In [231]:
import pandas as pd
import janitor
import matplotlib.pyplot as plt
import seaborn as sns
from matplotlib.ticker import MaxNLocator
import math
import plotly.express as px

import country_converter as coco
cc = coco.CountryConverter()

%matplotlib inline
In [232]:
sns.set_theme(context='notebook', style='ticks', palette='colorblind', font='sans-serif', font_scale=1, color_codes=True, rc=None)
sns.palplot(sns.color_palette())
In [233]:
outdir="wos_processed_data"

wos = pd.read_excel(f"../{outdir}/wos_processed.xlsx")
wos_univ = pd.read_excel(f"../{outdir}/wos_institution_locations_harmonized.xlsx")
In [234]:
def eurovoc_classer(x):
    eurovoc_classification = {"Eastern Europe":["Bulgaria","Czech Republic","Croatia","Hungary","Poland","Romania","Slovakia","Slovenia"],
                          "Northern Europe":["Denmark","Estonia","Finland","Latvia","Lithuania","Sweden","Norway","Iceland"],
                          "Southern Europe":["Cyprus","Greece","Italy","Portugal","Spain","Malta"],
                          "Western Europe":["Austria","Belgium","France","Germany","Luxembourg","Netherlands","Switzerland","United Kingdom","Ireland"]}
    if x == 'China':
        return x
    for k in eurovoc_classification.keys():
        if x in eurovoc_classification[k]:
            return k
In [235]:
wos_country = pd.read_excel(f"../{outdir}/wos_countries.xlsx")
wos_country_types = pd.read_excel(f"../{outdir}/wos_country_types.xlsx")
In [236]:
wos_country_types["Eurovoc_Class"] = wos_country_types["Country"].map(eurovoc_classer)
wos_country_types
Out[236]:
Country Country_Type Eurovoc_Class
0 Belgium EU Western Europe
1 China China China
2 Luxembourg EU Western Europe
3 Netherlands EU Western Europe
4 Norway Non-EU associate Northern Europe
5 United Kingdom Non-EU associate Western Europe
6 France EU Western Europe
7 Sweden EU Northern Europe
8 Italy EU Southern Europe
9 Denmark EU Northern Europe
10 Germany EU Western Europe
11 Slovenia EU Eastern Europe
12 Estonia EU Northern Europe
13 Finland EU Northern Europe
14 Bulgaria EU Eastern Europe
15 Slovakia EU Eastern Europe
16 Spain EU Southern Europe
17 Poland EU Eastern Europe
18 Czech Republic EU Eastern Europe
19 Greece EU Southern Europe
20 Malta EU Southern Europe
21 Austria EU Western Europe
22 Switzerland Non-EU associate Western Europe
23 Ireland EU Western Europe
24 Portugal EU Southern Europe
25 Romania EU Eastern Europe
26 Hungary EU Eastern Europe
27 Cyprus EU Southern Europe
28 Croatia EU Eastern Europe
29 Lithuania EU Northern Europe
30 Latvia EU Northern Europe
In [237]:
# len(wos),len(wos_univ_locations)
In [238]:
# wos_addresses = pd.read_excel(f"/{outdir}/wos_addresses.xlsx")

# wos_affiliations = pd.read_excel(f"/{outdir}/wos_affiliations.xlsx")

# wos_author_locations = pd.read_excel(f"/{outdir}/wos_author_locations.xlsx")

# wos_univ_locations = pd.read_excel(f"/{outdir}/wos_univ_locations.xlsx")
In [239]:
record_col = "UT (Unique WOS ID)"

Output - per yer, by Metrix taxonomy¶

In [240]:
# def nth_repl_all(s, sub="", repl="<br>", nth=2):
#     find = s.find(sub)
#     # loop util we find no match
#     i = 1
#     while find != -1:
#         # if i  is equal to nth we found nth matches so replace
#         if i == nth:
#             s = s[:find]+repl+s[find + len(sub):]
#             i = 0
#         # find + len(sub) + 1 means we start after the last match
#         find = s.find(sub, find + len(sub) + 1)
#         i += 1
#     return s.replace("<br>&","&<br")

def replace_nth(s, sub=" ", repl="<br>", n=2):
    chunks = s.split(sub)
    size = len(chunks)
    rows = size // n + (0 if size % n == 0 else 1)
    return (repl.join([
        sub.join([chunks[i * n + j] for j in range(n if (i + 1) * n < size else size - i * n)])
        for i in range(rows)
    ])).replace("<br>&"," &<br>")


groups = ['Domain_English',"Field_English",'SubField_English']
data = wos.groupby(groups, as_index=False)[record_col].nunique().sort_values(ascending=False, by=record_col)
data["percent"] = data[record_col]/data[record_col].sum()*100

# data[groups] = data[groups].applymap(replace_nth)
for c in ["Domain_English","Field_English","SubField_English"]:
    data[c] = data[c]+"<br>("+(pd.DataFrame(data[c],columns=[c]).merge(data.groupby(c,as_index=False)[record_col].sum(), on=c)[record_col]).astype(str)+")"
data
Out[240]:
Domain_English Field_English SubField_English UT (Unique WOS ID) percent
37 Applied Sciences<br>(29985) Information & Communication Technologies<br>(1... Artificial Intelligence & Image Processing<br>... 7915 17.184108
44 Applied Sciences<br>(29985) Information & Communication Technologies<br>(2... Networking & Telecommunications<br>(303) 5360 11.636995
32 Applied Sciences<br>(29985) Engineering<br>(3940) Geological & Geomatics Engineering<br>(436) 2576 5.592705
33 Applied Sciences<br>(29985) Engineering<br>(1226) Industrial Engineering & Automation<br>(425) 2316 5.028224
15 Applied Sciences<br>(29985) Enabling & Strategic Technologies<br>(9232) Energy<br>(598) 1965 4.266175
... ... ... ... ... ...
11 Applied Sciences<br>(29985) Economics & Business <br>(9232) Business & Management<br>(792) 1 0.002171
46 Applied Sciences<br>(29985) Social Sciences<br>(2032) Anthropology<br>(285) 1 0.002171
54 Arts & Humanities<br>(8457) Philosophy & Theology<br>(3385) Philosophy<br>(208) 1 0.002171
52 Arts & Humanities<br>(8457) Historical Studies<br>(3385) History of Social Sciences<br>(211) 1 0.002171
129 Health Sciences<br>(5341) Psychology & Cognitive Sciences<br>(1067) General Psychology & Cognitive Sciences<br>(19) 1 0.002171

175 rows × 5 columns

In [241]:
fig = px.sunburst(data, path=groups, values="percent",
                  color='Domain_English',title="Distribution of topics<br>(METRIX classification)", template='plotly')
fig.update_traces(hovertemplate='%{label}<br>%{value:.2f}%')
fig.show(config= dict(displayModeBar = False))

