dataframe Data

import numpy as np
import pandas as pd
from pandas import Series, DataFrame

# 创建 DataFrame
import webbrowser

link = 'https://www.tiobe.com/tiobe-index'
webbrowser.open(link)

# 从网站上复制排行榜

True

# 创建一个dataFrame

# 从粘贴板中解析

df = pd.read_clipboard()

df

	Jun 2019	Jun 2018	Change	Programming Language	Ratings	Change.1
0	1	1	NaN	Java	15.004%	-0.36%
1	2	2	NaN	C	13.300%	-1.64%
2	3	4	change	Python	8.530%	+2.77%
3	4	3	change	C++	7.384%	-0.95%
4	5	6	change	Visual Basic .NET	4.624%	+0.86%
5	6	5	change	C#	4.483%	+0.17%
6	7	8	change	JavaScript	2.716%	+0.22%
7	8	7	change	PHP	2.567%	-0.31%
8	9	9	NaN	SQL	2.224%	-0.12%
9	10	16	change	Assembly language	1.479%	+0.56%
10	11	15	change	Swift	1.419%	+0.27%
11	12	12	NaN	Objective-C	1.391%	+0.21%
12	13	11	change	Ruby	1.388%	+0.13%
13	14	60	change	Groovy	1.300%	+1.11%
14	15	18	change	Go	1.257%	+0.38%
15	16	14	change	Perl	1.173%	+0.03%
16	17	19	change	Delphi/Object Pascal	1.129%	+0.25%
17	18	17	change	MATLAB	1.077%	+0.18%
18	19	13	change	Visual Basic	1.069%	-0.08%
19	20	20	NaN	PL/SQL	0.929%	+0.08%

type(df)

pandas.core.frame.DataFrame

df.columns

Index(['Jun 2019', 'Jun 2018', 'Change', 'Programming Language', 'Ratings',
'Change.1'],
dtype='object')

df.Ratings

0 15.004%
1 13.300%
2 8.530%
3 7.384%
4 4.624%
5 4.483%
6 2.716%
7 2.567%
8 2.224%
9 1.479%
10 1.419%
11 1.391%
12 1.388%
13 1.300%
14 1.257%
15 1.173%
16 1.129%
17 1.077%
18 1.069%
19 0.929%
Name: Ratings, dtype: object

df.Change

0 NaN
1 NaN
2 change
3 change
4 change
5 change
6 change
7 change
8 NaN
9 change
10 change
11 NaN
12 change
13 change
14 change
15 change
16 change
17 change
18 change
19 NaN
Name: Change, dtype: object

# 操作 生成新的 dataFrame

df_new = DataFrame(df, columns = [ 'Programming Language','Jun 2018','Jun 2019','Ratings'])

df_new

	Programming Language	Jun 2018	Jun 2019	Ratings
0	Java	1	1	15.004%
1	C	2	2	13.300%
2	Python	4	3	8.530%
3	C++	3	4	7.384%
4	Visual Basic .NET	6	5	4.624%
5	C#	5	6	4.483%
6	JavaScript	8	7	2.716%
7	PHP	7	8	2.567%
8	SQL	9	9	2.224%
9	Assembly language	16	10	1.479%
10	Swift	15	11	1.419%
11	Objective-C	12	12	1.391%
12	Ruby	11	13	1.388%
13	Groovy	60	14	1.300%
14	Go	18	15	1.257%
15	Perl	14	16	1.173%
16	Delphi/Object Pascal	19	17	1.129%
17	MATLAB	17	18	1.077%
18	Visual Basic	13	19	1.069%
19	PL/SQL	20	20	0.929%

df["Jun 2018"]

0 1
1 2
2 4
3 3
4 6
5 5
6 8
7 7
8 9
9 16
10 15
11 12
12 11
13 60
14 18
15 14
16 19
17 17
18 13
19 20
Name: Jun 2018, dtype: int64

type(df["Jun 2018"])

pandas.core.series.Series

df_new = DataFrame(df, columns = [ 'Programming Language','Jun 2018','Jun 2019','Rt'])

