python数据分析——双均线策略

import tushare as ts
import pandas as pd
from pandas import DataFrame,Series
df = pd.read_csv('maotai.csv',index_col='date',parse_dates=['date'])
df.drop(labels='Unnamed: 0',axis=1,inplace=True)
df

Out[1]:

	open	close	high	low	volume	code
date
2001-08-27	5.392	5.554	5.902	5.132	406318.00	600519
2001-08-28	5.467	5.759	5.781	5.407	129647.79	600519
2001-08-29	5.777	5.684	5.781	5.640	53252.75	600519
2001-08-30	5.668	5.796	5.860	5.624	48013.06	600519
2001-08-31	5.804	5.782	5.877	5.749	23231.48	600519
2001-09-03	5.812	5.779	5.870	5.757	22112.09	600519
2001-09-04	5.782	5.852	5.949	5.762	37006.77	600519
2001-09-05	5.876	5.849	5.924	5.813	26066.95	600519
2001-09-06	5.835	5.734	5.854	5.704	28997.03	600519
2001-09-07	5.702	5.574	5.773	5.570	31552.25	600519
2001-09-10	5.531	5.734	5.757	5.470	18878.89	600519
2001-09-11	5.749	5.670	5.773	5.656	11390.81	600519
2001-09-12	5.520	5.621	5.656	5.515	25045.19	600519
2001-09-13	5.626	5.607	5.671	5.577	10986.68	600519
2001-09-14	5.626	5.671	5.702	5.593	7672.83	600519
2001-09-17	5.637	5.599	5.670	5.546	8983.97	600519
2001-09-18	5.606	5.663	5.710	5.601	10773.26	600519
2001-09-19	5.671	5.768	5.768	5.634	8650.53	600519
2001-09-20	5.765	5.720	5.788	5.702	11173.35	600519
2001-09-21	5.668	5.634	5.718	5.624	7879.72	600519
2001-09-24	5.634	5.632	5.685	5.624	4068.60	600519
2001-09-25	5.668	5.660	5.709	5.632	3488.45	600519
2001-09-26	5.642	5.637	5.699	5.624	4956.26	600519
2001-09-27	5.637	5.734	5.777	5.624	8778.04	600519
2001-09-28	5.765	5.795	5.812	5.702	17088.47	600519
2001-10-08	5.781	5.715	5.809	5.663	6552.17	600519
2001-10-09	5.718	5.827	5.859	5.718	9558.52	600519
2001-10-10	5.827	5.640	5.848	5.629	17548.69	600519
2001-10-11	5.626	5.585	5.702	5.570	12306.84	600519
2001-10-12	5.609	5.624	5.726	5.320	20010.70	600519
...	...	...	...	...	...	...
2019-01-16	658.000	661.100	665.650	653.600	42083.00	600519
2019-01-17	663.000	659.250	669.700	655.800	30284.00	600519
2019-01-18	665.000	683.610	690.200	661.500	68609.00	600519
2019-01-21	690.000	686.980	698.880	681.880	47051.00	600519
2019-01-22	686.000	671.000	686.000	665.220	42122.00	600519
2019-01-23	667.220	665.660	674.500	663.130	33624.00	600519
2019-01-24	670.300	672.500	677.830	664.680	29155.00	600519
2019-01-25	675.880	679.700	684.900	669.930	28986.00	600519
2019-01-28	684.000	677.000	693.980	676.030	36102.00	600519
2019-01-29	677.500	685.000	688.000	668.000	30342.00	600519
2019-01-30	684.990	676.000	686.220	676.000	22699.00	600519
2019-01-31	680.000	689.600	689.600	677.560	36696.00	600519
2019-02-01	697.040	692.670	699.000	689.610	30520.00	600519
2019-02-11	695.000	725.300	729.500	688.180	58140.00	600519
2019-02-12	723.000	717.920	725.490	715.200	35091.00	600519
2019-02-13	723.000	735.250	736.160	717.220	35677.00	600519
2019-02-14	731.200	737.160	743.660	730.140	32258.00	600519
2019-02-15	734.880	724.780	734.880	723.020	23237.00	600519
2019-02-18	731.000	740.000	744.950	731.000	37745.00	600519
2019-02-19	740.960	730.760	742.500	726.660	29501.00	600519
2019-02-20	735.000	722.000	735.000	716.060	37882.00	600519
2019-02-21	720.000	720.250	730.480	717.000	29850.00	600519
2019-02-22	717.000	726.010	728.490	714.100	25908.00	600519
2019-02-25	730.750	742.330	744.440	717.990	82622.00	600519
2019-02-26	747.800	727.350	749.180	726.000	57964.00	600519
2019-02-27	733.000	740.700	758.020	731.000	65942.00	600519
2019-02-28	737.900	755.010	763.420	736.950	56986.00	600519
2019-03-01	761.500	789.300	790.000	761.000	63840.00	600519
2019-03-04	795.000	781.860	798.330	777.220	84585.00	600519
2019-03-05	785.000	779.780	789.550	775.880	44830.00	600519

