同花顺Supermind量化交易 运用SVM算法“打板”-- SVM算法应用

课程简介：介绍股票涨跌停板机制，对股票涨停进行分类，并研究股票涨停后的收益情况，最终采用SVM算法进行“打板”研究。

dt = dataclosedf
dt = dt.sort_values(by='date')

import matplotlib.pyplot as plt
import pandas as pd
import numpy as np


plt.style.use('seaborn')
fig = plt.figure()
axes = fig.add_axes([0.1, 0.1, 1, 0.618]) #插入面板

x1_list=list(dt['1日收盘价'])
y=np.array(x1_list)
x=np.array(range(0,len(x1_list)))
axes.scatter(x,y,c='tomato')
axes.set_xlabel('time',fontsize=15)
axes.set_ylabel('down_up',fontsize=15)
axes.set_title(' one day distribution',fontsize=18)
# #设置X轴
axes.set_xticks([0,100,200,300,400,500])
axes.set_xticklabels([list(dt.index)[0],list(dt.index)[100],list(dt.index)[200],list(dt.index)[300],list(dt.index)[400],list(dt.index)[500]],fontsize=15)

plt.style.use('seaborn')
fig = plt.figure()
axes = fig.add_axes([0.1, 0.1, 1, 0.618]) #插入面板

x1_list=list(dt['2日收盘价'])
y=np.array(x1_list)
x=np.array(range(0,len(x1_list)))
axes.scatter(x,y,c='tomato')
axes.set_xlabel('time',fontsize=15)
axes.set_ylabel('down_up',fontsize=15)
axes.set_title(' two day distribution',fontsize=18)
# #设置X轴
axes.set_xticks([0,100,200,300,400,500])
axes.set_xticklabels([list(dt.index)[0],list(dt.index)[100],list(dt.index)[200],list(dt.index)[300],list(dt.index)[400],list(dt.index)[500]],fontsize=15)

plt.style.use('seaborn')
fig = plt.figure()
axes = fig.add_axes([0.1, 0.1, 1, 0.618]) #插入面板

x1_list=list(dt['3日收盘价'])
y=np.array(x1_list)
x=np.array(range(0,len(x1_list)))
axes.scatter(x,y,c='tomato')
axes.set_xlabel('time',fontsize=15)
axes.set_ylabel('down_up',fontsize=15)
axes.set_title(' three day distribution',fontsize=18)
# #设置X轴
axes.set_xticks([0,100,200,300,400,500])
axes.set_xticklabels([list(dt.index)[0],list(dt.index)[100],list(dt.index)[200],list(dt.index)[300],list(dt.index)[400],list(dt.index)[500]],fontsize=15)

Out[13]:

[<matplotlib.text.Text at 0x7f1b30cd7630>,
 <matplotlib.text.Text at 0x7f1b313e20b8>,
 <matplotlib.text.Text at 0x7f1b30b9b630>,
 <matplotlib.text.Text at 0x7f1b313b9cc0>,
 <matplotlib.text.Text at 0x7f1b31aee0f0>,
 <matplotlib.text.Text at 0x7f1b30c90b00>]

In [14]:

labeldt = dataclosedf
labeldt['1日收盘价'] = labeldt['1日收盘价'].apply(lambda x:1 if x>0 else -1)
labeldt['2日收盘价'] = labeldt['2日收盘价'].apply(lambda x:1 if x>0 else -1)
labeldt['3日收盘价'] = labeldt['3日收盘价'].apply(lambda x:1 if x>0 else -1)
labeldt = labeldt.sort_values(by='date')
labeldt

Out[14]:

	stock	date	1日收盘价	2日收盘价	3日收盘价
2014-01-03	600010.SH	2014-01-03	-1	-1	-1
2014-01-16	000767.SZ	2014-01-16	-1	-1	-1
2014-02-12	000971.SZ	2014-02-12	-1	-1	-1
2014-02-21	000554.SZ	2014-02-21	-1	-1	-1
2014-02-28	600680.SH	2014-02-28	1	1	1
2014-03-10	300116.SZ	2014-03-10	-1	-1	-1
2014-03-13	000923.SZ	2014-03-13	-1	1	1
2014-03-27	000687.SZ	2014-03-27	-1	-1	-1
2014-04-03	000918.SZ	2014-04-03	-1	-1	-1
2014-04-10	300278.SZ	2014-04-10	1	1	1
2014-04-30	601001.SH	2014-04-30	1	-1	-1
2014-05-21	002660.SZ	2014-05-21	1	1	1
2014-06-04	600601.SH	2014-06-04	-1	-1	-1
2014-06-05	600074.SH	2014-06-05	-1	-1	-1
2014-06-06	002535.SZ	2014-06-06	1	1	1
2014-06-16	300198.SZ	2014-06-16	-1	-1	-1
2014-06-30	002093.SZ	2014-06-30	-1	-1	-1
2014-07-02	300288.SZ	2014-07-02	1	1	1
2014-07-04	002070.SZ	2014-07-04	-1	-1	-1
2014-07-07	600568.SH	2014-07-07	-1	1	1
2014-07-08	600435.SH	2014-07-08	1	1	1
2014-07-11	002629.SZ	2014-07-11	1	-1	-1
2014-07-16	000868.SZ	2014-07-16	-1	-1	-1
2014-07-25	600319.SH	2014-07-25	-1	1	1
2014-07-28	600157.SH	2014-07-28	1	1	1
2014-08-07	600556.SH	2014-08-07	-1	-1	-1
2014-08-11	600222.SH	2014-08-11	-1	-1	-1
2014-08-14	300208.SZ	2014-08-14	-1	1	1
2014-08-18	002125.SZ	2014-08-18	1	-1	1
2014-08-21	000922.SZ	2014-08-21	1	1	1
...	...	...	...	...	...
2018-12-19	002845.SZ	2018-12-19	1	-1	1
2018-12-25	000531.SZ	2018-12-25	-1	-1	-1
2018-12-26	300687.SZ	2018-12-26	-1	-1	-1
2018-12-27	300407.SZ	2018-12-27	-1	-1	-1
2018-12-28	601619.SH	2018-12-28	-1	-1	-1
2019-01-04	300125.SZ	2019-01-04	1	1	1
2019-01-07	300588.SZ	2019-01-07	-1	-1	-1
2019-01-08	600677.SH	2019-01-08	-1	-1	-1
2019-01-09	600452.SH	2019-01-09	1	1	1
2019-01-10	300076.SZ	2019-01-10	-1	-1	-1
2019-01-11	002941.SZ	2019-01-11	-1	-1	-1
2019-01-14	603220.SH	2019-01-14	-1	-1	1
2019-01-16	600446.SH	2019-01-16	-1	-1	-1
2019-01-18	600470.SH	2019-01-18	1	1	1
2019-01-21	300693.SZ	2019-01-21	-1	1	1
2019-01-22	300503.SZ	2019-01-22	-1	-1	-1
2019-01-24	002170.SZ	2019-01-24	-1	-1	-1
2019-01-25	600721.SH	2019-01-25	1	-1	-1
2019-01-28	000637.SZ	2019-01-28	-1	-1	-1
2019-01-31	300250.SZ	2019-01-31	1	1	1
2019-02-01	002011.SZ	2019-02-01	-1	-1	-1
2019-02-11	600532.SH	2019-02-11	-1	-1	-1
2019-02-12	600318.SH	2019-02-12	1	-1	-1
2019-02-13	300097.SZ	2019-02-13	1	1	1
2019-02-14	300256.SZ	2019-02-14	-1	1	1
2019-02-18	002099.SZ	2019-02-18	1	1	-1
2019-02-19	300468.SZ	2019-02-19	-1	-1	-1
2019-02-20	600393.SH	2019-02-20	-1	-1	1
2019-02-21	002565.SZ	2019-02-21	1	1	-1
2019-02-22	300063.SZ	2019-02-22	1	-1	-1

503 rows × 5 columns

In [15]:

tradeday = list(get_trade_days(startdate, '20200202', count=None).strftime('%Y-%m-%d'))

timelist = []
trlist= []
lplist =[]
q_trlist = []
for d in tradeday:
    time = 0
    tr = 0
    lp = 0
    q_tr = 0
    if d in list(labeldt['date']):
        stock = labeldt['stock'][d]
        day = tradeday[tradeday.index(d)+1]
        stockdata = get_price(stock,None,day,'1m',['close','high','low','open','turnover_rate'],True,'pre',bar_count=241,is_panel=0)
        
        pc = stockdata.iloc[0].close
        highlimit = round(pc*1.1,2)
        
        stockdata = stockdata.iloc[-240:]
        
        for m in list(range(0,240)):
            
            rc = stockdata.iloc[m].close
            h = stockdata.iloc[(m+1)].high
            
            if rc == highlimit:
                q_tr +=stockdata.iloc[m].turnover_rate
                
            if rc<highlimit:
                time += 1
                tr +=stockdata.iloc[m].turnover_rate
                lp = min(stockdata.iloc[m].low/highlimit-1,lp)
            
            if rc<highlimit and h == highlimit:
                break
        if time>0:
            timelist.append(time)
            trlist.append(round(tr,2))
            lplist.append(round(lp*100,2))
            q_trlist.append(round(q_tr,2))
timelist

Out[15]:

