In [8]:
import pandas as pd
import math
import matplotlib.pyplot as plt
import numpy as np
In [4]:
data = pd.read_csv('knetwork2.csv')
In [5]:
data
Out[5]:
Unnamed: 0
Year
Country 1
Country 2
No. of Collaborations
No. of Publications of Country 1
No. of Publications of Country 2
Collaborators
Total No. of Publications
Continent of Country 1
Continent of Country 2
Percent of Total Publications of Country 1
Percent of Total Publications of Country 2
Rank of Country 1
Rank of Country 2
0
0
2000
USA
Mexico
5.0
286.0
8.0
USA & Mexico
1391.0
North America
North America
20.560748
0.575126
1/133
25/133
1
1
2000
USA
Canada
5.0
286.0
33.0
USA & Canada
1391.0
North America
North America
20.560748
2.372394
1/133
10/133
2
16
2000
USA
Venezuela
1.0
286.0
1.0
USA & Venezuela
1391.0
North America
South America
20.560748
0.071891
1/133
57/133
3
33
2000
USA
Egypt
1.0
286.0
8.0
USA & Egypt
1391.0
North America
Africa
20.560748
0.575126
1/133
26/133
4
48
2000
USA
China
3.0
286.0
27.0
USA & China
1391.0
North America
Asia
20.560748
1.941050
1/133
12/133
5
53
2000
USA
Russia
14.0
286.0
110.0
USA & Russia
1391.0
North America
Asia
20.560748
7.907980
1/133
4/133
6
54
2000
USA
Japan
20.0
286.0
205.0
USA & Japan
1391.0
North America
Asia
20.560748
14.737599
1/133
2/133
7
61
2000
USA
Korea
1.0
286.0
47.0
USA & Korea
1391.0
North America
Asia
20.560748
3.378864
1/133
7/133
8
63
2000
USA
Arabia
1.0
286.0
2.0
USA & Arabia
1391.0
North America
Asia
20.560748
0.143781
1/133
43/133
9
75
2000
USA
Israel
3.0
286.0
15.0
USA & Israel
1391.0
North America
Asia
20.560748
1.078361
1/133
17/133
10
85
2000
USA
Germany
25.0
286.0
163.0
USA & Germany
1391.0
North America
Europe
20.560748
11.718188
1/133
3/133
11
86
2000
USA
France
8.0
286.0
102.0
USA & France
1391.0
North America
Europe
20.560748
7.332854
1/133
5/133
12
88
2000
USA
Italy
4.0
286.0
47.0
USA & Italy
1391.0
North America
Europe
20.560748
3.378864
1/133
6/133
13
92
2000
USA
Poland
2.0
286.0
10.0
USA & Poland
1391.0
North America
Europe
20.560748
0.718907
1/133
23/133
14
93
2000
USA
Romania
1.0
286.0
11.0
USA & Romania
1391.0
North America
Europe
20.560748
0.790798
1/133
22/133
15
94
2000
USA
Netherlands
1.0
286.0
16.0
USA & Netherlands
1391.0
North America
Europe
20.560748
1.150252
1/133
16/133
16
95
2000
USA
Belgium
2.0
286.0
34.0
USA & Belgium
1391.0
North America
Europe
20.560748
2.444285
1/133
9/133
17
99
2000
USA
Hungary
3.0
286.0
12.0
USA & Hungary
1391.0
North America
Europe
20.560748
0.862689
1/133
20/133
18
103
2000
USA
Switzerland
3.0
286.0
19.0
USA & Switzerland
1391.0
North America
Europe
20.560748
1.365924
1/133
14/133
19
108
2000
USA
Norway
1.0
286.0
5.0
USA & Norway