4174 rows × 6 columns

In [6]:

# 收盘价的5日均值和30日均值
ma5 = df['close'].rolling(5).mean()
ma30 =  df['close'].rolling(30).mean()
df['ma5'] = ma5
df['ma30'] = ma30

 

s1 = ma5 < ma30 T->F金叉 F->T死叉 s2 = ma5 >= ma30 s1 T T F F T T F F
s2 F F T T F F T T T F T T T F T F T F F F T F

~(s1 | s2.shift(1))

In [9]:

# 金叉时间
s1 = ma5 < ma30 
s2 = ma5 >= ma30 
df.loc[~(s1 | s2.shift(1))].index

Out[9]:

DatetimeIndex(['2001-08-27', '2001-08-28', '2001-08-29', '2001-08-30',
               '2001-08-31', '2001-09-03', '2001-09-04', '2001-09-05',
               '2001-09-06', '2001-09-07',
               ...
               '2017-07-24', '2017-09-18', '2017-12-15', '2018-03-16',
               '2018-05-09', '2018-07-18', '2018-07-25', '2018-09-20',
               '2018-12-04', '2019-01-03'],
              dtype='datetime64[ns]', name='date', length=120, freq=None)

In [11]:

# 死叉时间
df.loc[s1&s2.shift(1)].index

Out[11]:

DatetimeIndex(['2002-01-17', '2002-01-30', '2002-03-29', '2002-07-29',
               '2002-12-27', '2003-03-17', '2003-04-22', '2003-06-20',
               '2003-06-30', '2003-08-04', '2004-02-27', '2004-05-11',
               '2004-06-07', '2004-08-20', '2004-11-23', '2005-04-20',
               '2005-05-16', '2005-06-15', '2005-09-27', '2006-07-10',
               '2006-07-31', '2006-08-24', '2006-09-13', '2007-02-08',
               '2007-04-23', '2007-05-09', '2007-07-12', '2007-09-12',
               '2007-11-12', '2007-11-22', '2008-01-31', '2008-03-18',
               '2008-05-23', '2008-08-12', '2008-12-31', '2009-03-12',
               '2009-04-30', '2009-08-20', '2009-09-02', '2009-10-20',
               '2009-12-18', '2010-01-22', '2010-02-26', '2010-06-23',
               '2010-10-15', '2010-11-02', '2010-12-24', '2011-03-02',
               '2011-03-30', '2011-09-08', '2011-12-08', '2012-07-24',
               '2012-08-02', '2012-08-15', '2012-09-21', '2012-11-07',
               '2012-12-25', '2013-01-18', '2013-03-18', '2013-06-21',
               '2013-07-12', '2013-10-25', '2013-11-26', '2013-12-04',
               '2014-04-01', '2014-04-30', '2014-08-22', '2014-09-16',
               '2014-10-13', '2014-11-21', '2015-01-19', '2015-06-17',
               '2015-07-17', '2015-09-28', '2015-11-26', '2015-12-10',
               '2016-01-05', '2016-08-05', '2016-08-18', '2016-11-21',
               '2017-07-06', '2017-09-08', '2017-11-29', '2018-02-05',
               '2018-03-27', '2018-06-28', '2018-07-23', '2018-07-31',
               '2018-10-15', '2018-12-25'],
              dtype='datetime64[ns]', name='date', freq=None)