[111,
 2,
 209,
 1,
 1,
 1,
 1,
 25,
 1,
 2,
 1,
 2,
 1,
 1,
 3,
 1,
 5,
 228,
 19,
 11,
 4,
 60,
 1,
 1,
 1,
 6,
 95,
 3,
 1,
 211,
 1,
 6,
 2,
 1,
 6,
 5,
 1,
 91,
 135,
 2,
 1,
 1,
 236,
 149,
 52,
 6,
 3,
 2,
 2,
 1,
 6,
 1,
 1,
 1,
 4,
 38,
 1,
 6,
 1,
 14,
 180,
 1,
 1,
 1,
 1,
 1,
 2,
 1,
 1,
 172,
 1,
 142,
 43,
 26,
 1,
 1,
 4,
 1,
 5,
 30,
 3,
 5,
 5,
 5,
 4,
 2,
 5,
 5,
 20,
 1,
 102,
 6,
 166,
 1,
 1,
 24,
 1,
 1,
 136,
 26,
 3,
 2,
 4,
 1,
 3,
 1,
 2,
 25,
 5,
 2,
 83,
 1,
 5,
 1,
 1,
 1,
 1,
 1,
 8,
 4,
 19,
 2,
 1,
 7,
 3,
 25,
 1,
 2,
 76,
 8,
 2,
 28,
 1,
 1,
 2,
 1,
 1,
 1,
 1,
 3,
 1,
 1,
 1,
 1,
 1,
 1,
 2,
 2,
 1,
 24,
 2,
 1,
 1,
 1,
 3,
 4,
 60,
 2,
 1,
 1,
 1,
 1,
 2,
 3,
 1,
 228,
 5,
 27,
 179,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 82,
 1,
 1,
 1,
 2,
 5,
 2,
 1,
 148,
 4,
 1,
 1,
 1,
 1,
 2,
 29,
 2,
 9,
 3,
 1,
 2,
 3,
 11,
 1,
 1,
 1,
 1,
 1,
 2,
 1,
 2,
 1,
 1,
 2,
 2,
 171,
 1,
 157,
 1,
 2,
 4,
 3,
 1,
 2,
 2,
 120,
 1,
 30,
 3,
 1,
 1,
 1,
 1,
 1,
 1,
 106,
 1,
 1,
 26,
 1,
 127,
 5,
 1,
 2,
 4,
 1,
 1,
 2,
 1,
 1,
 2,
 1,
 201,
 7,
 88,
 1,
 1,
 1,
 53,
 3,
 1,
 2,
 1,
 1,
 1,
 2,
 1,
 5,
 1,
 9,
 8,
 28,
 1,
 156,
 1,
 43,
 5,
 24,
 16,
 2,
 1,
 5,
 1,
 10,
 1,
 1,
 33,
 203,
 2,
 1,
 7,
 31,
 2,
 229,
 1,
 1,
 1,
 1,
 118,
 45,
 41,
 2,
 2,
 2,
 1,
 77,
 2,
 120,
 2,
 45,
 58,
 3,
 3,
 22,
 1,
 1,
 1,
 4,
 1,
 6,
 1,
 1,
 140,
 6,
 40,
 1,
 43,
 10,
 1,
 1,
 10,
 1,
 1,
 1,
 6,
 181,
 5,
 19,
 1,
 1,
 1,
 34,
 3,
 2,
 1,
 6,
 1,
 1,
 1,
 10,
 1,
 2,
 1,
 1,
 1,
 10,
 1,
 1,
 114,
 1,
 1,
 1,
 1,
 12,
 189,
 1,
 1,
 7,
 1,
 11,
 1,
 35,
 1,
 12,
 1,
 2,
 1,
 17,
 1,
 3,
 42,
 1,
 1,
 3,
 31,
 1,
 1,
 1,
 53,
 3,
 1,
 1,
 1,
 13,
 1,
 1,
 75,
 15,
 1,
 21,
 3,
 1,
 3,
 13,
 1,
 16,
 2,
 10,
 1,
 1,
 1,
 1,
 1,
 2,
 9,
 1,
 2,
 3,
 1,
 1,
 3,
 125,
 1,
 6,
 40,
 1,
 47,
 1,
 2,
 1,
 5,
 1,
 1,
 2,
 26,
 1,
 1,
 5,
 1,
 1,
 1,
 3,
 93,
 2,
 5,
 2,
 1,
 108,
 23,
 1,
 4,
 1,
 3,
 2,
 1,
 1,
 28,
 1,
 35,
 104,
 1,
 2,
 1,
 5,
 27,
 176,
 1,
 11,
 1,
 1,
 58,
 1,
 1,
 42,
 84,
 5,
 2,
 1,
 7,
 26,
 11,
 6,
 22,
 1,
 27,
 9,
 3,
 2,
 1,
 1,
 1,
 1,
 1,
 175,
 1,
 15,
 1,
 1,
 1,
 7,
 108,
 1,
 88,
 149,
 10,
 14]

In [16]:

labeldt['time'] = timelist
labeldt['Change'] = trlist
labeldt['drop range'] = lplist
labeldt['limit Change'] = q_trlist
labeldt

Out[16]:

	stock	date	1日收盘价	2日收盘价	3日收盘价	time	Change	drop range	limit Change
2014-01-03	600010.SH	2014-01-03	-1	-1	-1	111	4.66	-3.65	0.00
2014-01-16	000767.SZ	2014-01-16	-1	-1	-1	2	0.23	-2.27	0.00
2014-02-12	000971.SZ	2014-02-12	-1	-1	-1	209	10.74	-7.14	0.00
2014-02-21	000554.SZ	2014-02-21	-1	-1	-1	1	3.99	-1.19	9.58
2014-02-28	600680.SH	2014-02-28	1	1	1	1	0.79	-0.60	1.95
2014-03-10	300116.SZ	2014-03-10	-1	-1	-1	1	1.16	-1.14	15.01
2014-03-13	000923.SZ	2014-03-13	-1	1	1	1	1.42	-1.99	2.48
2014-03-27	000687.SZ	2014-03-27	-1	-1	-1	25	8.88	-7.78	1.11
2014-04-03	000918.SZ	2014-04-03	-1	-1	-1	1	0.68	-4.82	0.43
2014-04-10	300278.SZ	2014-04-10	1	1	1	2	4.56	-2.59	3.06
2014-04-30	601001.SH	2014-04-30	1	-1	-1	1	0.17	-0.81	0.64
2014-05-21	002660.SZ	2014-05-21	1	1	1	2	2.72	-1.87	0.88
2014-06-04	600601.SH	2014-06-04	-1	-1	-1	1	1.00	-2.28	0.00
2014-06-05	600074.SH	2014-06-05	-1	-1	-1	1	1.00	-1.17	2.63
2014-06-06	002535.SZ	2014-06-06	1	1	1	3	2.15	-2.86	1.05
2014-06-16	300198.SZ	2014-06-16	-1	-1	-1	1	1.01	-3.84	1.28
2014-06-30	002093.SZ	2014-06-30	-1	-1	-1	5	3.30	-3.93	0.00
2014-07-02	300288.SZ	2014-07-02	1	1	1	228	20.97	-4.61	4.82
2014-07-04	002070.SZ	2014-07-04	-1	-1	-1	19	7.00	-8.27	0.60
2014-07-07	600568.SH	2014-07-07	-1	1	1	11	3.71	-5.23	0.00
2014-07-08	600435.SH	2014-07-08	1	1	1	4	1.20	-2.31	4.53
2014-07-11	002629.SZ	2014-07-11	1	-1	-1	60	14.15	-5.76	3.86
2014-07-16	000868.SZ	2014-07-16	-1	-1	-1	1	0.69	-2.19	5.31
2014-07-25	600319.SH	2014-07-25	-1	1	1	1	1.57	-1.83	3.54
2014-07-28	600157.SH	2014-07-28	1	1	1	1	1.48	-2.11	4.34
2014-08-07	600556.SH	2014-08-07	-1	-1	-1	6	4.43	-5.58	0.00
2014-08-11	600222.SH	2014-08-11	-1	-1	-1	95	4.91	-5.48	0.00
2014-08-14	300208.SZ	2014-08-14	-1	1	1	3	2.98	-2.43	3.87
2014-08-18	002125.SZ	2014-08-18	1	-1	1	1	0.73	-1.55	5.67
2014-08-21	000922.SZ	2014-08-21	1	1	1	211	20.19	-12.07	0.00
...	...	...	...	...	...	...	...	...	...
2018-12-19	002845.SZ	2018-12-19	1	-1	1	2	1.35	-0.82	5.63
2018-12-25	000531.SZ	2018-12-25	-1	-1	-1	1	0.26	-1.28	0.00
2018-12-26	300687.SZ	2018-12-26	-1	-1	-1	7	6.95	-4.35	2.43
2018-12-27	300407.SZ	2018-12-27	-1	-1	-1	26	2.90	-4.58	3.67
2018-12-28	601619.SH	2018-12-28	-1	-1	-1	11	1.55	-2.54	3.17
2019-01-04	300125.SZ	2019-01-04	1	1	1	6	1.15	-2.67	0.20
2019-01-07	300588.SZ	2019-01-07	-1	-1	-1	22	7.75	-4.16	3.56
2019-01-08	600677.SH	2019-01-08	-1	-1	-1	1	3.41	-1.64	0.00
2019-01-09	600452.SH	2019-01-09	1	1	1	27	0.57	-3.31	0.00
2019-01-10	300076.SZ	2019-01-10	-1	-1	-1	9	5.39	-6.87	0.00
2019-01-11	002941.SZ	2019-01-11	-1	-1	-1	3	5.64	-3.13	0.00
2019-01-14	603220.SH	2019-01-14	-1	-1	1	2	9.77	-3.34	1.07
2019-01-16	600446.SH	2019-01-16	-1	-1	-1	1	0.66	-0.58	1.80
2019-01-18	600470.SH	2019-01-18	1	1	1	1	0.68	-0.45	2.56
2019-01-21	300693.SZ	2019-01-21	-1	1	1	1	3.01	-1.63	3.94
2019-01-22	300503.SZ	2019-01-22	-1	-1	-1	1	1.47	-1.62	1.12
2019-01-24	002170.SZ	2019-01-24	-1	-1	-1	1	2.70	-1.82	0.00
2019-01-25	600721.SH	2019-01-25	1	-1	-1	175	3.81	-4.69	0.48
2019-01-28	000637.SZ	2019-01-28	-1	-1	-1	1	1.05	-2.73	6.09
2019-01-31	300250.SZ	2019-01-31	1	1	1	15	1.20	-1.48	4.80
2019-02-01	002011.SZ	2019-02-01	-1	-1	-1	1	1.27	-3.88	1.30
2019-02-11	600532.SH	2019-02-11	-1	-1	-1	1	0.60	-2.15	1.84
2019-02-12	600318.SH	2019-02-12	1	-1	-1	1	0.47	-0.70	0.47
2019-02-13	300097.SZ	2019-02-13	1	1	1	7	4.94	-3.57	1.52
2019-02-14	300256.SZ	2019-02-14	-1	1	1	108	11.96	-8.09	0.50
2019-02-18	002099.SZ	2019-02-18	1	1	-1	1	0.28	-0.18	0.43
2019-02-19	300468.SZ	2019-02-19	-1	-1	-1	88	3.14	-6.16	1.44
2019-02-20	600393.SH	2019-02-20	-1	-1	1	149	16.27	-8.01	0.00
2019-02-21	002565.SZ	2019-02-21	1	1	-1	10	4.02	-7.37	0.62
2019-02-22	300063.SZ	2019-02-22	1	-1	-1	14	2.24	-2.49	4.45

