructions.
    • CAGR Calculation: Replaced cumulative return calculations with CAGR.
    • Code Refactoring: Improved readability by separating concerns and reducing redundancy.
    • Post-Hoc Display: Delayed display of results until the genetic algorithm concludes.

    Run this updated code to optimize and evaluate the portfolio based on your specified criteria.