Location of people

This page shows the location (by continent or country) of the Open Seeds people given their different roles

import geopandas
import matplotlib.pyplot as plt
import pandas as pd

path = geopandas.datasets.get_path('naturalearth_lowres')
world_df = geopandas.read_file(path)
baseurl = "https://raw.githubusercontent.com/open-life-science/open-life-science.github.io/main/_data/artifacts/openseeds/"
cohort_nb = 9

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
Cell In[2], line 1
----> 1 path = geopandas.datasets.get_path('naturalearth_lowres')
      2 world_df = geopandas.read_file(path)
      3 baseurl = "https://raw.githubusercontent.com/open-life-science/open-life-science.github.io/main/_data/artifacts/openseeds/"

File /usr/share/miniconda/envs/ols-stats/lib/python3.12/site-packages/geopandas/datasets/__init__.py:18, in get_path(dataset)
     12 error_msg = (
     13     "The geopandas.dataset has been deprecated and was removed in GeoPandas "
     14     f"1.0. You can get the original '{dataset}' data from "
     15     f"{ne_message if 'natural' in dataset else nybb_message}"
     16 )
     17 if dataset in _prev_available:
---> 18     raise AttributeError(error_msg)
     19 else:
     20     error_msg = (
     21         "The geopandas.dataset has been deprecated and "
     22         "was removed in GeoPandas 1.0. New sample datasets are now available "
     23         "in the geodatasets package (https://geodatasets.readthedocs.io/en/latest/)"
     24     )

AttributeError: The geopandas.dataset has been deprecated and was removed in GeoPandas 1.0. You can get the original 'naturalearth_lowres' data from https://www.naturalearthdata.com/downloads/110m-cultural-vectors/.

people_df = pd.read_csv(f"{baseurl}people.csv", index_col=0)

roles_df = {}
roles = []
for r in ["role", "participant", "mentor", "expert", "speaker", "facilitator", "organizer"]:
    role = r.capitalize()
    roles.append(role)
    roles_df[role] = pd.read_csv(f"{baseurl}/roles/{r}.csv", index_col=0)

Continents

Proportion of people without continent information

people_df.continent.isna().sum() / len(people_df.continent)

0.07705479452054795

def plot_role_percentage(data, title, ylab):
    '''
    Generate role percentage plots
    
    :param data: data to plot
    :param title: title for plots
    :param ylab: ylab
    '''
    fig, ax = plt.subplots()
    fig.set_dpi(300)
    (data
         .drop(columns=['TOTAL'])
         .transpose()
         .plot(ax=ax, colormap='tab20c'))
    plt.title(title)
    plt.xlabel('Cohorts')
    plt.ylabel(ylab)
    ax.legend(
        loc='center left',
        bbox_to_anchor=(1, 0.5),
        frameon=False,
        fontsize='x-small')
    
    fig, ax = plt.subplots()
    fig.set_dpi(300)
    (data
         .drop(columns=['TOTAL'])
         .transpose()
         .plot.bar(stacked=True, ax=ax, colormap='tab20c'))
    plt.title(title)
    plt.xlabel('Cohorts')
    plt.ylabel(ylab)
    ax.legend(
        loc='center left',
        bbox_to_anchor=(1, 0.5),
        frameon=False,
        fontsize='x-small')

All roles

continents_df = {}
continents_perc_df = {}
all_roles_continent = {}
for r in roles:
    continents_df[r] = (roles_df[r].groupby(['continent']).count()
        .rename(columns = {'country_3': 'total'})
        .drop(columns = ['city','first-name','last-name','pronouns','country','longitude','latitude']))
    continents_df[r].columns = [x.upper() for x in continents_df[r].columns]
    all_roles_continent[r] = continents_df[r].sum(axis=1)
    continents_perc_df[r] = 100 * continents_df[r] / continents_df[r].sum(axis = 0)
continents_perc_df['Role']