Domains¶

In [242]:
group = 'Domain_English'
data = wos.groupby(group, as_index=False)[record_col].nunique().sort_values(ascending=False, by=record_col)
data
Out[242]:
Domain_English UT (Unique WOS ID)
0 Applied Sciences 29985
5 Natural Sciences 8457
3 Health Sciences 5341
2 Economic & Social Sciences 1360
4 Multidisciplinary 847
1 Arts & Humanities 70
In [242]:
In [243]:
g = sns.barplot(data, x=record_col, y=group)
g.set_xlim(0,35000)
g.set_ylabel(None)
g.set_xlabel("Number of co-publications")
g.set_title("Distribution of Domains")
for i in g.containers:
    g.bar_label(i,fontsize=10)
In [244]:
fig = px.bar(data, x=record_col, y=group, color=group,
                              labels={
                     record_col: 'Number of co-publications',
                     group: "",
                 },
                title="Distribution of Domains", template='plotly')
fig.update_layout(showlegend=False, xaxis_tickformat='d',font_family="Montserrat")
fig.update_traces(hovertemplate='%{x:d}')
fig.add_shape(
        # Rectangle with reference to the plot
            type="rect",
            xref="paper",
            yref="paper",
            x0=0,
            y0=0,
            x1=1.0,
            y1=1.0,
            line=dict(
                color="black",
                 width=0.5,
             )
         )
fig.update_yaxes(
    showgrid=True,
    ticks="outside")
fig.update_xaxes(
    showgrid=True,
    ticks="outside")
fig.show(config= dict(displayModeBar = False))
In [245]:
# # define a function to divide each row's 'Count' by the value of the first year
# def divide_by_first_year(group):
#     group['relative_growth'] = group[record_col] / group.loc[group['Publication Year'] == group['Publication Year'].min(), record_col].values[0]
#     return group
#
#
#
# data = (wos.groupby(group)[record_col].nunique()
#         .unstack(fill_value=0).stack()
#         .reset_index()
#         .rename(columns={0:record_col})
#         .sort_values(ascending=False, by=group+[record_col]))
#
# # group by 'Topic'
# grouped = data.groupby('Domain_English')
# # apply the function to each group
# data = grouped.apply(divide_by_first_year).reset_index(drop=True)
# data['relative_growth'] = data['relative_growth']*100
In [245]:
In [246]:
group = ['Publication Year','Domain_English']
data = (wos.groupby(['Publication Year','Domain_English'])[record_col].nunique(dropna=False).unstack()
        .fillna(0)
        .stack()
        .reset_index()
        .rename(columns={0:record_col}))
data = data.merge(data[data[record_col]>0].sort_values(by=["Publication Year"], ascending=True).drop_duplicates(subset='Domain_English'),
                  on='Domain_English', suffixes=[None,"_relative_growth"])
data[record_col+"_relative_growth"] = (data[record_col]-data[record_col+"_relative_growth"])/data[record_col+"_relative_growth"]*100
data
Out[246]:
Publication Year Domain_English UT (Unique WOS ID) Publication Year_relative_growth UT (Unique WOS ID)_relative_growth
0 2011 Applied Sciences 490.0 2011 0.000000
1 2012 Applied Sciences 593.0 2011 21.020408
2 2013 Applied Sciences 738.0 2011 50.612245
3 2014 Applied Sciences 1031.0 2011 110.408163
4 2015 Applied Sciences 1201.0 2011 145.102041
... ... ... ... ... ...
67 2018 Natural Sciences 753.0 2011 316.022099
68 2019 Natural Sciences 999.0 2011 451.933702
69 2020 Natural Sciences 1232.0 2011 580.662983
70 2021 Natural Sciences 1403.0 2011 675.138122
71 2022 Natural Sciences 1665.0 2011 819.889503

72 rows × 5 columns

In [247]:
g=sns.lineplot(data.sort_values(ascending=True, by=group[-1]),y=record_col,x=group[0], hue=group[-1], marker="o")
g.set(xticks=list(range(2012,2022+1,2)))
g.legend(title=None)
g.set_xlabel(None)
g.set_ylabel(None)
g.set_title("Yearly output of co-publications")
Out[247]:
Text(0.5, 1.0, 'Yearly output of co-publications')
In [248]:
fig = px.line(data.sort_values(ascending=[True,True], by=[group[0],group[-1]]),y=record_col,x=group[0], color=group[-1], markers=True,                             labels={
                     record_col: 'Number of co-publications',
                     group[-1]: "Domain",
                 },
                title="Yearly output of co-publications", template='plotly')
fig.update_traces(hovertemplate='%{y:d}')
fig.update_layout(hovermode='x unified')
fig.add_shape(
        # Rectangle with reference to the plot
            type="rect",
            xref="paper",
            yref="paper",
            x0=0,
            y0=0,
            x1=1.0,
            y1=1.0,
            line=dict(
                color="black",
                 width=0.5,
             )
         )
fig.update_yaxes(
    showgrid=True,
    ticks="outside")
fig.update_xaxes(
    showgrid=True,
    ticks="outside")
fig.show(config= dict(displayModeBar = False))
In [250]:
fig = px.line(data.sort_values(ascending=[True,True], by=[group[0],group[-1]]),y=record_col+"_relative_growth",x=group[0], color=group[-1], markers=True,                             labels={
                     record_col+"_relative_growth": 'Rel. growth<br>in co-publications (%)',
                     group[-1]: "Domain",
                 },
                title="Relative growth in the output of co-publications", template='plotly')
fig.update_traces(hovertemplate='%{y:.2f}%')

fig.update_layout(hovermode='x unified',yaxis_tickformat='d',font_family="Montserrat")
fig.add_shape(
        # Rectangle with reference to the plot
            type="rect",
            xref="paper",
            yref="paper",
            x0=0,
            y0=0,
            x1=1.0,
            y1=1.0,
            line=dict(
                color="black",
                 width=0.5,
             )
         )
fig.update_yaxes(
    showgrid=True,
    ticks="outside")
fig.update_xaxes(
    showgrid=True,
    ticks="outside")
fig.update_yaxes(zeroline=True, zerolinewidth=0.5, zerolinecolor='grey')
fig.show(config= dict(displayModeBar = False))
In [17]:
In [18]:
pivot_data = pd.pivot_table(data, values=record_col, index=['Domain_English'],

                       columns=['Publication Year'], fill_value=0)
pivot_data
Out[18]:
Publication Year 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022
Domain_English
Applied Sciences 490 593 738 1031 1201 1535 1920 2808 3729 4446 5295 6199
Arts & Humanities 0 0 0 4 1 3 7 4 11 11 16 13
Economic & Social Sciences 20 22 29 28 34 40 84 105 160 211 252 375
Health Sciences 116 120 155 184 216 243 321 403 611 755 1035 1182
Multidisciplinary 15 21 43 52 57 64 75 76 83 97 115 149
Natural Sciences 181 223 298 318 380 437 568 753 999 1232 1403 1665
In [19]:
f, ax = plt.subplots(figsize=(9, 6))
g = sns.heatmap(pivot_data, annot=True, fmt="d", linewidths=.5, ax=ax)
g.set(xlabel="", ylabel="")
Out[19]:
[Text(0.5, 33.249999999999986, ''), Text(79.74999999999999, 0.5, '')]
In [20]:
import numpy as np
percent_pivot = pd.crosstab(data['Domain_English'], data['Publication Year'], values=data[record_col], aggfunc=np.sum, normalize='columns')*100
percent_pivot
Out[20]:
Publication Year 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022
Domain_English
Applied Sciences 59.610706 60.572012 58.432304 63.760049 63.578613 66.106804 64.537815 67.678959 66.672626 65.847156 65.241498 64.687467
Arts & Humanities 0.000000 0.000000 0.000000 0.247372 0.052938 0.129199 0.235294 0.096409 0.196674 0.162915 0.197141 0.135657
Economic & Social Sciences 2.433090 2.247191 2.296120 1.731602 1.799894 1.722653 2.823529 2.530730 2.860719 3.125000 3.104978 3.913180
Health Sciences 14.111922 12.257406 12.272367 11.379097 11.434621 10.465116 10.789916 9.713184 10.924370 11.181872 12.752587 12.334342
Multidisciplinary 1.824818 2.145046 3.404592 3.215832 3.017470 2.756245 2.521008 1.831767 1.483998 1.436611 1.416954 1.554837
Natural Sciences 22.019465 22.778345 23.594616 19.666048 20.116464 18.819983 19.092437 18.148952 17.861613 18.246445 17.286841 17.374517
In [21]:
f, ax = plt.subplots(figsize=(15, 6))
g = sns.heatmap(percent_pivot, annot=True, fmt='.2f', linewidths=.5, ax=ax, cbar=False)
for t in ax.texts: t.set_text(t.get_text() + " %")
g.set(xlabel="", ylabel="")
Out[21]:
[Text(0.5, 33.249999999999986, ''), Text(154.75, 0.5, '')]
In [146]:
# percent_pivot.T.plot(kind='bar',
#                     stacked=True,
#                     figsize=(10, 6))
In [147]:
# percent_pivot.T.plot(kind='bar',
#                         stacked=True,
#                         figsize=(15, 8))
#
# plt.legend(loc="lower left", ncol=2)
# # plt.ylabel("Release Year")
# # plt.xlabel("Proportion")
#
#
# for n, x in enumerate([*pivot_data.T.index.values]):
#     for (proportion, count, y_loc) in zip(percent_pivot.T.loc[x],
#                                           pivot_data.T.loc[x],
#                                           percent_pivot.T.loc[x].cumsum()):
#
#         plt.text(y=(y_loc - proportion) + (proportion / 2),
#                  x=n - 0.11,
#                  s=f'{count}',# ({np.round(proportion, 1)}%)',
#                  color="black",
#                  fontsize=8,
#                  fontweight="bold")
#
# plt.show()

Field¶

In [24]:
group = ['Publication Year',"Domain_English",'Field_English']
data = wos.groupby(group, as_index=False)[record_col].nunique().sort_values(ascending=False, by=group+[record_col])
data
Out[24]:
Publication Year Domain_English Field_English UT (Unique WOS ID)
233 2022 Natural Sciences Physics & Astronomy 596
232 2022 Natural Sciences Mathematics & Statistics 228
231 2022 Natural Sciences Earth & Environmental Sciences 409
230 2022 Natural Sciences Chemistry 251
229 2022 Natural Sciences Biology 181
... ... ... ... ...
4 2011 Applied Sciences Information & Communication Technologies 256
3 2011 Applied Sciences Engineering 166
2 2011 Applied Sciences Enabling & Strategic Technologies 53
1 2011 Applied Sciences Built Environment & Design 6
0 2011 Applied Sciences Agriculture, Fisheries & Forestry 9

234 rows × 4 columns

In [25]:
len(data[group[-2]].unique())
Out[25]:
6
In [25]:
In [26]:
data_complete = pd.DataFrame()

for cat in sorted(data[group[-2]].unique()):
    #data segment
    sub_data = data[data[group[-2]]==cat]
    sub_data = sub_data.complete({group[0]:range(int(data[group[0]].min()), int(data[group[0]].max()) + 1)}
                                 ,group[-1],fill_value=0)
    data_complete = pd.concat([data_complete,sub_data], ignore_index=True)
    #plot
    g=sns.lineplot(sub_data.sort_values(ascending=True, by=group[-1]),
                   y=record_col,x=group[0], hue=group[-1], marker="o")
    g.set(xticks=list(range(2012,2022+1,2)))
    g.legend(title=None)
    g.set_title(cat)
    g.yaxis.set_major_locator(MaxNLocator(integer=True))
    plt.show()
In [27]:
data_complete = pd.DataFrame()

# Creating subplot axes
fig, axes = plt.subplots(nrows=3,ncols=2,figsize=(15, 15))

for cat,ax in zip(sorted(data[group[-2]].unique()),axes.flatten()):
    #data segment
    sub_data = data[data[group[-2]]==cat]
    sub_data = sub_data.complete({group[0]:range(int(data[group[0]].min()), int(data[group[0]].max()) + 1)}
                                 ,group[-1],fill_value=0)
    data_complete = pd.concat([data_complete,sub_data], ignore_index=True)
    #plot
    g=sns.lineplot(sub_data.sort_values(ascending=True, by=group[-1]),
                   y=record_col,x=group[0], hue=group[-1], marker="o", ax=ax)
    g.set(xticks=list(range(2012,2022+1,2)))
    g.legend(title=None)
    g.set_title(cat)
    g.set_xlabel(None)
    g.set_ylabel(None)
    g.yaxis.set_major_locator(MaxNLocator(integer=True))
fig.suptitle("Number of co-publications in domains and respective fields", y=0.92)
plt.show()

SubField¶

In [28]:
group = ['Publication Year',"Domain_English",'Field_English',"SubField_English"]
data = wos.groupby(group, as_index=False)[record_col].nunique().sort_values(ascending=False, by=group+[record_col])
data
Out[28]:
Publication Year Domain_English Field_English SubField_English UT (Unique WOS ID)
1598 2022 Natural Sciences Physics & Astronomy Optics 134
1597 2022 Natural Sciences Physics & Astronomy Nuclear & Particle Physics 65
1596 2022 Natural Sciences Physics & Astronomy Mathematical Physics 10
1595 2022 Natural Sciences Physics & Astronomy General Physics 31
1594 2022 Natural Sciences Physics & Astronomy Fluids & Plasmas 79
... ... ... ... ... ...
4 2011 Applied Sciences Agriculture, Fisheries & Forestry Forestry 1
3 2011 Applied Sciences Agriculture, Fisheries & Forestry Food Science 1
2 2011 Applied Sciences Agriculture, Fisheries & Forestry Fisheries 2
1 2011 Applied Sciences Agriculture, Fisheries & Forestry Dairy & Animal Science 2
0 2011 Applied Sciences Agriculture, Fisheries & Forestry Agronomy & Agriculture 3

1599 rows × 5 columns

In [29]:
for cat in sorted(data[group[-2]].unique()):
    sub_data = data[data[group[-2]]==cat]
    sub_data = sub_data.complete({group[0]:range(int(data[group[0]].min()), int(data[group[0]].max()) + 1)}
                                 ,group[-1],fill_value=0)
    g=sns.lineplot(sub_data.sort_values(ascending=True, by=group[-1]),y=record_col,x=group[0],
                   hue=group[-1], marker="o", errorbar=None)
    g.set(xticks=list(range(2012,2022+1,2)))
    g.legend(title=None,bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0., ncols=math.ceil(len(g.legend_.texts)/12))
    g.set_title(f'Number or co-publications in {cat}')
    g.set_ylabel(None)
    plt.show()
In [31]:
from  matplotlib.ticker import FuncFormatter
import math
def orderOfMagnitude(number):
    return math.floor(math.log(number, 10))

def roundToNearest(number):
    order = orderOfMagnitude(number)
    # if order!=0:
    #     order+=1
    near = math.ceil(number/10**order)*10**order
    return near

