【数据分析】苹果公司股票数据处理

import numpy as np

import pandas as pd

from pandas import Series,DataFrame

app = pd.read_csv('./AAPL.csv')

app.shape

(9814, 7)

app.head()

	Date	Open	High	Low	Close	Adj Close	Volume
0	1980-12-12	0.513393	0.515625	0.513393	0.513393	0.407747	117258400.0
1	1980-12-15	0.488839	0.488839	0.486607	0.486607	0.386473	43971200.0
2	1980-12-16	0.453125	0.453125	0.450893	0.450893	0.358108	26432000.0
3	1980-12-17	0.462054	0.464286	0.462054	0.462054	0.366972	21610400.0
4	1980-12-18	0.475446	0.477679	0.475446	0.475446	0.377609	18362400.0

app.tail()

	Date	Open	High	Low	Close	Adj Close	Volume
9809	2019-11-06	256.769989	257.489990	255.369995	257.239990	256.470001	18966100.0
9810	2019-11-07	258.739990	260.350006	258.109985	259.429993	259.429993	23735100.0
9811	2019-11-08	258.690002	260.440002	256.850006	260.140015	260.140015	17496600.0
9812	2019-11-11	258.299988	262.470001	258.279999	262.200012	262.200012	20455300.0
9813	2019-11-12	261.549988	262.790009	260.920013	261.959991	261.959991	21826100.0

app.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 9814 entries, 0 to 9813
Data columns (total 7 columns):
Date         9814 non-null object
Open         9813 non-null float64
High         9813 non-null float64
Low          9813 non-null float64
Close        9813 non-null float64
Adj Close    9813 non-null float64
Volume       9813 non-null float64
dtypes: float64(6), object(1)
memory usage: 536.8+ KB

app[app.isnull().any(axis = 1)]

	Date	Open	High	Low	Close	Adj Close	Volume
165	1981-08-10	NaN	NaN	NaN	NaN	NaN	NaN

app.dropna(inplace = True)

app.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 9813 entries, 0 to 9813
Data columns (total 7 columns):
Date         9813 non-null object
Open         9813 non-null float64
High         9813 non-null float64
Low          9813 non-null float64
Close        9813 non-null float64
Adj Close    9813 non-null float64
Volume       9813 non-null float64
dtypes: float64(6), object(1)
memory usage: 613.3+ KB

app['Date'] = pd.to_datetime(app['Date'])

app.dtypes

Date         datetime64[ns]
Open                float64
High                float64
Low                 float64
Close               float64
Adj Close           float64
Volume              float64
dtype: object

app.head()

	Date	Open	High	Low	Close	Adj Close	Volume
0	1980-12-12	0.513393	0.515625	0.513393	0.513393	0.407747	117258400.0
1	1980-12-15	0.488839	0.488839	0.486607	0.486607	0.386473	43971200.0
2	1980-12-16	0.453125	0.453125	0.450893	0.450893	0.358108	26432000.0
3	1980-12-17	0.462054	0.464286	0.462054	0.462054	0.366972	21610400.0
4	1980-12-18	0.475446	0.477679	0.475446	0.475446	0.377609	18362400.0

app2 = app.set_index('Date')
app2

	Open	High	Low	Close	Adj Close	Volume
Date
1980-12-12	0.513393	0.515625	0.513393	0.513393	0.407747	117258400.0
1980-12-15	0.488839	0.488839	0.486607	0.486607	0.386473	43971200.0
1980-12-16	0.453125	0.453125	0.450893	0.450893	0.358108	26432000.0
1980-12-17	0.462054	0.464286	0.462054	0.462054	0.366972	21610400.0
1980-12-18	0.475446	0.477679	0.475446	0.475446	0.377609	18362400.0
...	...	...	...	...	...	...
2019-11-06	256.769989	257.489990	255.369995	257.239990	256.470001	18966100.0
2019-11-07	258.739990	260.350006	258.109985	259.429993	259.429993	23735100.0
2019-11-08	258.690002	260.440002	256.850006	260.140015	260.140015	17496600.0
2019-11-11	258.299988	262.470001	258.279999	262.200012	262.200012	20455300.0
2019-11-12	261.549988	262.790009	260.920013	261.959991	261.959991	21826100.0

9813 rows × 6 columns

app2['Adj Close'].plot(kind ='line')

<matplotlib.axes._subplots.AxesSubplot at 0x1ddedad8d68>

app2.resample('M').median().plot(kind ='line')

<matplotlib.axes._subplots.AxesSubplot at 0x1ddedae2710>

app2.resample('M').median()[['Adj Close','Open']].plot(kind ='line')

app2.resample('Y').median()[['High','Low']].plot(kind ='line')