python - Python：如何循环代码，以便一个接一个地从 csv 文件中提取列？

Question

我需要帮助的问题是：如何循环代码，以便它一个接一个地从 csv 文件中提取列？我的 excel 文件， r 和 m 目前各有 1 列（单元格数量相等）。我希望代码以与目前相同的方式执行计算，然后跳转到 csv m 和 r 中的第二列并执行相同的计算 - 我需要能够对所有列重复此过程（我有两个文件中大约有 1300 列）。你能告诉我怎么做吗？

编码

import math
import numpy

"""
Note - for some of the metrics the absolute value is returns. This is because if the risk (loss) is higher we want to
discount the expected excess return from the portfolio by a higher amount. Therefore risk should be positive.
"""


def vol(returns):
    # Return the standard deviation of returns
    return numpy.std(returns)


def beta(returns, market):
    # Create a matrix of [returns, market]
    m = numpy.matrix([returns, market])
    # Return the covariance of m divided by the standard deviation of the market returns
    return numpy.cov(m)[0][1] / numpy.std(market)


def lpm(returns, threshold, order):
    # This method returns a lower partial moment of the returns
    # Create an array he same length as returns containing the minimum return threshold
    threshold_array = numpy.empty(len(returns))
    threshold_array.fill(threshold)
    # Calculate the difference between the threshold and the returns
    diff = threshold_array - returns
    # Set the minimum of each to 0
    diff = diff.clip(min=0)
    # Return the sum of the different to the power of order
    return numpy.sum(diff ** order) / len(returns)


def hpm(returns, threshold, order):
    # This method returns a higher partial moment of the returns
    # Create an array he same length as returns containing the minimum return threshold
    threshold_array = numpy.empty(len(returns))
    threshold_array.fill(threshold)
    # Calculate the difference between the returns and the threshold
    diff = returns - threshold_array
    # Set the minimum of each to 0
    diff = diff.clip(min=0)
    # Return the sum of the different to the power of order
    return numpy.sum(diff ** order) / len(returns)


def var(returns, alpha):
    # This method calculates the historical simulation var of the returns
    sorted_returns = numpy.sort(returns)
    # Calculate the index associated with alpha
    index = int(alpha * len(sorted_returns))
    # VaR should be positive
    return abs(sorted_returns[index])


def cvar(returns, alpha):
    # This method calculates the condition VaR of the returns
    sorted_returns = numpy.sort(returns)
    # Calculate the index associated with alpha
    index = int(alpha * len(sorted_returns))
    # Calculate the total VaR beyond alpha
    sum_var = sorted_returns[0]
    for i in range(1, index):
        sum_var += sorted_returns[i]
    # Return the average VaR
    # CVaR should be positive
    return abs(sum_var / index)


def prices(returns, base):
    # Converts returns into prices
    s = [base]
    for i in range(len(returns)):
        s.append(base * (1 + returns[i]))
    return numpy.array(s)


def dd(returns, tau):
    # Returns the draw-down given time period tau
    values = prices(returns, 100)
    pos = len(values) - 1
    pre = pos - tau
    drawdown = float('+inf')
    # Find the maximum drawdown given tau
    while pre >= 0:
        dd_i = (values[pos] / values[pre]) - 1
        if dd_i < drawdown:
            drawdown = dd_i
        pos, pre = pos - 1, pre - 1
    # Drawdown should be positive
    return abs(drawdown)


def max_dd(returns):
    # Returns the maximum draw-down for any tau in (0, T) where T is the length of the return series
    max_drawdown = float('-inf')
    for i in range(0, len(returns)):
        drawdown_i = dd(returns, i)
        if drawdown_i > max_drawdown:
            max_drawdown = drawdown_i
    # Max draw-down should be positive
    return abs(max_drawdown)


def average_dd(returns, periods):
    # Returns the average maximum drawdown over n periods
    drawdowns = []
    for i in range(0, len(returns)):
        drawdown_i = dd(returns, i)
        drawdowns.append(drawdown_i)
    drawdowns = sorted(drawdowns)
    total_dd = abs(drawdowns[0])
    for i in range(1, periods):
        total_dd += abs(drawdowns[i])
    return total_dd / periods


def average_dd_squared(returns, periods):
    # Returns the average maximum drawdown squared over n periods
    drawdowns = []
    for i in range(0, len(returns)):
        drawdown_i = math.pow(dd(returns, i), 2.0)
        drawdowns.append(drawdown_i)
    drawdowns = sorted(drawdowns)
    total_dd = abs(drawdowns[0])
    for i in range(1, periods):
        total_dd += abs(drawdowns[i])
    return total_dd / periods


def treynor_ratio(er, returns, market, rf):
    return (er - rf) / beta(returns, market)


def sharpe_ratio(er, returns, rf):
    return (er - rf) / vol(returns)


def information_ratio(returns, benchmark):
    diff = returns - benchmark
    return numpy.mean(diff) / vol(diff)


