from AlgorithmImports import *
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
import numpy as np
import pandas as pd

# Custom fee model for 0.1% per trade
class PercentageFeeModel(FeeModel):
    def GetOrderFee(self, parameters):
        security = parameters.Security
        order = parameters.Order
        fee = 0.001 * security.Price * abs(order.Quantity)
        currency = security.QuoteCurrency.Symbol  # Correctly get the currency code
        return OrderFee(CashAmount(fee, currency))

class MLTradingAlgorithm(QCAlgorithm):
    
    def Initialize(self):
        # Algorithm Parameters
        self.SetStartDate(2019, 1, 1)         # Start date
        self.SetEndDate(2024, 12, 31)         # End date
        self.SetCash(10000)                   # Initial capital

        # Configurable ticker symbols with defaults
        self.trading_ticker = self.GetParameter("trading_ticker", "MSTR")
        self.benchmark_ticker = self.GetParameter("benchmark_ticker", "SPY")

        # Add trading equity with custom fee and slippage models
        trading_security = self.AddEquity(self.trading_ticker, Resolution.Daily)
        trading_security.SetFeeModel(PercentageFeeModel())
        trading_security.SetSlippageModel(ConstantSlippageModel(0))
        self.symbol = trading_security.Symbol
        
        # Add benchmark equity with custom fee and slippage models
        benchmark_security = self.AddEquity(self.benchmark_ticker, Resolution.Daily)
        benchmark_security.SetFeeModel(PercentageFeeModel())
        benchmark_security.SetSlippageModel(ConstantSlippageModel(0))
        self.benchmark_symbol = benchmark_security.Symbol

        # RollingWindow to store 200 days of TradeBar data for trading asset
        self.data = RollingWindow[TradeBar](200)

        # Warm-up period
        self.SetWarmUp(200)

        # Initialize Random Forest model
        self.model = RandomForestClassifier(random_state=42)
        self.training_count = 0
        self.is_model_trained = False  # Tracks if the model is trained

        # Schedule training every Monday at 10:00 AM
        self.Schedule.On(self.DateRules.Every(DayOfWeek.Monday), 
                         self.TimeRules.At(10, 0), 
                         self.TrainModel)
        
        # Initialize variables for benchmarking
        self.previous_portfolio_value = None
        self.previous_benchmark_close = None
        self.beat_benchmark_count = 0
    
    def OnData(self, data):
        # Ensure data exists for trading symbol
        if not data.ContainsKey(self.symbol):
            return
        
        trade_bar = data[self.symbol]
        if trade_bar is None:
            return
        
        # Add TradeBar to Rolling Window
        self.data.Add(trade_bar)

        # Check if RollingWindow is ready
        if not self.data.IsReady or self.data.Count < 200:
            return
        
        # Ensure model is trained before making predictions
        if not self.is_model_trained:
            self.Debug("Model is not trained yet. Skipping prediction.")
            return

        # Extract features for prediction
        df = self.GetFeatureDataFrame()
        if df is None or len(df) < 1:
            return
        
        latest_features = df.iloc[-1, :-1].values.reshape(1, -1)
        
        # Make predictions using probability threshold
        try:
            prob_class = self.model.predict_proba(latest_features)[0][1]  # Probability of class 1
            prediction = 1 if prob_class > 0.5 else 0
        except Exception as e:
            self.Debug(f"Error: Model prediction failed. {e}")
            return
        
        # Trading logic
        holdings = self.Portfolio[self.symbol].Quantity
        
        # Buy if prediction = 1 and not currently invested
        if prediction == 1 and holdings <= 0:
            self.SetHoldings(self.symbol, 1) 
        # Sell if prediction = 0 and currently invested
        elif prediction == 0 and holdings > 0:
            self.Liquidate(self.symbol)
        
        # Benchmarking against benchmark symbol
        if self.benchmark_symbol in data and data[self.benchmark_symbol] is not None:
            current_benchmark_close = data[self.benchmark_symbol].Close
            current_portfolio_value = self.Portfolio.TotalPortfolioValue
            
            # Calculate daily returns if previous values are available
            if self.previous_portfolio_value is not None and self.previous_benchmark_close is not None:
                strategy_return = (current_portfolio_value - self.previous_portfolio_value) / self.previous_portfolio_value
                benchmark_return = (current_benchmark_close - self.previous_benchmark_close) / self.previous_benchmark_close
                if strategy_return > benchmark_return:
                    self.beat_benchmark_count += 1
            
            # Update previous values
            self.previous_portfolio_value = current_portfolio_value
            self.previous_benchmark_close = current_benchmark_close

    def TrainModel(self):
        # Prepare training data
        df = self.GetFeatureDataFrame()
        if df is None or len(df) < 50:  # Require enough data to train
            self.Debug("Insufficient data for training.")
            return

        # Split data chronologically (no shuffle)
        X = df.iloc[:, :-1]  # Features
        y = df.iloc[:, -1]   # Target (0 or 1)
        
        X_train, X_test, y_train, y_test = train_test_split(
            X, y, test_size=0.2, shuffle=False, random_state=42
        )

        # Train Random Forest model
        self.model.fit(X_train, y_train)
        self.is_model_trained = True

        # Evaluate model performance
        y_train_prob = self.model.predict_proba(X_train)[:, 1]
        y_train_pred_binary = [1 if val > 0.5 else 0 for val in y_train_prob]
        train_accuracy = accuracy_score(y_train, y_train_pred_binary)

        y_test_prob = self.model.predict_proba(X_test)[:, 1]
        y_test_pred_binary = [1 if val > 0.5 else 0 for val in y_test_prob]
        test_accuracy = accuracy_score(y_test, y_test_pred_binary)
        
        self.training_count += 1
        self.Debug(f"Training #{self.training_count}: "
                   f"Train Accuracy: {train_accuracy:.2%}, "
                   f"Test Accuracy: {test_accuracy:.2%}")

    def GetFeatureDataFrame(self):
        # Wait until we have 200 data points in the rolling window
        if self.data.Count < 200:
            return None
        
        # Convert rolling window data to a DataFrame
        close_prices = [bar.Close for bar in self.data]
        df = pd.DataFrame(close_prices, columns=["Close"])
        
        # Feature Engineering
        df["SMA_10"] = df["Close"].rolling(window=10).mean()
        df["SMA_50"] = df["Close"].rolling(window=50).mean()
        
        # RSI Calculation
        delta = df["Close"].diff()
        gain = (delta.where(delta > 0, 0)).rolling(14).mean()
        loss = (-delta.where(delta < 0, 0)).rolling(14).mean()
        rs = gain / loss
        df["RSI"] = 100 - (100 / (1 + rs))
        
        # MACD Calculation
        df["MACD"] = df["Close"].ewm(span=12, adjust=False).mean() - df["Close"].ewm(span=26, adjust=False).mean()
        df["MACD_Signal"] = df["MACD"].ewm(span=9, adjust=False).mean()

        # Historical Volatility (HV_30)
        df["HV_30"] = df["Close"].pct_change().rolling(window=30).std() * np.sqrt(252)

        # Define Target: 1 if next day's Close > today's Close, else 0
        df["Target"] = (df["Close"].shift(-1) > df["Close"]).astype(int)
        
        # Remove rows with NaN values
        df.dropna(inplace=True)

        return df
    
    def OnEndOfAlgorithm(self):
        # Print the number of times the strategy beat the benchmark
        self.Log(f"Number of times strategy beat {self.benchmark_ticker}: {self.beat_benchmark_count}")