503 rows × 9 columns

In [17]:

updt = labeldt[labeldt['1日收盘价']==1]
downdt =  labeldt[labeldt['1日收盘价']==-1]
label = ['time','Change','drop range','limit Change']
from mpl_toolkits.mplot3d import Axes3D
xsup1 = updt[label[0]]
xsup2 = updt[label[1]]
xsup3 = updt[label[2]]
xsdown1 = downdt[label[0]]
xsdown2 = downdt[label[1]]
xsdown3 = downdt[label[2]]
fig = plt.figure()
ax = Axes3D(fig)
ax.scatter(xsup1,xsup2,xsup3,c='tomato')
ax.scatter(xsdown1,xsdown2,xsdown3,c='g')
ax.set_xlabel(label[0],fontsize=12)
ax.set_ylabel(label[1],fontsize=12)
ax.set_zlabel(label[2],fontsize=12)
ax.set_title('one day Data space 3D ',fontsize=20)
plt.show()

for l in label:
    fig = plt.figure()
    axes = fig.add_axes([0.1, 0.1, 1, 0.618]) 
    x1_list=list(updt[l])
    y=np.array(x1_list)
    x=np.array(range(0,len(x1_list)))
    axes.scatter(x,y,c='tomato')

    x1_list=list(downdt[l])
    y=np.array(x1_list)
    x=np.array(range(0,len(x1_list)))
    axes.scatter(x,y,c='g')
    axes.set_ylabel('value',fontsize=15)
    axes.set_title(l,fontsize=20)

In [55]:

labeldt
label = ['time','Change','drop range','limit Change']

train = labeldt[:300]
test = labeldt[-200:]
X=train[label]
Y=train['1日收盘价']
X_test=test[label]
Y_test=test['1日收盘价']

from sklearn import svm
model = svm.SVC(C=1, kernel='rbf', gamma=0.5, decision_function_shape='ovo')

model.fit(X, Y)
print('训练时,预测成功率 {}'.format(round(np.mean(model.predict(X)==Y),2)))
print('测试时,预测成功率 {}'.format(round(np.mean(model.predict(X_test)==Y_test),2)))

训练时,预测成功率 0.88
测试时,预测成功率 0.55

In [102]:

dataclosedf = datadf#[['stock','date','1日收盘价','2日收盘价','3日收盘价']]
dataclosedf = dataclosedf.sort_values(by='1日收盘价',ascending=False)


tradeday = list(get_trade_days(startdate, '20200202', count=None).strftime('%Y-%m-%d'))

timelist = []
trlist= []
lplist =[]
q_trlist = []
for d in tradeday:
    time = 0
    tr = 0
    lp = 0
    q_tr = 0
    if d in list(labeldt['date']):
        stock = labeldt['stock'][d]
        day = tradeday[tradeday.index(d)+1]
        stockdata = get_price(stock,None,day,'1m',['close','high','low','open','turnover_rate'],True,'pre',bar_count=241,is_panel=0)
        
        pc = stockdata.iloc[0].close
        highlimit = round(pc*1.1,2)
        
        stockdata = stockdata.iloc[-240:]
        
        for m in list(range(0,240)):
            
            rc = stockdata.iloc[m].close
            h = stockdata.iloc[(m+1)].high
            
            if rc == highlimit:
                q_tr +=stockdata.iloc[m].turnover_rate
                
            if rc<highlimit:
                time += 1
                tr +=stockdata.iloc[m].turnover_rate
                lp = min(stockdata.iloc[m].low/highlimit-1,lp)
            
            if rc<highlimit and h == highlimit:
                break
        if time>0:
            timelist.append(time)
            trlist.append(round(tr,2))
            lplist.append(round(lp*100,2))
            q_trlist.append(round(q_tr,2))
dataclosedf['time'] = timelist
dataclosedf['Change'] = trlist
dataclosedf['drop range'] = lplist
dataclosedf['limit Change'] = q_trlist
dataclosedf

Out[102]:

	stock	date	buyprice	当日收盘价	1日收盘价	1日开盘价	1日最高价	1日最低价	2日收盘价	2日开盘价	2日最高价	2日最低价	3日收盘价	3日开盘价	3日最高价	3日最低价	time	Change	drop range	limit Change
2015-05-19	002014.SZ	2015-05-19	9.44	9.44	0.109110	0.109110	0.109110	0.061441	0.229873	0.119703	0.229873	0.112288	0.363347	0.324153	0.363347	0.318856	111	4.66	-3.65	0.00
2014-07-08	600435.SH	2014-07-08	7.47	7.47	0.103079	0.038822	0.103079	0.024096	0.168675	0.156627	0.214190	0.140562	0.267738	0.164659	0.282463	0.143240	2	0.23	-2.27	0.00
2015-01-12	002738.SZ	2015-01-12	13.85	13.85	0.102527	0.010108	0.102527	-0.031047	0.215162	0.156679	0.215162	0.133574	0.338628	0.257762	0.338628	0.246209	209	10.74	-7.14	0.00
2015-05-20	000838.SZ	2015-05-20	6.69	6.69	0.101644	0.013453	0.101644	0.001495	0.038864	0.213752	0.213752	0.038864	0.143498	0.005979	0.143498	-0.008969	1	3.99	-1.19	9.58
2015-06-04	300309.SZ	2015-06-04	10.68	10.68	0.101124	0.088015	0.101124	0.061798	-0.008427	0.113296	0.113296	-0.010300	0.056180	-0.028090	0.056180	-0.029026	1	0.79	-0.60	1.95
2015-07-30	300368.SZ	2015-07-30	9.81	9.81	0.100917	-0.002039	0.100917	-0.040775	0.211009	0.113150	0.211009	0.076453	0.332314	0.332314	0.332314	0.298675	1	1.16	-1.14	15.01
2018-08-08	600470.SH	2018-08-08	4.66	4.66	0.100858	-0.034335	0.100858	-0.036481	-0.006438	0.072961	0.094421	-0.008584	-0.062232	-0.051502	-0.040773	-0.081545	1	1.42	-1.99	2.48
2014-07-28	600157.SH	2014-07-28	2.48	2.48	0.100806	-0.004032	0.100806	-0.012097	0.213710	0.153226	0.213710	0.137097	0.266129	0.262097	0.338710	0.241935	25	8.88	-7.78	1.11
2015-04-02	002006.SZ	2015-04-02	11.61	11.61	0.100775	0.088717	0.100775	0.063738	0.136090	0.193798	0.193798	0.074074	0.090439	0.114556	0.114556	0.055986	1	0.68	-4.82	0.43
2014-08-22	300356.SZ	2014-08-22	9.03	9.03	0.100775	0.014396	0.100775	0.014396	0.075305	0.071982	0.087486	0.047619	0.160576	0.107420	0.182724	0.091916	2	4.56	-2.59	3.06
2015-08-04	603616.SH	2015-08-04	18.16	18.16	0.100771	-0.011013	0.100771	-0.090308	0.210903	0.210903	0.210903	0.034692	0.332599	0.154185	0.332599	0.126652	1	0.17	-0.81	0.64
2018-08-07	300392.SZ	2018-08-07	6.75	6.75	0.100741	0.044444	0.100741	0.038519	0.210370	0.210370	0.210370	0.133333	0.331852	0.331852	0.331852	0.331852	2	2.72	-1.87	0.88
2017-03-15	002850.SZ	2017-03-15	84.81	84.81	0.100696	0.047046	0.100696	0.031364	0.054946	0.101167	0.141729	0.047046	0.039382	0.031246	0.053060	0.000000	1	1.00	-2.28	0.00
2015-07-17	002392.SZ	2015-07-17	6.56	6.56	0.100610	0.092988	0.100610	0.060976	0.211890	0.144817	0.211890	0.103659	0.321646	0.289634	0.333841	0.239329	1	1.00	-1.17	2.63
2018-03-16	002264.SZ	2018-03-16	8.95	8.95	0.100559	0.049162	0.100559	0.039106	0.128492	0.098324	0.173184	0.061453	0.241341	0.092737	0.241341	0.092737	3	2.15	-2.86	1.05
2015-03-16	600207.SH	2015-03-16	7.16	7.16	0.100559	0.005587	0.100559	-0.005587	0.150838	0.166201	0.210894	0.117318	0.113128	0.157821	0.157821	0.079609	1	1.01	-3.84	1.28
2014-09-12	300161.SZ	2014-09-12	14.82	14.82	0.100540	0.008772	0.100540	0.000000	0.089744	0.102564	0.176113	0.089069	0.057355	0.075574	0.075574	0.033738	5	3.30	-3.93	0.00
2016-11-01	300044.SZ	2016-11-01	9.55	9.55	0.100524	0.021990	0.100524	0.008377	0.067016	0.158115	0.211518	0.056545	0.086911	0.071204	0.106806	0.053403	228	20.97	-4.61	4.82
2018-11-21	002337.SZ	2018-11-21	4.28	4.28	0.100467	0.100467	0.100467	0.079439	0.210280	0.168224	0.210280	0.126168	0.088785	0.331776	0.331776	0.088785	19	7.00	-8.27	0.60
2018-05-21	002828.SZ	2018-05-21	17.92	17.92	0.100446	0.046875	0.100446	0.019531	0.210937	0.210937	0.210937	0.155692	NaN	NaN	NaN	NaN	11	3.71	-5.23	0.00
2015-05-04	600744.SH	2015-05-04	9.06	9.06	0.100442	0.100442	0.100442	0.004415	0.121413	0.034216	0.203091	0.024283	0.008830	0.088300	0.113687	0.008830	4	1.20	-2.31	4.53
