ChatGPT generated QC Algo

Hey AlMoJo,

ChatGPT is not trained to program a strategy in QC in most cases the code will be wrong and you will spend more time trying to correct the code rather than writing it on your own. 

I can name a few things that are missing for it to work:

1. You do not add the equity to your system you just name the symbols. 

for x in self.assets:
  self.AddEquity(x, Resolution.Daily).Symbol

2. The program does not enter any function you will have to add this:

 self.Schedule.On(self.DateRules.EveryDay("SPY"),
                 self.TimeRules.AfterMarketOpen("SPY", 1),
                 self.EveryDayAfterMarketOpen)

3. You will have to use the history request to feed your indicators:

#Initialize
for x in self.assets:
            self.AddEquity(x, Resolution.Daily).Symbol
            self.ma60 = self.SMA(x, 60)
            self.ma150 = self.SMA(x, 150)
            self.rsi = self.RSI(x, 30)
            
#GetSignal
if not df.empty:
   for time, price in df.loc[symbol]["close"].iteritems():
   #UPDATE INDICATORS FIRST HERE -- YOU WILL FIND A FEW COMMENTS ON HOW THIS WORKS IN THE FORUM
   df.loc[time, 'ma60'] = self.ma60.Current.Value
   df.loc[time, 'ma150'] = self.ma150.Current.Value
   df.loc[time, 'rsi30'] = self.rsi.Current.Value
   
   
   #Make sure that the Indicators correspond to the right symbols and dont mix up
   		

4. At the end you want to probably know what the values will be so you could try to plot them:

if len(df) >= self.min_data:
            X = df['open', 'high', 'low', 'close', 'volume', 'ma60', 'ma150', 'rsi30']
            X = (X - X.mean()) / X.std()
            X = X.values
            regressor = LogisticRegression(random_state=0, solver='lbfgs', max_iter=100)
            signal = np.where(df['close'].shift(-1) > df['close'], 1, -1)
            X_train, X_test, y_train, y_test = train_test_split(X, signal, test_size=0.2, random_state=1990)
            regressor.fit(X_train, y_train)
            self.Plot("Signal", "Value", np.sign(regressor.predict(X)[-1]))
            return np.sign(regressor.predict(X)[-1])
        else:
            return 0
            self.Plot("Signal", "Value", 0)

Note: I did not take a look at the CreateStopLossAndTakeProfitOrders function. Also not sure why you created a rolling window for the portfolio value you can take a look at it in the backtest results.

Hope it helps ;)

Thank you very much Nico Xenox it is very kind from you! 😊