df_new

	Programming Language	Jun 2018	Jun 2019	Rt
0	Java	1	1	NaN
1	C	2	2	NaN
2	Python	4	3	NaN
3	C++	3	4	NaN
4	Visual Basic .NET	6	5	NaN
5	C#	5	6	NaN
6	JavaScript	8	7	NaN
7	PHP	7	8	NaN
8	SQL	9	9	NaN
9	Assembly language	16	10	NaN
10	Swift	15	11	NaN
11	Objective-C	12	12	NaN
12	Ruby	11	13	NaN
13	Groovy	60	14	NaN
14	Go	18	15	NaN
15	Perl	14	16	NaN
16	Delphi/Object Pascal	19	17	NaN
17	MATLAB	17	18	NaN
18	Visual Basic	13	19	NaN
19	PL/SQL	20	20	NaN

df_new["Rt"] = range(0,20)

df_new

	Programming Language	Jun 2018	Jun 2019	Rt
0	Java	1	1	0
1	C	2	2	1
2	Python	4	3	2
3	C++	3	4	3
4	Visual Basic .NET	6	5	4
5	C#	5	6	5
6	JavaScript	8	7	6
7	PHP	7	8	7
8	SQL	9	9	8
9	Assembly language	16	10	9
10	Swift	15	11	10
11	Objective-C	12	12	11
12	Ruby	11	13	12
13	Groovy	60	14	13
14	Go	18	15	14
15	Perl	14	16	15
16	Delphi/Object Pascal	19	17	16
17	MATLAB	17	18	17
18	Visual Basic	13	19	18
19	PL/SQL	20	20	19

df_new["RF"] = np.arange(0,20)

df_new

	Programming Language	Jun 2018	Jun 2019	Rt	RF
0	Java	1	1	0	0
1	C	2	2	1	1
2	Python	4	3	2	2
3	C++	3	4	3	3
4	Visual Basic .NET	6	5	4	4
5	C#	5	6	5	5
6	JavaScript	8	7	6	6
7	PHP	7	8	7	7
8	SQL	9	9	8	8
9	Assembly language	16	10	9	9
10	Swift	15	11	10	10
11	Objective-C	12	12	11	11
12	Ruby	11	13	12	12
13	Groovy	60	14	13	13
14	Go	18	15	14	14
15	Perl	14	16	15	15
16	Delphi/Object Pascal	19	17	16	16
17	MATLAB	17	18	17	17
18	Visual Basic	13	19	18	18
19	PL/SQL	20	20	19	19

df_new["RFd"] =  pd.Series(np.arange(0,20))

df_new

	Programming Language	Jun 2018	Jun 2019	Rt	RF	RFd
0	Java	1	1	0	0	0
1	C	2	2	1	1	1
2	Python	4	3	2	2	2
3	C++	3	4	3	3	3
4	Visual Basic .NET	6	5	4	4	4
5	C#	5	6	5	5	5
6	JavaScript	8	7	6	6	6
7	PHP	7	8	7	7	7
8	SQL	9	9	8	8	8
9	Assembly language	16	10	9	9	9
10	Swift	15	11	10	10	10
11	Objective-C	12	12	11	11	11
12	Ruby	11	13	12	12	12
13	Groovy	60	14	13	13	13
14	Go	18	15	14	14	14
15	Perl	14	16	15	15	15
16	Delphi/Object Pascal	19	17	16	16	16
17	MATLAB	17	18	17	17	17
18	Visual Basic	13	19	18	18	18
19	PL/SQL	20	20	19	19	19

df_new["RF"] = pd.Series([100,200], index=[18,19])

df_new

	Programming Language	Jun 2018	Jun 2019	Rt	RF	RFd
0	Java	1	1	0	NaN	0
1	C	2	2	1	NaN	1
2	Python	4	3	2	NaN	2
3	C++	3	4	3	NaN	3
4	Visual Basic .NET	6	5	4	NaN	4
5	C#	5	6	5	NaN	5
6	JavaScript	8	7	6	NaN	6
7	PHP	7	8	7	NaN	7
8	SQL	9	9	8	NaN	8
9	Assembly language	16	10	9	NaN	9
10	Swift	15	11	10	NaN	10
11	Objective-C	12	12	11	NaN	11
12	Ruby	11	13	12	NaN	12
13	Groovy	60	14	13	NaN	13
14	Go	18	15	14	NaN	14
15	Perl	14	16	15	NaN	15
16	Delphi/Object Pascal	19	17	16	NaN	16
17	MATLAB	17	18	17	NaN	17
18	Visual Basic	13	19	18	100.0	18
19	PL/SQL	20	20	19	200.0	19