intraday_final_func.py

def backtestPerformanceVis(ticker, n_hours, training_hours, mov_avg, forecast_hours):
    """
    Consolidates the previous functions that support the backtesting process.
    """
    # Getting Price data
    print("Getting price data...")
    prices = getIntradayPrices(
        crypto=ticker, 
        n_hours=n_hours, 
        training_hours=training_hours, 
        mov_avg=mov_avg
    )

    # Predicting over time
    print("Running predictions...")
    pred_df = runningFBP(
        prices, 
        forecast_hours=forecast_hours, 
        training_hours=training_hours
    )
    
    # Adding sentiment positions to the prediction DF
    print("Getting positions...")
    positions = pred_df

    # Getting forecast prophet positions
    positions['fbp_positions'] = positions.apply(
        lambda x: fbpPositions(x, short=True), 
        axis=1
    )

    # Buy and hold position
    positions['buy_hold'] = 1

    # Random positions
    positions['random_positions'] = random.choices(
        [1,0,-1], k=len(positions)
    )
    
    # Getting returns each hour
    print("Performing the backtest...")
    log_returns = prices[['ds', 'open']].set_index(
        'ds'
    ).loc[positions.index].apply(np.log).diff()
    
    # The positions to backtest (shifted ahead by 1 to prevent lookahead bias)
    bt_positions = positions[[
        'buy_hold', 
        'random_positions',
        'fbp_positions'
    ]].shift(1)

    # The returns during the backtest
    returns = bt_positions.multiply(
        log_returns['open'], 
        axis=0
    )

    # Inversing the log returns to get daily portfolio balance
    performance = returns.cumsum().apply(
        np.exp
    ).dropna().fillna(
        method='ffill'
    )
    
    # Displaying the final balance of the portfolio
    print("Final Performance:")
    display(performance.tail(1))
    
    # Visualizing results
    fig = px.line(
        performance,
        x=performance.index,
        y=performance.columns,
        title='FBProphet, Buy&Hold, Random Positions',
        labels={"value": "Portfolio Balance",
                "index": "Date"}
    )

    return fig.show()