def modigliani_ratio(er, returns, benchmark, rf):
    np_rf = numpy.empty(len(returns))
    np_rf.fill(rf)
    rdiff = returns - np_rf
    bdiff = benchmark - np_rf
    return (er - rf) * (vol(rdiff) / vol(bdiff)) + rf


def excess_var(er, returns, rf, alpha):
    return (er - rf) / var(returns, alpha)


def conditional_sharpe_ratio(er, returns, rf, alpha):
    return (er - rf) / cvar(returns, alpha)


def omega_ratio(er, returns, rf, target=0):
    return (er - rf) / lpm(returns, target, 1)


def sortino_ratio(er, returns, rf, target=0):
    return (er - rf) / math.sqrt(lpm(returns, target, 2))


def kappa_three_ratio(er, returns, rf, target=0):
    return (er - rf) / math.pow(lpm(returns, target, 3), float(1/3))


def gain_loss_ratio(returns, target=0):
    return hpm(returns, target, 1) / lpm(returns, target, 1)


def upside_potential_ratio(returns, target=0):
    return hpm(returns, target, 1) / math.sqrt(lpm(returns, target, 2))


def calmar_ratio(er, returns, rf):
    return (er - rf) / max_dd(returns)


def sterling_ration(er, returns, rf, periods):
    return (er - rf) / average_dd(returns, periods)


def burke_ratio(er, returns, rf, periods):
    return (er - rf) / math.sqrt(average_dd_squared(returns, periods))


def test_risk_metrics(r, m):
    print("vol =", vol(r))
    print("beta =", beta(r, m))
    print("hpm(0.0)_1 =", hpm(r, 0.0, 1))
    print("lpm(0.0)_1 =", lpm(r, 0.0, 1))
    print("VaR(0.05) =", var(r, 0.05))
    print("CVaR(0.05) =", cvar(r, 0.05))
    print("Drawdown(5) =", dd(r, 5))
    print("Max Drawdown =", max_dd(r))


def test_risk_adjusted_metrics(r, m):
    # Returns from the portfolio (r) and market (m)
    # Expected return
    e = numpy.mean(r)
    # Risk free rate
    f = 0.06
    # Risk-adjusted return based on Volatility
    print("Treynor Ratio =", treynor_ratio(e, r, m, f))
    print("Sharpe Ratio =", sharpe_ratio(e, r, f))
    print("Information Ratio =", information_r
          atio(r, m))
    # Risk-adjusted return based on Value at Risk
    print("Excess VaR =", excess_var(e, r, f, 0.05))
    print("Conditional Sharpe Ratio =", conditional_sharpe_ratio(e, r, f, 0.05))
    # Risk-adjusted return based on Lower Partial Moments
    print("Omega Ratio =", omega_ratio(e, r, f))
    print("Sortino Ratio =", sortino_ratio(e, r, f))
    print("Kappa 3 Ratio =", kappa_three_ratio(e, r, f))
    print("Gain Loss Ratio =", gain_loss_ratio(r))
    print("Upside Potential Ratio =", upside_potential_ratio(r))
    # Risk-adjusted return based on Drawdown risk
    print("Calmar Ratio =", calmar_ratio(e, r, f))
    print("Sterling Ratio =", sterling_ration(e, r, f, 5))
    print("Burke Ratio =", burke_ratio(e, r, f, 5))


if __name__ == "__main__":
    import csv

    # load r
    with open(r'C:\Users\Lenovo\Documents\r.csv') as csvfile:  # change your filename here
        r = numpy.array([float(x[0]) for x in csv.reader(csvfile)])

    # load m
    with open(r'C:\Users\Lenovo\Documents\m.csv') as csvfile:  # change your filename here
        m = numpy.array([float(x[0]) for x in csv.reader(csvfile)])

    test_risk_metrics(r, m)
    test_risk_adjusted_metrics(r, m)

标签： pythonpython-3.xnumpy

Answer 1

既然您提到每列可能有不同的长度，那么我提出一个解决方案，您可以逐行读取r和文件，而不是逐列读取。m原因是因为通过不同长度的列进行迭代会出现问题，但更重要的是，这也意味着我们必须将整个 CSV 加载到内存中，然后对列进行迭代。当我们逐行读取时，我们使用的内存更少，而且我们不必担心每行元素的长度不同。

由于我们是逐行阅读，我们不再需要依赖 csv 包。我们可以简单地将我们的文件加载为文本文件，并将我们的值用空格、逗号或您认为合适的任何其他标点符号分隔。出于本示例的目的，我将使用逗号分隔值。

假设我们的r_values文件在下面，其中文件中的每一行代表一个值数组以提供给您的函数：

1.22,3.33,3.24,0.32,0.13
2.42,35.43,2.43,87.77,0.98,0.32,32.43,9.56,74.32,2.32
8.78,0.23,64.61,7.23,8.77,76.77