2015-08-26	000628.SZ	2015-08-26	11.45	11.45	0.100437	0.082969	0.100437	0.061135	0.210480	0.210480	0.210480	0.210480	0.089083	0.222707	0.222707	0.089083	60	14.15	-5.76	3.86
2014-09-19	000852.SZ	2014-09-19	16.13	16.13	0.100434	0.003100	0.100434	0.000620	0.115933	0.075635	0.141971	0.058896	0.115313	0.112213	0.135152	0.088655	1	0.69	-2.19	5.31
2017-08-29	603042.SH	2017-08-29	33.56	33.56	0.100417	-0.021454	0.100417	-0.027414	0.076281	0.031585	0.103397	0.008641	0.030691	0.056317	0.093564	0.027712	1	1.57	-1.83	3.54
2015-02-04	000875.SZ	2015-02-04	5.28	5.28	0.100379	0.041667	0.100379	0.009470	0.090909	0.115530	0.181818	0.062500	0.009470	0.045455	0.077652	-0.017045	1	1.48	-2.11	4.34
2017-03-13	601212.SH	2017-03-13	10.66	10.66	0.100375	-0.016886	0.100375	-0.031895	0.211069	0.158537	0.211069	0.137899	0.332083	0.280488	0.332083	0.267355	6	4.43	-5.58	0.00
2018-08-09	300392.SZ	2018-08-09	8.17	8.17	0.100367	0.100367	0.100367	0.100367	0.210526	0.188494	0.210526	0.144431	0.097919	0.200734	0.200734	0.089351	95	4.91	-5.48	0.00
2015-12-02	000668.SZ	2015-12-02	26.61	26.61	0.100338	0.050733	0.100338	0.033070	0.066892	0.104848	0.162345	0.062383	0.071778	0.069523	0.086809	0.044344	3	2.98	-2.43	3.87
2017-08-22	300678.SZ	2017-08-22	29.01	29.01	0.100310	0.061358	0.100310	0.042744	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	1	0.73	-1.55	5.67
2014-02-28	600680.SH	2014-02-28	13.26	13.26	0.100302	0.045249	0.100302	0.045249	0.210407	0.118401	0.210407	0.105581	0.331825	0.272247	0.331825	0.272247	211	20.19	-12.07	0.00
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
2016-02-25	300280.SZ	2016-02-25	31.52	29.89	-0.122462	-0.084074	-0.054569	-0.146574	-0.210343	-0.147525	-0.147525	-0.210343	-0.216371	-0.216688	-0.191942	-0.264911	2	1.35	-0.82	5.63
2015-10-23	300081.SZ	2015-10-23	16.35	15.89	-0.125994	-0.078287	-0.056881	-0.125994	-0.099694	-0.173089	-0.083792	-0.176758	-0.185321	-0.124771	-0.116820	-0.188991	1	0.26	-1.28	0.00
2018-06-14	002096.SZ	2018-06-14	8.44	8.16	-0.130332	-0.092417	-0.092417	-0.130332	-0.218009	-0.210900	-0.187204	-0.218009	-0.172986	-0.254739	-0.169431	-0.255924	7	6.95	-4.35	2.43
2018-06-15	002423.SZ	2018-06-15	14.62	14.08	-0.133379	-0.110807	-0.110807	-0.133379	-0.112859	-0.220246	-0.056772	-0.220246	-0.178523	-0.158687	-0.083447	-0.189466	26	2.90	-4.58	3.67
2016-12-19	300268.SZ	2016-12-19	50.41	48.50	-0.134100	-0.067249	-0.048006	-0.134100	-0.218806	-0.176552	-0.167824	-0.220591	-0.218409	-0.226146	-0.199564	-0.238643	11	1.55	-2.54	3.17
2018-08-02	002400.SZ	2018-08-02	3.62	3.46	-0.140884	-0.093923	-0.088398	-0.140884	-0.174033	-0.157459	-0.151934	-0.182320	-0.140884	-0.149171	-0.135359	-0.168508	6	1.15	-2.67	0.20
2017-04-14	000616.SZ	2017-04-14	6.12	5.78	-0.145425	-0.101307	-0.084967	-0.150327	-0.145425	-0.153595	-0.111111	-0.156863	-0.156863	-0.156863	-0.140523	-0.181373	22	7.75	-4.16	3.56
2015-05-22	300201.SZ	2015-05-22	11.64	10.16	-0.146048	-0.185567	-0.088488	-0.214777	-0.060137	-0.158935	-0.060137	-0.162371	-0.066151	-0.005155	-0.001718	-0.095361	1	3.41	-1.64	0.00
2015-04-27	300188.SZ	2015-04-27	17.96	16.97	-0.150334	-0.084076	-0.055122	-0.150334	NaN	NaN	NaN	NaN	-0.149220	-0.116927	-0.097439	-0.149777	27	0.57	-3.31	0.00
2018-12-06	300006.SZ	2018-12-06	4.92	4.42	-0.154472	-0.097561	-0.085366	-0.168699	-0.203252	-0.172764	-0.166667	-0.203252	-0.199187	-0.201220	-0.191057	-0.203252	9	5.39	-6.87	0.00
2015-03-05	300364.SZ	2015-03-05	16.04	14.58	-0.154613	-0.085411	-0.026808	-0.175810	-0.149002	-0.158354	-0.125312	-0.175810	-0.143392	-0.155860	-0.092893	-0.163965	3	5.64	-3.13	0.00
2018-11-29	600936.SH	2018-11-29	5.10	4.77	-0.154902	-0.109804	-0.107843	-0.158824	-0.117647	-0.158824	-0.090196	-0.162745	-0.133333	-0.133333	-0.129412	-0.150980	2	9.77	-3.34	1.07
