python数据分析——数据筛选实例【茅台】

import tushare as ts
import pandas as pd
from pandas import DataFrame,Series

DataFrame

- 索引:
    - df[col] df[[c1,c2]]:取列
    - df.loc[index] : 取行
    - df.loc[index,col] : 取元素
- 切片:
    - df[a:b]:切行
    - df.loc[:,a:b]:切列
- df运算:Series运算一致
- df级联:拼接

In [8]:

df = pd.read_csv('maotai.csv',index_col='date',parse_dates=['date'])
df.drop(labels='Unnamed: 0',axis=1,inplace=True)
df

Out[8]:

	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 [9]:

#假如我从2010年1月1日开始，每月第一个交易日买入1手股票，每年最后一个交易日卖出所有股票，到今天为止，我的收益如何？
price_last = df['open'][-1]
df = df['2010':'2019'] #剔除首尾无用的数据
#Pandas提供了resample函数用便捷的方式对时间序列进行重采样，根据时间粒度的变大或者变小分为降采样和升采样：
df_monthly = df.resample("M").first()
df_yearly = df.resample("Y").last()[:-1] #去除最后一年
cost_money = 0
hold = 0 #每年持有的股票
for year in range(2010, 2020):
    
    cost_money -= df_monthly.loc[str(year)]['open'].sum()*100
    hold += len(df_monthly[str(year)]['open']) * 100
    if year != 2019:
        cost_money += df_yearly[str(year)]['open'][0] * hold
        hold = 0 #每年持有的股票
cost_money += hold * price_last

print(cost_money)

 

310250.69999999984

In [7]:

Out[7]:

	open	close	high	low	volume	code
date
2010-01-04	109.760	108.446	109.760	108.044	44304.88	600519
2010-01-05	109.116	108.127	109.441	107.846	31513.18	600519
2010-01-06	107.840	106.417	108.165	106.129	39889.03	600519
2010-01-07	106.417	104.477	106.691	103.302	48825.55	600519
2010-01-08	104.655	103.379	104.655	102.167	36702.09	600519
2010-01-11	104.400	102.926	105.230	102.422	24461.03	600519
2010-01-12	103.028	105.708	106.040	102.492	31063.40	600519
2010-01-13	104.649	103.022	105.389	102.741	37924.44	600519
2010-01-14	103.379	107.552	107.974	103.379	46454.64	600519
2010-01-15	107.533	108.401	110.641	107.533	45938.50	600519
2010-01-18	108.484	109.110	109.926	108.420	21461.53	600519
2010-01-19	109.116	108.337	109.441	108.165	17818.91	600519
2010-01-20	108.427	105.881	108.580	105.804	20972.95	600519
2010-01-21	105.842	106.397	107.450	105.613	17257.48	600519
2010-01-22	106.314	104.738	106.755	103.309	25432.94	600519
2010-01-25	104.560	105.957	106.761	103.704	23239.15	600519
2010-01-26	107.380	106.378	108.593	105.038	32889.16	600519
2010-01-27	105.951	104.643	107.068	104.400	19316.57	600519
2010-01-28	104.566	107.974	108.708	104.336	30267.52	600519
2010-01-29	108.452	107.552	108.612	107.004	37172.82	600519
2010-02-01	107.769	107.776	108.216	106.576	29655.94	600519
2010-02-02	107.208	106.263	108.484	106.117	15493.53	600519
2010-02-03	106.066	105.887	107.272	104.783	23034.65	600519
2010-02-04	105.868	107.591	108.006	105.376	22475.33	600519
2010-02-05	106.959	109.282	109.684	106.570	26234.30	600519
2010-02-08	109.282	109.269	112.058	108.816	31496.10	600519
2010-02-09	109.760	109.193	110.609	108.822	14151.24	600519
2010-02-10	109.760	109.652	110.137	108.931	6398.14	600519
2010-02-11	109.633	110.641	111.318	109.505	14945.05	600519
2010-02-12	111.018	110.456	111.164	109.888	9346.40	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

2221 rows × 6 columns

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

 

