同花顺Supermind量化交易 技术面分析专题（一）-- 相似k线的形态验证与选股

形态验证并选股-“相似K线”的技术应用:

“W底”，“多头上涨”，“趋势回踩”，”上涨中继“这些都是常见的K线形态，以”上涨中继“为例，当股价快速上涨后，出现盘整形态而非顶部形态，预示股价还会进一步上涨，那么本节主要讲述”上涨中继”形态是否能够预测未来股价上涨，以及如何应用“上涨中继”形态，来快速选股。 

第一步：选取一段标准的“上涨中继”形态K线图
 

第二步：形态验证，在历史行情中寻找相似度高达0.8的K线图，并计算后5日、20日、60日的收益率。分析： 1.历史4年中“上涨中继”形态发生后，后5日上涨概率仅为30%，后20上涨概率也仅为50%，但后60日上涨概率高达70% 2.形态发生后，5日收益率均值为-2.45%，20日收益率均值仅为0.97%，但后60日收益率均值高达15.60% 并初步得出结论： 上涨中继形态发生后，技术分析者应该尽量选择低位介入，并且持有一段时间，而不是早早离场。 

第三步：形态选股应用，我们认为“上涨中继”是一个较优质的中线买入机会，我们对全市场个股进行“上涨中继”形态选股，寻找出相似度最高的股票：ST天业，相似度为0.895，K线形态符合“上涨中继”，如下： 

结束语:

"相似K线"技术相比于传统的K线组合而言更具技术性，其还有较多的运用空间，比如：运用顶部形态来监控个股潜在的下跌风险，运用相似度来监控个股是否脱离大盘走势，研究各类形态的上涨预测能力，并应用于选股等等。 注意：文中对股价的预测来源于模型运算结果，不构成投资建议！

参考文献:

-日本蜡烛图技术 [美] 史蒂夫·尼森

点击获取内容完整源码（仅支持PC）:

点击→机器学习

微信扫码，在线阅读~:

形态验证:快速上涨后，出现盘整形态，后续上涨的可能性多大？

data = get_price('603383.SH',None,'20190114','1d',['open','high','low','close'],bar_count=60,is_panel =1)startdate ='20181019'
enddate ='20190114'import numpy as np
import matplotlib.pyplot as plt 
from matplotlib.finance import candlestick2_ohlc
import datetimeclose1 = data['close']
open1 = data['open']
high1 = data['high']
low1 = data['low']#画图
fig,ax = plt.subplots(figsize = (10,6.18),facecolor='white')
fig.subplots_adjust() ticks = ax.set_xticks([0,60])
labels = ax.set_xticklabels([startdate,enddate], fontsize=10) plt.yticks()  
plt.title("{} K线走势图".format('上涨中继'),fontsize = 15)  
plt.ylabel("股价",fontsize = 15)  
candlestick2_ohlc(ax,open1,high1,low1,close1,width=0.6,colorup='red',colordown='green')

(<matplotlib.collections.LineCollection at 0x7f8b266317f0>,<matplotlib.collections.PolyCollection at 0x7f8b26983da0>)

data = get_price('603383.SH','20181019','20190211','1d',['open','high','low','close'],is_panel =1)startdate ='20181019'
enddate ='20190211'import numpy as np
import matplotlib.pyplot as plt 
from matplotlib.finance import candlestick2_ohlc
import datetimeclose1 = data['close']
open1 = data['open']
high1 = data['high']
low1 = data['low']#画图
fig,ax = plt.subplots(figsize = (10,6.18),facecolor='white')
fig.subplots_adjust() ticks = ax.set_xticks([0,60])
labels = ax.set_xticklabels([startdate,enddate], fontsize=10) #支撑线
plt.plot([60,60],[np.min(low1),np.max(high1)],'gold',linewidth=3)plt.yticks()  
plt.title("{}形态发生后，理想中的后续走势".format('上涨中继'),fontsize = 15)  
plt.ylabel("股价",fontsize = 15)  
candlestick2_ohlc(ax,open1,high1,low1,close1,width=0.6,colorup='red',colordown='green')

