六、股票市场分析实战项目一
数据获取
import pandas_datareader as pdr
alibaba = pdr.get_data_yahoo('BABA')
alibaba.head()
结果：
| Open | High | Low | Close | Adj Close | Volume | |
|---|---|---|---|---|---|---|
| Date | ||||||
| 2014-09-19 | 92.699997 | 99.699997 | 89.949997 | 93.889999 | 93.889999 | 271879400 |
| 2014-09-22 | 92.699997 | 92.949997 | 89.500000 | 89.889999 | 89.889999 | 66657800 |
| 2014-09-23 | 88.940002 | 90.480003 | 86.620003 | 87.169998 | 87.169998 | 39009800 |
| 2014-09-24 | 88.470001 | 90.570000 | 87.220001 | 90.570000 | 90.570000 | 32088000 |
| 2014-09-25 | 91.089996 | 91.500000 | 88.500000 | 88.919998 | 88.919998 | 28598000 |
alibaba.shape#(789, 6) alibaba.tail()
结果：
| Open | High | Low | Close | Adj Close | Volume | |
|---|---|---|---|---|---|---|
| Date | ||||||
| 2017-10-30 | 178.429993 | 181.899994 | 177.589996 | 181.580002 | 181.580002 | 20219700 |
| 2017-10-31 | 183.570007 | 185.119995 | 181.811005 | 184.889999 | 184.889999 | 21256700 |
| 2017-11-01 | 187.880005 | 188.880005 | 183.580002 | 186.080002 | 186.080002 | 28594700 |
| 2017-11-02 | 190.990005 | 191.220001 | 183.309998 | 184.809998 | 184.809998 | 41239900 |
| 2017-11-03 | 186.509995 | 186.929993 | 182.059998 | 183.210007 | 183.210007 | 19621400 |
alibaba.describe()#汇总信息，基本信息
结果：
| Open | High | Low | Close | Adj Close | Volume | |
|---|---|---|---|---|---|---|
| count | 789.000000 | 789.000000 | 789.000000 | 789.000000 | 789.000000 | 7.890000e+02 |
| mean | 98.879004 | 99.977879 | 97.622681 | 98.800431 | 98.800431 | 1.681925e+07 |
| std | 29.076254 | 29.240037 | 28.743547 | 29.007961 | 29.007961 | 1.427472e+07 |
| min | 57.299999 | 58.650002 | 57.200001 | 57.389999 | 57.389999 | 3.775300e+06 |
| 25% | 79.849998 | 80.989998 | 79.150002 | 79.889999 | 79.889999 | 1.003060e+07 |
| 50% | 89.099998 | 90.459999 | 88.059998 | 88.900002 | 88.900002 | 1.340540e+07 |
| 75% | 106.500000 | 107.550003 | 105.129997 | 105.980003 | 105.980003 | 1.915080e+07 |
| max | 190.990005 | 191.220001 | 183.580002 | 186.080002 | 186.080002 | 2.718794e+08 |
alibaba.info()#也是基本信息
结果：
<class 'pandas.core.frame.DataFrame'> DatetimeIndex: 789 entries, 2014-09-19 to 2017-11-03 Data columns (total 6 columns): Open 789 non-null float64 High 789 non-null float64 Low 789 non-null float64 Close 789 non-null float64 Adj Close 789 non-null float64 Volume 789 non-null int64 dtypes: float64(5), int64(1) memory usage: 43.1 KB
历史趋势分析
# 基本信息 import numpy as np import pandas as pd from pandas import Series, DataFrame # 股票数据的读取 import pandas_datareader as pdr # 可视化 import matplotlib.pyplot as plt import seaborn as sns %matplotlib inline # time from datetime import datetime
start = datetime(2015,9,20)
alibaba = pdr.get_data_yahoo('BABA', start=start)
amazon = pdr.get_data_yahoo('AMZN', start=start)
alibaba.to_csv('../homework/BABA.csv')
amazon.to_csv('../homework/AMZN.csv')
alibaba.head()
结果：
| Open | High | Low | Close | Adj Close | Volume | |
|---|---|---|---|---|---|---|
| Date | ||||||
| 2015-09-21 | 65.379997 | 66.400002 | 62.959999 | 63.900002 | 63.900002 | 22355100 |
| 2015-09-22 | 62.939999 | 63.270000 | 61.580002 | 61.900002 | 61.900002 | 14897900 |
| 2015-09-23 | 61.959999 | 62.299999 | 59.680000 | 60.000000 | 60.000000 | 22684600 |
| 2015-09-24 | 59.419998 | 60.340000 | 58.209999 | 59.919998 | 59.919998 | 20645700 |
| 2015-09-25 | 60.630001 | 60.840000 | 58.919998 | 59.240002 | 59.240002 | 17009100 |
alibaba['Adj Close'].plot(legend=True)
结果：<matplotlib.axes._subplots.AxesSubplot at 0x11d910588>
alibaba['Volume'].plot(legend=True)
结果：<matplotlib.axes._subplots.AxesSubplot at 0x120ebcda0>
alibaba['Adj Close'].plot() amazon['Adj Close'].plot()
结果：<matplotlib.axes._subplots.AxesSubplot at 0x120ee9a90>
alibaba.head()
结果：
| Open | High | Low | Close | Adj Close | Volume | |
|---|---|---|---|---|---|---|
| Date | ||||||
| 2015-09-21 | 65.379997 | 66.400002 | 62.959999 | 63.900002 | 63.900002 | 22355100 |
| 2015-09-22 | 62.939999 | 63.270000 | 61.580002 | 61.900002 | 61.900002 | 14897900 |
| 2015-09-23 | 61.959999 | 62.299999 | 59.680000 | 60.000000 | 60.000000 | 22684600 |
| 2015-09-24 | 59.419998 | 60.340000 | 58.209999 | 59.919998 | 59.919998 | 20645700 |
| 2015-09-25 | 60.630001 | 60.840000 | 58.919998 | 59.240002 | 59.240002 | 17009100 |
alibaba['high-low'] = alibaba['High'] - alibaba['Low'] alibaba.head()
结果：
| Open | High | Low | Close | Adj Close | Volume | high-low | |
|---|---|---|---|---|---|---|---|
| Date | |||||||
| 2015-09-21 | 65.379997 | 66.400002 | 62.959999 | 63.900002 | 63.900002 | 22355100 | 3.440003 |
| 2015-09-22 | 62.939999 | 63.270000 | 61.580002 | 61.900002 | 61.900002 | 14897900 | 1.689998 |
| 2015-09-23 | 61.959999 | 62.299999 | 59.680000 | 60.000000 | 60.000000 | 22684600 | 2.619999 |
| 2015-09-24 | 59.419998 | 60.340000 | 58.209999 | 59.919998 | 59.919998 | 20645700 | 2.130001 |
| 2015-09-25 | 60.630001 | 60.840000 | 58.919998 | 59.240002 | 59.240002 | 17009100 | 1.920002 |
alibaba['high-low'].plot()
结果：<matplotlib.axes._subplots.AxesSubplot at 0x120fdcf98>
# daily return 每天变化情况 alibaba['daily-return'] = alibaba['Adj Close'].pct_change() #.pct_change() 实现每天每天变化情况 alibaba['daily-return'].plot(figsize=(10,4),linestyle='--',marker='o')#figsize图大小，marker每个数据点类型
结果：<matplotlib.axes._subplots.AxesSubplot at 0x121504d68>
alibaba['daily-return'].plot(kind='hist')#可以看出，基本上在-0.025到.025之间，所以股票价格稳定
结果：<matplotlib.axes._subplots.AxesSubplot at 0x12169c630>
sns.distplot(alibaba['daily-return'].dropna(),bins=100,color='purple')
结果：<matplotlib.axes._subplots.AxesSubplot at 0x121b15f98>
风险分析
# 基本信息 import numpy as np import pandas as pd from pandas import Series, DataFrame # 股票数据的读取 import pandas_datareader as pdr # 可视化 import matplotlib.pyplot as plt import seaborn as sns %matplotlib inline # time from datetime import datetime
start = datetime(2015,1,1) company = ['AAPL','GOOG','MSFT','AMZN','FB']#5家公司 top_tech_df = pdr.get_data_yahoo(company, start=start)['Adj Close']
top_tech_df.to_csv('../homework/top5.csv')
top_tech_df.head()
结果：
| AAPL | AMZN | FB | GOOG | MSFT | |
|---|---|---|---|---|---|
| Date | |||||
| 2017-11-03 | 172.500000 | 1111.599976 | 178.919998 | 1032.479980 | 84.139999 |
| 2017-11-02 | 168.110001 | 1094.219971 | 178.919998 | 1025.579956 | 84.050003 |
| 2017-11-01 | 166.889999 | 1103.680054 | 182.660004 | 1025.500000 | 83.180000 |
| 2017-10-31 | 169.039993 | 1105.280029 | 180.059998 | 1016.640015 | 83.180000 |
| 2017-10-30 | 166.720001 | 1110.849976 | 179.869995 | 1017.109985 | 83.889999 |
top_tech_dr = top_tech_df.pct_change()#股票数据每天的变化 top_tech_dr.head()
结果：
| AAPL | AMZN | FB | GOOG | MSFT | |
|---|---|---|---|---|---|
| Date | |||||
| 2017-11-03 | NaN | NaN | NaN | NaN | NaN |
| 2017-11-02 | -0.025449 | -0.015635 | 0.000000 | -0.006683 | -0.001070 |
| 2017-11-01 | -0.007257 | 0.008646 | 0.020903 | -0.000078 | -0.010351 |
| 2017-10-31 | 0.012883 | 0.001450 | -0.014234 | -0.008640 | 0.000000 |
| 2017-10-30 | -0.013725 | 0.005039 | -0.001055 | 0.000462 | 0.008536 |
top_tech_df.plot()#GOOG与AMZN曲线比较相似
结果：<matplotlib.axes._subplots.AxesSubplot at 0x122293fd0>
top_tech_df[['AAPL','FB','MSFT']].plot()#画出其中三列
结果：<matplotlib.axes._subplots.AxesSubplot at 0x1225960b8>
sns.jointplot('AMZN','GOOG', top_tech_dr, kind='scatter')#kind='scatter'表示散点图；看点是否在一条斜率为45度的直线上来观察两家股票的相关性，注意坐标大小代表的是上升或者下降
结果：<seaborn.axisgrid.JointGrid at 0x124dd0f98>
sns.jointplot('MSFT','FB', top_tech_dr, kind='scatter')
结果：<seaborn.axisgrid.JointGrid at 0x125928940>
sns.pairplot(top_tech_dr.dropna())#.dropna()表示去掉NaN
结果：<seaborn.axisgrid.PairGrid at 0x125fa27f0>
top_tech_dr['AAPL'].quantile(0.52) #结果：-0.0001447090809730694
top_tech_dr['MSFT'].quantile(0.05)#有（1-%5）的信心每天的变化最大为-0.021328913487084877 （最大亏损为%2）
结果：-0.021328913487084877
vips = pdr.get_data_yahoo('VIPS', start=start)['Adj Close']
vips.plot()
结果：<matplotlib.axes._subplots.AxesSubplot at 0x127b0f7b8>
vips.pct_change().quantile(0.2)#-0.02181125767068397