使用tushare包获取某股票的历史行情数据

In [14]:

df = ts.get_k_data("600519",start="1988-01-01")
df.to_csv("600519.csv")
df

Out[14]:

	date	open	close	high	low	volume	code
0	2001-08-27	5.392	5.554	5.902	5.132	406318.00	600519
1	2001-08-28	5.467	5.759	5.781	5.407	129647.79	600519
2	2001-08-29	5.777	5.684	5.781	5.640	53252.75	600519
3	2001-08-30	5.668	5.796	5.860	5.624	48013.06	600519
4	2001-08-31	5.804	5.782	5.877	5.749	23231.48	600519
5	2001-09-03	5.812	5.779	5.870	5.757	22112.09	600519
6	2001-09-04	5.782	5.852	5.949	5.762	37006.77	600519
7	2001-09-05	5.876	5.849	5.924	5.813	26066.95	600519
8	2001-09-06	5.835	5.734	5.854	5.704	28997.03	600519
9	2001-09-07	5.702	5.574	5.773	5.570	31552.25	600519
10	2001-09-10	5.531	5.734	5.757	5.470	18878.89	600519
11	2001-09-11	5.749	5.670	5.773	5.656	11390.81	600519
12	2001-09-12	5.520	5.621	5.656	5.515	25045.19	600519
13	2001-09-13	5.626	5.607	5.671	5.577	10986.68	600519
14	2001-09-14	5.626	5.671	5.702	5.593	7672.83	600519
15	2001-09-17	5.637	5.599	5.670	5.546	8983.97	600519
16	2001-09-18	5.606	5.663	5.710	5.601	10773.26	600519
17	2001-09-19	5.671	5.768	5.768	5.634	8650.53	600519
18	2001-09-20	5.765	5.720	5.788	5.702	11173.35	600519
19	2001-09-21	5.668	5.634	5.718	5.624	7879.72	600519
20	2001-09-24	5.634	5.632	5.685	5.624	4068.60	600519
21	2001-09-25	5.668	5.660	5.709	5.632	3488.45	600519
22	2001-09-26	5.642	5.637	5.699	5.624	4956.26	600519
23	2001-09-27	5.637	5.734	5.777	5.624	8778.04	600519
24	2001-09-28	5.765	5.795	5.812	5.702	17088.47	600519
25	2001-10-08	5.781	5.715	5.809	5.663	6552.17	600519
26	2001-10-09	5.718	5.827	5.859	5.718	9558.52	600519
27	2001-10-10	5.827	5.640	5.848	5.629	17548.69	600519
28	2001-10-11	5.626	5.585	5.702	5.570	12306.84	600519
29	2001-10-12	5.609	5.624	5.726	5.320	20010.70	600519
...	...	...	...	...	...	...	...
4118	2018-12-07	595.600	587.000	598.860	584.700	26841.00	600519
4119	2018-12-10	576.000	577.230	587.500	574.180	24640.00	600519
4120	2018-12-11	577.000	582.990	586.550	577.000	16316.00	600519
4121	2018-12-12	588.790	589.000	589.200	582.800	19921.00	600519
4122	2018-12-13	590.000	601.750	606.880	589.600	40399.00	600519
4123	2018-12-14	598.010	592.960	599.800	592.000	24554.00	600519
4124	2018-12-17	592.570	590.520	595.970	585.010	24895.00	600519
4125	2018-12-18	585.880	590.940	591.540	585.000	19222.00	600519
4126	2018-12-19	589.000	577.800	590.990	576.030	25715.00	600519
4127	2018-12-20	576.220	574.500	581.500	568.890	26940.00	600519
4128	2018-12-21	571.000	567.410	573.450	562.210	30640.00	600519
4129	2018-12-24	563.500	568.000	570.910	558.000	19109.00	600519
4130	2018-12-25	562.220	565.790	567.500	553.610	26592.00	600519
4131	2018-12-26	563.810	560.080	568.400	558.000	17866.00	600519
4132	2018-12-27	570.000	563.000	571.850	562.220	29493.00	600519
4133	2018-12-28	563.300	590.010	596.400	560.000	63678.00	600519
4134	2019-01-02	609.980	598.980	612.000	595.010	62286.00	600519
4135	2019-01-03	599.970	590.000	601.660	585.800	30977.00	600519
4136	2019-01-04	587.280	602.000	607.670	582.020	37683.00	600519
4137	2019-01-07	608.000	605.490	612.000	602.220	34750.00	600519
4138	2019-01-08	605.500	604.790	612.000	600.280	28838.00	600519
4139	2019-01-09	609.990	616.120	626.160	609.040	49892.00	600519
4140	2019-01-10	617.130	618.770	624.880	610.250	29043.00	600519
4141	2019-01-11	625.000	635.880	637.000	618.750	38884.00	600519
4142	2019-01-14	633.000	624.600	635.890	621.550	25648.00	600519
4143	2019-01-15	627.860	659.980	661.500	625.000	55764.00	600519
4144	2019-01-16	658.000	661.100	665.650	653.600	42083.00	600519
4145	2019-01-17	663.000	659.250	669.700	655.800	30284.00	600519
4146	2019-01-18	665.000	683.610	690.200	661.500	68609.00	600519
4147	2019-01-21	690.000	686.980	698.880	681.880	47051.00	600519

4148 rows × 7 columns

In [15]:

df.head()

Out[15]:

	date	open	close	high	low	volume	code
0	2001-08-27	5.392	5.554	5.902	5.132	406318.00	600519
1	2001-08-28	5.467	5.759	5.781	5.407	129647.79	600519
2	2001-08-29	5.777	5.684	5.781	5.640	53252.75	600519
3	2001-08-30	5.668	5.796	5.860	5.624	48013.06	600519
4	2001-08-31	5.804	5.782	5.877	5.749	23231.48	600519

In [20]:

df = pd.read_csv("600519.csv", index_col='date',parse_dates=['date'])[['open','close','high','low']]
df.head()

Out[20]:

	open	close	high	low
date
2001-08-27	5.392	5.554	5.902	5.132
2001-08-28	5.467	5.759	5.781	5.407
2001-08-29	5.777	5.684	5.781	5.640
2001-08-30	5.668	5.796	5.860	5.624
2001-08-31	5.804	5.782	5.877	5.749

 

输出该股票所有收盘比开盘上涨3%以上的日期

In [19]:

df[(df['close']-df['open'])/df['open']>=0.03].index

Out[19]:

DatetimeIndex(['2001-08-27', '2001-08-28', '2001-09-10', '2001-12-21',
               '2002-01-18', '2002-01-31', '2003-01-14', '2003-10-29',
               '2004-01-05', '2004-01-14',
               ...
               '2018-06-20', '2018-08-09', '2018-08-21', '2018-08-27',
               '2018-09-18', '2018-09-26', '2018-10-19', '2018-10-31',
               '2018-11-13', '2018-12-28'],
              dtype='datetime64[ns]', name='date', length=291, freq=None)

 

输出该股票所有开盘比前日收盘跌幅超过2%的日期

In [20]:

df[(df['open']-df['close'].shift(1))/df['close'].shift(1)<=-0.02].index

Out[20]:

DatetimeIndex(['2001-09-12', '2002-06-26', '2002-12-13', '2004-07-01',
               '2004-10-29', '2006-08-21', '2006-08-23', '2007-01-25',
               '2007-02-01', '2007-02-06', '2007-03-19', '2007-05-21',
               '2007-05-30', '2007-06-05', '2007-07-27', '2007-09-05',
               '2007-09-10', '2008-03-13', '2008-03-17', '2008-03-25',
               '2008-03-27', '2008-04-22', '2008-04-23', '2008-04-29',
               '2008-05-13', '2008-06-10', '2008-06-13', '2008-06-24',
               '2008-06-27', '2008-08-11', '2008-08-19', '2008-09-23',
               '2008-10-10', '2008-10-15', '2008-10-16', '2008-10-20',
               '2008-10-23', '2008-10-27', '2008-11-06', '2008-11-12',
               '2008-11-20', '2008-11-21', '2008-12-02', '2009-02-27',
               '2009-03-25', '2009-08-13', '2010-04-26', '2010-04-30',
               '2011-08-05', '2012-03-27', '2012-08-10', '2012-11-22',
               '2012-12-04', '2012-12-24', '2013-01-16', '2013-01-25',
               '2013-09-02', '2014-04-25', '2015-01-19', '2015-05-25',
               '2015-07-03', '2015-07-08', '2015-07-13', '2015-08-24',
               '2015-09-02', '2015-09-15', '2017-11-17', '2018-02-06',
               '2018-02-09', '2018-03-23', '2018-03-28', '2018-07-11',
               '2018-10-11', '2018-10-24', '2018-10-25', '2018-10-29',
               '2018-10-30'],
              dtype='datetime64[ns]', name='date', freq=None)

 

假如我从2010年1月1日开始，每月第一个交易日买入1手股票，每年最后一个交易日卖出所有股票，到今天为止，我的收益如何？

In [21]:

df['open'][-1]

Out[21]:

690.0

In [22]:

price_last = df['open'][-1]
df = df['2010-01':'2019-01'] #剔除首尾无用的数据
df

Out[22]:

	open	close	high	low
date
2010-01-04	109.760	108.446	109.760	108.044
2010-01-05	109.116	108.127	109.441	107.846
2010-01-06	107.840	106.417	108.165	106.129
2010-01-07	106.417	104.477	106.691	103.302
2010-01-08	104.655	103.379	104.655	102.167
2010-01-11	104.400	102.926	105.230	102.422
2010-01-12	103.028	105.708	106.040	102.492
2010-01-13	104.649	103.022	105.389	102.741
2010-01-14	103.379	107.552	107.974	103.379
2010-01-15	107.533	108.401	110.641	107.533
2010-01-18	108.484	109.110	109.926	108.420
2010-01-19	109.116	108.337	109.441	108.165
2010-01-20	108.427	105.881	108.580	105.804
2010-01-21	105.842	106.397	107.450	105.613
2010-01-22	106.314	104.738	106.755	103.309
2010-01-25	104.560	105.957	106.761	103.704
2010-01-26	107.380	106.378	108.593	105.038
2010-01-27	105.951	104.643	107.068	104.400
2010-01-28	104.566	107.974	108.708	104.336
2010-01-29	108.452	107.552	108.612	107.004
2010-02-01	107.769	107.776	108.216	106.576
2010-02-02	107.208	106.263	108.484	106.117
2010-02-03	106.066	105.887	107.272	104.783
2010-02-04	105.868	107.591	108.006	105.376
2010-02-05	106.959	109.282	109.684	106.570
2010-02-08	109.282	109.269	112.058	108.816
2010-02-09	109.760	109.193	110.609	108.822
2010-02-10	109.760	109.652	110.137	108.931
2010-02-11	109.633	110.641	111.318	109.505
2010-02-12	111.018	110.456	111.164	109.888
...	...	...	...	...
2018-12-07	595.600	587.000	598.860	584.700
2018-12-10	576.000	577.230	587.500	574.180
2018-12-11	577.000	582.990	586.550	577.000
2018-12-12	588.790	589.000	589.200	582.800
2018-12-13	590.000	601.750	606.880	589.600
2018-12-14	598.010	592.960	599.800	592.000
2018-12-17	592.570	590.520	595.970	585.010
2018-12-18	585.880	590.940	591.540	585.000
2018-12-19	589.000	577.800	590.990	576.030
2018-12-20	576.220	574.500	581.500	568.890
2018-12-21	571.000	567.410	573.450	562.210
2018-12-24	563.500	568.000	570.910	558.000
2018-12-25	562.220	565.790	567.500	553.610
2018-12-26	563.810	560.080	568.400	558.000
2018-12-27	570.000	563.000	571.850	562.220
2018-12-28	563.300	590.010	596.400	560.000
2019-01-02	609.980	598.980	612.000	595.010
2019-01-03	599.970	590.000	601.660	585.800
2019-01-04	587.280	602.000	607.670	582.020
2019-01-07	608.000	605.490	612.000	602.220
2019-01-08	605.500	604.790	612.000	600.280
2019-01-09	609.990	616.120	626.160	609.040
2019-01-10	617.130	618.770	624.880	610.250
2019-01-11	625.000	635.880	637.000	618.750
2019-01-14	633.000	624.600	635.890	621.550
2019-01-15	627.860	659.980	661.500	625.000
2019-01-16	658.000	661.100	665.650	653.600
2019-01-17	663.000	659.250	669.700	655.800
2019-01-18	665.000	683.610	690.200	661.500
2019-01-21	690.000	686.980	698.880	681.880

2195 rows × 4 columns

In [28]:

df_monthly = df.resample("M").first()
df_monthly.head()

Out[28]:

	open	close	high	low
date
2010-01-31	109.760	108.446	109.760	108.044
2010-02-28	107.769	107.776	108.216	106.576
2010-03-31	106.219	106.085	106.857	105.925
2010-04-30	101.324	102.141	102.422	101.311
2010-05-31	81.676	82.091	82.678	80.974

In [29]:

df_yearly = df.resample("A").last()[:-1] #去除最后一年
df_yearly

Out[29]:

	open	close	high	low
date
2010-12-31	117.103	118.469	118.701	116.620
2011-12-31	138.039	138.468	139.600	136.105
2012-12-31	155.208	152.087	156.292	150.144
2013-12-31	93.188	96.480	97.179	92.061
2014-12-31	157.642	161.056	161.379	157.132
2015-12-31	207.487	207.458	208.704	207.106
2016-12-31	317.239	324.563	325.670	317.239
2017-12-31	707.948	687.725	716.329	681.918
2018-12-31	563.300	590.010	596.400	560.000

In [31]:

df_monthly.loc[str(year)]

