用的是米筐的研究模块，从结果来看，均值方差模型对参数的敏感性很高，很多参数都不如随机权重，很难应用到实战。
import pandas as pdimport numpy as npfrom scipy import linalgimport matplotlib.pyplot as pltstockslist = ['000001.XSHE','000002.XSHE','600004.XSHG','600033.XSHG','000651.XSHE']data = get_price_change_rate(stockslist,start_date = '20100101',end_date = '20200420')data.to_csv('MeanVar.csv')print(data.head(20))train_set = data[data.index<'20171231']#print(train_set.tail(20))test_set = data[data.index>'20180101']#print(test_set.head(20)) #看一下5个股票的历史表现cumreturn = (1 + data).cumprod()cumreturn.plot()plt.title('Cumulative Return of Stocks')plt.show() #相关性分析data.corr() #核心模块，实现均值方差模型的计算class MeanVariance: #传入收益率数据 def __init__(self,returns): self.returns = returns #定义最小化方差函数，即求解二次规划 def minVar(self,goalRet): covs = np.array(self.returns.cov()) means = np.array(self.returns.mean()) L1 = np.append(np.append(covs.swapaxes(0,1),[means],0), [np.ones(len(means))],0).swapaxes(0,1) L2 = list(np.ones(len(means))) L2.extend([0,0]) L3 = list(means) L3.extend([0,0]) L4 = np.array([L2,L3]) L = np.append(L1,L4,0) results = linalg.solve(L,np.append(np.zeros(len(means)),[1,goalRet],0)) return np.array([list(self.returns.columns),results[:-2]]) #定义绘制最小方差前缘曲线函数 def frontierCurve(self): goals = [x/500000 for x in range(-100,4000)] variances = list(map(lambda x: self.calVar(self.minVar(x)[1,:].astype(np.float)),goals)) plt.plot(variances,goals) #定义各资产比例，计算收益率均值 def meanRet(self,fracs): meanRisky = ffn.to_returns(self.returns).mean() #assert (len(meanRisky == len(fracs),'Length of fractions must be equal to number of assets') return np.sum(np.multiply(meanRisky,np.array(fracs))) #定义各资产比例，计算收益率方差 def calVar(self,fracs): return np.dot(np.dot(fracs,self.returns.cov()),fracs) #计算有效前缘minVar = MeanVariance(data)minVar.frontierCurve() #计算训练集权重varMinimizer = MeanVariance(train_set)goal_return = 0.003portfolio_weight = varMinimizer.minVar(goal_return)portfolio_weight #计算测试集收益率test_return = np.dot(test_set,np.array([portfolio_weight[1,:].astype(np.float)]).swapaxes(0,1))test_return = pd.DataFrame(test_return,index = test_set.index)test_cum_return = (1+test_return).cumprod()#计算随机权重组合sim_weight = np.random.uniform(0,1,(100,len(stockslist)))sim_weight = np.apply_along_axis(lambda x: x/sum(x),1,sim_weight)sim_return = np.dot(test_set,sim_weight.swapaxes(0,1))sim_return = pd.DataFrame(sim_return,index = test_cum_return.index)sim_cum_return = (1+sim_return).cumprod()plt.plot(sim_cum_return.index,sim_cum_return,color = 'green')plt.plot(test_cum_return.index,test_cum_return,label = 'MeanVar')plt.legend()plt.title('MeanVar & Random')