1391.0
North America
Europe
20.560748
0.359454
1/133
31/133
20
109
2000
USA
Georgia
4.0
286.0
5.0
USA & Georgia
1391.0
North America
Europe
20.560748
0.359454
1/133
30/133
21
114
2000
USA
Lithuania
1.0
286.0
1.0
USA & Lithuania
1391.0
North America
Europe
20.560748
0.071891
1/133
49/133
22
127
2000
USA
Monaco
1.0
286.0
1.0
USA & Monaco
1391.0
North America
Europe
20.560748
0.071891
1/133
50/133
23
129
2000
USA
Australia
3.0
286.0
12.0
USA & Australia
1391.0
North America
Oceania
20.560748
0.862689
1/133
19/133
24
184
2000
Mexico
Russia
1.0
8.0
110.0
Mexico & Russia
1391.0
North America
Asia
0.575126
7.907980
25/133
4/133
25
322
2000
Canada
Korea
1.0
33.0
47.0
Canada & Korea
1391.0
North America
Asia
2.372394
3.378864
10/133
7/133
26
325
2000
Canada
Malaysia
1.0
33.0
1.0
Canada & Malaysia
1391.0
North America
Asia
2.372394
0.071891
10/133
55/133
27
341
2000
Canada
Kuwait
1.0
33.0
1.0
Canada & Kuwait
1391.0
North America
Asia
2.372394
0.071891
10/133
54/133
28
346
2000
Canada
Germany
2.0
33.0
163.0
Canada & Germany
1391.0
North America
Europe
2.372394
11.718188
10/133
3/133
29
354
2000
Canada
Romania
1.0
33.0
11.0
Canada & Romania
1391.0
North America
Europe
2.372394
0.790798
10/133
22/133
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
5357
148730
2016
Sweden
Austria
2.0
36.0
31.0
Sweden & Austria
2568.0
Europe
Europe
1.401869
1.207165
16/133
19/133
5358
148732
2016
Sweden
Switzerland
3.0
36.0
44.0
Sweden & Switzerland
2568.0
Europe
Europe
1.401869
1.713396
16/133
15/133
5359
148736
2016
Sweden
Finland
1.0
36.0
13.0
Sweden & Finland
2568.0
Europe
Europe
1.401869
0.506231
16/133
32/133
5360
148743
2016
Sweden
Lithuania
1.0
36.0
9.0
Sweden & Lithuania
2568.0
Europe
Europe
1.401869
0.350467
16/133
39/133
5361
148746
2016
Sweden
Slovenia
2.0
36.0
15.0
Sweden & Slovenia
2568.0
Europe
Europe
1.401869
0.584112
16/133
29/133
5362
148750
2016
Sweden
Luxembourg
3.0
36.0
6.0
Sweden & Luxembourg
2568.0
Europe
Europe
1.401869
0.233645
16/133
47/133
5363
148762
2016
Austria
Switzerland
6.0
31.0
44.0
Austria & Switzerland
2568.0
Europe
Europe
1.207165
1.713396
19/133
15/133
5364
148764
2016
Austria
Denmark
1.0
31.0
6.0
Austria & Denmark
2568.0
Europe
Europe
1.207165
0.233645
19/133
44/133
5365
148770
2016
Austria
Croatia
2.0
31.0
3.0
Austria & Croatia
2568.0
Europe
Europe
1.207165
0.116822
19/133
56/133
5366
148776
2016
Austria
Slovenia
2.0
31.0
15.0
Austria & Slovenia
2568.0
Europe
Europe
1.207165
0.584112
19/133
29/133
5367
148780
2016
Austria
Luxembourg
1.0
31.0
6.0
Austria & Luxembourg
2568.0
Europe
Europe
1.207165
0.233645
19/133
47/133
5368
148786
2016
Austria
Monaco
1.0
31.0
3.0
Austria & Monaco
