python数据处理——Numpy特殊例程

2021-01-04 10:13:09 浏览数 (1)

参考链接: Python中的numpy.extract

转载自:https://www.jianshu.com/p/dcc02facd405 

字典排序: 

import numpy as np

import datetime

# 日期转成字符串

def datestr2num(s):

    return datetime.datetime.strptime(s, "%d-%m-%Y").toordinal()

# 读取 AAPL 的日期和收盘价

# 并转换日期格式

dates,closes=np.loadtxt('AAPL.csv', delimiter=',', usecols=(1, 6), converters={1:datestr2num}, unpack=True)

# lexsort 接受属性的数组或元组

# 根据这些属性排序,返回下标

# 靠后的属性优先排序

indices = np.lexsort((dates, closes))

print "Indices", indices

print ["%s %s" % (datetime.date.fromordinal(int(dates[i])),  closes[i]) for i in indices]

'''

['2011-01-28 336.1', '2011-02-22 338.61', '2011-01-31 339.32', '2011-02-23 342.62', '2011-02-24 342.88', '2011-02-03 343.44', '2011-02-02 344.32', '2011-02-01 345.03', '2011-02-04 346.5', '2011-03-10 346.67', '2011-02-25 348.16', '2011-03-01 349.31', '2011-02-18 350.56', '2011-02-07 351.88', '2011-03-11 351.99', '2011-03-02 352.12', '2011-03-09 352.47', '2011-02-28 353.21', '2011-02-10 354.54', '2011-02-08 355.2', '2011-03-07 355.36', '2011-03-08 355.76', '2011-02-11 356.85', '2011-02-09 358.16', '2011-02-17 358.3', '2011-02-14 359.18', '2011-03-03 359.56', '2011-02-15 359.9', '2011-03-04 360.0', '2011-02-16 363.13']

''' 

复数排序: 

import numpy as np

# 生成随机的复数

np.random.seed(42)

complex_numbers = np.random.random(5) 1j * np.random.random(5)

print "Complex numbersn", complex_numbers

# sort_complex 按照先实部后虚部的顺序对复数排序

print "Sortedn", np.sort_complex(complex_numbers)

'''

Sorted

[ 0.39342751 0.34955771j  0.40597665 0.77477433j  0.41516850 0.26221878j

  0.86631422 0.74612422j  0.92293095 0.81335691j] 

 使用 searchsorted 

import numpy as np

a = np.arange(5)

# searchsorted 的第一个参数 a 是有序数组

# 第二个参数 v 是插入值的数组

# 返回插入值在有序数组中的位置

indices = np.searchsorted(a, [-2, 7])

print "Indices", indices

# Indices [0 5]

# 将这些值插入后,数组也能保持有序

print "The full array", np.insert(a, indices, [-2, 7])

# The full array [-2  0  1  2  3  4  7] 

 从数组移除元素 

import numpy as np

a = np.arange(7)

# condition 是一个布尔索引

condition = (a % 2) == 0

# extract 从 a 中选取条件为 condition 的元素

# 等价于 a[conditon]

print "Even numbers", np.extract(condition, a)

# Even numbers [0 2 4 6]

# nonzero 选取 a 的非零元素

# 等价于 a[a != 0]

print "Non zero", np.nonzero(a)

# Non zero (array([1, 2, 3, 4, 5, 6]),) 

期值与现值预测 

import numpy as np

from matplotlib.pyplot import plot, show

# 期值预测

# fv(rate, n, pmt, pv)

# rate:利率,n:周期数量

# pmt:周期性投入,pv:现值

# 这个例子是计算,假设现在你存了 1000 元,之后每个季度多存 10 元,年利率是 3%,五年之后你有多少钱。

# 负值表示你失去的钱

print "Future value", np.fv(0.03/4, 5 * 4, -10, -1000)

# Future value 1376.09633204

fvals = []

# 计算第 i 年有多少钱

for i in xrange(1, 10):

   fvals.append(np.fv(.03/4, i * 4, -10, -1000))

plot(fvals, 'bo')

show()

