Python笔记_第五篇_Python数据分析基础教程_文件的读写

时间:2022-06-16 21:26:15

  1. 读写文件(基本)

  savetxt、loadtxt

i2 = np.eye(2)
print(i2)
np.savetxt(r"C:\Users\Thomas\Desktop\eye.txt",i2)

c,v = np.loadtxt(r"C:\Users\Thomas\Desktop\data.csv",delimiter=',',usecols=(6,7),unpack=True)
print(c,v)
#[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.]

  delimiter=用什么进行分隔符,一般csv文件都是逗号

  usecols=6,7,表示获取第七和第八字段数据,也就是股票的收盘价和成交量。

  unpack变量为真:拆分存储不同列的数据,即分别将收盘价和成交量的数据赋值给c和v,也就是分开显示的意思。

 

  2. 加权平均价格:average

     VWAP

import numpy as np

# 加权平均价格
c,v = np.loadtxt(r"C:\Users\Thomas\Desktop\data.csv",delimiter=',',usecols=(6,7),unpack=True)
vwap = np.average(c,weights=v)
print("VWAP = ", vwap)
#VWAP =  350.5895493532009

 

  

  3. 算术平均值:mean

 

import numpy as np

# 加权平均价格
c,v = np.loadtxt(r"C:\Users\Thomas\Desktop\data.csv",delimiter=',',usecols=(6,7),unpack=True)
mean = np.mean(c)
print("mean = ", mean)
#mean =  351.0376666666667

 

  4. 时间加权平均价格:

  TWAP

 

import numpy as np

# 加权平均价格
c,v = np.loadtxt(r"C:\Users\Thomas\Desktop\data.csv",delimiter=',',usecols=(6,7),unpack=True)
t = np.arange(len(c))
twap = np.average(c,weights=t)
print("twap = ", twap)
#twap =  352.4283218390804

 

  5. 最大值、最小值、极差值

  max、min、ptp:

 

import numpy as np

# 最大值、最小值、极差值
h,l = np.loadtxt(r"C:\Users\Thomas\Desktop\data.csv",delimiter=',',usecols=(4,5),unpack=True)
highest = np.max(h)
lowest = np.min(l)
spread_highest = np.ptp(h)
spread_lowest = np.ptp(l)

print("highest = ", highest)
print("lowest = ", lowest)
print("spread_highest = ", spread_highest)
print("spread_lowest = ", spread_lowest)
#highest =  364.9
#lowest =  333.53
#spread_highest =  24.859999999999957
#spread_lowest =  26.970000000000027

 

  6. 中位数:median  

  排序函数:msort

  方差:var

  标准差:std

 

import numpy as np

# 中位数
c = np.loadtxt(r"C:\Users\Thomas\Desktop\data.csv",delimiter=',',usecols=(6,),unpack=True)
print("median = ",np.median(c))

# 排序函数
print("sorted_close = ",np.msort(c))

# 方差函数
print("var = ",np.var(c))

# 标准差函数
print("std = ",np.std(c))

#median =  352.055
#sorted_close =  [336.1  338.61 339.32 342.62 342.88 343.44 344.32 345.03 346.5  346.67
# 348.16 349.31 350.56 351.88 351.99 352.12 352.47 353.21 354.54 355.2
# 355.36 355.76 356.85 358.16 358.3  359.18 359.56 359.9  360.   363.13]
#var =  50.126517888888884
#std =  7.080008325481608

 

 

  7. 差分函数:diff

  条件选择函数:where

# 差分函数
c = np.loadtxt(r"C:\Users\Thomas\Desktop\data.csv",delimiter=',',usecols=(6,),unpack=True)
print("diff = ",np.diff(c))

# 条件选择函数
print("price > 0",np.where(c > 0))

#diff =  [  3.22   5.71  -0.71  -0.88   3.06   5.38   3.32   2.96  -3.62   2.31
#   2.33   0.72   3.23  -4.83  -7.74 -11.95   4.01   0.26   5.28   5.05
#  -3.9    2.81   7.44   0.44  -4.64   0.4   -3.29  -5.8    5.32]
#price > 0 (array([ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16,
#       17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29], dtype=int64),)

  

  8. 日期分析:

 

import numpy as np
from datetime import datetime

def datestr2num(s):
   return datetime.strptime(s.decode('ascii'), "%d-%m-%Y").date().weekday()

dates, close=np.loadtxt(r"C:\Users\Thomas\Desktop\data.csv", delimiter=',', usecols=(1,6), converters={1: datestr2num}, unpack=True)
print("dates = ",dates)

#dates =  [4. 0. 1. 2. 3. 4. 0. 1. 2. 3. 4. 0. 1. 2. 3. 4. 1. 2. 3. 4. 0. 1. 2. 3.
# 4. 0. 1. 2. 3. 4.]

 

   注意:这里的s要解析ascii码

 

  9. summarize函数:对轴或者维度的编号进行定义

  apply_along_axis:这个函数会调用另外一个有我们给出的函数,作用于每一个数组元素上。目前我们的数组总有3个元素,分别用于示例数据总的3个星期,元素中的索引值对应于实例数据中的1天。

 

23

1

23