###利用numpy进行历史股价分析
import sys
import numpy as np
#读入文件
c,v = np.loadtxt('data.csv',delimiter= ',',usecols= (6,7),unpack=True)
#print(c)
#print(v)
#计算成交量加权平均价格
vwap = np.average(c,weights = v)
print("VWAP =",vwap)
#算数平均值函数
print("mean = ",c.mean())#时间加权平均价格
t = np.arange(len(c))
print("twap = ",np.average(c,weights= t))#寻找最大值和最小值
h,l = np.loadtxt('data.csv',delimiter=',',usecols=(4,5),unpack = True)
print("highest = ",np.max(h))
print("lowest = ",np.min(l))
print((np.max(h)+np.min(l))/2)print("Spread high price",np.ptp(h))
print("Spread low price",np.ptp(l))#统计分析
c = np.loadtxt('data.csv',delimiter= ',',usecols= (6,),unpack= True)
print("median = ",np.median(c))
sorted = np.msort(c)
print("sorted =",sorted)N = len(c)
# 注意list的下标不能是小数，所以要整型化；
print("middle =",sorted[int((N-1)/2)])
print("average meddle =",(sorted[int(N/2)]+sorted[int((N-1)/2)])/2)# 总体方差与样本方差的区别，
print("variance =",np.var(c))  #方差 numpy自带的公式
print("variance from definition =",np.mean((c-c.mean())**2)) #根据定义来求得方差# 股票收益率
c = np.loadtxt('data.csv',delimiter=',',usecols=(6,),unpack=True)
# 注意np.sort(c)与c.sort()的区别，一个返回新的数组，一个等于内部自排
# sorted1 =np.sort(-c)  这里是降序排列，注意！！！
# print(sorted1)# 差分函数，数组相邻元素之间的差值
returns = np.diff( c )/(c[ : -1])
print(returns)
print("Standard deviation =",np.std(returns))logreturns = np.diff(np.log(c))# 返回一个数组，里面是收益率大于0的数据
posretindices = np.where(returns >0)
print(posretindices)
# 年度波动率
annua_volatility = np.std(logreturns)/np.mean(logreturns)
annua_volatility =annua_volatility / np.sqrt(1./252.)
print("Annual volatility",annua_volatility)#月度波动率
print("Monthly volatility",annua_volatility * np.sqrt(1./12.))# 日期分析
from datetime import datetime
'''
Monday 0
Tuesday 1
Wednesday 2
Thursday 3
Friday 4
Saturday 5
Sunday 6
'''#编译器在打开data.csv文件时，将表格里的第2列数组值提取出来返回给dates，
# 第二列值是日期格式字符串，但因为我们是以二进制编码的格式打开第二列值是，
# 返回的值字节字符串bytes，所以需要把它便会string，则对字符串解码用函数
# decode('asii')，变成string格式。
def datestr2num(s):return datetime.strptime(s.decode('ascii'),"%d-%m-%Y").date().weekday()dates,close=np.loadtxt("data.csv",delimiter= ',',usecols=(1,6),converters={1: datestr2num},unpack= True)
print("Dates =",dates)averages = np.zeros(5)
for i in range(5):indices = np.where(dates==i)prices = np.take(close,indices )avg = np.mean(prices)print("Day",i,"prices",prices,"Average",avg)averages[i] = avgtop = np.max(averages)
print("Heigest average",top)
print("Top day of the week",np.argmax(averages))# 简单移动平均线
from matplotlib.pyplot import  plot
from matplotlib.pyplot import  showN = 5weights = np.ones(N)/N
print("Weight",weights)c = np.loadtxt("data.csv",delimiter=',',usecols=(6,),unpack=True)
sma = np.convolve(weights,c)[N-1:-N+1] # N-1到-N+1的用权值为weight计算
t = np.arange(N-1,len(c))
plot(t,c[N-1:],lw=1.0)
plot(t,sma,lw=2.0)
#show()#指数移动平均线
x = np.arange(5)
print("Exp",np.exp(x))
print("Linspace",np.linspace(-1,0,5))N = 5weight = np.exp(np.linspace(-1.,0.,N))
weight/=weight.sum()
print("Weights",weights)ema = np.convolve(weight,c)[N-1:-N+1]
t = np.arange(N-1,len(c))
plot(t,c[N-1:],lw=1.0)
plot(t,ema,lw=2.0)
show()# 布林带