ScikitLearn Long/Short Algorithm

import numpy as np
from sklearn.linear_model import LinearRegression

class ScikitLearnLongShortAlgorithm(QCAlgorithm):
    def initialize(self):
        self.set_start_date(2015, 10, 7)
        self.set_end_date(2024, 10, 8)
        self.lookback = 28
        self.set_cash(1000000)
        symbols = ["SPY", "AAPL", "NFLX", "ADBE", "META", "LLY", "WMT", "NVDA", "BA", "MSFT", "AMZN", "GOOG", "JPM", "HD", "NKE", "TSLA"]
        self.symbols = [self.add_equity(symbol, Resolution.MINUTE).symbol for symbol in symbols]
        self.schedule.on(self.date_rules.every_day(), 
                         self.time_rules.after_market_open("SPY", 28), 
                         self.regression)
        self.schedule.on(self.date_rules.every_day(), 
                         self.time_rules.after_market_open("SPY", 30), 
                         self.trade)
    def regression(self):
        history = self.history(self.symbols, self.lookback, Resolution.DAILY)
        self.prices = {}
        self.slopes = {}
        for symbol in self.symbols:
            if not history.empty:
                self.prices[symbol] = list(history.loc[symbol.value]['open'])
        A = range(self.lookback + 1)
        for symbol in self.symbols:
            if symbol in self.prices:
                Y = self.prices[symbol]
                X = np.column_stack([np.ones(len(A)), A])
                length = min(len(X), len(Y))
                X = X[-length:]
                Y = Y[-length:]
                A = A[-length:]
                reg = LinearRegression().fit(X, Y)
                b = reg.intercept_
                a = reg.coef_[1]
                self.slopes[symbol] = a / b
    def trade(self):
        if not self.prices:
            return
        thod_buy = 0.003
        thod_sell = -0.006
        thod_liquidate = -0.005
        thod_cover = 0.001
        allocation = 2 / len(self.symbols)
        for holding in self.portfolio.values():
            slope = self.slopes[holding.symbol]
            if holding.invested and holding.is_long and slope < thod_liquidate:
                self.liquidate(holding.symbol)
            if holding.invested and holding.is_short and slope > thod_cover:
                self.liquidate(holding.symbol)
        for symbol in self.symbols:
            slope = self.slopes[symbol]
            if slope > thod_buy and not self.portfolio[symbol].invested:
                self.set_holdings(symbol, allocation)
            elif slope < thod_sell and not self.portfolio[symbol].invested:
                self.set_holdings(symbol, -allocation)

Sources: CAPM Alpha Ranking Strategy On Dow 30 Companies, Gaussian Naive Bayes Model