Collabs¶

In [32]:
wos_univ_locations = wos_univ.merge(wos_country_types, on="Country")
wos_univ_locations.sample(100)
Out[32]:
UT (Unique WOS ID) Institution Country Institution_harm merge_iter Country_Type
41191 WOS:000538161600016 Anhui Univ China Anhui Univ 0 China
175692 WOS:000709411500003 Univ Porto Portugal Univ Porto 0 EU
75198 WOS:000831217100027 Zhejiang Univ China Zhejiang Univ 0 China
48614 WOS:000597938400003 Shanghai Jiao Tong Univ China Shanghai Jiao Tong Univ 0 China
133670 WOS:000411824101159 Univ Pisa Italy Univ Pisa 0 EU
... ... ... ... ... ... ...
2892 WOS:000293708200019 Natl Univ Def Technol China Natl Univ Def Technol 0 China
125259 WOS:000663324800010 INRAE France INRAE 0 EU
55780 WOS:000659952900011 Huazhong Univ Sci & Technol China Huazhong Univ Sci & Technol 0 China
138600 WOS:000744399000001 Brignone Clin Italy Brignone Clin 0 EU
31040 WOS:000471758500010 Chinese Acad Sci China Chinese Acad Sci 0 China

100 rows × 6 columns

In [33]:
wos_collabs = wos_univ_locations[wos_univ_locations["Country_Type"]!="Other"][[record_col,"Country"]].drop_duplicates()
In [34]:
collab_desc = wos_collabs[wos_collabs["Country"]!="China"]["Country"].value_counts().reset_index()
collab_desc["percent_of_copubs"] = collab_desc["count"]/wos_collabs[record_col].nunique()*100
collab_desc["percent_contrib_in_copubs"] = collab_desc["count"]/wos_collabs[record_col].size*100
collab_desc = collab_desc.merge(wos_country_types, on="Country")
collab_desc

c_dict = {"count":"Number of co-publications",
          "percent_of_copubs":"Percent of co-publications",
          "percent_contrib_in_copubs":"Contribution to co-publications"}


# Creating subplot axes
# fig, axes = plt.subplots(ncols=3,figsize=(15, 15))
# for c,ax in zip(c_dict.keys(),axes.flatten()):
for c in c_dict.keys():
    data = collab_desc[["Country",c,"Country_Type"]]
    plt.figure(figsize=(9,12))
    g = sns.barplot(data, x=c, y="Country", hue="Country_Type", dodge=False)
    g.set_xlim(0,roundToNearest(data[c].max()))
    g.set_ylabel(None)
    g.set_xlabel(c_dict.get(c))
    g.set_title(c_dict.get(c))
    g.legend(title=None, loc="right")
    for i in g.containers:
        g.bar_label(i,fontsize=10, fmt='%.1f%%' if 'percent' in c else '%.0f')
    if 'percent' in c:
        g.xaxis.set_major_locator(MaxNLocator(integer=True))
        vals = g.get_xticks()
        g.set_xticklabels([str(int(val))+'%' for val in vals])
    plt.show()

C:\Users\radvanyi\AppData\Local\Temp\ipykernel_30956\556627507.py:29: UserWarning:

FixedFormatter should only be used together with FixedLocator


C:\Users\radvanyi\AppData\Local\Temp\ipykernel_30956\556627507.py:29: UserWarning:

FixedFormatter should only be used together with FixedLocator
In [35]:
wos_collabs_EU = wos_univ_locations[~wos_univ_locations["Country_Type"].isin(["Other","China"])][[record_col,"Country"]].drop_duplicates()
wos_collabs_EU = wos_collabs_EU.merge(wos_collabs_EU, on=record_col)
EU_co_occur = pd.crosstab(wos_collabs_EU['Country_x'], wos_collabs_EU['Country_y'], values=wos_collabs_EU[record_col], aggfunc='nunique', normalize='all').fillna(0)

# Generate a mask for the upper triangle
mask = np.triu(np.ones_like(EU_co_occur, dtype=bool))

# Set up the matplotlib figure
f, ax = plt.subplots(figsize=(11, 9))

# Draw the heatmap with the mask and correct aspect ratio
g = sns.heatmap(EU_co_occur, mask=mask,
            square=True, linewidths=.5)

g.set_ylabel(None)
g.set_xlabel(None)
Out[35]:
Text(0.5, 71.74999999999994, '')
In [36]:
wos_collabs_EU = wos_univ_locations[~wos_univ_locations["Country_Type"].isin(["Other","China"])][[record_col,"Country"]].drop_duplicates()
wos_collabs_EU = wos_collabs_EU.merge(wos_collabs_EU, on=record_col)
wos_collabs_EU
EU_co_occur = pd.crosstab(wos_collabs_EU['Country_x'], wos_collabs_EU['Country_y'], values=wos_collabs_EU[record_col], aggfunc='nunique').fillna(0).astype(int)


# Generate a mask for the upper triangle
mask = np.triu(np.ones_like(EU_co_occur, dtype=bool))
data = np.where(mask,None,EU_co_occur)
EU_co_occur.columns
Out[36]:
Index(['Austria', 'Belgium', 'Bulgaria', 'Croatia', 'Cyprus', 'Czech Republic',
       'Denmark', 'Estonia', 'Finland', 'France', 'Germany', 'Greece',
       'Hungary', 'Ireland', 'Italy', 'Latvia', 'Lithuania', 'Luxembourg',
       'Malta', 'Netherlands', 'Norway', 'Poland', 'Portugal', 'Romania',
       'Slovakia', 'Slovenia', 'Spain', 'Sweden', 'Switzerland',
       'United Kingdom'],
      dtype='object', name='Country_y')
In [37]:
fig = px.imshow(data,
                labels=dict(x="Country (x)", y="Country (y)", color="Co-publication"),
                x=list(EU_co_occur.columns),
                y=list(EU_co_occur.index), title="Intraeuropean patterns"
               )
fig.update_layout(title_x=0.5,
                   width=1000, height=1000,
                   xaxis_showgrid=False,
                   yaxis_showgrid=False,
                   yaxis_autorange='reversed', template='plotly_white')
fig.update_xaxes(tickangle= -90)
fig.update_yaxes(
    ticks="outside")
fig.update_xaxes(
    ticks="outside")
fig.show(config= dict(displayModeBar = False))
In [122]:
collab_year = wos_collabs[wos_collabs["Country"]!="China"].copy()
collab_year = collab_year.merge(wos_country_types, on="Country").merge(wos[[record_col,"Publication Year"]],on=record_col).drop_duplicates()
data = collab_year.groupby(["Publication Year",'Country_Type'],as_index=False)[record_col].nunique()


g=sns.lineplot(data,y=record_col,x="Publication Year", hue="Country_Type", marker="o")
g.set(xticks=list(range(2012,2022+1,2)))
g.legend(title=None)
g.set_xlabel(None)
g.set_ylabel(None)
g.set_title("Yearly output of co-publications with China")
Out[122]:
Text(0.5, 1.0, 'Yearly output of co-publications with China')
In [123]:
data = (collab_year.groupby(['Publication Year',"Country"])[record_col]
        .nunique(dropna=False).unstack()
        .fillna(0)
        .stack()
        .reset_index()
        .rename(columns={0:record_col}))
data = data.merge(data[data[record_col]>0].sort_values(by=["Publication Year"], ascending=True).drop_duplicates(subset="Country"),
                  on=["Country"], suffixes=[None,"_relative_growth"])
data[record_col+"_relative_growth"] = (data[record_col]-data[record_col+"_relative_growth"])/data[record_col+"_relative_growth"]*100
data
Out[123]:
Publication Year Country UT (Unique WOS ID) Publication Year_relative_growth UT (Unique WOS ID)_relative_growth
0 2011 Austria 22.0 2011 0.000000
1 2012 Austria 24.0 2011 9.090909
2 2013 Austria 26.0 2011 18.181818
3 2014 Austria 39.0 2011 77.272727
4 2015 Austria 50.0 2011 127.272727
... ... ... ... ... ...
355 2018 United Kingdom 1837.0 2011 406.060606
356 2019 United Kingdom 2430.0 2011 569.421488
357 2020 United Kingdom 3108.0 2011 756.198347
358 2021 United Kingdom 3718.0 2011 924.242424
359 2022 United Kingdom 4245.0 2011 1069.421488