	TOTAL	OLS-1	OLS-2	OLS-3	OLS-4	OLS-5	OLS-6	OLS-7	OLS-8
continent
Africa	16.377649	8.974359	13.970588	6.428571	3.921569	13.28125	19.587629	30.0	25.185185
Asia	8.477842	7.692308	3.676471	13.571429	7.843137	10.15625	5.154639	2.0	1.481481
Europe	48.362235	51.282051	55.882353	60.714286	58.823529	48.43750	55.670103	38.0	46.666667
North America	12.909441	25.641026	18.382353	12.857143	20.588235	11.71875	9.278351	8.0	5.185185
Oceania	1.926782	1.282051	3.676471	2.857143	1.960784	0.78125	1.030928	2.0	0.740741
South America	11.946050	5.128205	4.411765	3.571429	6.862745	15.62500	9.278351	20.0	20.740741

role = 'Role'
plot_role_percentage(continents_perc_df[role], f'All {role.lower()}s', f'{role} (%)')

all_roles_continent_df = (pd.DataFrame.from_dict(all_roles_continent)
    .fillna(0)
    .drop(columns=['Organizer', 'Role'])
    .reindex(['Participant', 'Mentor','Speaker','Expert','Facilitator'], axis=1)
    .assign(total=lambda df: df.sum(axis = 1)))
all_roles_continent_df = 100 * all_roles_continent_df / all_roles_continent_df.sum(axis = 0)
all_roles_continent_df

	Participant	Mentor	Speaker	Expert	Facilitator	total
continent
Africa	20.212766	13.417722	8.810573	5.341880	46.666667	14.866980
Asia	10.771277	4.556962	4.845815	3.418803	5.333333	6.781429
Europe	43.218085	56.708861	57.709251	64.529915	32.000000	52.477830
North America	11.037234	11.392405	15.859031	17.094017	5.333333	12.936881
Oceania	0.797872	2.278481	4.845815	2.777778	0.000000	2.034429
South America	13.962766	11.645570	7.929515	6.837607	10.666667	10.902452

fig, ax = plt.subplots()
fig.set_dpi(300)
(all_roles_continent_df
     .drop(columns=['total'])
     .transpose()
     .plot.bar(stacked=True, ax=ax, colormap='tab20c'))
plt.xlabel('Roles')
ax.legend(
    loc='center left',
    bbox_to_anchor=(1, 0.5),
    frameon=False,
    fontsize='x-small')

<matplotlib.legend.Legend at 0x1374cf950>

Participants

continents_perc_df['Participant']

	TOTAL	OLS-1	OLS-2	OLS-3	OLS-4	OLS-5	OLS-6	OLS-7	OLS-8
continent
Africa	19.944598	17.241379	21.153846	4.6875	6.060606	16.923077	35.483871	39.215686	25.757576
Asia	10.526316	13.793103	7.692308	28.1250	15.151515	15.384615	6.451613	0.000000	0.000000
Europe	42.936288	27.586207	48.076923	53.1250	57.575758	36.923077	48.387097	29.411765	45.454545
North America	11.357341	34.482759	19.230769	10.9375	9.090909	9.230769	0.000000	3.921569	6.060606
Oceania	0.831025	0.000000	1.923077	1.5625	0.000000	0.000000	3.225806	0.000000	0.000000
South America	14.404432	6.896552	1.923077	1.5625	12.121212	21.538462	6.451613	27.450980	22.727273

role = 'Participant'
plot_role_percentage(continents_perc_df[role], f'{role}s', f'{role} (%)')

Mentors

continents_perc_df['Mentor']

	TOTAL	OLS-1	OLS-2	OLS-3	OLS-4	OLS-5	OLS-6	OLS-7	OLS-8
continent
Africa	13.970588	10.0	13.888889	8.823529	0.000	8.571429	19.354839	24.242424	18.421053
Asia	4.411765	5.0	2.777778	5.882353	3.125	8.571429	3.225806	6.060606	2.631579
Europe	52.941176	70.0	58.333333	61.764706	62.500	68.571429	67.741935	39.393939	47.368421
North America	12.500000	10.0	16.666667	11.764706	25.000	8.571429	3.225806	9.090909	2.631579
Oceania	2.941176	0.0	2.777778	5.882353	3.125	0.000000	0.000000	3.030303	0.000000
South America	13.235294	5.0	5.555556	5.882353	6.250	5.714286	6.451613	18.181818	28.947368

role = 'Mentor'
plot_role_percentage(continents_perc_df[role], f'{role}s', f'{role} (%)')

Speakers

continents_perc_df['Speaker']