Out[31]:

	open	close	high	low
date
2018-01-31	690.200	693.996	700.218	680.232
2018-02-28	756.262	747.122	756.558	742.379
2018-03-31	717.808	731.582	736.394	713.637
2018-04-30	670.480	670.539	681.326	664.673
2018-05-31	650.760	658.480	659.624	636.029
2018-06-30	740.614	734.679	744.410	728.417
2018-07-31	734.520	711.550	739.330	703.000
2018-08-31	731.400	714.940	732.300	714.110
2018-09-30	652.000	666.210	667.670	650.800
2018-10-31	715.410	686.150	719.000	686.150
2018-11-30	555.000	563.000	585.500	551.250
2018-12-31	589.000	601.200	605.000	584.770

In [33]:

cost_money = 0
hold = 0 #每年持有的股票
for year in range(2010, 2020):
    
    cost_money -= df_monthly.loc[str(year)]['open'].sum()*100
    hold += len(df_monthly[str(year)]['open']) * 100
    if year != 2019:
        cost_money += df_yearly[str(year)]['open'][0] * hold
        hold = 0 #每年持有的股票
    #print(cost_money)

cost_money += hold * price_last

print(cost_money)
        
# df_monthly['2001']

 

289604.69999999984

In [56]:

df['2017']

Out[56]:

	open	close	high	low
date
2017-01-03	329.299	329.575	331.979	327.851
2017-01-04	329.634	346.667	346.923	329.615
2017-01-05	344.785	341.574	346.213	340.293
2017-01-06	341.475	345.534	354.419	340.943
2017-01-09	342.618	343.317	347.622	341.377
2017-01-10	343.258	343.800	346.755	341.436
2017-01-11	342.815	340.303	342.815	338.382
2017-01-12	341.386	341.879	342.224	339.377
2017-01-13	341.810	339.731	342.214	338.756
2017-01-16	339.003	336.382	339.663	333.752
2017-01-17	337.495	343.928	346.263	336.904
2017-01-18	343.682	349.789	351.454	342.037
2017-01-19	349.711	349.435	353.139	346.460
2017-01-20	349.612	349.701	352.075	347.770
2017-01-23	351.563	345.987	354.439	344.253
2017-01-24	346.036	345.090	347.543	341.583
2017-01-25	344.765	342.450	344.765	341.042
2017-01-26	342.953	339.288	343.603	336.215
2017-02-03	340.845	341.682	343.977	339.860
2017-02-06	343.298	341.682	343.692	339.820
2017-02-07	341.672	338.461	342.224	338.027
2017-02-08	338.638	339.081	340.352	337.564
2017-02-09	339.860	342.431	343.593	339.475
2017-02-10	343.426	339.938	344.608	339.860
2017-02-13	338.874	344.539	346.657	336.825
2017-02-14	344.332	344.992	347.346	343.898
2017-02-15	346.263	343.337	347.189	342.027
2017-02-16	343.307	342.904	343.426	340.362
2017-02-17	343.701	345.337	349.159	342.322
2017-02-20	345.189	355.907	356.921	344.795
...	...	...	...	...
2017-10-20	581.000	574.330	581.000	571.760
2017-10-23	574.920	573.410	580.500	568.000
2017-10-24	572.000	567.330	573.800	563.610
2017-10-25	569.750	565.670	571.680	562.060
2017-10-26	605.000	605.090	613.000	591.910
2017-10-27	602.110	649.630	655.000	600.030
2017-10-30	643.050	622.080	644.000	621.000
2017-10-31	622.010	618.030	627.600	611.880
2017-11-01	620.880	623.010	631.540	619.220
2017-11-02	626.950	626.920	629.780	621.000
2017-11-03	628.650	639.170	643.440	628.650
2017-11-06	641.500	653.060	657.620	640.200
2017-11-07	650.580	642.070	657.150	638.180
2017-11-08	642.330	650.380	654.500	642.330
2017-11-09	648.000	650.070	654.150	644.610
2017-11-10	650.430	677.950	683.400	650.430
2017-11-13	680.000	687.880	692.780	675.800
2017-11-14	687.140	678.750	687.220	677.350
2017-11-15	678.750	688.080	689.990	674.000
2017-11-16	686.010	719.110	719.960	686.010
2017-11-17	696.000	690.250	709.000	677.770
2017-11-20	676.800	679.150	685.600	660.000
2017-11-21	669.000	677.250	688.800	662.020
2017-11-22	677.000	650.520	688.000	650.000
2017-11-23	642.000	633.730	646.000	630.220
2017-11-24	635.900	630.040	642.500	622.230
2017-11-27	634.000	621.290	636.330	613.010
2017-11-28	625.060	648.230	648.880	624.000
2017-11-29	649.940	638.120	651.970	634.010
2017-11-30	635.510	631.000	648.480	626.000

223 rows × 4 columns