360 rows × 5 columns

In [88]:
data["ISO3"] = cc.pandas_convert(series=data["Country"], to='ISO3')
fig = px.choropleth(data, locations="ISO3", color=record_col, hover_name="Country",
                    animation_frame='Publication Year', scope="europe", template='plotly', range_color=[data[record_col].min(),data[record_col].max()])
fig.show()
In [89]:
data["ISO3"] = cc.pandas_convert(series=data["Country"], to='ISO3')
fig = px.choropleth(data, locations="ISO3", color=record_col+"_relative_growth", hover_name="Country",
                    animation_frame='Publication Year', scope="europe", template='plotly',
                    range_color=[data[record_col+"_relative_growth"].min(),data[record_col+"_relative_growth"].max()])
fig.show()
In [157]:
data = data.merge(wos_country_types, on='Country')
data
Out[157]:
Publication Year Country UT (Unique WOS ID) Publication Year_relative_growth UT (Unique WOS ID)_relative_growth Country_Type Eurovoc_Class
0 2011 Austria 22.0 2011 0.000000 EU Western Europe
1 2012 Austria 24.0 2011 9.090909 EU Western Europe
2 2013 Austria 26.0 2011 18.181818 EU Western Europe
3 2014 Austria 39.0 2011 77.272727 EU Western Europe
4 2015 Austria 50.0 2011 127.272727 EU Western Europe
... ... ... ... ... ... ... ...
355 2018 United Kingdom 1837.0 2011 406.060606 Non-EU associate Western Europe
356 2019 United Kingdom 2430.0 2011 569.421488 Non-EU associate Western Europe
357 2020 United Kingdom 3108.0 2011 756.198347 Non-EU associate Western Europe
358 2021 United Kingdom 3718.0 2011 924.242424 Non-EU associate Western Europe
359 2022 United Kingdom 4245.0 2011 1069.421488 Non-EU associate Western Europe

360 rows × 7 columns

In [190]:
# fig = px.line(data.sort_values(ascending=True, by='Publication Year'),y=record_col,x='Publication Year', color="Eurovoc_Class",line_group="Country", markers=True,
#               labels={
#                      record_col: 'Number of co-publications',
#                   "Eurovoc_Class": "Region"
#                  },
#                 title="Yearly output of co-publications", template='plotly',hover_name= "Country")
# fig.update_traces(hovertemplate='<b>%{hovertext}</b><br>%{x}<br>Co-publications: %{y}')
# # fig.update_layout(hovermode='x unified')
# fig.add_shape(
#         # Rectangle with reference to the plot
#             type="rect",
#             xref="paper",
#             yref="paper",
#             x0=0,
#             y0=0,
#             x1=1.0,
#             y1=1.0,
#             line=dict(
#                 color="black",
#                  width=0.5,
#              )
#          )
# fig.update_yaxes(
#     showgrid=True,
#     ticks="outside")
# fig.update_xaxes(
#     showgrid=True,
#     ticks="outside")
# fig.show(config= dict(displayModeBar = False))
In [165]:
# fig.data[0].hovertemplate
Out[165]:
'<b>%{hovertext}</b><br><br>Eurovoc_Class=Western Europe<br>Country=Austria<br>Publication Year=%{x}<br>Number of co-publications=%{y}<extra></extra>'
In [189]:
# fig = px.line(data.sort_values(ascending=True, by='Publication Year'),
#               y=record_col+"_relative_growth",
#               x='Publication Year',
#               color="Eurovoc_Class",line_group="Country",markers=True,
#               labels={
#                      record_col+"_relative_growth": 'Relative growth of co-publications (%)',"Eurovoc_Class": "Region"
#                  },
#                 title="Relative growth of co-publications<br>(baseline: 2011)", template='plotly',hover_name= "Country")
# fig.update_traces(hovertemplate='<b>%{hovertext}</b><br>%{x}<br>Relative growth: %{y}%')
# fig.add_shape(
#         # Rectangle with reference to the plot
#             type="rect",
#             xref="paper",
#             yref="paper",
#             x0=0,
#             y0=0,
#             x1=1.0,
#             y1=1.0,
#             line=dict(
#                 color="black",
#                  width=0.5,
#              )
#          )
# fig.update_yaxes(
#     showgrid=True,
#     ticks="outside")
# fig.update_xaxes(
#     showgrid=True,
#     ticks="outside")
# fig.show(config= dict(displayModeBar = False))
In [193]:
from plotly.subplots import make_subplots
import plotly.graph_objects as go

figsuper = make_subplots(rows=1, cols=2, subplot_titles=["Yearly output of co-publications","Relative growth of co-publications<br>(baseline: 2011)"])

fig = px.line(data.sort_values(ascending=True, by='Publication Year'),
              y=record_col,
              x='Publication Year',
              color="Eurovoc_Class",
              line_group="Country",
              markers=True,
              labels={
                     record_col: 'Number of co-publications',
                  "Eurovoc_Class": "Region"
                 },
                title="Yearly output of co-publications",hover_name= "Country")
fig.update_traces(hovertemplate='<b>%{hovertext}</b><br>%{x}<br>Co-publications: %{y}')

for trace in list(fig.select_traces()):
    figsuper.add_trace(trace,
        row=1, col=1
    )

fig = px.line(data.sort_values(ascending=True, by='Publication Year'),
              y=record_col+"_relative_growth",
              x='Publication Year',
              color="Eurovoc_Class",line_group="Country",markers=True,
              labels={
                     record_col+"_relative_growth": 'Relative growth of co-publications (%)',"Eurovoc_Class": "Region"
                 },
                title="Relative growth of co-publications<br>(baseline: 2011)", template='plotly',hover_name= "Country")
fig.update_traces(hovertemplate='<b>%{hovertext}</b><br>%{x}<br>Relative growth: %{y}%')
fig.add_shape(
        # Rectangle with reference to the plot
            type="rect",
            xref="paper",
            yref="paper",
            x0=0,
            y0=0,
            x1=1.0,
            y1=1.0,
            line=dict(
                color="black",
                 width=0.5,
             )
         )

for trace in list(fig.select_traces()):
    trace.showlegend=False
    trace
    figsuper.add_trace(trace,
        row=1, col=2
    )

