实战：基于NumPy的股价统计分析应用
基于NumPy的股价统计分析应用
构造数据
- 构造以下数据。其中，第4-8列，即EXCEL表格中的D-H列，分别为股票的开盘价，最高价，最低价，收盘价，成交量。
with open("./data/stock_data.csv", "w") as fdata:
fdata.write("""AAPL,28-01-2011, ,344.17,344.4,333.53,336.1,21144800
AAPL,31-01-2011, ,335.8,340.04,334.3,339.32,13473000
AAPL,01-02-2011, ,341.3,345.65,340.98,345.03,15236800
AAPL,02-02-2011, ,344.45,345.25,343.55,344.32,9242600
AAPL,03-02-2011, ,343.8,344.24,338.55,343.44,14064100
AAPL,04-02-2011, ,343.61,346.7,343.51,346.5,11494200
AAPL,07-02-2011, ,347.89,353.25,347.64,351.88,17322100
AAPL,08-02-2011, ,353.68,355.52,352.15,355.2,13608500
AAPL,09-02-2011, ,355.19,359,354.87,358.16,17240800
AAPL,10-02-2011, ,357.39,360,348,354.54,33162400
AAPL,11-02-2011, ,354.75,357.8,353.54,356.85,13127500
AAPL,14-02-2011, ,356.79,359.48,356.71,359.18,11086200
AAPL,15-02-2011, ,359.19,359.97,357.55,359.9,10149000
AAPL,16-02-2011, ,360.8,364.9,360.5,363.13,17184100
AAPL,17-02-2011, ,357.1,360.27,356.52,358.3,18949000
AAPL,18-02-2011, ,358.21,359.5,349.52,350.56,29144500
AAPL,22-02-2011, ,342.05,345.4,337.72,338.61,31162200
AAPL,23-02-2011, ,338.77,344.64,338.61,342.62,23994700
AAPL,24-02-2011, ,344.02,345.15,338.37,342.88,17853500
AAPL,25-02-2011, ,345.29,348.43,344.8,348.16,13572000
AAPL,28-02-2011, ,351.21,355.05,351.12,353.21,14395400
AAPL,01-03-2011, ,355.47,355.72,347.68,349.31,16290300
AAPL,02-03-2011, ,349.96,354.35,348.4,352.12,21521000
AAPL,03-03-2011, ,357.2,359.79,355.92,359.56,17885200
AAPL,04-03-2011, ,360.07,360.29,357.75,360,16188000
AAPL,07-03-2011, ,361.11,361.67,351.31,355.36,19504300
AAPL,08-03-2011, ,354.91,357.4,352.25,355.76,12718000
AAPL,09-03-2011, ,354.69,354.76,350.6,352.47,16192700
AAPL,10-03-2011, ,349.69,349.77,344.9,346.67,18138800
AAPL,11-03-2011, ,345.4,352.32,345,351.99,16824200
""")
读取数据
- 使用 np.loadtxt 方法读取CSV文件
import numpy as np
end_price, turnover = np.loadtxt(
fname="./data/stock_data.csv",
delimiter=',',
usecols=(6, 7),
unpack=True
)
print(end_price)
print(turnover)
[336.1 339.32 345.03 344.32 343.44 346.5 351.88 355.2 358.16 354.54
356.85 359.18 359.9 363.13 358.3 350.56 338.61 342.62 342.88 348.16
353.21 349.31 352.12 359.56 360. 355.36 355.76 352.47 346.67 351.99]
[21144800. 13473000. 15236800. 9242600. 14064100. 11494200. 17322100.
13608500. 17240800. 33162400. 13127500. 11086200. 10149000. 17184100.
18949000. 29144500. 31162200. 23994700. 17853500. 13572000. 14395400.
16290300. 21521000. 17885200. 16188000. 19504300. 12718000. 16192700.
18138800. 16824200.]
numpy.loadtxt需要传入4个关键字参数：
1.fname是文件名，数据类型为字符串str；
2.delimiter是分隔符，数据类型为字符串str；
3.usecols是读取的列数，数据类型为元组tuple,其中元素个数有多少个，则选出多少列；
4.unpack是是否解包，数据类型为布尔bool。
应用
计算成交量加权平均价格
- 概念：成交量加权平均价格，英文名VWAP(Volume-Weighted Average Price，成交量加权平均价格）是一个非常重要的经济学量，代表着金融资产的“平均”价格。
- 某个价格的成交量越大，该价格所占的权重就越大。VWAP就是以成交量为权重计算出来的加权平均值。
import numpy as np
end_price, turnover = np.loadtxt(
fname="./data/stock_data.csv",
delimiter=',',
usecols=(6, 7),
unpack=True
)
print(np.average(end_price))
print(np.average(end_price, weights=turnover))
351.0376666666667
350.5895493532009
计算最大值和最小值
import numpy as np
high_price, low_price = np.loadtxt(
fname="./data/stock_data.csv",
delimiter=',',
usecols=(4, 5),
unpack=True
)
print("max=", high_price.max())
print("min=", low_price.min())
max= 364.9
min= 333.53
计算极差
- 计算股价近期最高价的最大值和最小值的差值 和 计算股价近期最低价的最大值和最小值的差值
np.ptp(a, axis=None, out=None, keepdims=
)
import numpy as np
high_price, low_price = np.loadtxt(
fname="./data/stock_data.csv",
delimiter=',',
usecols=(4, 5),
unpack=True
)
print("max - min of high price:", np.ptp(high_price))
print("max - min of low price:", np.ptp(low_price))
max - min of high price: 24.859999999999957
max - min of low price: 26.970000000000027
计算中位数
- 计算收盘价的中位数。
import numpy as np
end_price = np.loadtxt(
fname="./data/stock_data.csv",
delimiter=',',
usecols=6
)
print("median =", np.median(end_price))
median = 352.055
计算方差
- 计算收盘价的方差。
import numpy as np
end_price = np.loadtxt(
fname="./data/stock_data.csv",
delimiter=',',
usecols=6
)
print("variance =", np.var(end_price))
print("variance =", end_price.var())
variance = 50.126517888888884
variance = 50.126517888888884
计算股票收益率、年波动率及月波动率
- 在投资学中，波动率是对价格变动的一种度量，历史波动率可以根据历史价格数据计算得出。计算历史波动率时，需要用到对数收益率。
- 年波动率等于对数收益率的标准差除以其均值，再乘以交易日的平方根，通常交易日取252天。
- 月波动率等于对数收益率的标准差除以其均值，再乘以交易月的平方根。通常交易月取12月。
import numpy as np
end_price = np.loadtxt(
fname="./data/stock_data.csv",
delimiter=',',
usecols=6
)
log_returns = np.diff(np.log(end_price))
annual_volatility = log_returns.std() / log_returns.mean() * np.sqrt(252)
monthly_volatility = log_returns.std() / log_returns.mean() * np.sqrt(12)
print("年波动率", annual_volatility)
print("月波动率", monthly_volatility)
年波动率 129.27478991115134
月波动率 28.210071915112593
