Numpy数据分析相关API总结--学习笔记

Numpy数据分析API总结

numpy常见函数

加载文件

import numpy as np
np.loadtxt(
    'path',delimiter = ',',usecols = (0,2),unpack = False,
    dtype = 'U10 f8',converters =  {
   1:func} # 转换器函数字典
)

案例，绘制K线图

绘制收盘价格折线图

import numpy as np
import datetime as dt
import matplotlib.pyplot as mp
import matplotlib.dates as md

def dmy2ymd(dmy):
    dmy = str(dmy,encoding = 'utf-8')
    time = dt.datetime.strptime(dmy,'%d-%m-%Y')
    t = time.date().strftime('%Y-%m-%d')
    return t

dates,opening_prices,highest_prices,lowest_prices,closing_prices = 
    np.loadtxt('aapl.csv',delimiter = ',',usecols = (1,3,4,5,6),
    unpack = True,dtype = 'M8[D],f8,f8,f8,f8',
    converters = {
   1,dmy2ymd})

# 折线图
mp.figure('AAPL', facecolor='lightgray')
mp.title('AAPL', fontsize=16)
mp.xlabel('Date', fontsize=14)
mp.ylabel('Price', fontsize=14)
mp.tick_params(labelsize=10)
mp.grid(linestyle=':')

# 设置x轴刻度定位器
ax = mp.gca()
ax.xaxis.set_major_locator(
    md.WeekdayLocator(byweekday=md.MO))
ax.xaxis.set_major_formatter(
    md.DateFormatter('%d %b %Y'))
ax.xaxis.set_minor_locator(md.DayLocator())

# 为了日期显示合理，修改dates的dtype
dates = dates.astype(md.datetime.datetime)
mp.plot(dates, closing_prices, alpha=0.3,
        color='dodgerblue', linewidth=2,
        linestyle='--', label='AAPL CP')
mp.legend()
mp.show()

在上图基础上添加蜡烛图，即包含实体（开盘价、收盘价）和影线（最高价、最低价）的bar

# 控制实体与影线的颜色
rise = closing_prices >= opening_prices
color = np.array(
    ['white' if x else 'green' for x in rise])
ecolor = np.array(
    ['red' if x else 'green' for x in rise])
# 绘制实体
mp.bar(dates, closing_prices - opening_prices,
       0.8, opening_prices, color=color,
       edgecolor=ecolor, zorder=3)
# 绘制影线
mp.vlines(dates, lowest_prices, highest_prices,
          color=ecolor)

算数平局值

np.mean(array)

加权平均值

np.average(array,weights = array2)

最大值、最小值、极差

np.max()
np.min()
np.ptp()

# 返回下标
np.argmax()
np.argmin()

# 将满足条件的同维数组组合成新的数组
np.maximun(a_array,b_array)
np.minimum(a_array,b_array)

中位数

np.median(array)

标准差

np.std(array,[ddof=1])  总体[样本]标准差

移动平均

案例：绘制5日均线

import datetime as dt
import numpy as np
import matplotlib.pyplot as mp
import matplotlib.dates as md
def dmy2ymd(dmy):
    dmy = str(dmy, encoding='utf-8')
    date = dt.datetime.strptime(dmy, '%d-%m-%Y').date()
    ymd = date.strftime('%Y-%m-%d')
    return ymd  
dates, closing_prices = np.loadtxt('../data/aapl.csv', delimiter=',',
    usecols=(1, 6), unpack=True, dtype='M8[D], f8', converters={
   1: dmy2ymd})

# 处理数据    
sma51 = np.zeros(closing_prices.size - 4)
for i in range(sma51.size):
    sma51[i] = closing_prices[i:i + 5].mean()


# 开始绘制5日均线
mp.figure('Simple Moving Average', facecolor='lightgray')
mp.title('Simple Moving Average', fontsize=20)
mp.xlabel('Date', fontsize=14)
mp.ylabel('Price', fontsize=14)
ax = mp.gca()
# 设置水平坐标每个星期一为主刻度
ax.xaxis.set_major_locator(md.WeekdayLocator( byweekday=md.MO))
# 设置水平坐标每一天为次刻度
ax.xaxis.set_minor_locator(md.DayLocator())
# 设置水平坐标主刻度标签格式
ax.xaxis.set_major_formatter(md.DateFormatter('%d %b %Y'))
mp.tick_params(labelsize=10)
mp.grid(linestyle=':')
dates = dates.astype(md.datetime.datetime)

mp.plot(dates, closing_prices, c='lightgray', label='Closing Price')
mp.plot(dates[4:], sma51, c='orangered', label='SMA-5(1)')
mp.legend()
mp.gcf().autofmt_xdate()
mp.show()

卷积实现移动平均

sma5 = np.convolve(array,np.ones(5)/5,'valid') # 'valid'==有效，same == 同维，full = 完全卷积
mp.plot(x[4:],sma5,color = 'green',alpha = 0.5,linewidth = 6, label ='sma5')

布林带

布林带的组成：中轨：移动平均线；上轨：中轨+2×标准差；下轨：中轨-2×标准差
API：

weights = np.exp(np.linspace(-1, 0, 5))
weights /= weights.sum()
em5 = np.convolve(closing_prices, weights[::-1], 'valid')
stds = np.zeros(em5.size)
for i in range(stds.size):
stds[i] = closing_prices[i:i + 5].std()
stds *= 2
lowers = medios - stds
uppers = medios