figsuper.update_yaxes(
    showgrid=True,showline=True, linewidth=1, linecolor='black', mirror=True,
    ticks="outside")
figsuper.update_xaxes(
    showgrid=True,showline=True, linewidth=1, linecolor='black', mirror=True,
    ticks="outside")
figsuper.update_layout({'template':"plotly"})
figsuper.show(config= dict(displayModeBar = False))
In [40]:
year_pivot = pd.crosstab(collab_year['Country'], collab_year['Publication Year'], values=collab_year[record_col], aggfunc='nunique').fillna(0).astype(int)
year_pivot
Out[40]:
Publication Year 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022
Country
Austria 22 24 26 39 50 57 72 89 138 137 185 205
Belgium 34 38 40 65 71 81 90 133 179 213 242 292
Bulgaria 4 5 8 9 7 19 21 18 10 25 32 19
Croatia 1 2 6 8 10 7 10 19 27 29 33 35
Cyprus 2 1 5 5 5 5 8 7 15 28 36 43
Czech Republic 13 15 16 21 20 36 37 56 64 81 93 123
Denmark 35 33 40 59 68 74 101 195 234 245 293 343
Estonia 3 3 7 10 12 10 15 15 16 38 45 39
Finland 31 35 44 82 100 125 126 198 241 256 289 380
France 117 130 174 231 269 325 348 491 648 691 807 858
Germany 123 172 192 273 310 365 456 604 801 907 1210 1386
Greece 15 18 19 32 35 50 47 81 114 122 139 181
Hungary 11 11 21 16 20 38 34 47 61 61 83 90
Ireland 13 16 22 31 27 45 66 72 84 116 167 187
Italy 51 70 84 116 178 187 247 325 441 571 641 811
Latvia 0 0 1 0 1 8 10 15 10 9 13 18
Lithuania 1 2 10 4 4 13 12 23 38 36 38 38
Luxembourg 2 3 3 1 8 9 13 15 18 22 35 51
Malta 1 0 0 0 1 1 0 0 6 2 7 10
Netherlands 72 64 77 103 139 166 220 297 408 470 529 655
Norway 30 42 60 76 67 88 104 134 222 253 304 311
Poland 17 31 37 57 73 82 98 110 138 181 276 353
Portugal 16 23 35 41 45 58 79 119 136 147 204 212
Romania 7 15 13 16 25 26 37 57 64 55 48 62
Slovakia 9 6 6 10 12 22 18 27 27 34 36 45
Slovenia 7 7 10 12 17 27 22 47 54 31 48 40
Spain 50 49 69 112 138 185 232 273 356 386 473 640
Sweden 34 50 59 83 113 170 233 232 385 359 428 510
Switzerland 37 50 54 74 74 95 155 195 233 263 349 447
United Kingdom 363 417 531 660 781 979 1350 1837 2430 3108 3718 4245
In [41]:
f, ax = plt.subplots(figsize=(15, 15))
g = sns.heatmap(year_pivot, annot=True, fmt="d", linewidths=.5, ax=ax)
g.set(xlabel="", ylabel="")
for i in range(year_pivot.shape[0]+1):
    ax.axhline(i, color='white', lw=10)
In [42]:
year_percent_pivot = pd.crosstab(collab_year['Country'], collab_year['Publication Year'], values=collab_year[record_col], aggfunc='nunique', normalize='columns').fillna(0)*100
year_percent_pivot
Out[42]:
Publication Year 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022
Country
Austria 1.962533 1.801802 1.557819 1.736420 1.865672 1.699970 1.689744 1.552958 1.816267 1.543488 1.712804 1.623248
Belgium 3.033006 2.852853 2.396645 2.894034 2.649254 2.415747 2.112180 2.320712 2.355883 2.399730 2.240533 2.312139
Bulgaria 0.356824 0.375375 0.479329 0.400712 0.261194 0.566657 0.492842 0.314081 0.131614 0.281658 0.296269 0.150447
Croatia 0.089206 0.150150 0.359497 0.356189 0.373134 0.208768 0.234687 0.331530 0.355357 0.326724 0.305527 0.277140
Cyprus 0.178412 0.075075 0.299581 0.222618 0.186567 0.149120 0.187749 0.122143 0.197420 0.315457 0.333302 0.340486
Czech Republic 1.159679 1.126126 0.958658 0.934996 0.746269 1.073665 0.868341 0.977142 0.842327 0.912573 0.861031 0.973949
Denmark 3.122212 2.477477 2.396645 2.626892 2.537313 2.206979 2.370336 3.402548 3.079758 2.760252 2.712712 2.715971
Estonia 0.267618 0.225225 0.419413 0.445236 0.447761 0.298240 0.352030 0.261734 0.210582 0.428121 0.416628 0.308813
Finland 2.765388 2.627628 2.636309 3.650935 3.731343 3.728005 2.957052 3.454894 3.171887 2.884182 2.675678 3.008948
France 10.437110 9.759760 10.425404 10.284951 10.037313 9.692812 8.167097 8.567440 8.528560 7.785038 7.471530 6.793887
Germany 10.972346 12.912913 11.503895 12.154942 11.567164 10.885774 10.701713 10.539173 10.542248 10.218567 11.202666 10.974741
Greece 1.338091 1.351351 1.138406 1.424755 1.305970 1.491202 1.103027 1.413366 1.500395 1.374493 1.286918 1.433209
Hungary 0.981267 0.825826 1.258238 0.712378 0.746269 1.133313 0.797935 0.820101 0.802843 0.687247 0.768447 0.712645
Ireland 1.159679 1.201201 1.318155 1.380232 1.007463 1.342082 1.548932 1.256325 1.105554 1.306895 1.546153 1.480719
Italy 4.549509 5.255255 5.032954 5.164737 6.641791 5.577095 5.796761 5.670913 5.804159 6.433078 5.934636 6.421728
Latvia 0.000000 0.000000 0.059916 0.000000 0.037313 0.238592 0.234687 0.261734 0.131614 0.101397 0.120359 0.142529
Lithuania 0.089206 0.150150 0.599161 0.178094 0.149254 0.387712 0.281624 0.401326 0.500132 0.405588 0.351819 0.300895
Luxembourg 0.178412 0.225225 0.179748 0.044524 0.298507 0.268416 0.305093 0.261734 0.236904 0.247859 0.324044 0.403832
Malta 0.089206 0.000000 0.000000 0.000000 0.037313 0.029824 0.000000 0.000000 0.078968 0.022533 0.064809 0.079183
Netherlands 6.422837 4.804805 4.613541 4.585931 5.186567 4.950790 5.163107 5.182342 5.369834 5.295178 4.897695 5.186476
Norway 2.676182 3.153153 3.594967 3.383793 2.500000 2.624515 2.440742 2.338161 2.921822 2.850383 2.814554 2.462586
Poland 1.516503 2.327327 2.216896 2.537845 2.723881 2.445571 2.299930 1.919386 1.816267 2.039207 2.555319 2.795154
Portugal 1.427297 1.726727 2.097064 1.825467 1.679104 1.729794 1.854025 2.076426 1.789945 1.656151 1.888714 1.678676
Romania 0.624442 1.126126 0.778910 0.712378 0.932836 0.775425 0.868341 0.994591 0.842327 0.619648 0.444403 0.490934
Slovakia 0.802855 0.450450 0.359497 0.445236 0.447761 0.656129 0.422436 0.471122 0.355357 0.383055 0.333302 0.356323
Slovenia 0.624442 0.525526 0.599161 0.534283 0.634328 0.805249 0.516311 0.820101 0.710713 0.349256 0.444403 0.316731
Spain 4.460303 3.678679 4.134212 4.986643 5.149254 5.517447 5.444731 4.763567 4.685444 4.348806 4.379224 5.067701
Sweden 3.033006 3.753754 3.535051 3.695459 4.216418 5.070086 5.468200 4.048159 5.067123 4.044615 3.962596 4.038324
Switzerland 3.300624 3.753754 3.235470 3.294746 2.761194 2.833284 3.637644 3.402548 3.066596 2.963046 3.231182 3.539473
United Kingdom 32.381802 31.306306 31.815458 29.385574 29.141791 29.197733 31.682704 32.053743 31.982101 35.015773 34.422739 33.613113
In [43]:
f, ax = plt.subplots(figsize=(15, 15))
g = sns.heatmap(year_percent_pivot, annot=True, fmt='.1f', linewidths=(.5), ax=ax, cbar=False)
for t in ax.texts: t.set_text(t.get_text() + " %")
g.set(xlabel="", ylabel="")
for i in range(year_percent_pivot.shape[1]+1):
    ax.axvline(i, color='white', lw=10)
In [43]:
In [44]:
# Institutional collab
In [251]:
wos_univ_locations = wos_univ.merge(wos_country_types, on="Country")
wos_univ_collabs = wos_univ_locations[wos_univ_locations["Country_Type"]!="Other"][[record_col,"Country","Institution_harm","Country_Type","Eurovoc_Class"]].drop_duplicates()
wos_univ_collabs["ISO3"] = cc.pandas_convert(series=wos_univ_collabs["Country"], to='ISO3')
wos_univ_collabs["Institution_harm_label"] = wos_univ_collabs["Institution_harm"] + " ("+wos_univ_collabs["ISO3"]+ ")"
wos_univ_collabs.sample(100)
Out[251]:
UT (Unique WOS ID) Country Institution_harm Country_Type Eurovoc_Class ISO3 Institution_harm_label
86064 WOS:000640648500012 Netherlands Eindhoven Univ Technol EU Western Europe NLD Eindhoven Univ Technol (NLD)
115079 WOS:000798227800073 United Kingdom Univ Leeds Non-EU associate Western Europe GBR Univ Leeds (GBR)
97887 WOS:000431633800004 United Kingdom Francis Crick Inst Non-EU associate Western Europe GBR Francis Crick Inst (GBR)
147070 WOS:000460118200077 Germany Johannes Gutenberg Univ Mainz EU Western Europe DEU Johannes Gutenberg Univ Mainz (DEU)
93724 WOS:000371153900007 United Kingdom Royal Marsden Fdn Trust Non-EU associate Western Europe GBR Royal Marsden Fdn Trust (GBR)
... ... ... ... ... ... ... ...
75906 WOS:000838382400015 China China Aerosp Sci & Ind Corp China China CHN China Aerosp Sci & Ind Corp (CHN)
153124 WOS:000802927600001 Germany Rhein Westfal Aachen EU Western Europe DEU Rhein Westfal Aachen (DEU)
82197 WOS:000911585800012 China Chinese Acad Med Sci China China CHN Chinese Acad Med Sci (CHN)
150080 WOS:000605979600009 Germany Univ Med Ctr Goettingen EU Western Europe DEU Univ Med Ctr Goettingen (DEU)
112004 WOS:000717881300001 United Kingdom Imperial Coll London Non-EU associate Western Europe GBR Imperial Coll London (GBR)

