其他分享
首页 > 其他分享> > 3 Pandas实战-股票分析

3 Pandas实战-股票分析

作者:互联网

需求:股票分析

import tushare as ts
import pandas as pd
from pandas import DataFrame,Series
import numpy as np
#获取某只股票的历史行情数据
#code:字符串形式的股票代码
df = ts.get_k_data(code='600519',start='2000-01-01')
df
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
... ... ... ... ... ... ... ...
4376 2019-12-30 1170.200 1185.800 1195.500 1170.200 40760.00 600519
4377 2019-12-31 1183.000 1183.000 1188.000 1176.510 22588.00 600519
4378 2020-01-02 1128.000 1130.000 1145.060 1116.000 148099.00 600519
4379 2020-01-03 1117.000 1078.560 1117.000 1076.900 130318.00 600519
4380 2020-01-06 1070.860 1077.990 1092.900 1067.300 63414.00 600519
4381 2020-01-07 1077.500 1094.530 1099.000 1076.400 47853.00 600519
4382 2020-01-08 1085.050 1088.140 1095.500 1082.580 25008.00 600519
4383 2020-01-09 1094.000 1102.700 1105.390 1090.000 37405.00 600519
4384 2020-01-10 1109.000 1112.500 1115.990 1102.500 35975.00 600519
4385 2020-01-13 1112.500 1124.270 1129.200 1112.000 38515.00 600519
4386 2020-01-14 1124.200 1107.400 1124.890 1103.000 35144.00 600519
4387 2020-01-15 1109.010 1112.130 1121.600 1105.000 26029.00 600519
4388 2020-01-16 1118.870 1107.000 1118.870 1102.580 23191.00 600519
4389 2020-01-17 1110.000 1107.500 1112.780 1101.010 23472.00 600519
4390 2020-01-20 1111.860 1091.000 1111.860 1082.000 35391.00 600519
4391 2020-01-21 1081.000 1075.300 1087.000 1072.300 32874.00 600519
4392 2020-01-22 1070.000 1075.510 1084.000 1055.380 36200.00 600519
4393 2020-01-23 1076.000 1052.800 1076.000 1037.000 53468.00 600519
4394 2020-02-03 985.000 1003.920 1010.680 980.000 123442.00 600519
4395 2020-02-04 1015.000 1038.010 1057.000 1011.010 62624.00 600519
4396 2020-02-05 1050.000 1049.990 1054.000 1033.030 47418.00 600519
4397 2020-02-06 1059.430 1071.000 1075.000 1052.020 47171.00 600519
4398 2020-02-07 1070.010 1076.000 1077.000 1061.020 31278.00 600519
4399 2020-02-10 1062.000 1066.490 1074.600 1057.200 30533.00 600519
4400 2020-02-11 1063.000 1098.000 1099.680 1062.800 47917.00 600519
4401 2020-02-12 1089.000 1097.270 1098.790 1085.880 28125.00 600519
4402 2020-02-13 1098.000 1091.000 1113.890 1088.010 30357.00 600519
4403 2020-02-14 1090.450 1088.000 1093.510 1083.110 23287.00 600519
4404 2020-02-17 1082.500 1093.820 1096.190 1082.400 27028.00 600519
4405 2020-02-18 1090.010 1084.000 1096.880 1083.000 26664.00 600519