In [12]:

#如果我从假如我从2010年1月1日开始，初始资金为100000元，金叉尽量买入，死叉全部卖出，则到今天为止，我的炒股收益率如何？
df = df['2010':'2019']
df

Out[12]:

	open	close	high	low	volume	code	ma5	ma30
date
2010-01-04	109.760	108.446	109.760	108.044	44304.88	600519	108.5402	109.306267
2010-01-05	109.116	108.127	109.441	107.846	31513.18	600519	108.4178	109.256500
2010-01-06	107.840	106.417	108.165	106.129	39889.03	600519	107.8512	109.191000
2010-01-07	106.417	104.477	106.691	103.302	48825.55	600519	107.1672	108.971067
2010-01-08	104.655	103.379	104.655	102.167	36702.09	600519	106.1692	108.833000
2010-01-11	104.400	102.926	105.230	102.422	24461.03	600519	105.0652	108.749633
2010-01-12	103.028	105.708	106.040	102.492	31063.40	600519	104.5814	108.573933
2010-01-13	104.649	103.022	105.389	102.741	37924.44	600519	103.9024	108.237867
2010-01-14	103.379	107.552	107.974	103.379	46454.64	600519	104.5174	108.076200
2010-01-15	107.533	108.401	110.641	107.533	45938.50	600519	105.5218	107.990467
2010-01-18	108.484	109.110	109.926	108.420	21461.53	600519	106.7586	107.992167
2010-01-19	109.116	108.337	109.441	108.165	17818.91	600519	107.2844	107.848367
2010-01-20	108.427	105.881	108.580	105.804	20972.95	600519	107.8562	107.664600
2010-01-21	105.842	106.397	107.450	105.613	17257.48	600519	107.6252	107.535267
2010-01-22	106.314	104.738	106.755	103.309	25432.94	600519	106.8926	107.316367
2010-01-25	104.560	105.957	106.761	103.704	23239.15	600519	106.2620	107.127700
2010-01-26	107.380	106.378	108.593	105.038	32889.16	600519	105.8702	106.964333
2010-01-27	105.951	104.643	107.068	104.400	19316.57	600519	105.6226	106.774167
2010-01-28	104.566	107.974	108.708	104.336	30267.52	600519	105.9380	106.769933
2010-01-29	108.452	107.552	108.612	107.004	37172.82	600519	106.5008	106.816700
2010-02-01	107.769	107.776	108.216	106.576	29655.94	600519	106.8646	106.893933
2010-02-02	107.208	106.263	108.484	106.117	15493.53	600519	106.8416	106.867333
2010-02-03	106.066	105.887	107.272	104.783	23034.65	600519	107.0904	106.847333
2010-02-04	105.868	107.591	108.006	105.376	22475.33	600519	107.0138	106.866900
2010-02-05	106.959	109.282	109.684	106.570	26234.30	600519	107.3598	106.841367
2010-02-08	109.282	109.269	112.058	108.816	31496.10	600519	107.6584	106.858167
2010-02-09	109.760	109.193	110.609	108.822	14151.24	600519	108.2444	106.873300
2010-02-10	109.760	109.652	110.137	108.931	6398.14	600519	108.9974	106.886700
2010-02-11	109.633	110.641	111.318	109.505	14945.05	600519	109.6074	106.978167
2010-02-12	111.018	110.456	111.164	109.888	9346.40	600519	109.8422	107.047733
...	...	...	...	...	...	...	...	...
2019-01-16	658.000	661.100	665.650	653.600	42083.00	600519	640.0660	596.694000
2019-01-17	663.000	659.250	669.700	655.800	30284.00	600519	648.1620	598.594667
2019-01-18	665.000	683.610	690.200	661.500	68609.00	600519	657.7080	601.045000
2019-01-21	690.000	686.980	698.880	681.880	47051.00	600519	670.1840	604.217667
2019-01-22	686.000	671.000	686.000	665.220	42122.00	600519	672.3880	607.017667
2019-01-23	667.220	665.660	674.500	663.130	33624.00	600519	673.3000	609.965333
2019-01-24	670.300	672.500	677.830	664.680	29155.00	600519	675.9500	612.949000
2019-01-25	675.880	679.700	684.900	669.930	28986.00	600519	675.1680	615.972333
2019-01-28	684.000	677.000	693.980	676.030	36102.00	600519	673.1720	618.480667
2019-01-29	677.500	685.000	688.000	668.000	30342.00	600519	675.9720	621.548667
2019-01-30	684.990	676.000	686.220	676.000	22699.00	600519	678.0400	624.398000
2019-01-31	680.000	689.600	689.600	677.560	36696.00	600519	681.4600	627.686667
2019-02-01	697.040	692.670	699.000	689.610	30520.00	600519	684.0540	631.515667
2019-02-11	695.000	725.300	729.500	688.180	58140.00	600519	693.7140	636.542333
2019-02-12	723.000	717.920	725.490	715.200	35091.00	600519	700.2980	641.559333
2019-02-13	723.000	735.250	736.160	717.220	35677.00	600519	712.1480	647.134333
2019-02-14	731.200	737.160	743.660	730.140	32258.00	600519	721.6600	652.846667
2019-02-15	734.880	724.780	734.880	723.020	23237.00	600519	728.0820	658.336667
2019-02-18	731.000	740.000	744.950	731.000	37745.00	600519	731.0220	664.236667
2019-02-19	740.960	730.760	742.500	726.660	29501.00	600519	733.5900	668.928333
2019-02-20	735.000	722.000	735.000	716.060	37882.00	600519	730.9400	673.029000
2019-02-21	720.000	720.250	730.480	717.000	29850.00	600519	727.5580	677.370667
2019-02-22	717.000	726.010	728.490	714.100	25908.00	600519	727.8040	681.504333
2019-02-25	730.750	742.330	744.440	717.990	82622.00	600519	728.2700	686.065667
2019-02-26	747.800	727.350	749.180	726.000	57964.00	600519	727.5880	690.151000
2019-02-27	733.000	740.700	758.020	731.000	65942.00	600519	731.3280	694.303667
2019-02-28	737.900	755.010	763.420	736.950	56986.00	600519	738.2800	698.845000
2019-03-01	761.500	789.300	790.000	761.000	63840.00	600519	750.9380	703.959000
2019-03-04	795.000	781.860	798.330	777.220	84585.00	600519	758.8440	709.201000
2019-03-05	785.000	779.780	789.550	775.880	44830.00	600519	769.3300	713.194333

2221 rows × 8 columns

In [13]:

df['ma5']=df['close'].rolling(5).mean()
df['ma30']=df['close'].rolling(30).mean()

 

C:jupyterlibsite-packagesipykernel_launcher.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  """Entry point for launching an IPython kernel.
C:jupyterlibsite-packagesipykernel_launcher.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  

In [15]:

sr1 = df['ma5'] < df['ma30']
sr2 = df['ma5'] >= df['ma30']
death_cross = df[sr1 & sr2.shift(1)].index
golden_cross = df[~(sr1 | sr2.shift(1))].index

In [16]:

first_money = 100000
money = first_money
hold = 0#持有多少股
sr1 = pd.Series(1, index=golden_cross)
sr2 = pd.Series(0, index=death_cross)
#根据时间排序
sr = sr1.append(sr2).sort_index()

for i in range(0, len(sr)):
    p = df['open'][sr.index[i]] # 开盘价
    if sr[i] == 1:
        #金叉
        buy = (money // (100 * p))
        hold += buy*100
        money -= buy*100*p
    else:
        money += hold * p
        hold = 0

        
p = df['open'][-1]
now_money = hold * p + money

print(now_money - first_money)

 

1086009.8999999994