100 rows × 7 columns

In [113]:
color_discrete_map= {'China': '#EF553B',
                                      'EU': '#636EFA',
                                      'Non-EU associate': '#00CC96'}
In [261]:
TOPN = 25


wos_univ_ch = wos_univ_collabs[wos_univ_collabs["Country_Type"]=="China"]
wos_univ_eu = wos_univ_collabs[wos_univ_collabs["Country_Type"]!="China"]

wos_univ_eu_strict = wos_univ_collabs[wos_univ_collabs["Country_Type"]=="EU"]

data_eu = (wos_univ_eu.groupby(["Country","Institution_harm_label","Country_Type"], as_index=False)[record_col].nunique()
           .sort_values(by=record_col,ascending=False).head(TOPN).copy()).sort_values(by="Country_Type")

data_eu_strict = (wos_univ_eu_strict.groupby(["Country","Institution_harm_label","Eurovoc_Class"], as_index=False)[record_col].nunique()
           .sort_values(by=record_col,ascending=False).head(TOPN).copy())

data_ch = (wos_univ_ch.groupby(["Country","Institution_harm","Country_Type"], as_index=False)[record_col].nunique()
           .sort_values(by=record_col,ascending=False).head(TOPN).copy())


for data,c_scope, y_lab, col_by, pat in zip([data_eu,data_eu_strict,data_ch],
                        ["European countries in scope","EU-28 only","China"],
                        ["Institution_harm_label","Institution_harm_label","Institution_harm"],
                        ["Country","Eurovoc_Class","Country_Type"],
                                       ["Country_Type",None,None]):
    fig = px.bar(data, x=record_col, y=y_lab, color=col_by, color_discrete_map=color_discrete_map,pattern_shape=pat,
                              labels={
                     record_col: 'Number of co-publications',
                     "Institution_harm": "Institution",
                                  "Institution_harm_label": "Institution",
                                  "Country_Type":"Country type",
                                  "Eurovoc_Class":"Region"
                 },
                title=f"Most visible institutions (top {TOPN} within {c_scope})", template='plotly')
    fig.update_layout(xaxis_tickformat='d',font_family="Montserrat",yaxis={'categoryorder':'total ascending'},
                                         width=1000, height=1000,)
    fig.update_traces(hovertemplate='%{x:d}')
    fig.add_shape(
            # Rectangle with reference to the plot
                type="rect",
                xref="paper",
                yref="paper",
                x0=0,
                y0=0,
                x1=1.0,
                y1=1.0,
                line=dict(
                    color="black",
                     width=0.5,
                 )
             )
    fig.update_yaxes(
        showgrid=True,
        ticks="outside")
    fig.update_xaxes(
        showgrid=True,
        ticks="outside")
    fig.show(config= dict(displayModeBar = False))
In [47]:
wos_univ_test = wos_univ_locations[wos_univ_locations["Country_Type"]!="Other"][[record_col,"Country","Institution","Institution_harm","Country_Type"]].drop_duplicates()
www = wos_univ_test.groupby(["Institution","Institution_harm"], as_index=False)[record_col].nunique()
www[www["Institution_harm"]=="Chinese Acad Sci"]
Out[47]:
Institution Institution_harm UT (Unique WOS ID)
16 Chinese Acad Sci Chinese Acad Sci 1
3149 Chinese Acad Sci Chinese Acad Sci 4614
3153 Chinese Acad Sci AIRCAS Chinese Acad Sci 2
3155 Chinese Acad Sci CAREERI CAS Chinese Acad Sci 1
3157 Chinese Acad Sci CASIA Chinese Acad Sci 8
3159 Chinese Acad Sci GUCAS Chinese Acad Sci 2
3160 Chinese Acad Sci IAP Chinese Acad Sci 1
3161 Chinese Acad Sci IECAS Chinese Acad Sci 2
3162 Chinese Acad Sci IME CAS Chinese Acad Sci 1
3163 Chinese Acad Sci IMECAS Chinese Acad Sci 1
3164 Chinese Acad Sci ITP CAS Chinese Acad Sci 1
3166 Chinese Acad Sci NAOC Chinese Acad Sci 1
3167 Chinese Acad Sci NAOC CAS Chinese Acad Sci 2
13501 RCEES Chinese Acad Sci Chinese Acad Sci 1
19499 ZIAT Chinese Acad Sci Chinese Acad Sci 1
In [265]:
wos_univ_ch = wos_univ_collabs[wos_univ_collabs["Country_Type"]=="China"]
wos_univ_eu = wos_univ_collabs[wos_univ_collabs["Country_Type"]!="China"]

