数据分析——从入门到精通(十二)

import numpy as np
import pandas as pd 
from pandas import Series,DataFrame
import matplotlib.pyplot as plt

# 当前文档显示matplotlib的图像：可视化
%matplotlib inline

# 读取数据  data/AAPL.csv

apple = pd.read_csv('data/AAPL.csv')
apple.head()

	Date	Open	High	Low	Close	Adj Close	Volume
0	1980-12-12	0.513393	0.515625	0.513393	0.513393	0.421597	117258400
1	1980-12-15	0.488839	0.488839	0.486607	0.486607	0.399601	43971200
2	1980-12-16	0.453125	0.453125	0.450893	0.450893	0.370272	26432000
3	1980-12-17	0.462054	0.464286	0.462054	0.462054	0.379437	21610400
4	1980-12-18	0.475446	0.477679	0.475446	0.475446	0.390436	18362400

# dataframe的属性 比series 多一个columns
# 查看每一个字段的类型
apple.dtypes

Date          object
Open         float64
High         float64
Low          float64
Close        float64
Adj Close    float64
Volume         int64
dtype: object

apple.info()    # 信息的描述

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 9296 entries, 0 to 9295
Data columns (total 7 columns):
Date         9296 non-null object
Open         9296 non-null float64
High         9296 non-null float64
Low          9296 non-null float64
Close        9296 non-null float64
Adj Close    9296 non-null float64
Volume       9296 non-null int64
dtypes: float64(5), int64(1), object(1)
memory usage: 472.1+ KB

# 将data这一列转化为日期类型
# 两种方式，第一种通过映射
# 第二种
pd.to_datetime(apple['Date'])

0      1980-12-12
1      1980-12-15
2      1980-12-16
3      1980-12-17
4      1980-12-18
          ...    
9291   2017-10-17
9292   2017-10-18
9293   2017-10-19
9294   2017-10-20
9295   2017-10-23
Name: Date, Length: 9296, dtype: datetime64[ns]

apple.Date  # dataframe的列可以作为对象的属性来访问

0       1980-12-12
1       1980-12-15
2       1980-12-16
3       1980-12-17
4       1980-12-18
           ...    
9291    2017-10-17
9292    2017-10-18
9293    2017-10-19
9294    2017-10-20
9295    2017-10-23
Name: Date, Length: 9296, dtype: object

apple2 = apple.copy()
apple2.Date = pd.to_datetime(apple.Date)
apple2.dtypes

Date         datetime64[ns]
Open                float64
High                float64
Low                 float64
Close               float64
Adj Close           float64
Volume                int64
dtype: object

# 自省函数
# setattr(obj,property,value)
# getattr(obj,property)
# hasattr(obj,property)  返回bool值

# 将Date列设置为行索引
apple2.set_index('Date',drop=False)

	Date	Open	High	Low	Close	Adj Close	Volume
Date
1980-12-12	1980-12-12	0.513393	0.515625	0.513393	0.513393	0.421597	117258400
1980-12-15	1980-12-15	0.488839	0.488839	0.486607	0.486607	0.399601	43971200
1980-12-16	1980-12-16	0.453125	0.453125	0.450893	0.450893	0.370272	26432000
1980-12-17	1980-12-17	0.462054	0.464286	0.462054	0.462054	0.379437	21610400
1980-12-18	1980-12-18	0.475446	0.477679	0.475446	0.475446	0.390436	18362400
...	...	...	...	...	...	...	...
2017-10-17	2017-10-17	159.779999	160.869995	159.229996	160.470001	160.470001	18997300
2017-10-18	2017-10-18	160.419998	160.710007	159.600006	159.759995	159.759995	16374200
2017-10-19	2017-10-19	156.750000	157.080002	155.020004	155.979996	155.979996	42584200
2017-10-20	2017-10-20	156.610001	157.750000	155.960007	156.250000	156.250000	23974100
2017-10-23	2017-10-23	156.889999	157.690002	155.500000	156.169998	156.169998	21867200

9296 rows × 7 columns

apple2.set_index('Date',drop=True)

	Open	High	Low	Close	Adj Close	Volume
Date
1980-12-12	0.513393	0.515625	0.513393	0.513393	0.421597	117258400
1980-12-15	0.488839	0.488839	0.486607	0.486607	0.399601	43971200
1980-12-16	0.453125	0.453125	0.450893	0.450893	0.370272	26432000
1980-12-17	0.462054	0.464286	0.462054	0.462054	0.379437	21610400
1980-12-18	0.475446	0.477679	0.475446	0.475446	0.390436	18362400
...	...	...	...	...	...	...
2017-10-17	159.779999	160.869995	159.229996	160.470001	160.470001	18997300
2017-10-18	160.419998	160.710007	159.600006	159.759995	159.759995	16374200
2017-10-19	156.750000	157.080002	155.020004	155.979996	155.979996	42584200
2017-10-20	156.610001	157.750000	155.960007	156.250000	156.250000	23974100
2017-10-23	156.889999	157.690002	155.500000	156.169998	156.169998	21867200

9296 rows × 6 columns

apple2.set_index('Date',drop=True,inplace=True)
apple2.head(10)

	Open	High	Low	Close	Adj Close	Volume
Date
1980-12-12	0.513393	0.515625	0.513393	0.513393	0.421597	117258400
1980-12-15	0.488839	0.488839	0.486607	0.486607	0.399601	43971200
1980-12-16	0.453125	0.453125	0.450893	0.450893	0.370272	26432000
1980-12-17	0.462054	0.464286	0.462054	0.462054	0.379437	21610400
1980-12-18	0.475446	0.477679	0.475446	0.475446	0.390436	18362400
1980-12-19	0.504464	0.506696	0.504464	0.504464	0.414265	12157600
1980-12-22	0.529018	0.531250	0.529018	0.529018	0.434428	9340800
1980-12-23	0.551339	0.553571	0.551339	0.551339	0.452758	11737600
1980-12-24	0.580357	0.582589	0.580357	0.580357	0.476588	12000800
1980-12-26	0.633929	0.636161	0.633929	0.633929	0.520581	13893600

# 绘制 "Adj Close	" 字段的图形

apple2['Adj Close'].plot()

<matplotlib.axes._subplots.AxesSubplot at 0x87bb630>

# 查看最后五条数据
apple2.tail()

	Open	High	Low	Close	Adj Close	Volume
Date
2017-10-17	159.779999	160.869995	159.229996	160.470001	160.470001	18997300
2017-10-18	160.419998	160.710007	159.600006	159.759995	159.759995	16374200
2017-10-19	156.750000	157.080002	155.020004	155.979996	155.979996	42584200
2017-10-20	156.610001	157.750000	155.960007	156.250000	156.250000	23974100
2017-10-23	156.889999	157.690002	155.500000	156.169998	156.169998	21867200