	TOTAL	OLS-1	OLS-2	OLS-3	OLS-4	OLS-5	OLS-6	OLS-7	OLS-8
continent
Africa	10.112360	5.555556	12.500000	15.0	0.000000	6.666667	0.000000	14.285714	9.090909
Asia	5.617978	0.000000	0.000000	5.0	5.882353	0.000000	10.526316	7.142857	9.090909
Europe	52.808989	66.666667	66.666667	70.0	70.588235	46.666667	57.894737	42.857143	54.545455
North America	16.853933	27.777778	8.333333	5.0	17.647059	26.666667	10.526316	14.285714	18.181818
Oceania	5.617978	0.000000	8.333333	5.0	0.000000	6.666667	0.000000	7.142857	9.090909
South America	8.988764	0.000000	4.166667	0.0	5.882353	13.333333	21.052632	14.285714	0.000000

role = 'Speaker'
plot_role_percentage(continents_perc_df[role], f'{role}s', f'{role} (%)')

Experts

continents_perc_df['Expert']

	TOTAL	OLS-1	OLS-2	OLS-3	OLS-4	OLS-5	OLS-6	OLS-7	OLS-8
continent
Africa	6.547619	5.405405	4.615385	3.174603	0.000000	4.0	2.631579	0.0	22.727273
Asia	4.166667	5.405405	1.538462	3.174603	4.347826	4.0	2.631579	0.0	0.000000
Europe	62.500000	67.567568	63.076923	68.253968	58.695652	76.0	68.421053	75.0	59.090909
North America	15.476190	16.216216	18.461538	17.460317	30.434783	12.0	15.789474	25.0	4.545455
Oceania	2.976190	2.702703	6.153846	3.174603	2.173913	0.0	0.000000	0.0	0.000000
South America	8.333333	2.702703	6.153846	4.761905	4.347826	4.0	10.526316	0.0	13.636364

role = 'Expert'
plot_role_percentage(continents_perc_df[role], f'{role}s', f'{role} (%)')

Facilitators

continents_perc_df['Facilitator']

	TOTAL	OLS-1	OLS-2	OLS-3	OLS-4	OLS-5	OLS-6	OLS-7	OLS-8
continent
Africa	46.666667	NaN	NaN	0.0	28.571429	40.0	42.857143	40.0	66.666667
Asia	3.333333	NaN	NaN	0.0	14.285714	20.0	14.285714	0.0	0.000000
Europe	30.000000	NaN	NaN	100.0	42.857143	40.0	28.571429	40.0	20.000000
North America	6.666667	NaN	NaN	0.0	14.285714	0.0	14.285714	0.0	0.000000
South America	13.333333	NaN	NaN	0.0	0.000000	0.0	0.000000	20.0	13.333333

role = 'Facilitator'
plot_role_percentage(continents_perc_df[role], f'{role}s', f'{role} (%)')

Countries

people_df.country.nunique()

60

Proportion of people without country information

people_df.country.isna().sum() / len(people_df.country)

0.06335616438356165

Country repartition

countries_df = {}
countries_perc_df = {}
for r in roles: 
    countries_df[r] = (roles_df[r].groupby(['country']).count()
        .rename(columns = {'country_3': 'total'})
        .drop(columns = ['city','first-name','last-name','pronouns','continent','longitude','latitude']))
    countries_df[r].columns = [x.upper() for x in countries_df[r].columns]
    countries_perc_df[r] = 100 * countries_df[r] / countries_df[r].sum(axis = 0)

countries_perc_df['Role']

	TOTAL	OLS-1	OLS-2	OLS-3	OLS-4	OLS-5	OLS-6	OLS-7	OLS-8
country
Argentina	5.780347	0.000000	1.470588	1.428571	3.921569	6.766917	3.061224	7.920792	15.555556
Australia	1.926782	1.282051	3.676471	2.857143	1.960784	0.751880	1.020408	1.980198	0.740741
Austria	0.192678	0.000000	0.735294	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
Bangladesh	0.192678	0.000000	0.735294	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
Belgium	0.385356	0.000000	0.000000	1.428571	0.000000	0.000000	0.000000	0.000000	0.000000
Benin	0.192678	0.000000	0.000000	0.000000	0.000000	0.751880	0.000000	0.000000	0.000000
Bolivia	0.000000	0.000000	0.000000	0.000000	0.000000	3.007519	0.000000	0.000000	0.000000
Brazil	3.082852	5.128205	2.941176	1.428571	1.960784	2.255639	4.081633	3.960396	1.481481
Cameroon	2.119461	0.000000	0.000000	0.714286	0.000000	1.503759	2.040816	8.910891	2.962963
Canada	2.890173	5.128205	7.352941	2.142857	0.980392	3.007519	2.040816	1.980198	0.740741
Chile	0.385356	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	1.980198	0.740741
China	0.192678	1.282051	0.735294	0.000000	0.000000	0.751880	1.020408	0.000000	0.000000
Colombia	1.156069	0.000000	0.000000	0.714286	0.980392	0.751880	2.040816	5.940594	2.222222
Czechia	0.770713	0.000000	0.735294	2.142857	0.000000	0.000000	0.000000	0.000000	0.000000
Denmark	0.385356	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.990099	0.740741
Egypt	0.192678	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.990099	0.000000
Estonia	0.385356	0.000000	0.000000	0.714286	0.000000	0.000000	0.000000	0.990099	0.740741
Eswatini	0.192678	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.740741
Ethiopia	0.192678	0.000000	0.735294	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
France	2.312139	3.846154	4.411765	3.571429	5.882353	1.503759	1.020408	2.970297	2.962963
Germany	6.743738	10.256410	8.088235	10.000000	7.843137	6.766917	5.102041	6.930693	3.703704
Ghana	0.770713	0.000000	0.735294	0.714286	0.980392	1.503759	0.000000	0.990099	0.000000
Greece	0.578035	2.564103	1.470588	1.428571	0.980392	0.751880	1.020408	0.000000	0.740741
Hong Kong	0.192678	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.740741
Hungary	0.192678	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.990099	0.000000
India	3.660886	2.564103	0.735294	5.714286	3.921569	3.007519	3.061224	0.990099	0.740741
Indonesia	0.963391	0.000000	0.735294	2.857143	0.000000	0.000000	0.000000	0.000000	0.000000
Ireland	0.963391	0.000000	0.000000	0.714286	0.000000	0.000000	2.040816	3.960396	0.740741
Italy	1.926782	1.282051	0.735294	2.857143	1.960784	0.751880	4.081633	1.980198	0.740741
Japan	0.192678	1.282051	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
Kazakhstan	0.192678	0.000000	0.000000	0.000000	0.000000	0.751880	0.000000	0.000000	0.000000
Kenya	4.238921	7.692308	4.411765	1.428571	1.960784	3.007519	9.183673	7.920792	8.148148
Luxembourg	0.192678	1.282051	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
Mali	0.385356	0.000000	1.470588	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
Mexico	0.385356	0.000000	0.735294	1.428571	0.980392	0.751880	1.020408	0.990099	0.740741
Nepal	0.770713	1.282051	0.000000	2.142857	0.000000	0.000000	0.000000	0.000000	0.000000
Netherlands	8.477842	3.846154	4.411765	3.571429	6.862745	6.766917	7.142857	4.950495	22.222222
Nigeria	3.853565	0.000000	1.470588	1.428571	0.980392	1.503759	3.061224	8.910891	8.888889
Norway	0.578035	2.564103	0.000000	0.000000	0.980392	0.751880	0.000000	0.000000	0.000000
Peru	1.348748	0.000000	0.000000	0.000000	0.000000	5.263158	0.000000	0.000000	0.000000
Poland	0.192678	0.000000	0.000000	0.000000	0.980392	0.000000	0.000000	0.000000	0.000000
Portugal	0.385356	0.000000	0.000000	1.428571	0.000000	0.000000	0.000000	0.000000	0.000000
Romania	0.192678	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.990099	0.740741
Russian Federation	0.192678	1.282051	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
Saudi Arabia	0.770713	0.000000	0.000000	1.428571	2.941176	0.751880	1.020408	0.990099	0.000000
South Africa	3.853565	1.282051	4.411765	2.142857	0.000000	4.511278	5.102041	0.990099	3.703704
South Korea	0.000000	0.000000	0.000000	0.000000	0.000000	0.751880	1.020408	0.000000	0.000000
Spain	3.082852	1.282051	2.205882	6.428571	1.960784	3.759398	1.020408	0.000000	1.481481
Sweden	0.385356	0.000000	0.735294	0.000000	0.980392	0.751880	1.020408	0.000000	0.740741
Switzerland	1.734104	1.282051	4.411765	1.428571	1.960784	0.751880	3.061224	0.990099	0.740741
Thailand	0.192678	1.282051	0.000000	0.000000	0.980392	0.000000	0.000000	0.000000	0.000000
Turkey	0.963391	0.000000	0.735294	1.428571	0.000000	3.759398	0.000000	0.000000	0.000000
Uganda	0.385356	0.000000	0.735294	0.000000	0.000000	0.000000	0.000000	0.990099	0.740741
United Kingdom	18.111753	21.794872	27.941176	25.000000	28.431373	24.060150	29.591837	11.881188	10.370370
United Kingdom / Ukraine	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.990099	0.000000
United States	9.633911	20.512821	10.294118	9.285714	18.627451	7.518797	6.122449	4.950495	3.703704
Uruguay	0.192678	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.740741
Uzbekistan	0.192678	0.000000	0.000000	0.000000	0.000000	0.751880	0.000000	0.000000	0.000000

len(countries_perc_df['Role'])

58

Maps

def plot_map(data, column, title, legend, label=""):
    """
    Plot colored map by data
    
    :param data: data to plot
    :param column: column to plot
    :param title: title for plots
    :param legend: boolean to plot legend or not
    :param label: label for legend
    """
    
    fig, ax = plt.subplots(figsize=(15, 10))
    fig.set_dpi(300)
    
    data.plot(
        column=column,
        ax=ax,
        legend=legend,
        legend_kwds={'label': label, 'orientation': "horizontal"},
        cmap='YlGn')
    plt.title(title)
    ax.set_axis_off()

Presence/absence

country_code_df = (roles_df["Role"].groupby(['country_3']).count()
    .rename(columns = {'country': 'total'})
    .drop(columns = ['city','first-name','last-name','pronouns','continent','longitude','latitude'])
)
country_code_df[country_code_df != 0] = 1
country_code_df = (country_code_df
    .rename_axis("iso_a3")
    .reset_index()
)
country_world_df = pd.merge(world_df, country_code_df, on='iso_a3', how='outer')
country_world_df['total'].fillna(0, inplace=True)
for i in range(1, cohort_nb):
    country_world_df[f'ols-{i}'].fillna(0, inplace=True)
country_world_df.head()

	pop_est	continent	name	iso_a3	gdp_md_est	geometry	total	ols-1	ols-2	ols-3	ols-4	ols-5	ols-6	ols-7	ols-8
0	889953.0	Oceania	Fiji	FJI	5496.0	MULTIPOLYGON (((180.00000 -16.06713, 180.00000...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	58005463.0	Africa	Tanzania	TZA	63177.0	POLYGON ((33.90371 -0.95000, 34.07262 -1.05982...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	603253.0	Africa	W. Sahara	ESH	907.0	POLYGON ((-8.66559 27.65643, -8.66512 27.58948...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3	37589262.0	North America	Canada	CAN	1736425.0	MULTIPOLYGON (((-122.84000 49.00000, -122.9742...	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0
4	328239523.0	North America	United States of America	USA	21433226.0	MULTIPOLYGON (((-122.84000 49.00000, -120.0000...	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0	1.0

country_code_df

	iso_a3	total	ols-1	ols-2	ols-3	ols-4	ols-5	ols-6	ols-7	ols-8
0	ARG	1	0	1	1	1	1	1	1	1
1	AUS	1	1	1	1	1	1	1	1	1
2	AUT	1	0	1	0	0	0	0	0	0
3	BEL	1	0	0	1	0	0	0	0	0
4	BEN	1	0	0	0	0	1	0	0	0
5	BGD	1	0	1	0	0	0	0	0	0
6	BRA	1	1	1	1	1	1	1	1	1
7	CAN	1	1	1	1	1	1	1	1	1
8	CHE	1	1	1	1	1	1	1	1	1
9	CHL	1	0	0	0	0	0	0	1	1
10	CHN	1	1	1	0	0	1	1	0	0
11	CMR	1	0	0	1	0	1	1	1	1
12	COL	1	0	0	1	1	1	1	1	1
13	CZE	1	0	1	1	0	0	0	0	0
14	DEU	1	1	1	1	1	1	1	1	1
15	DNK	1	0	0	0	0	0	0	1	1
16	EGY	1	0	0	0	0	0	0	1	0
17	ESP	1	1	1	1	1	1	1	0	1
18	EST	1	0	0	1	0	0	0	1	1
19	ETH	1	0	1	0	0	0	0	0	0
20	FRA	1	1	1	1	1	1	1	1	1
21	GBR	1	1	1	1	1	1	1	1	1
22	GHA	1	0	1	1	1	1	0	1	0
23	GRC	1	1	1	1	1	1	1	0	1
24	HKG	1	0	0	0	0	0	0	0	1
25	HUN	1	0	0	0	0	0	0	1	0
26	IDN	1	0	1	1	0	0	0	0	0
27	IND	1	1	1	1	1	1	1	1	1
28	IRL	1	0	0	1	0	0	1	1	1
29	ITA	1	1	1	1	1	1	1	1	1
30	JPN	1	1	0	0	0	0	0	0	0
31	KAZ	1	0	0	0	0	1	0	0	0
32	KEN	1	1	1	1	1	1	1	1	1
33	LUX	1	1	0	0	0	0	0	0	0
34	MEX	1	0	1	1	1	1	1	1	1
35	MLI	1	0	1	0	0	0	0	0	0
36	NGA	1	0	1	1	1	1	1	1	1
37	NLD	1	1	1	1	1	1	1	1	1
38	NOR	1	1	0	0	1	1	0	0	0
39	NPL	1	1	0	1	0	0	0	0	0
40	PER	1	0	0	0	0	1	0	0	0
41	POL	1	0	0	0	1	0	0	0	0
42	PRT	1	0	0	1	0	0	0	0	0
43	ROU	1	0	0	0	0	0	0	1	1
44	RUS	1	1	0	0	0	0	0	0	0
45	SAU	1	0	0	1	1	1	1	1	0
46	SWE	1	0	1	0	1	1	1	0	1
47	SWZ	1	0	0	0	0	0	0	0	1
48	THA	1	1	0	0	1	0	0	0	0
49	TUR	1	0	1	1	0	1	0	0	0
50	UGA	1	0	1	0	0	0	0	1	1
51	URY	1	0	0	0	0	0	0	0	1
52	USA	1	1	1	1	1	1	1	1	1
53	UZB	1	0	0	0	0	1	0	0	0
54	ZAF	1	1	1	1	0	1	1	1	1

plot_map(country_world_df, 'total', f'All cohorts / All roles', False, "Presence/absence by Country")
plt.savefig(f'../results/openseeds/location/all-roles-all-cohorts.png', bbox_inches='tight')

for i in range(1,cohort_nb):
    plot_map(country_world_df, f'ols-{i}', f'OLS-{i} / All roles', False)

Density by number

country_code_df = {}
country_world_df = {}
for r in roles: 
    country_code_df[r] = (roles_df[r].groupby(['country_3']).count()
        .rename(columns = {'country': 'total'})
        .drop(columns = ['city','first-name','last-name','pronouns','continent','longitude','latitude'])
        )
    country_code_df[r] = 100 * country_code_df[r] / country_code_df[r].sum(axis = 0)
    country_code_df[r] = (country_code_df[r]
        .rename_axis("iso_a3")
        .reset_index())
    
    country_world_df[r] = pd.merge(world_df, country_code_df[r], on='iso_a3', how='outer')
    country_world_df[r]['total'].fillna(0, inplace=True)
    for i in range(1, cohort_nb):
        country_world_df[r][f'ols-{i}'].fillna(0, inplace=True)
    country_world_df[r].head()

def plot_role_map(data, role):
    '''
    Generate role percentage plots
    
    :param data: data to plot
    :param title: title for plots
    '''
    plot_map(data, 'total', f'All cohorts / All {role}s', True, "Percentage by Country")
        
    #plt.savefig(f'../../results/openseeds/location/{role}-all-cohorts.png', bbox_inches='tight')
    
    for i in range(1,cohort_nb):
        plot_map(data, f'ols-{i}', f'OLS-{i} / All {role}s', True, "Percentage by Country")

All roles

role = 'Role'
plot_role_map(country_world_df[role], role.lower())

Participants

role = 'Participant'

Number of countries

len(country_code_df[role])

49

plot_role_map(country_world_df[role], role.lower())

Mentors

role = 'Mentor'
plot_role_map(country_world_df[role], role.lower())

Speakers

role = 'Speaker'
plot_role_map(country_world_df[role], role.lower())

Experts

role = 'Expert'
plot_role_map(country_world_df[role], role.lower())

Facilitators

role = 'Facilitator'
plot_role_map(country_world_df[role], role.lower())