2018-04-11	300705.SZ	2018-04-11	28.85	26.79	-0.164298	-0.071404	-0.049567	-0.164298	-0.224263	-0.198614	-0.164298	-0.235355	-0.236742	-0.250260	-0.228076	-0.253380	1	0.66	-0.58	1.80
2018-10-26	603999.SH	2018-10-26	5.75	5.25	-0.177391	-0.142609	-0.142609	-0.177391	-0.160000	-0.184348	-0.137391	-0.205217	-0.161739	-0.172174	-0.149565	-0.180870	1	0.68	-0.45	2.56
2019-01-10	300076.SZ	2019-01-10	5.68	5.13	-0.179577	-0.140845	-0.125000	-0.184859	-0.179577	-0.158451	-0.144366	-0.197183	-0.170775	-0.188380	-0.160211	-0.198944	1	3.01	-1.63	3.94
2014-12-22	600169.SH	2014-12-22	8.81	7.95	-0.181612	-0.113507	-0.091941	-0.187287	-0.205448	-0.205448	-0.185017	-0.225880	-0.125993	-0.187287	-0.125993	-0.197503	1	1.47	-1.62	1.12
2015-05-14	300431.SZ	2015-05-14	105.32	91.51	-0.187524	-0.191132	-0.137486	-0.218002	-0.106248	-0.165970	-0.106248	-0.173092	-0.016901	-0.050893	-0.016901	-0.106248	1	2.70	-1.82	0.00
2018-11-05	300748.SZ	2018-11-05	36.32	31.29	-0.217786	-0.174009	-0.146476	-0.223568	-0.185022	-0.208700	-0.177037	-0.236509	-0.229075	-0.215584	-0.201542	-0.243667	175	3.81	-4.69	0.48
2015-09-14	000797.SZ	2015-09-14	7.66	6.38	-0.251958	-0.223238	-0.184073	-0.251958	-0.199739	-0.259791	-0.176240	-0.283290	-0.227154	-0.202350	-0.154047	-0.228460	1	1.05	-2.73	6.09
2015-07-06	002234.SZ	2015-07-06	12.73	10.44	-0.261587	-0.260801	-0.231736	-0.261587	-0.226237	-0.335428	-0.206599	-0.335428	NaN	NaN	NaN	NaN	15	1.20	-1.48	4.80
2018-01-10	600652.SH	2018-01-10	8.94	8.94	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	-0.083893	-0.051454	-0.020134	-0.090604	1	1.27	-3.88	1.30
2017-04-11	002774.SZ	2017-04-11	22.72	22.72	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	-0.100352	-0.078785	-0.034771	-0.100352	1	0.60	-2.15	1.84
2017-07-07	002885.SZ	2017-07-07	31.91	31.91	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	1	0.47	-0.70	0.47
2016-03-03	000982.SZ	2016-03-03	8.22	8.22	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	7	4.94	-3.57	1.52
2017-11-10	002409.SZ	2017-11-10	41.15	41.15	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	108	11.96	-8.09	0.50
2015-03-24	300310.SZ	2015-03-24	9.98	9.98	NaN	NaN	NaN	NaN	-0.071142	-0.046092	-0.039078	-0.100200	-0.044088	-0.090180	-0.002004	-0.097194	1	0.28	-0.18	0.43
2014-02-12	000971.SZ	2014-02-12	3.64	3.64	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	-0.027473	-0.098901	-0.002747	-0.098901	88	3.14	-6.16	1.44
2016-02-17	600234.SH	2016-02-17	22.85	22.22	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	149	16.27	-8.01	0.00
2018-05-14	002930.SZ	2018-05-14	41.53	41.53	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	0.099928	0.059475	0.099928	0.037804	10	4.02	-7.37	0.62
2017-04-12	600550.SH	2017-04-12	12.54	12.54	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	14	2.24	-2.49	4.45

503 rows × 20 columns

In [184]:

xdf = dataclosedf.dropna(axis=0)

In [185]:

xdf = xdf.sort_values(by='date')
xlabel = ['time','Change','drop range','limit Change']
ylabel = '3日收盘价'
xdf[ylabel] =xdf[ylabel].apply(lambda x:1 if x>0.02 else -1)

train = xdf[:300]
test = xdf[-200:]

X=train[xlabel]
Y=train[ylabel]

X_test=test[xlabel]
Y_test=test[ylabel]

from sklearn import svm
model = svm.SVC(C=5, kernel='rbf', gamma=0.5)

model.fit(X, Y)
print('训练时,预测成功率 {}'.format(round(np.mean(model.predict(X)==Y),2)))
print('测试时,预测成功率 {}'.format(round(np.mean(model.predict(X_test)==Y_test),2)))
len(list(test[test[ylabel]==1].index)),len(list(test[test[ylabel]==-1].index))

训练时,预测成功率 0.92
测试时,预测成功率 0.6

Out[185]:

(49, 151)

查看以上策略详情请到supermind量化交易官网查看：同花顺Supermind量化交易 运用SVM算法“打板”-- SVM算法应用