2568.0
Europe
Europe
1.207165
0.116822
19/133
58/133
5369
148788
2016
Austria
Australia
3.0
31.0
23.0
Austria & Australia
2568.0
Europe
Oceania
1.207165
0.895639
19/133
22/133
5370
148821
2016
Switzerland
Denmark
1.0
44.0
6.0
Switzerland & Denmark
2568.0
Europe
Europe
1.713396
0.233645
15/133
44/133
5371
148824
2016
Switzerland
Norway
2.0
44.0
7.0
Switzerland & Norway
2568.0
Europe
Europe
1.713396
0.272586
15/133
42/133
5372
148826
2016
Switzerland
Ireland
1.0
44.0
6.0
Switzerland & Ireland
2568.0
Europe
Europe
1.713396
0.233645
15/133
46/133
5373
148827
2016
Switzerland
Croatia
2.0
44.0
3.0
Switzerland & Croatia
2568.0
Europe
Europe
1.713396
0.116822
15/133
56/133
5374
148837
2016
Switzerland
Luxembourg
1.0
44.0
6.0
Switzerland & Luxembourg
2568.0
Europe
Europe
1.713396
0.233645
15/133
47/133
5375
148845
2016
Switzerland
Australia
3.0
44.0
23.0
Switzerland & Australia
2568.0
Europe
Oceania
1.713396
0.895639
15/133
22/133
5376
148859
2016
Bulgaria
Macedonia
1.0
10.0
1.0
Bulgaria & Macedonia
2568.0
Europe
Europe
0.389408
0.038941
36/133
82/133
5377
148864
2016
Bulgaria
Luxembourg
1.0
10.0
6.0
Bulgaria & Luxembourg
2568.0
Europe
Europe
0.389408
0.233645
36/133
47/133
5378
148879
2016
Denmark
Ireland
1.0
6.0
6.0
Denmark & Ireland
2568.0
Europe
Europe
0.233645
0.233645
44/133
46/133
5379
148891
2016
Denmark
Malta
1.0
6.0
1.0
Denmark & Malta
2568.0
Europe
Europe
0.233645
0.038941
44/133
75/133
5380
148921
2016
Slovakia
Monaco
1.0
18.0
3.0
Slovakia & Monaco
2568.0
Europe
Europe
0.700935
0.116822
26/133
58/133
5381
149006
2016
Ireland
Malta
1.0
6.0
1.0
Ireland & Malta
2568.0
Europe
Europe
0.233645
0.038941
46/133
75/133
5382
149021
2016
Croatia
Slovenia
1.0
3.0
15.0
Croatia & Slovenia
2568.0
Europe
Europe
0.116822
0.584112
56/133
29/133
5383
149025
2016
Croatia
Luxembourg
1.0
3.0
6.0
Croatia & Luxembourg
2568.0
Europe
Europe
0.116822
0.233645
56/133
47/133
5384
149033
2016
Croatia
Australia
2.0
3.0
23.0
Croatia & Australia
2568.0
Europe
Oceania
0.116822
0.895639
56/133
22/133
5385
149075
2016
Lithuania
Slovenia
1.0
9.0
15.0
Lithuania & Slovenia
2568.0
Europe
Europe
0.350467
0.584112
39/133
29/133
5386
149178
2016
Luxembourg
Australia
1.0
6.0
23.0
Luxembourg & Australia
2568.0
Europe
Oceania
0.233645
0.895639
47/133
22/133
5387 rows × 15 columns
In [7]:
data['No. of Publications of Country 1'] - data['No. of Publications of Country 2']
Out[7]:
0 278.0
1 253.0
2 285.0
3 278.0
4 259.0
5 176.0
6 81.0
7 239.0
8 284.0
9 271.0
10 123.0
11 184.0
12 239.0
13 276.0
14 275.0
15 270.0
16 252.0
17 274.0
18 267.0
19 281.0
20 281.0
21 285.0
22 285.0
23 274.0
24 -102.0
25 -14.0
26 32.0
27 32.0
28 -130.0
29 22.0
...