(<matplotlib.collections.LineCollection at 0x7f8b25d5b978>,<matplotlib.collections.PolyCollection at 0x7f8b25d5b780>)

data = get_price('603383.SH',None,'20190114','1d',['open','high','low','close'],bar_count=60,is_panel =1)close1 = data['close']
open1 = data['open']
high1 = data['high']
low1 = data['low']indexcode = '000300.SH'
startdate = '20140101'
enddate = '20190201'
stocklist = get_index_stocks(indexcode,enddate)
data = get_price(stocklist,startdate,enddate,'1d',['open','high','low','close'],is_panel =1)
#收盘价
closedf = data['close'].fillna(0)
opendf = data['open'].fillna(0)
highdf = data['high'].fillna(0)
lowdf = data['low'].fillna(0)dt = pd.DataFrame(columns=['stock','startdate','enddate','T'])trade = list(closedf.index.strftime('%Y%m%d'))
num = trade.index(enddate)
stocklist = list(closedf.columns)
y=0
import datetime
for d in list(range(60,num-20,20)):print(d,num)close2 = closedf.iloc[d-59:d+1]opens2 = opendf.iloc[d-59:d+1]high2 = highdf.iloc[d-59:d+1]low2 = lowdf.iloc[d-59:d+1]for s in stocklist:corropen = round(np.corrcoef(open1,opens2[s])[0][1],3)corrhigh = round(np.corrcoef(high1,high2[s])[0][1],3)corrlow = round(np.corrcoef(low1,low2[s])[0][1],3)corrclose = round(np.corrcoef(close1,close2[s])[0][1],3)#综合值T = (corropen+corrhigh+corrlow+corrclose)/4startdate = trade[d-59]enddate = trade[d+1]dt.loc[y] = [s,startdate,enddate,T]y+=1dt = dt.fillna(0)
dt = dt.sort_values(by='T',ascending=False)
dt

60 1242
80 1242
100 1242
120 1242
140 1242
160 1242
180 1242
200 1242
220 1242
240 1242
260 1242
280 1242
300 1242
320 1242
340 1242
360 1242
380 1242
400 1242
420 1242
440 1242
460 1242
480 1242
500 1242
520 1242
540 1242
560 1242
580 1242
600 1242
620 1242
640 1242
660 1242
680 1242
700 1242
720 1242
740 1242
760 1242
780 1242
800 1242
820 1242
840 1242
860 1242
880 1242
900 1242
920 1242
940 1242
960 1242
980 1242
1000 1242
1020 1242
1040 1242
1060 1242
1080 1242
1100 1242
1120 1242
1140 1242
1160 1242
1180 1242
1200 1242
1220 1242

Out[29]:

17700 rows × 4 columns

In [30]:

for s in [0,-1]:stock = dt.iloc[s].stockstartdate = dt.iloc[s].startdateenddate = dt.iloc[s].enddateimport numpy as npimport matplotlib.pyplot as plt from matplotlib.finance import candlestick2_ohlcimport datetimes = stocktrade = list(closedf.index.strftime('%Y%m%d'))num = trade.index(enddate)close1 = closedf[s].iloc[num-59:num+21]open1 = opendf[s].iloc[num-59:num+21]high1 = highdf[s].iloc[num-59:num+21]low1 = lowdf[s].iloc[num-59:num+21]#画图fig,ax = plt.subplots(figsize = (10,6.18),facecolor='white')fig.subplots_adjust() #支撑线plt.plot([60,60],[np.min(low1),np.max(high1)],'gold',linewidth=3)ticks = ax.set_xticks([0,60])labels = ax.set_xticklabels([startdate,enddate], fontsize=10) plt.yticks()  plt.title("{} K线走势图".format(s),fontsize = 15)  plt.ylabel("股价",fontsize = 15)  candlestick2_ohlc(ax,open1,high1,low1,close1,width=0.6,colorup='red',colordown='green')

highdt = dt[dt['T']>0.8]
highdt['code'] = highdt.index
highdt['buyprice'] = highdt['code'].apply(lambda x:closedf[list(highdt['stock'])[list(highdt['code']).index(x)]].iloc[list(highdt['code']).index(x)])
highdt = highdt[highdt['buyprice']!=0]
highdt['5day'] = highdt['code'].apply(lambda x:closedf[list(highdt['stock'])[list(highdt['code']).index(x)]].iloc[list(highdt['code']).index(x)+5])
highdt['20day'] = highdt['code'].apply(lambda x:closedf[list(highdt['stock'])[list(highdt['code']).index(x)]].iloc[list(highdt['code']).index(x)+20])
highdt['60day'] = highdt['code'].apply(lambda x:closedf[list(highdt['stock'])[list(highdt['code']).index(x)]].iloc[list(highdt['code']).index(x)+60])
highdt['5day']=highdt['5day']/highdt['buyprice']-1
highdt['20day']=highdt['20day']/highdt['buyprice']-1
highdt['60day']=highdt['60day']/highdt['buyprice']-1
highdt

284 rows × 9 columns

highdt.describe()

Out[32]:

In [33]:

import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
fig = plt.figure()
axes = fig.add_axes([0.1, 0.1, 1, 0.618]) #插入面板2
x1_list = list(highdt['5day'])
y=np.array(x1_list)
x=np.array(range(0,len(x1_list)))
axes.plot(x, y, 'r')
axes.set_xlabel('相似度递减',fontsize=15)
axes.set_ylabel('收益率',fontsize=15)
axes.set_title('上涨中继买入后五日收益率',fontsize=15)

<matplotlib.text.Text at 0x7f8b26065f60>

import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
fig = plt.figure()
axes = fig.add_axes([0.1, 0.1, 1, 0.618]) #插入面板2
x1_list = list(highdt['20day'])
y=np.array(x1_list)
x=np.array(range(0,len(x1_list)))
axes.plot(x, y, 'r')
axes.set_xlabel('相似度递减',fontsize=15)
axes.set_ylabel('收益率',fontsize=15)
axes.set_title('上涨中继买入后二十日收益率',fontsize=15)

<matplotlib.text.Text at 0x7f8b273dcc18>

import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
fig = plt.figure()
axes = fig.add_axes([0.1, 0.1, 1, 0.618]) #插入面板2
x1_list = list(highdt['60day'])
y=np.array(x1_list)
x=np.array(range(0,len(x1_list)))
axes.plot(x, y, 'r')
axes.set_xlabel('相似度递减',fontsize=15)
axes.set_ylabel('收益率',fontsize=15)
axes.set_title('上涨中继买入后六十日收益率',fontsize=15)

<matplotlib.text.Text at 0x7f8b25cb0748>

形态选股应用

以上涨中继作为筛选形态，从历史行情中挑出一段行情。

data = get_price('603383.SH',None,'20190114','1d',['open','high','low','close'],bar_count=60,is_panel =1)startdate ='20181019'
enddate ='20190114'import numpy as np
import matplotlib.pyplot as plt 
from matplotlib.finance import candlestick2_ohlc
import datetimeclose1 = data['close']
open1 = data['open']
high1 = data['high']
low1 = data['low']#画图
fig,ax = plt.subplots(figsize = (10,6.18),facecolor='white')
fig.subplots_adjust() ticks = ax.set_xticks([0,60])
labels = ax.set_xticklabels([startdate,enddate], fontsize=10) plt.yticks()  
plt.title("{} K线走势图".format('趋势上涨'),fontsize = 15)  
plt.ylabel("股价",fontsize = 15)  
candlestick2_ohlc(ax,open1,high1,low1,close1,width=0.6,colorup='red',colordown='green')

(<matplotlib.collections.LineCollection at 0x7f8b273c4a90>,<matplotlib.collections.PolyCollection at 0x7f8b273c4e80>)

全市场中寻找目前趋势上涨的股票

date = '20190211'
stocklist = list(get_all_securities('stock',date).index)
stocklist

['300056.SZ','300674.SZ','300108.SZ','300357.SZ','600841.SH','600495.SH','300249.SZ','002852.SZ','000058.SZ','002568.SZ','300199.SZ','300490.SZ','000893.SZ','603859.SH','600565.SH','603063.SH','600117.SH','300036.SZ','300746.SZ','002906.SZ','600052.SH','002187.SZ','300613.SZ','000596.SZ','002351.SZ','000736.SZ','000810.SZ','002767.SZ','601318.SH','300183.SZ','002755.SZ','002502.SZ','603722.SH','002298.SZ','300711.SZ','300678.SZ','600362.SH','002176.SZ','600887.SH','300430.SZ','300712.SZ','300291.SZ','300486.SZ','600876.SH','601988.SH','601100.SH','603688.SH','600078.SH','603958.SH','000811.SZ','000537.SZ','300260.SZ','002434.SZ','000541.SZ','002673.SZ','600804.SH','603268.SH','300567.SZ','600038.SH','300382.SZ','600370.SH','000150.SZ','600158.SH','000888.SZ','603458.SH','300723.SZ','300670.SZ','600100.SH','600678.SH','603566.SH','600237.SH','002166.SZ','002073.SZ','300071.SZ','601666.SH','600422.SH','002642.SZ','000027.SZ','002537.SZ','000631.SZ','002457.SZ','603359.SH','600189.SH','600592.SH','600290.SH','603988.SH','002857.SZ','300105.SZ','603321.SH','601398.SH','600755.SH','002480.SZ','600919.SH','300690.SZ','603133.SH','300328.SZ','300759.SZ','603979.SH','002055.SZ','002741.SZ','300391.SZ','600211.SH','002278.SZ','000639.SZ','300273.SZ','300543.SZ','000823.SZ','300521.SZ','000762.SZ','002493.SZ','000597.SZ','600765.SH','000826.SZ','300680.SZ','300341.SZ','002628.SZ','603611.SH','000573.SZ','000766.SZ','001979.SZ','600620.SH','300575.SZ','000726.SZ','002920.SZ','002081.SZ','002797.SZ','002383.SZ','300471.SZ','600011.SH','600151.SH','300628.SZ','600007.SH','300488.SZ','300539.SZ','000831.SZ','000539.SZ','300538.SZ','600814.SH','000889.SZ','002839.SZ','600926.SH','600805.SH','002155.SZ','002319.SZ','600562.SH','000652.SZ','000603.SZ','600313.SH','002131.SZ','000812.SZ','300332.SZ','600775.SH','603886.SH','000963.SZ','300535.SZ','000656.SZ','002261.SZ','603029.SH','300369.SZ','600326.SH','600811.SH','300451.SZ','600488.SH','600392.SH','603966.SH','600597.SH','002651.SZ','002733.SZ','600509.SH','600477.SH','300485.SZ','600978.SH','603712.SH','601179.SH','600055.SH','002903.SZ','000968.SZ','002526.SZ','000088.SZ','603260.SH','000690.SZ','600185.SH','002392.SZ','600398.SH','300444.SZ','002865.SZ','002897.SZ','002057.SZ','603678.SH','002510.SZ','600409.SH','002484.SZ','300065.SZ','002943.SZ','002276.SZ','000510.SZ','300431.SZ','300097.SZ','600022.SH','600171.SH','000014.SZ','300124.SZ','300651.SZ','600983.SH','002915.SZ','600010.SH','000683.SZ','600621.SH','002476.SZ','300368.SZ','300525.SZ','300394.SZ','300453.SZ','000955.SZ','300003.SZ','600777.SH','002144.SZ','002584.SZ','002592.SZ','600220.SH','600221.SH','603716.SH','300658.SZ','600622.SH','002832.SZ','603603.SH','002381.SZ','300195.SZ','000806.SZ','002451.SZ','300224.SZ','600088.SH','002418.SZ','300347.SZ','603733.SH','600153.SH','603679.SH','601800.SH','601108.SH','002743.SZ','600982.SH','300320.SZ','000922.SZ','603648.SH','300045.SZ','600187.SH','600594.SH','300634.SZ','600673.SH','000096.SZ','600306.SH','600651.SH','002577.SZ','601010.SH','600103.SH','002204.SZ','603311.SH','600846.SH','000760.SZ','002033.SZ','603585.SH','600396.SH','002438.SZ','002564.SZ','000543.SZ','601311.SH','603689.SH','000782.SZ','300725.SZ','002727.SZ','603685.SH','600094.SH','600609.SH','300365.SZ','002691.SZ','600785.SH','002037.SZ','601966.SH','300591.SZ','000902.SZ','600888.SH','603036.SH','603916.SH','002668.SZ','600405.SH','603839.SH','300167.SZ','002294.SZ','600209.SH','000589.SZ','603986.SH','000925.SZ','002390.SZ','600826.SH','000068.SZ','000680.SZ','300139.SZ','603383.SH','603887.SH','000973.SZ','002137.SZ','300505.SZ','002788.SZ','300026.SZ','000055.SZ','002787.SZ','000004.SZ','600360.SH','600480.SH','000558.SZ','300545.SZ','300305.SZ','600059.SH','603520.SH','002397.SZ','300307.SZ','300620.SZ','002314.SZ','000403.SZ','600086.SH','000070.SZ','002009.SZ','002302.SZ','300705.SZ','600583.SH','300572.SZ','000868.SZ','603701.SH','002032.SZ','603056.SH','600499.SH','600936.SH','603612.SH','000605.SZ','300103.SZ','300663.SZ','000807.SZ','300581.SZ','300450.SZ','603059.SH','600764.SH','600395.SH','601952.SH','600272.SH','002761.SZ','000969.SZ','002201.SZ','300091.SZ','002689.SZ','300079.SZ','300161.SZ','600280.SH','300321.SZ','600579.SH','300423.SZ','603917.SH','000533.SZ','300151.SZ','002747.SZ','603037.SH','002181.SZ','002461.SZ','002305.SZ','002112.SZ','600338.SH','600839.SH','300514.SZ','600248.SH','002309.SZ','603897.SH','300568.SZ','603829.SH','601633.SH','600714.SH','300311.SZ','600724.SH','300532.SZ','600284.SH','601838.SH','000521.SZ','300114.SZ','603589.SH','002329.SZ','002024.SZ','600779.SH','603718.SH','300573.SZ','002663.SZ','000069.SZ','002817.SZ','300698.SZ','603668.SH','000937.SZ','603908.SH','002156.SZ','000531.SZ','601668.SH','600292.SH','002725.SZ','603500.SH','000528.SZ','002026.SZ','002648.SZ','601038.SH','000629.SZ','000777.SZ','000692.SZ','000566.SZ','603111.SH','002653.SZ','000548.SZ','300659.SZ','600063.SH','600066.SH','300482.SZ','002866.SZ','300176.SZ','300403.SZ','002530.SZ','600702.SH','600985.SH','000861.SZ','600416.SH','002268.SZ','300326.SZ','002323.SZ','300638.SZ','600606.SH','300603.SZ','603227.SH','600293.SH','600812.SH','000835.SZ','002106.SZ','000421.SZ','000666.SZ','002478.SZ','300381.SZ','603033.SH','600998.SH','600479.SH','600079.SH','600875.SH','002095.SZ','300295.SZ','600819.SH','000892.SZ','300044.SZ','600848.SH','603936.SH','600635.SH','600468.SH','000407.SZ','002931.SZ','300258.SZ','600029.SH','300336.SZ','002690.SZ','600655.SH','300399.SZ','300325.SZ','600555.SH','000821.SZ','600677.SH','600572.SH','002858.SZ','600240.SH','603138.SH','600608.SH','600310.SH','600522.SH','000587.SZ','601211.SH','600335.SH','000988.SZ','600196.SH','600435.SH','300107.SZ','600099.SH','600433.SH','600641.SH','603787.SH','600067.SH','601579.SH','600385.SH','002100.SZ','002345.SZ','603222.SH','000635.SZ','300319.SZ','002688.SZ','600207.SH','000153.SZ','002833.SZ','600235.SH','603677.SH','002084.SZ','000619.SZ','603968.SH','603085.SH','603889.SH','002170.SZ','002358.SZ','601808.SH','603198.SH','000655.SZ','002695.SZ','300069.SZ','603810.SH','600893.SH','300081.SZ','600508.SH','601128.SH','000819.SZ','002815.SZ','600871.SH','601368.SH','600665.SH','002221.SZ','600418.SH','600536.SH','600255.SH','300123.SZ','603189.SH','300078.SZ','600854.SH','603690.SH','601101.SH','601828.SH','002013.SZ','600163.SH','002344.SZ','603919.SH','002444.SZ','300134.SZ','300480.SZ','600461.SH','300256.SZ','600082.SH','002572.SZ','000001.SZ','601777.SH','002242.SZ','300353.SZ','000977.SZ','002341.SZ','300607.SZ','000576.SZ','603659.SH','002543.SZ','601326.SH','600999.SH','000516.SZ','002758.SZ','600020.SH','300266.SZ','300616.SZ','300682.SZ','002621.SZ','000410.SZ','000897.SZ','300225.SZ','600793.SH','002003.SZ','600817.SH','000938.SZ','002371.SZ','002353.SZ','300261.SZ','002064.SZ','002548.SZ','300452.SZ','603517.SH','002677.SZ','300642.SZ','600550.SH','600009.SH','000735.SZ','002336.SZ','000595.SZ','300588.SZ','002054.SZ','002824.SZ','300232.SZ','603389.SH','000961.SZ','002440.SZ','300013.SZ','603166.SH','300218.SZ','300677.SZ','002317.SZ','002508.SZ','002664.SZ','300226.SZ','300269.SZ','002905.SZ','000783.SZ','002582.SZ','300741.SZ','000509.SZ','600323.SH','002731.SZ','600618.SH','601996.SH','603299.SH','300310.SZ','603328.SH','600083.SH','600823.SH','300030.SZ','300197.SZ','002448.SZ','300717.SZ','300188.SZ','600798.SH','603456.SH','002819.SZ','002545.SZ','603999.SH','300121.SZ','000505.SZ','300635.SZ','300145.SZ','002306.SZ','300395.SZ','300590.SZ','603496.SH','002483.SZ','603351.SH','000932.SZ','002554.SZ','002005.SZ','002307.SZ','002789.SZ','300021.SZ','300424.SZ','600726.SH','600507.SH','600657.SH','000585.SZ','300052.SZ','000554.SZ','002250.SZ','300020.SZ','000801.SZ','603416.SH','002883.SZ','300083.SZ','600460.SH','601678.SH','601228.SH','300633.SZ','002316.SZ','002368.SZ','300294.SZ','600653.SH','002099.SZ','002586.SZ','600881.SH','601858.SH','600822.SH','300417.SZ','600800.SH','601086.SH','300208.SZ','600987.SH','603880.SH','000623.SZ','000007.SZ','600397.SH','300407.SZ','000995.SZ','300059.SZ','300173.SZ','000951.SZ','603901.SH','600319.SH','600525.SH','603136.SH','600271.SH','002578.SZ','600642.SH','600801.SH','603179.SH','300459.SZ','300533.SZ','601799.SH','000828.SZ','600090.SH','600267.SH','000839.SZ','300697.SZ','000933.SZ','600995.SH','300418.SZ','603183.SH','600420.SH','300117.SZ','601208.SH','000719.SZ','300560.SZ','000778.SZ','300293.SZ','300461.SZ','002802.SZ','300040.SZ','601555.SH','002665.SZ','600410.SH','002193.SZ','300074.SZ','600652.SH','002409.SZ','000780.SZ','002297.SZ','300089.SZ','300171.SZ','002606.SZ','600278.SH','600346.SH','002888.SZ','600016.SH','600241.SH','002566.SZ','603506.SH','002539.SZ','600275.SH','002705.SZ','603789.SH','002619.SZ','002855.SZ','300720.SZ','600637.SH','300660.SZ','300436.SZ','600623.SH','000488.SZ','600260.SH','300398.SZ','000858.SZ','002707.SZ','603976.SH','002401.SZ','300462.SZ','000536.SZ','001696.SZ','002928.SZ','600966.SH','600439.SH','300507.SZ','002464.SZ','300593.SZ','000795.SZ','002022.SZ','600792.SH','000939.SZ','300033.SZ','000878.SZ','300489.SZ','603159.SH','603838.SH','600231.SH','600145.SH','300262.SZ','002827.SZ','601099.SH','300109.SZ','002110.SZ','300440.SZ','300760.SZ','002282.SZ','300062.SZ','600467.SH','603866.SH','600601.SH','603011.SH','600213.SH','600282.SH','600816.SH','300622.SZ','300244.SZ','600519.SH','603569.SH','600184.SH','600114.SH','603819.SH','603869.SH','002419.SZ','300213.SZ','600093.SH','603386.SH','002718.SZ','601020.SH','002714.SZ','002835.SZ','000705.SZ','002312.SZ','600838.SH','002763.SZ','300137.SZ','300702.SZ','300279.SZ','300589.SZ','300541.SZ','600517.SH','300277.SZ','002004.SZ','002659.SZ','300247.SZ','300067.SZ','600733.SH','603039.SH','000950.SZ','002060.SZ','002849.SZ','002645.SZ','002078.SZ','300684.SZ','600035.SH','000561.SZ','603987.SH','002056.SZ','300322.SZ','000613.SZ','000860.SZ','600614.SH','601598.SH','000006.SZ','300189.SZ','002732.SZ','000971.SZ','300058.SZ','603158.SH','600363.SH','603638.SH','300443.SZ','603667.SH','600559.SH','002420.SZ','002528.SZ','002909.SZ','000710.SZ','002765.SZ','002929.SZ','603626.SH','600372.SH','300526.SZ','002223.SZ','000166.SZ','600098.SH','603700.SH','600379.SH','002002.SZ','300467.SZ','002311.SZ','600222.SH','601857.SH','603933.SH','600586.SH','002334.SZ','002198.SZ','300229.SZ','300283.SZ','000921.SZ','600436.SH','002366.SZ','600845.SH','000532.SZ','600810.SH','300136.SZ','300601.SZ','601929.SH','002927.SZ','600959.SH','603366.SH','603555.SH','600201.SH','603583.SH','603797.SH','601226.SH','300017.SZ','601901.SH','002875.SZ','300404.SZ','603077.SH','600682.SH','002547.SZ','300665.SZ','002244.SZ','600225.SH','300066.SZ','300555.SZ','002191.SZ','601162.SH','603556.SH','002154.SZ','600735.SH','601958.SH','603607.SH','600754.SH','002473.SZ','601118.SH','002254.SZ','600890.SH','002426.SZ','300379.SZ','000593.SZ','002696.SZ','000901.SZ','300692.SZ','002801.SZ','603396.SH','002333.SZ','000712.SZ','002910.SZ','000158.SZ','002722.SZ','600901.SH','600667.SH','603533.SH','002837.SZ','002738.SZ','600072.SH','600423.SH','603167.SH','300509.SZ','600452.SH','002210.SZ','000018.SZ','600366.SH','603336.SH','000581.SZ','002212.SZ','300276.SZ','000818.SZ','300722.SZ','002088.SZ','300112.SZ','601699.SH','600885.SH','600546.SH','300126.SZ','600685.SH','601606.SH','601615.SH','600356.SH','601158.SH','002945.SZ','002753.SZ','600766.SH','600829.SH','600148.SH','300495.SZ','601798.SH','000607.SZ','300504.SZ','601766.SH','603363.SH','600686.SH','002911.SZ','300222.SZ','600179.SH','600723.SH','002708.SZ','300548.SZ','300618.SZ','603939.SH','300164.SZ','300344.SZ','601811.SH','300481.SZ','300389.SZ','600337.SH','002076.SZ','000790.SZ','300455.SZ','002011.SZ','002602.SZ','000998.SZ','600076.SH','000852.SZ','603629.SH','000962.SZ','002590.SZ','600183.SH','601007.SH','002327.SZ','002864.SZ','002068.SZ','603018.SH','300375.SZ','601021.SH','600567.SH','600860.SH','603666.SH','601928.SH','002559.SZ','002678.SZ','603816.SH',...]