# 现值预测

# pv(rate, n, pmt, fv)

# fv 为期值,其它同上

# 这个例子是计算,五年后想得到 1376.09633204 元,其它条件同上,现在应存多少钱。

print "Present value", np.pv(0.03/4, 5 * 4, -10, 1376.09633204)

Present value -999.999999999

# Present value -999.999999999

# 周期性投入预测

# pmt(rate, n, pv, fv=0) 参数含义同上

# 假设你贷款 100 万元,利率为 10%,需要在 30 年内还完,每个月需要还多少呢?

print "Payment", np.pmt(0.01/12, 12 * 30, 10000000)

# Payment -32163.9520447

# 周期数量预测

# nper(rate, pmt, fv, pv=0) 参数含义同上

# 假设你贷款 9000 元,利率为 10%,每个月还 100 元

# 多少个月能还完?

print "Number of payments", np.nper(0.10/12, -100, 9000)

# Number of payments 167.047511801

# 利率

# 假设我们知道除了利率之外的其他参数

# rate(n, pmt, pv, fv)

print "Interest rate", 12 * np.rate(167, -100, 9000, 0)

# Interest rate 0.0999756420664

注: 

假设现在存入pv元钱(正),之后就不存了,年利率为rate,n年之后余额是pv * (1 rate) ** n。 

如果之后每年都往里面存 pmt 元(正),fv[i] = fv[i - 1] * (1 rate) pmt。 

年数余额0pv1pv * (1 rate) pmt2pv * (1 rate) ** 2 pmt * (1 rate) pmt3pv * (1 rate) ** 3 pmt * (1 rate) ** 2 pmt * (1 rate) pmtnpv * (1 rate) ** n pmt * ((1 rate) ** n - 1) / rate

np.fv中的pv和pmt是负的,求完之后取相反数即可。 

计算净现值(NPV)、内部收益率(IRR) 

import numpy as np

# 生成五个 100 以内的随机数作为现金流序列

# -100 为初始值

cashflows = np.random.randint(100, size=5)

cashflows = np.insert(cashflows, 0, -100)

print "Cashflows", cashflows

# Cashflows [-100   38   48   90   17   36]

# npv(rate, vals) 计算净现值

# npv = np.sum(vals / (np.ones(length) rate) ** np.arange(length))

# 其中 l = len(vals)

print "Net present value", np.npv(0.03, cashflows)

# Net present value 107.435682443

# irr(vals) 计算内部收益率

# 满足 npv(irr, vals) == 0

print "Internal rate of return", np.irr([-100, 38, 48, 90,

  17, 36])

# Internal rate of return 0.373420226888

布林窗口 

# 布林窗口是三角平滑窗口

# 参数为 n 的布林函数是 (0,0) 到 (n/2,1) 再到 (n,0) 的线段

# bartlett 函数返回布林窗口函数值的数组,x 范围从 0 到 n

window = np.bartlett(42)

plot(window)

show()

使用布莱克曼窗口来平滑股票价格 

import numpy as np

from matplotlib.pyplot import plot, show, legend

from matplotlib.dates import datestr2num

import sys

# 获取 AAPL 收盘价

closes=np.loadtxt('AAPL.csv', delimiter=',', usecols=(6,), converters={1:datestr2num}, unpack=True)

# 读入天数

N = int(sys.argv[1])

# 创建布莱克曼窗口

window = np.blackman(N)

# 使用卷积函数来平滑收盘价

smoothed = np.convolve(window/window.sum(), closes, mode='same')

# 绘制原始和平滑后的收盘价

plot(smoothed[N:-N], lw=2, label="smoothed")

plot(closes[N:-N], label="closes")

legend(loc='best')

show()

汉明窗口 

# 使用方法同布林窗口

window = np.hamming(42)

plot(window)

show()

凯撒窗口 

# kaiser(M, beta)

window = np.kaiser(42, 14)

plot(window)

show()

修正贝塞尔函数 

x = np.linspace(0, 4, 100)

vals = np.i0(x)

plot(x, vals)

show()

sinc 函数 

# sinc(x) = sin(pi * x) / (pi * x)

# 在 0 处取极限值 1

x = np.linspace(0, 4, 100)

vals = np.sinc(x)

plot(x, vals)

show()

0 人点赞