4406 rows × 7 columns

#将互联网上获取的股票数据存储到本地
df.to_csv('./maotai.csv')#调用to_xxx方法将df中的数据写入到本地进行存储
#将本地存储的数据读入到df
df = pd.read_csv('./maotai.csv')
df.head()
Unnamed: 0 date open close high low volume code
0 0 2001-08-27 5.392 5.554 5.902 5.132 406318.00 600519
1 1 2001-08-28 5.467 5.759 5.781 5.407 129647.79 600519
2 2 2001-08-29 5.777 5.684 5.781 5.640 53252.75 600519
3 3 2001-08-30 5.668 5.796 5.860 5.624 48013.06 600519
4 4 2001-08-31 5.804 5.782 5.877 5.749 23231.48 600519
#需要对读取出来的数据进行相关的处理
#删除df中指定的一列
df.drop(labels='Unnamed: 0',axis=1,inplace=True)
#查看每一列的数据类型
df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 4406 entries, 0 to 4405
Data columns (total 7 columns):
date      4406 non-null object
open      4406 non-null float64
close     4406 non-null float64
high      4406 non-null float64
low       4406 non-null float64
volume    4406 non-null float64
code      4406 non-null int64
dtypes: float64(5), int64(1), object(1)
memory usage: 241.0+ KB
#将date列转为时间序列类型
df['date'] = pd.to_datetime(df['date'])
df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 4406 entries, 0 to 4405
Data columns (total 7 columns):
date      4406 non-null datetime64[ns]
open      4406 non-null float64
close     4406 non-null float64
high      4406 non-null float64
low       4406 non-null float64
volume    4406 non-null float64
code      4406 non-null int64
dtypes: datetime64[ns](1), float64(5), int64(1)
memory usage: 241.0 KB
#将date列作为源数据的行索引
df.set_index('date',inplace=True)
df.head()
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
#输出该股票所有收盘比开盘上涨3%以上的日期
#伪代码:(收盘-开盘)/开盘 > 0.03
(df['open'] - df['close']) / df['open'] > 0.03

#在分析的过程中如果产生了boolean值则下一步马上将布尔值作为源数据的行索引
 #如果布尔值作为df的行索引,则可以取出true对应的行数据,忽略false对应的行数据
df.loc[(df['open'] - df['close']) / df['open'] > 0.03] #获取了True对应的行数据(满足需求的行数据)

df.loc[(df['open'] - df['close']) / df['open'] > 0.03].index #df的行数据
DatetimeIndex(['2001-10-10', '2001-11-07', '2001-11-16', '2001-12-20',
               '2002-01-04', '2002-01-17', '2002-01-28', '2002-04-17',
               '2002-11-08', '2003-01-02',
               ...
               '2018-06-27', '2018-07-02', '2018-08-17', '2018-10-08',
               '2018-10-10', '2018-10-23', '2019-07-03', '2019-09-11',
               '2019-11-29', '2020-01-03'],
              dtype='datetime64[ns]', name='date', length=165, freq=None)
#输出该股票所有开盘比前日收盘跌幅超过2%的日期
#伪代码:(开盘-前日收盘)/前日收盘 < -0.02
(df['open'] - df['close'].shift(1))/df['close'].shift(1) < -0.02
#将布尔值作为源数据的行索引取出True对应的行数据
df.loc[(df['open'] - df['close'].shift(1))/df['close'].shift(1) < -0.02]