我们的m_values文件是：

4.23,7.56,98.65,4.87,9.32
3.34,9.45,0.32,86.44,9.45,3.53,0.65,0.43,1.43,65.54
3.34,89.54,8.43,7.54,83.2,8.43

现在在我们的__name__ == '__main__'块中，我们加载文件，并遍历这些行，同时将它们传递给test_risk_metricsandtest_risk_adjusted_metrics函数：

if __name__ == "__main__":
    with open(r'C:\path\to\r_values.csv') as r_file, \
         open(r'C:\path\to\m_values.csv') as m_file:
        for r, m in zip(r_file, m_file):
            # since our lines are separated by commas, we use `split` function
            # we also cast our values as float
            r = numpy.array([float(x) for x in r.split(',')])
            m = numpy.array([float(x) for x in m.split(',')])

            # diagnostic check
            print(r)  # comment out
            print(m)  # comment out

            # pass to `test_risk_metrics` and `test_risk_adjusted_metrics`
            test_risk_metrics(r, m)
            test_risk_adjusted_metrics(r, m)

最后，这是输出：

[1.22 3.33 3.24 0.32 0.13]
[ 4.23  7.56 98.65  4.87  9.32]
vol = 1.3866996790942157
beta = 0.9980359303098474
hpm(0.0)_1 = 1.6480000000000001
lpm(0.0)_1 = 0.0
VaR(0.05) = 0.13
test.py:68: RuntimeWarning: divide by zero encountered in double_scalars
  return abs(sum_var / index)
CVaR(0.05) = inf
Drawdown(5) = 0.1299999999999999
Max Drawdown = 0.7390300230946882
Treynor Ratio = 1.591125080543938
Sharpe Ratio = 1.145165044703315
Information Ratio = -0.6443354312329719
Excess VaR = 12.215384615384616
Conditional Sharpe Ratio = 0.0
test.py:162: RuntimeWarning: divide by zero encountered in double_scalars
  return (er - rf) / lpm(returns, target, 1)
Omega Ratio = inf
test.py:166: RuntimeWarning: divide by zero encountered in double_scalars
  return (er - rf) / math.sqrt(lpm(returns, target, 2))
Sortino Ratio = inf
test.py:170: RuntimeWarning: divide by zero encountered in double_scalars
  return (er - rf) / math.pow(lpm(returns, target, 3), float(1/3))
Kappa 3 Ratio = inf
test.py:174: RuntimeWarning: divide by zero encountered in double_scalars
  return hpm(returns, target, 1) / lpm(returns, target, 1)
Gain Loss Ratio = inf
test.py:178: RuntimeWarning: divide by zero encountered in double_scalars
  return hpm(returns, target, 1) / math.sqrt(lpm(returns, target, 2))
Upside Potential Ratio = inf
Calmar Ratio = 2.1487625
Sterling Ratio = 2.993751401271527
Burke Ratio = 2.647015918149671
[ 2.42 35.43  2.43 87.77  0.98  0.32 32.43  9.56 74.32  2.32]
[ 3.34  9.45  0.32 86.44  9.45  3.53  0.65  0.43  1.43 65.54]
vol = 30.812687581579116
beta = 14.103506402406339
hpm(0.0)_1 = 24.798
lpm(0.0)_1 = 0.0
VaR(0.05) = 0.32
CVaR(0.05) = inf
Drawdown(5) = 0.6140350877192983
Max Drawdown = 0.9851301115241635
Treynor Ratio = 1.7540318906636725
Sharpe Ratio = 0.8028510961435648
Information Ratio = 0.20592426973227423
Excess VaR = 77.30624999999999
Conditional Sharpe Ratio = 0.0
Omega Ratio = inf
Sortino Ratio = inf
Kappa 3 Ratio = inf
Gain Loss Ratio = inf
Upside Potential Ratio = inf
Calmar Ratio = 25.111403773584907
Sterling Ratio = 78.07671376290729
Burke Ratio = 50.392183664218216
[ 8.78  0.23 64.61  7.23  8.77 76.77]
[ 3.34 89.54  8.43  7.54 83.2   8.43]
vol = 30.714112074998287
beta = -18.831320000339733
hpm(0.0)_1 = 27.731666666666666
lpm(0.0)_1 = 0.0
VaR(0.05) = 0.23
CVaR(0.05) = inf
Drawdown(5) = 6.9519427402863
Max Drawdown = 6.9519427402863
Treynor Ratio = -1.4694491233842049
Sharpe Ratio = 0.9009430778626281
Information Ratio = -0.09563177846201822
Excess VaR = 120.31159420289855
Conditional Sharpe Ratio = 0.0
Omega Ratio = inf
Sortino Ratio = inf
Kappa 3 Ratio = inf
Gain Loss Ratio = inf
Upside Potential Ratio = inf
Calmar Ratio = 3.9804221209001316
Sterling Ratio = 73.39338628531124
Burke Ratio = 50.28169156965575