data = get_price(stocklist,None,date,'1d',['open','high','low','close'],bar_count = 60,is_panel =1)
data

<class 'pandas.core.panel.Panel'>
Dimensions: 4 (items) x 60 (major_axis) x 3585 (minor_axis)
Items axis: close to open
Major_axis axis: 2018-11-09 00:00:00 to 2019-02-11 00:00:00
Minor_axis axis: 000001.SZ to 603999.SH

closedf = data['close'].fillna(0)
opendf = data['open'].fillna(0)
highdf = data['high'].fillna(0)
lowdf = data['low'].fillna(0)
lowdf

lowdf

Out[39]:

dt = pd.DataFrame(columns=['stock','startdate','enddate','T'])data = get_price('603383.SH',None,'20190114','1d',['open','high','low','close'],bar_count=60,is_panel =1)close1 = data['close']
open1 = data['open']
high1 = data['high']
low1 = data['low']stocklist = list(closedf.columns)
y=0
for s in stocklist:corropen = round(np.corrcoef(open1,opendf[s])[0][1],3)corrhigh = round(np.corrcoef(high1,highdf[s])[0][1],3)corrlow = round(np.corrcoef(low1,lowdf[s])[0][1],3)corrclose = round(np.corrcoef(close1,closedf[s])[0][1],3)#综合值T = (corropen+corrhigh+corrlow+corrclose)/4startdate = '20181109'enddate = '20190211'dt.loc[y] = [s,startdate,enddate,T]y+=1
dt = dt.fillna(0)
dt = dt.sort_values(by='T',ascending=False)
dt

dt

Out[40]:

3585 rows × 4 columns

查看相似最高的股票和最低的股票

for s in [0,-1]:stock = dt.iloc[s].stockstartdate = dt.iloc[s].startdateenddate = dt.iloc[s].enddateimport numpy as npimport matplotlib.pyplot as plt from matplotlib.finance import candlestick2_ohlcimport datetimes = stocktrade = list(closedf.index.strftime('%Y%m%d'))num = trade.index(enddate)close1 = closedf[s]open1 = opendf[s]high1 = highdf[s]low1 = lowdf[s]#画图fig,ax = plt.subplots(figsize = (10,6.18),facecolor='white')fig.subplots_adjust() ticks = ax.set_xticks([0,60])labels = ax.set_xticklabels([startdate,enddate], fontsize=10) plt.yticks()  plt.title("{} K线走势图".format(s),fontsize = 15)  plt.ylabel("股价",fontsize = 15)  candlestick2_ohlc(ax,open1,high1,low1,close1,width=0.6,colorup='red',colordown='green')

查看以上策略详细请 到 supermind量化交易官网查看：技术面分析专题（一）-- 相似k线的形态验证与选股