python - 如何修复 TypeError: *: 'method' 和 'float' 不支持的操作数类型

Question

尝试运行此代码时，我不断收到此错误。我不是 CS 学生，也没有编码背景，但我的教授认为给我们一个需要高水平编码知识的项目是个好主意。我不知道我能做些什么来解决这个问题。

TypeError                                 Traceback (most recent call last)
<ipython-input-11-851da82dbe8c> in <module>()
     18   weights /= np.sum(weights)
     19   portfolio_return = np.sum(mean_returns * weights) * 252
---> 20   portfolio_std_dev = np.sqrt(np.dot(weights.T,np.dot(cov_matrix, weights))) * np.sqrt(252)
     21   results[0,i] = portfolio_return
     22   results[1,i] = portfolio_std_dev

TypeError: unsupported operand type(s) for *: 'method' and 'float'

编辑：这是更完整的代码：

import pandas_datareader.data as web 
import numpy as np 
import pandas as pd
import matplotlib.pyplot as plt 

stocks = ['AMZN','V','K','GOOG','MSFT','JPM','GS','C','AMD','LOW','VZ','GE',
         'FB','AXP','AAPL','TSLA','PSX','NFLX','DG','BABA']
num_stocks = len(stocks)
data = web.DataReader(stocks,data_source='yahoo',start='01/01/2010')['Adj Close']
data = data.pct_change()
mean_returns = data.mean()
cov_matrix = data.cov
num_portfolios = 25000
results = np.zeros((3+num_stocks,num_portfolios))

for i in range(num_portfolios):
  weights = np.array(np.random.random(num_stocks))
  weights /= np.sum(weights)
  portfolio_return = np.sum(mean_returns * weights) * 252
  portfolio_std_dev = np.sqrt(np.dot(weights.T,np.dot(cov_matrix, weights))) * np.sqrt(252)
  results[0,i] = portfolio_return
  results[1,i] = portfolio_std_dev
  results[2,i] = results[0,i] / results[1,i]
  results[3:,i] = weights     

标签： python