df.loc[(df['open'] - df['close'].shift(1))/df['close'].shift(1) < -0.02].index
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', '2019-05-06', '2019-05-08', '2019-10-16',
               '2020-01-02', '2020-02-03'],
              dtype='datetime64[ns]', name='date', freq=None)
new_df = df['2010-01':'2020-02']
new_df
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
... ... ... ... ... ... ...
2019-12-30 1170.200 1185.800 1195.500 1170.200 40760.00 600519
2019-12-31 1183.000 1183.000 1188.000 1176.510 22588.00 600519
2020-01-02 1128.000 1130.000 1145.060 1116.000 148099.00 600519
2020-01-03 1117.000 1078.560 1117.000 1076.900 130318.00 600519
2020-01-06 1070.860 1077.990 1092.900 1067.300 63414.00 600519
2020-01-07 1077.500 1094.530 1099.000 1076.400 47853.00 600519
2020-01-08 1085.050 1088.140 1095.500 1082.580 25008.00 600519
2020-01-09 1094.000 1102.700 1105.390 1090.000 37405.00 600519
2020-01-10 1109.000 1112.500 1115.990 1102.500 35975.00 600519
2020-01-13 1112.500 1124.270 1129.200 1112.000 38515.00 600519
2020-01-14 1124.200 1107.400 1124.890 1103.000 35144.00 600519
2020-01-15 1109.010 1112.130 1121.600 1105.000 26029.00 600519
2020-01-16 1118.870 1107.000 1118.870 1102.580 23191.00 600519
2020-01-17 1110.000 1107.500 1112.780 1101.010 23472.00 600519
2020-01-20 1111.860 1091.000 1111.860 1082.000 35391.00 600519
2020-01-21 1081.000 1075.300 1087.000 1072.300 32874.00 600519
2020-01-22 1070.000 1075.510 1084.000 1055.380 36200.00 600519
2020-01-23 1076.000 1052.800 1076.000 1037.000 53468.00 600519
2020-02-03 985.000 1003.920 1010.680 980.000 123442.00 600519
2020-02-04 1015.000 1038.010 1057.000 1011.010 62624.00 600519
2020-02-05 1050.000 1049.990 1054.000 1033.030 47418.00 600519
2020-02-06 1059.430 1071.000 1075.000 1052.020 47171.00 600519
2020-02-07 1070.010 1076.000 1077.000 1061.020 31278.00 600519
2020-02-10 1062.000 1066.490 1074.600 1057.200 30533.00 600519
2020-02-11 1063.000 1098.000 1099.680 1062.800 47917.00 600519
2020-02-12 1089.000 1097.270 1098.790 1085.880 28125.00 600519
2020-02-13 1098.000 1091.000 1113.890 1088.010 30357.00 600519
2020-02-14 1090.450 1088.000 1093.510 1083.110 23287.00 600519
2020-02-17 1082.500 1093.820 1096.190 1082.400 27028.00 600519
2020-02-18 1090.010 1084.000 1096.880 1083.000 26664.00 600519

2453 rows × 6 columns

new_df.head(2)
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
#买股票:找每个月的第一个交易日对应的行数据(捕获到开盘价)==》每月的第一行数据
#根据月份从原始数据中提取指定的数据
#每月第一个交易日对应的行数据
df_monthly = new_df.resample('M').first()#数据的重新取样
df_monthly
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
... ... ... ... ... ... ...
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
2019-04-30 860.000 859.000 868.950 851.000 60934.00 600519
2019-05-31 925.500 906.000 935.000 893.000 135099.00 600519
2019-06-30 892.000 892.000 901.350 886.280 34479.00 600519
2019-07-31 1004.520 1031.860 1035.600 1000.220 52337.00 600519
2019-08-31 976.510 959.300 977.000 953.020 35089.00 600519
2019-09-30 1139.990 1138.760 1144.980 1129.000 28234.00 600519
2019-10-31 1153.000 1167.100 1180.000 1152.010 31045.00 600519
2019-11-30 1181.000 1185.000 1191.950 1172.500 22811.00 600519
2019-12-31 1118.200 1133.000 1140.020 1118.200 30784.00 600519
2020-01-31 1128.000 1130.000 1145.060 1116.000 148099.00 600519
2020-02-29 985.000 1003.920 1010.680 980.000 123442.00 600519

122 rows × 6 columns

#买入股票花费的总金额
cost = df_monthly['open'].sum()*100
cost
4010206.1
#卖出股票到手的钱
#特殊情况:2020年买入的股票卖不出去
new_df.resample('A').last()
#将2020年最后一行切出去
df_yearly = new_df.resample('A').last()[:-1]
df_yearly
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 1183.000 1183.000 1188.000 1176.510 22588.0 600519
#卖出股票到手的钱
resv = df_yearly['open'].sum()*1200
resv
4368184.8
#最后手中剩余的股票需要估量其价值计算到总收益中
#使用昨天的收盘价作为剩余股票的单价
last_monry = 200*new_df['close'][-1]
#计算总收益
resv+last_monry-cost
574778.6999999997

需求:双均线策略制定

df = pd.read_csv('./maotai.csv').drop(labels='Unnamed: 0',axis=1)
df
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
... ... ... ... ... ... ... ...
4376 2019-12-30 1170.200 1185.800 1195.500 1170.200 40760.00 600519
4377 2019-12-31 1183.000 1183.000 1188.000 1176.510 22588.00 600519
4378 2020-01-02 1128.000 1130.000 1145.060 1116.000 148099.00 600519
4379 2020-01-03 1117.000 1078.560 1117.000 1076.900 130318.00 600519
4380 2020-01-06 1070.860 1077.990 1092.900 1067.300 63414.00 600519
4381 2020-01-07 1077.500 1094.530 1099.000 1076.400 47853.00 600519
4382 2020-01-08 1085.050 1088.140 1095.500 1082.580 25008.00 600519
4383 2020-01-09 1094.000 1102.700 1105.390 1090.000 37405.00 600519
4384 2020-01-10 1109.000 1112.500 1115.990 1102.500 35975.00 600519
4385 2020-01-13 1112.500 1124.270 1129.200 1112.000 38515.00 600519
4386 2020-01-14 1124.200 1107.400 1124.890 1103.000 35144.00 600519
4387 2020-01-15 1109.010 1112.130 1121.600 1105.000 26029.00 600519
4388 2020-01-16 1118.870 1107.000 1118.870 1102.580 23191.00 600519
4389 2020-01-17 1110.000 1107.500 1112.780 1101.010 23472.00 600519
4390 2020-01-20 1111.860 1091.000 1111.860 1082.000 35391.00 600519
4391 2020-01-21 1081.000 1075.300 1087.000 1072.300 32874.00 600519
4392 2020-01-22 1070.000 1075.510 1084.000 1055.380 36200.00 600519
4393 2020-01-23 1076.000 1052.800 1076.000 1037.000 53468.00 600519
4394 2020-02-03 985.000 1003.920 1010.680 980.000 123442.00 600519
4395 2020-02-04 1015.000 1038.010 1057.000 1011.010 62624.00 600519
4396 2020-02-05 1050.000 1049.990 1054.000 1033.030 47418.00 600519
4397 2020-02-06 1059.430 1071.000 1075.000 1052.020 47171.00 600519
4398 2020-02-07 1070.010 1076.000 1077.000 1061.020 31278.00 600519
4399 2020-02-10 1062.000 1066.490 1074.600 1057.200 30533.00 600519
4400 2020-02-11 1063.000 1098.000 1099.680 1062.800 47917.00 600519
4401 2020-02-12 1089.000 1097.270 1098.790 1085.880 28125.00 600519
4402 2020-02-13 1098.000 1091.000 1113.890 1088.010 30357.00 600519
4403 2020-02-14 1090.450 1088.000 1093.510 1083.110 23287.00 600519
4404 2020-02-17 1082.500 1093.820 1096.190 1082.400 27028.00 600519
4405 2020-02-18 1090.010 1084.000 1096.880 1083.000 26664.00 600519

4406 rows × 7 columns

#将date列转为时间序列且将其作为源数据的行索引
df['date'] = pd.to_datetime(df['date'])
df.set_index('date',inplace=True)
df.head()
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
ma5 = df['close'].rolling(5).mean()
ma30 = df['close'].rolling(30).mean()
ma5
date
2001-08-27          NaN
2001-08-28          NaN
2001-08-29          NaN
2001-08-30          NaN
2001-08-31       5.7150
2001-09-03       5.7600
2001-09-04       5.7786
2001-09-05       5.8116
2001-09-06       5.7992
2001-09-07       5.7576
2001-09-10       5.7486
2001-09-11       5.7122
2001-09-12       5.6666
2001-09-13       5.6412
2001-09-14       5.6606
2001-09-17       5.6336
2001-09-18       5.6322
2001-09-19       5.6616
2001-09-20       5.6842
2001-09-21       5.6768
2001-09-24       5.6834
2001-09-25       5.6828
2001-09-26       5.6566
2001-09-27       5.6594
2001-09-28       5.6916
2001-10-08       5.7082
2001-10-09       5.7416
2001-10-10       5.7422
2001-10-11       5.7124
2001-10-12       5.6782
                ...    
2019-12-30    1153.1200
2019-12-31    1160.1200
2020-01-02    1159.3800
2020-01-03    1148.0720
2020-01-06    1131.0700
2020-01-07    1112.8160
2020-01-08    1093.8440
2020-01-09    1088.3840
2020-01-10    1095.1720
2020-01-13    1104.4280
2020-01-14    1107.0020
2020-01-15    1111.8000
2020-01-16    1112.6600
2020-01-17    1111.6600
2020-01-20    1105.0060
2020-01-21    1098.5860
2020-01-22    1091.2620
2020-01-23    1080.4220
2020-02-03    1059.7060
2020-02-04    1049.1080
2020-02-05    1044.0460
2020-02-06    1043.1440
2020-02-07    1047.7840
2020-02-10    1060.2980
2020-02-11    1072.2960
2020-02-12    1081.7520
2020-02-13    1085.7520
2020-02-14    1088.1520
2020-02-17    1093.6180
2020-02-18    1090.8180
Name: close, Length: 4406, dtype: float64
import matplotlib.pyplot as plt
%matplotlib inline
plt.plot(ma5[50:180])
plt.plot(ma30[50:180])
[<matplotlib.lines.Line2D at 0x125d96588>]

png

ma5 = ma5[30:]
ma30 = ma30[30:]
s1 = ma5 < ma30
s2 = ma5 > ma30
df = df[30:]
death_ex = s1 & s2.shift(1) #判定死叉的条件
df.loc[death_ex] #死叉对应的行数据
death_date = df.loc[death_ex].index
golden_ex = ~(s1 | s2.shift(1))#判定金叉的条件
golden_date = df.loc[golden_ex].index #金叉的时间

image.png

s1 = Series(data=1,index=golden_date) #1作为金叉的标识
s2 = Series(data=0,index=death_date) #0作为死叉的标识

s = s1.append(s2)
s = s.sort_index() #存储的是金叉和死叉对应的时间
s = s['2010':'2020']##存储的是金叉和死叉对应的时间
first_monry = 100000 #本金,不变
money = first_monry #可变的,买股票话的钱和卖股票收入的钱都从该变量中进行操作
hold = 0 #持有股票的数量(股数:100股=1手)

for i in range(0,len(s)): #i表示的s这个Series中的隐式索引
    #i = 0(死叉:卖) = 1(金叉:买)
    if s[i] == 1:#金叉的时间
        #基于100000的本金尽可能多的去买入股票
        #获取股票的单价(金叉时间对应的行数据中的开盘价)
        time = s.index[i] #金叉的时间
        p = df.loc[time]['open'] #股票的单价
        hand_count = money // (p*100) #使用100000最多买入多少手股票
        hold = hand_count * 100 
        
        money -= (hold * p) #将买股票话的钱从money中减去
    else:
        #将买入的股票卖出去
        
        #找出卖出股票的单价
        death_time = s.index[i]
        p_death = df.loc[death_time]['open'] #卖股票的单价
        money += (p_death * hold) #卖出的股票收入加入到money
        hold = 0

#如何判定最后一天为金叉还是死叉
last_monry = hold * df['close'][-1] #剩余股票的价值

#总收益
money + last_monry - first_monry
1501254.9999999995

标签:实战,分析,01,02,600519,2020,09,Pandas,2001
来源: https://www.cnblogs.com/huahuawang/p/14888953.html