5357 5.0
5358 -8.0
5359 23.0
5360 27.0
5361 21.0
5362 30.0
5363 -13.0
5364 25.0
5365 28.0
5366 16.0
5367 25.0
5368 28.0
5369 8.0
5370 38.0
5371 37.0
5372 38.0
5373 41.0
5374 38.0
5375 21.0
5376 9.0
5377 4.0
5378 0.0
5379 5.0
5380 15.0
5381 5.0
5382 -12.0
5383 -3.0
5384 -20.0
5385 -6.0
5386 -17.0
dtype: float64
In [39]:
"""Here, I try to make a histogram and normal distribution of the difference between countries in number of publications"""
Out[39]:
'Here, I try to make a histogram and normal distribution of the difference between countries in number of publications'
In [9]:
pub_diff = data['No. of Publications of Country 1'] - data['No. of Publications of Country 2']
In [34]:
abs_pub_diff = abs(pub_diff)
In [35]:
mu = np.mean(abs_pub_diff)
In [36]:
mu
Out[36]:
90.04418043437906
In [37]:
np.std(abs_pub_diff)
Out[37]:
95.31926897474308
In [38]:
from scipy.stats import norm
# Fit a normal distribution to the data:
mu, std = norm.fit(abs_pub_diff)
# Plot the histogram.
plt.hist(abs_pub_diff, bins=len(abs_pub_diff), normed=True, alpha=0.6, color='g')
# Plot the PDF.
xmin, xmax = plt.xlim()
x = np.linspace(xmin, xmax, 100)
p = norm.pdf(x, mu, std)
plt.plot(x, p, 'k', linewidth=2)
title = "Fit results: mu = %.2f, std = %.2f" % (mu, std)
plt.title(title)
plt.show()
In [40]:
"""Next, I'm going to filter out all of the countries that are above the mean difference."""
Out[40]:
"Next, I'm going to filter out all of the countries that are above the mean difference."
In [94]:
x = (np.where(abs_pub_diff < mu))
x = np.reshape(x,np.size(x))
y = x.tolist()
In [95]:
data['Collaborators'][y]
Out[95]:
6 USA & Japan
25 Canada & Korea
26 Canada & Malaysia
27 Canada & Kuwait
29 Canada & Romania
30 Canada & Sweden
31 Canada & Switzerland
32 Canada & Monaco
33 Brazil & Peru
36 Brazil & France
37 Brazil & Italy
38 Brazil & Netherlands
39 Brazil & Czech
40 Brazil & Hungary
43 Venezuela & Italy
44 Venezuela & Romania
46 Sudan & Sweden
48 China & Russia
50 China & Italy
51 China & Belgium
52 China & Hungary
53 China & Switzerland
56 Russia & Korea
57 Russia & Germany
58 Russia & France
59 Russia & Italy
60 Russia & Spain
63 Russia & Belgium
66 Russia & Sweden
72 Japan & Germany
...
5357 Sweden & Austria
5358 Sweden & Switzerland
5359 Sweden & Finland
5360 Sweden & Lithuania
5361 Sweden & Slovenia
5362 Sweden & Luxembourg
5363 Austria & Switzerland
5364 Austria & Denmark
5365 Austria & Croatia
5366 Austria & Slovenia
5367 Austria & Luxembourg
5368 Austria & Monaco
5369 Austria & Australia
5370 Switzerland & Denmark
5371 Switzerland & Norway
5372 Switzerland & Ireland
5373 Switzerland & Croatia
5374 Switzerland & Luxembourg
5375 Switzerland & Australia
5376 Bulgaria & Macedonia
5377 Bulgaria & Luxembourg
5378 Denmark & Ireland
5379 Denmark & Malta
5380 Slovakia & Monaco
5381 Ireland & Malta
5382 Croatia & Slovenia
5383 Croatia & Luxembourg
5384 Croatia & Australia
5385 Lithuania & Slovenia
5386 Luxembourg & Australia
Name: Collaborators, dtype: object
In [56]:
x
Out[56]:
(array([ 6, 25, 26, ..., 5384, 5385, 5386]),)
In [ ]:
Content source: ksakloth/KnowledgeNetworks
Similar notebooks: