import numpy as np
import pandas as pd
from pandas import Series, DataFrame
import pandas_datareader as pdr
import matplotlib.pyplot as plt
import seaborn as sns
from datetime import datetime
start = datetime(2015,9,20)
alibaba = pdr.get_data_yahoo('BABA', start=start)
amazon = pdr.get_components_yahoo('AMZN')
alibaba = pd.read_csv('/Users/bennyrhys/Desktop/数据分析可视化-数据集/homework/BABA.csv',index_col=0)
amazon = pd.read_csv('/Users/bennyrhys/Desktop/数据分析可视化-数据集/homework/AMZN.csv',index_col=0)
alibaba.head()
|
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 |
amazon.head()
|
Open |
High |
Low |
Close |
Adj Close |
Volume |
Date |
|
|
|
|
|
|
2015-09-21 |
544.330017 |
549.780029 |
539.590027 |
548.390015 |
548.390015 |
3283300 |
2015-09-22 |
539.710022 |
543.549988 |
532.659973 |
538.400024 |
538.400024 |
3841700 |
2015-09-23 |
538.299988 |
541.210022 |
534.000000 |
536.070007 |
536.070007 |
2237600 |
2015-09-24 |
530.549988 |
534.559998 |
522.869995 |
533.750000 |
533.750000 |
3501000 |
2015-09-25 |
542.570007 |
542.799988 |
521.400024 |
524.250000 |
524.250000 |
4031000 |
alibaba['Adj Close'].plot(legend=True)
<matplotlib.axes._subplots.AxesSubplot at 0x1a252e4ad0>
alibaba['Volume'].plot(legend=True)
<matplotlib.axes._subplots.AxesSubplot at 0x1a216b9790>
alibaba['Adj Close'].plot()
amazon['Adj Close'].plot()
<matplotlib.axes._subplots.AxesSubplot at 0x1a26641290>
alibaba['high-low'] = alibaba['High'] - alibaba['Low']
alibaba.head()
|
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()
<matplotlib.axes._subplots.AxesSubplot at 0x1a26668a90>
alibaba['daily-return'] = alibaba['Adj Close'].pct_change()
alibaba.head()
|
Open |
High |
Low |
Close |
Adj Close |
Volume |
high-low |
daily-return |
Date |
|
|
|
|
|
|
|
|
2015-09-21 |
65.379997 |
66.400002 |
62.959999 |
63.900002 |
63.900002 |
22355100 |
3.440003 |
NaN |
2015-09-22 |
62.939999 |
63.270000 |
61.580002 |
61.900002 |
61.900002 |
14897900 |
1.689998 |
-0.031299 |
2015-09-23 |
61.959999 |
62.299999 |
59.680000 |
60.000000 |
60.000000 |
22684600 |
2.619999 |
-0.030695 |
2015-09-24 |
59.419998 |
60.340000 |
58.209999 |
59.919998 |
59.919998 |
20645700 |
2.130001 |
-0.001333 |
2015-09-25 |
60.630001 |
60.840000 |
58.919998 |
59.240002 |
59.240002 |
17009100 |
1.920002 |
-0.011348 |
alibaba['daily-return'].plot()
<matplotlib.axes._subplots.AxesSubplot at 0x1a28c20410>
alibaba['daily-return'].plot(figsize=(10,4),linestyle='--',marker='o')
<matplotlib.axes._subplots.AxesSubplot at 0x1a29240a90>
alibaba['daily-return'].plot(kind='hist')
<matplotlib.axes._subplots.AxesSubplot at 0x1a2786f050>
sns.distplot(alibaba['daily-return'].dropna(),bins=100, color='purple')
<matplotlib.axes._subplots.AxesSubplot at 0x1a28bf8710>