wos_univ_dipol = wos_univ_eu.merge(wos_univ_ch, on=record_col, suffixes=('_eu', '_ch')).merge(wos[[record_col,"Domain_English","Field_English","SubField_English"]], on =record_col)
wos_univ_dipol.sample(100)
Out[265]:
UT (Unique WOS ID) Country_eu Institution_harm_eu Country_Type_eu Eurovoc_Class_eu ISO3_eu Institution_harm_label_eu Country_ch Institution_harm_ch Country_Type_ch Eurovoc_Class_ch ISO3_ch Institution_harm_label_ch Domain_English Field_English SubField_English
329695 WOS:000702508000001 Greece Sch Pedag & Technol Educ EU Southern Europe GRC Sch Pedag & Technol Educ (GRC) China Huanghuai Univ China China CHN Huanghuai Univ (CHN) Applied Sciences Engineering Geological & Geomatics Engineering
103762 WOS:000696019400001 France Inst Phys 2 Infinis Lyon EU Western Europe FRA Inst Phys 2 Infinis Lyon (FRA) China Fudan Univ China China CHN Fudan Univ (CHN) Natural Sciences Physics & Astronomy Nuclear & Particle Physics
237699 WOS:000353892300005 France SUBATECH EU Western Europe FRA SUBATECH (FRA) China Shanghai Inst Appl Phys China China CHN Shanghai Inst Appl Phys (CHN) Natural Sciences Physics & Astronomy Nuclear & Particle Physics
123610 WOS:000571262000008 Luxembourg Luxembourg Ctr Syst Biomed EU Western Europe LUX Luxembourg Ctr Syst Biomed (LUX) China Wuhan Univ Sci & Technol China China CHN Wuhan Univ Sci & Technol (CHN) Applied Sciences Information & Communication Technologies Artificial Intelligence & Image Processing
77119 WOS:000494411700001 Germany Tech Univ Berlin EU Western Europe DEU Tech Univ Berlin (DEU) China Dalian Univ Technol China China CHN Dalian Univ Technol (CHN) Economic & Social Sciences Social Sciences Information & Library Sciences
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
317783 WOS:000747086300011 Germany Tech Univ Dresden EU Western Europe DEU Tech Univ Dresden (DEU) China East China Univ Sci & Technol China China CHN East China Univ Sci & Technol (CHN) Health Sciences Biomedical Research Developmental Biology
118549 WOS:000830403500012 Italy Univ Firenze EU Southern Europe ITA Univ Firenze (ITA) China Peking Univ China China CHN Peking Univ (CHN) Natural Sciences Physics & Astronomy Nuclear & Particle Physics
2175 WOS:000345858500052 Italy Univ Genoa EU Southern Europe ITA Univ Genoa (ITA) China Peking Univ China China CHN Peking Univ (CHN) Natural Sciences Physics & Astronomy Nuclear & Particle Physics
312657 WOS:000467489901126 Germany Tech Univ Munich EU Western Europe DEU Tech Univ Munich (DEU) China Fudan Univ China China CHN Fudan Univ (CHN) Health Sciences Clinical Medicine Nuclear Medicine & Medical Imaging
269060 WOS:000679252300003 United Kingdom De Montfort Univ Non-EU associate Western Europe GBR De Montfort Univ (GBR) China Beijing Univ Technol China China CHN Beijing Univ Technol (CHN) Applied Sciences Information & Communication Technologies Artificial Intelligence & Image Processing

100 rows × 16 columns

In [266]:
fig = px.parallel_categories(wos_univ_dipol[["Country_eu","Domain_English","Country_ch"]])
fig.show()
In [271]:
data_ch.columns
Out[271]:
Index(['Country', 'Institution_harm', 'Country_Type', 'UT (Unique WOS ID)'], dtype='object')
In [272]:
subfilter = ((wos_univ_dipol["Institution_harm_label_eu"].isin(data_eu["Institution_harm_label"]))&
             (wos_univ_dipol["Institution_harm_ch"].isin(data_ch["Institution_harm"])))

fig = px.parallel_categories(wos_univ_dipol[subfilter][["Country_eu","Domain_English","Country_ch"]])
fig.show()
In [282]:
subfilter = ((wos_univ_dipol["Institution_harm_label_eu"].isin(data_eu["Institution_harm_label"]))&
             (wos_univ_dipol["Institution_harm_ch"].isin(data_ch["Institution_harm"])))

fig = px.parallel_categories(wos_univ_dipol[subfilter][["Country_eu","Institution_harm_eu","Domain_English","Institution_harm_ch"]])
fig.show()
In [283]:
sub_df =wos_univ_dipol[subfilter]

inst_co_occur = pd.crosstab(sub_df['Institution_harm_label_eu'], sub_df['Institution_harm_ch'],
                            values=sub_df[record_col], aggfunc='nunique').fillna(0).astype(int)
inst_co_occur

mask = np.triu(np.ones_like(inst_co_occur, dtype=bool))
data = np.where(mask,inst_co_occur,inst_co_occur)

fig = px.imshow(data,
                labels=dict(x="Institute (CH)", y="Institute (EU)", color="Co-publication"),
                x=list(inst_co_occur.columns),
                y=list(inst_co_occur.index), title=f"Most visible institutions (top {TOPN} within Europe)"
               )
fig.update_layout(title_x=0.5,
                   width=1000, height=1000,
                   xaxis_showgrid=False,
                   yaxis_showgrid=False,
                   yaxis_autorange='reversed', template='plotly_white')
fig.update_xaxes(tickangle= -90)
fig.update_yaxes(
    ticks="outside")
fig.update_xaxes(
    ticks="outside")
fig.show(config= dict(displayModeBar = False))
In [284]:
subfilter = ((wos_univ_dipol["Institution_harm_label_eu"].isin(data_eu_strict["Institution_harm_label"]))&
             (wos_univ_dipol["Institution_harm_ch"].isin(data_ch["Institution_harm"])))

fig = px.parallel_categories(wos_univ_dipol[subfilter][["Country_eu","Institution_harm_eu","Domain_English","Institution_harm_ch"]])
fig.show()
In [285]:
sub_df =wos_univ_dipol[subfilter]

inst_co_occur = pd.crosstab(sub_df['Institution_harm_label_eu'], sub_df['Institution_harm_ch'],
                            values=sub_df[record_col], aggfunc='nunique').fillna(0).astype(int)
inst_co_occur

mask = np.triu(np.ones_like(inst_co_occur, dtype=bool))
data = np.where(mask,inst_co_occur,inst_co_occur)

fig = px.imshow(data,
                labels=dict(x="Institute (CH)", y="Institute (EU)", color="Co-publication"),
                x=list(inst_co_occur.columns),
                y=list(inst_co_occur.index), title=f"Most visible institutions (top {TOPN} within Europe)"
               )
fig.update_layout(title_x=0.5,
                   width=1000, height=1000,
                   xaxis_showgrid=False,
                   yaxis_showgrid=False,
                   yaxis_autorange='reversed', template='plotly_white')
fig.update_xaxes(tickangle= -90)
fig.update_yaxes(
    ticks="outside")
fig.update_xaxes(
    ticks="outside")
fig.show(config= dict(displayModeBar = False))
In [ ]:
import dash_bio
In [ ]: