global south stats from openalex api

global_south.py

import requests
from iso3166 import countries

GLOBAL_SOUTH_COUNTRIES = [
    # source https://meta.wikimedia.org/wiki/List_of_countries_by_regional_classification
    "Afghanistan",
    "Algeria",
    "American Samoa",
    "Angola",
    "Anguilla",
    "Antarctica",
    "Antigua and Barbuda",
    "Argentina",
    "Aruba",
    "Bahamas",
    "Bahrain",
    "Bangladesh",
    "Barbados",
    "Belize",
    "Benin",
    "Bermuda",
    "Bhutan",
    "Bolivia, Plurinational State Of",
    "Botswana",
    "Bouvet Island",
    "Brazil",
    "British Indian Ocean Territory",
    "Brunei Darussalam",
    "Burkina Faso",
    "Burundi",
    "Cambodia",
    "Cameroon",
    "Cabo Verde",
    "Cayman Islands",
    "Central African Republic",
    "Chad",
    "Chile",
    "China",
    "Christmas Island",
    "Cocos (Keeling) Islands",
    "Colombia",
    "Comoros",
    "Congo",
    "Congo, Democratic Republic of the",
    "Cook Islands",
    "Costa Rica",
    "Côte D'Ivoire",
    "Cuba",
    "Djibouti",
    "Dominica",
    "Dominican Republic",
    "Ecuador",
    "Egypt",
    "El Salvador",
    "Equatorial Guinea",
    "Eritrea",
    "Eswatini",
    "Ethiopia",
    "Falkland Islands (Malvinas)",
    "Fiji",
    "French Guiana",
    "French Polynesia",
    "French Southern Territories",
    "Gabon",
    "Gambia",
    "Ghana",
    "Grenada",
    "Guadeloupe",
    "Guam",
    "Guatemala",
    "Guinea",
    "Guinea-Bissau",
    "Guyana",
    "Haiti",
    "Heard Island and McDonald Islands",
    "Honduras",
    "Hong Kong",
    "India",
    "Indonesia",
    "Iran, Islamic Republic of",
    "Iraq",
    "Jamaica",
    "Jordan",
    "Kenya",
    "Kiribati",
    "Korea, Democratic People's Republic of",
    "Kuwait",
    "Kyrgyzstan",
    "Lao People's Democratic Republic",
    "Lebanon",
    "Lesotho",
    "Liberia",
    "Libya",
    "Macao",
    "Madagascar",
    "Malawi",
    "Malaysia",
    "Maldives",
    "Mali",
    "Marshall Islands",
    "Martinique",
    "Mauritania",
    "Mauritius",
    "Mayotte",
    "Mexico",
    "Micronesia, Federated States of",
    "Mongolia",
    "Montserrat",
    "Morocco",
    "Mozambique",
    "Myanmar",
    "Namibia",
    "Nauru",
    "Nepal",
    "Netherlands",
    "New Caledonia",
    "Nicaragua",
    "Niger",
    "Nigeria",
    "Niue",
    "Norfolk Island",
    "Northern Mariana Islands",
    "Oman",
    "Pakistan",
    "Palau",
    "Palestine, State of",
    "Panama",
    "Papua New Guinea",
    "Paraguay",
    "Peru",
    "Philippines",
    "Pitcairn",
    "Puerto Rico",
    "Qatar",
    "Réunion",
    "Rwanda",
    "Saint Barthélemy",
    "Saint Helena, Ascension and Tristan da Cunha",
    "Saint Kitts and Nevis",
    "Saint Lucia",
    "Saint Martin (French Part)",
    "Saint Vincent and the Grenadines",
    "Samoa",
    "Sao Tome and Principe",
    "Saudi Arabia",
    "Senegal",
    "Seychelles",
    "Sierra Leone",
    "Solomon Islands",
    "Somalia",
    "South Africa",
    "South Georgia and the South Sandwich Islands",
    "South Sudan",
    "Sri Lanka",
    "Sudan",
    "Suriname",
    "Syrian Arab Republic",
    "Tajikistan",
    "Tanzania, United Republic of",
    "Thailand",
    "Timor-Leste",
    "Togo",
    "Tokelau",
    "Tonga",
    "Trinidad and Tobago",
    "Tunisia",
    "Turkmenistan",
    "Turks and Caicos Islands",
    "Tuvalu",
    "Uganda",
    "United Arab Emirates",
    "United States Minor Outlying Islands",
    "Uruguay",
    "Uzbekistan",
    "Vanuatu",
    "Venezuela, Bolivarian Republic of",
    "Viet nam",
    "Virgin Islands, British",
    "Virgin Islands, U.S.",
    "Wallis and Futuna",
    "Western Sahara",
    "Yemen",
    "Zambia",
    "Zimbabwe",
]


def institutions_in_global_south():
    total = 0
    for country in GLOBAL_SOUTH_COUNTRIES:
        country_code = countries.get(country).alpha2
        r = requests.get(
            f"https://api.openalex.org/institutions?filter=country_code:{country_code}&mailto=jason@ourresearch.org"
        )
        institution_count = r.json()["meta"]["count"]
        print(
            f"{institution_count} institutions in {countries.get(country).name} ({country_code})"
        )
        total = total + institution_count
    return total


def works_from_global_south():
    total = 0
    for country in GLOBAL_SOUTH_COUNTRIES:
        country_code = countries.get(country).alpha2
        r = requests.get(
            f"https://api.openalex.org/works?filter=authorships.institutions.country_code:{country_code}&mailto=jason@ourresearch.org"
        )
        works_count = r.json()["meta"]["count"]
        print(
            f"{works_count} works from {countries.get(country).name} ({country_code})"
        )
        total = total + works_count
    return total


def authors_from_global_south():
    total = 0
    for country in GLOBAL_SOUTH_COUNTRIES:
        country_code = countries.get(country).alpha2
        r = requests.get(
            f"https://api.openalex.org/authors?filter=last_known_institution.country_code:{country_code}&mailto=jason@ourresearch.org"
        )
        authors_count = r.json()["meta"]["count"]
        print(
            f"{authors_count} from {countries.get(country).name} ({country_code})"
        )
        total = total + authors_count
    return total


if __name__ == "__main__":
    institutions_count = institutions_in_global_south()
    print(f"{institutions_count:,} institutions in the Global South")
    # 22,073 institutions in the Global South

    works_count = works_from_global_south()
    print(f"{works_count:,} works from the Global South")
    # 22,978,980 works from the Global South

    authors_count = authors_from_global_south()
    print(f"{authors_count:,} authors with last known affiliation in Global South")
    # 21,076,110 authors with last known affiliation in Global South