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 

In [3]:

df = ts.get_k_data('600519',start='1999-01-01') 

In [5]:

#将df存储到本地
df.to_csv('./maotai.csv') 

In [9]:

#将date这列数据类型转成事件序列,然后将改列作为原数据的行索引
df = pd.read_csv('./maotai.csv',index_col='date',parse_dates=['date']) df.drop(labels='Unnamed: 0',axis=1,inplace=True) df.head(5) 

Out[9]:

	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

In [26]:

#输出该股票所有收盘比开盘上涨3%以上的日期。
s = (df['close'] - df['open'])/df['open'] > 0.03 df.loc[s].index 

Out[26]:

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',
               ...
               '2018-08-27', '2018-09-18', '2018-09-26', '2018-10-19',
               '2018-10-31', '2018-11-13', '2018-12-28', '2019-01-15',
               '2019-02-11', '2019-03-01'],
              dtype='datetime64[ns]', name='date', length=294, freq=None)

In [20]:

#输出该股票所有开盘比前日收盘跌幅超过2%的日期。
s1 = (df['open'] - df['close'].shift(1))/df['close'].shift(1) < -0.02 s1 

Out[20]:

date
2001-08-27    False
2001-08-28    False
2001-08-29    False
2001-08-30    False
2001-08-31    False
2001-09-03    False
2001-09-04    False
2001-09-05    False
2001-09-06    False
2001-09-07    False
2001-09-10    False
2001-09-11    False
2001-09-12     True
2001-09-13    False
2001-09-14    False
2001-09-17    False
2001-09-18    False
2001-09-19    False
2001-09-20    False
2001-09-21    False
2001-09-24    False
2001-09-25    False
2001-09-26    False
2001-09-27    False
2001-09-28    False
2001-10-08    False
2001-10-09    False
2001-10-10    False
2001-10-11    False
2001-10-12    False
              ...  
2019-01-16    False
2019-01-17    False
2019-01-18    False
2019-01-21    False
2019-01-22    False
2019-01-23    False
2019-01-24    False
2019-01-25    False
2019-01-28    False
2019-01-29    False
2019-01-30    False
2019-01-31    False
2019-02-01    False
2019-02-11    False
2019-02-12    False
2019-02-13    False
2019-02-14    False
2019-02-15    False
2019-02-18    False
2019-02-19    False
2019-02-20    False
2019-02-21    False
2019-02-22    False
2019-02-25    False
2019-02-26    False
2019-02-27    False
2019-02-28    False
2019-03-01    False
2019-03-04    False
2019-03-05    False
Length: 4174, dtype: bool

In [23]:

df.loc[s1].index 

Out[23]:

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)

In [33]:

#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？
data = df['2010':'2019'] data.head() 

Out[33]:

	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

In [35]:

#对数据进行重新取样
monthes = data.resample('M').first() 

Out[35]:

	open	close	high	low	volume	code
date
2010-01-31	109.760	108.446	109.760	108.044	44304.88	600519
2010-02-28	107.769	107.776	108.216	106.576	29655.94	600519
2010-03-31	106.219	106.085	106.857	105.925	21734.74	600519
2010-04-30	101.324	102.141	102.422	101.311	23980.83	600519
2010-05-31	81.676	82.091	82.678	80.974	23975.16	600519
2010-06-30	84.075	84.637	85.166	83.278	23525.57	600519
2010-07-31	81.586	81.057	81.586	80.725	7449.69	600519
2010-08-31	89.296	92.465	93.567	89.296	42965.73	600519
2010-09-30	102.288	101.052	103.834	100.420	25589.00	600519
2010-10-31	108.858	111.776	113.045	108.858	31608.00	600519
2010-11-30	105.122	105.483	106.217	104.478	49658.00	600519
2010-12-31	130.759	130.372	133.980	128.839	38016.00	600519
2011-01-31	120.388	119.487	121.033	117.619	60462.00	600519
2011-02-28	114.656	116.124	117.136	114.334	17758.00	600519
2011-03-31	115.113	115.068	115.899	114.527	23059.00	600519
2011-04-30	115.931	115.596	116.813	115.010	18227.00	600519
2011-05-31	117.876	119.718	120.324	117.232	41270.00	600519
2011-06-30	131.467	135.197	135.255	130.772	39093.00	600519
2011-07-31	137.895	137.272	137.895	136.033	15810.00	600519
2011-08-31	148.519	145.689	148.519	145.274	18572.00	600519
2011-09-30	153.798	151.491	154.357	150.789	25689.00	600519
2011-10-31	136.735	134.672	137.394	134.407	14283.00	600519
2011-11-30	145.546	148.418	148.640	145.066	27147.00	600519
2011-12-31	152.724	152.466	154.149	150.625	33785.00	600519
2012-01-31	137.179	132.716	138.089	132.523	33878.00	600519
2012-02-29	133.382	133.347	135.044	132.437	24824.00	600519
2012-03-31	145.789	145.116	147.186	144.980	16920.00	600519
2012-04-30	140.474	147.566	147.852	140.474	40960.00	600519
2012-05-31	161.893	161.878	162.301	159.027	35339.00	600519
2012-06-30	170.489	172.187	174.071	169.565	38504.00	600519
...	...	...	...	...	...	...
2016-10-31	289.945	294.268	295.142	289.945	21103.00	600519
2016-11-30	308.828	307.594	309.847	306.496	19512.00	600519
2016-12-31	310.819	311.810	315.277	309.537	27941.00	600519
2017-01-31	324.689	324.961	327.331	323.261	20763.00	600519
2017-02-28	336.073	336.898	339.162	335.102	20936.00	600519
2017-03-31	344.912	346.378	347.923	344.815	21944.00	600519
2017-04-30	374.595	378.480	383.657	373.954	40789.00	600519
2017-05-31	399.791	400.257	403.093	397.440	23291.00	600519
2017-06-30	429.804	436.390	437.040	428.357	40604.00	600519
2017-07-31	460.595	447.161	460.595	444.762	49628.00	600519
2017-08-31	474.266	473.517	476.238	470.716	27501.00	600519
2017-09-30	483.337	488.248	489.332	483.170	31451.00	600519
2017-10-31	517.196	520.381	528.052	512.819	34891.00	600519
2017-11-30	612.188	614.288	622.698	610.551	43435.00	600519
2017-12-31	629.078	613.637	630.044	611.448	47192.00	600519
2018-01-31	690.200	693.996	700.218	680.232	49612.00	600519
2018-02-28	756.262	747.122	756.558	742.379	50582.00	600519
2018-03-31	717.808	731.582	736.394	713.637	44794.00	600519
2018-04-30	670.480	670.539	681.326	664.673	32039.00	600519
2018-05-31	650.760	658.480	659.624	636.029	70259.00	600519
2018-06-30	740.614	734.679	744.410	728.417	36177.00	600519
2018-07-31	734.520	711.550	739.330	703.000	37558.00	600519
2018-08-31	731.400	714.940	732.300	714.110	25237.00	600519
2018-09-30	652.000	666.210	667.670	650.800	30179.00	600519
2018-10-31	715.410	686.150	719.000	686.150	82745.00	600519
2018-11-30	555.000	563.000	585.500	551.250	98106.00	600519
2018-12-31	589.000	601.200	605.000	584.770	83414.00	600519
2019-01-31	609.980	598.980	612.000	595.010	62286.00	600519
2019-02-28	697.040	692.670	699.000	689.610	30520.00	600519
2019-03-31	761.500	789.300	790.000	761.000	63840.00	600519

111 rows × 6 columns

In [36]:

years = data.resample('Y').last() 

Out[36]:

	open	close	high	low	volume	code
date
2010-12-31	117.103	118.469	118.701	116.620	46084.0	600519
2011-12-31	138.039	138.468	139.600	136.105	29460.0	600519
2012-12-31	155.208	152.087	156.292	150.144	51914.0	600519
2013-12-31	93.188	96.480	97.179	92.061	57546.0	600519
2014-12-31	157.642	161.056	161.379	157.132	46269.0	600519
2015-12-31	207.487	207.458	208.704	207.106	19673.0	600519
2016-12-31	317.239	324.563	325.670	317.239	34687.0	600519
2017-12-31	707.948	687.725	716.329	681.918	76038.0	600519
2018-12-31	563.300	590.010	596.400	560.000	63678.0	600519
2019-12-31	785.000	779.780	789.550	775.880	44830.0	600519

转载于:https://www.cnblogs.com/bilx/p/11611899.html