Initial project setup with Django, including core models, admin configuration, GraphQL schema, and data population script.

.gitignore

@@ -0,0 +1,4 @@
+**/*.json
+venv
+migrations
+db.sqlite3*

BridgeMentor/asgi.py

@@ -0,0 +1,16 @@
+"""
+ASGI config for BridgeMentor project.
+
+It exposes the ASGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/4.2/howto/deployment/asgi/
+"""
+
+import os
+
+from django.core.asgi import get_asgi_application
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'BridgeMentor.settings')
+
+application = get_asgi_application()

BridgeMentor/settings.py

@@ -0,0 +1,130 @@
+"""
+Django settings for BridgeMentor project.
+
+Generated by 'django-admin startproject' using Django 4.2.20.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/4.2/topics/settings/
+
+For the full list of settings and their values, see
+https://docs.djangoproject.com/en/4.2/ref/settings/
+"""
+
+from pathlib import Path
+
+# Build paths inside the project like this: BASE_DIR / 'subdir'.
+BASE_DIR = Path(__file__).resolve().parent.parent
+
+
+# Quick-start development settings - unsuitable for production
+# See https://docs.djangoproject.com/en/4.2/howto/deployment/checklist/
+
+# SECURITY WARNING: keep the secret key used in production secret!
+SECRET_KEY = 'django-insecure-*bimkkt===!#m(@d!x*he9z4gj#+ewbt9(y0o=8si2ny88w+yd'
+
+# SECURITY WARNING: don't run with debug turned on in production!
+DEBUG = True
+
+ALLOWED_HOSTS = []
+
+
+# Application definition
+
+INSTALLED_APPS = [
+    'django.contrib.admin',
+    'django.contrib.auth',
+    'django.contrib.contenttypes',
+    'django.contrib.sessions',
+    'django.contrib.messages',
+    'django.contrib.staticfiles',
+    'django_filters',
+    'graphene_django',
+    'core',
+]
+
+MIDDLEWARE = [
+    'django.middleware.security.SecurityMiddleware',
+    'django.contrib.sessions.middleware.SessionMiddleware',
+    'django.middleware.common.CommonMiddleware',
+    'django.middleware.csrf.CsrfViewMiddleware',
+    'django.contrib.auth.middleware.AuthenticationMiddleware',
+    'django.contrib.messages.middleware.MessageMiddleware',
+    'django.middleware.clickjacking.XFrameOptionsMiddleware',
+]
+
+ROOT_URLCONF = 'BridgeMentor.urls'
+
+TEMPLATES = [
+    {
+        'BACKEND': 'django.template.backends.django.DjangoTemplates',
+        'DIRS': [],
+        'APP_DIRS': True,
+        'OPTIONS': {
+            'context_processors': [
+                'django.template.context_processors.debug',
+                'django.template.context_processors.request',
+                'django.contrib.auth.context_processors.auth',
+                'django.contrib.messages.context_processors.messages',
+            ],
+        },
+    },
+]
+
+WSGI_APPLICATION = 'BridgeMentor.wsgi.application'
+
+
+# Database
+# https://docs.djangoproject.com/en/4.2/ref/settings/#databases
+
+DATABASES = {
+    'default': {
+        'ENGINE': 'django.db.backends.sqlite3',
+        'NAME': BASE_DIR / 'db.sqlite3',
+    }
+}
+
+
+# Password validation
+# https://docs.djangoproject.com/en/4.2/ref/settings/#auth-password-validators
+
+AUTH_PASSWORD_VALIDATORS = [
+    {
+        'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator',
+    },
+]
+
+
+# Internationalization
+# https://docs.djangoproject.com/en/4.2/topics/i18n/
+
+LANGUAGE_CODE = 'en-us'
+
+TIME_ZONE = 'UTC'
+
+USE_I18N = True
+
+USE_TZ = True
+
+
+# Static files (CSS, JavaScript, Images)
+# https://docs.djangoproject.com/en/4.2/howto/static-files/
+
+STATIC_URL = 'static/'
+
+# Default primary key field type
+# https://docs.djangoproject.com/en/4.2/ref/settings/#default-auto-field
+
+DEFAULT_AUTO_FIELD = 'django.db.models.BigAutoField'
+
+GRAPHENE = {
+    "SCHEMA": "core.schema.schema"  # Adjust to match your project
+}

BridgeMentor/urls.py

@@ -0,0 +1,25 @@
+"""
+URL configuration for BridgeMentor project.
+
+The `urlpatterns` list routes URLs to views. For more information please see:
+    https://docs.djangoproject.com/en/4.2/topics/http/urls/
+Examples:
+Function views
+    1. Add an import:  from my_app import views
+    2. Add a URL to urlpatterns:  path('', views.home, name='home')
+Class-based views
+    1. Add an import:  from other_app.views import Home
+    2. Add a URL to urlpatterns:  path('', Home.as_view(), name='home')
+Including another URLconf
+    1. Import the include() function: from django.urls import include, path
+    2. Add a URL to urlpatterns:  path('blog/', include('blog.urls'))
+"""
+from graphene_django.views import GraphQLView
+from django.contrib import admin
+from django.urls import path
+
+urlpatterns = [
+    path('admin/', admin.site.urls),
+    path("graphql/", GraphQLView.as_view(graphiql=True)),
+
+]

BridgeMentor/wsgi.py

@@ -0,0 +1,16 @@
+"""
+WSGI config for BridgeMentor project.
+
+It exposes the WSGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/4.2/howto/deployment/wsgi/
+"""
+
+import os
+
+from django.core.wsgi import get_wsgi_application
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'BridgeMentor.settings')
+
+application = get_wsgi_application()

core/admin.py

@@ -0,0 +1,92 @@
+from django.contrib import admin
+from .models import (
+    Institution, Author, Affiliation, Domain, Field, Subfield, Topic,
+    AuthorTopic, Work, AuthorYearlyStats, Concept, AuthorConcept
+)
+
+
+admin.site.site_header = "BridgeMentor Admin"
+admin.site.site_title = "BridgeMentor Data Management"
+admin.site.index_title = "BridgeMentor Dashboard"
+
+
+@admin.register(Institution)
+class InstitutionAdmin(admin.ModelAdmin):
+    list_display = ('id', 'name', 'ror_id', 'country_code', 'institution_type')
+    search_fields = ('name', 'ror_id')
+    list_filter = ('country_code', 'institution_type')
+
+
+@admin.register(Author)
+class AuthorAdmin(admin.ModelAdmin):
+    list_display = ('id', 'name', 'orcid', 'h_index',
+                    'i10_index', 'cited_by_count', 'works_count')
+    search_fields = ('name', 'orcid')
+    list_filter = ('h_index',)
+
+
+@admin.register(Affiliation)
+class AffiliationAdmin(admin.ModelAdmin):
+    list_display = ('author', 'institution', 'year', 'is_last_known')
+    list_filter = ('year', 'is_last_known', 'institution')
+    search_fields = ('author__name', 'institution__name')
+
+
+@admin.register(Domain)
+class DomainAdmin(admin.ModelAdmin):
+    list_display = ('id', 'name')
+    search_fields = ('name',)
+
+
+@admin.register(Field)
+class FieldAdmin(admin.ModelAdmin):
+    list_display = ('id', 'name', 'domain')
+    list_filter = ('domain',)
+    search_fields = ('name',)
+
+
+@admin.register(Subfield)
+class SubfieldAdmin(admin.ModelAdmin):
+    list_display = ('id', 'name', 'field')
+    list_filter = ('field',)
+    search_fields = ('name',)
+
+
+@admin.register(Topic)
+class TopicAdmin(admin.ModelAdmin):
+    list_display = ('id', 'name', 'subfield')
+    list_filter = ('subfield',)
+    search_fields = ('name',)
+
+
+@admin.register(AuthorTopic)
+class AuthorTopicAdmin(admin.ModelAdmin):
+    list_display = ('author', 'topic', 'count', 'share_value')
+    list_filter = ('topic',)
+    search_fields = ('author__name', 'topic__name')
+
+
+@admin.register(Work)
+class WorkAdmin(admin.ModelAdmin):
+    list_display = ('id', 'title', 'author', 'year', 'cited_by_count')
+    list_filter = ('year',)
+    search_fields = ('title', 'author__name')
+
+
+@admin.register(AuthorYearlyStats)
+class AuthorYearlyStatsAdmin(admin.ModelAdmin):
+    list_display = ('author', 'year', 'works_count', 'cited_by_count')
+    list_filter = ('year',)
+    search_fields = ('author__name',)
+
+
+@admin.register(Concept)
+class ConceptAdmin(admin.ModelAdmin):
+    list_display = ('id', 'name', 'level', 'score')
+    search_fields = ('name',)
+
+
+@admin.register(AuthorConcept)
+class AuthorConceptAdmin(admin.ModelAdmin):
+    list_display = ('author', 'concept', 'level', 'score')
+    search_fields = ('author__name', 'concept__name')

core/apps.py

@@ -0,0 +1,6 @@
+from django.apps import AppConfig
+
+
+class CoreConfig(AppConfig):
+    default_auto_field = 'django.db.models.BigAutoField'
+    name = 'core'

core/models.py

@@ -0,0 +1,140 @@
+from django.db import models
+
+
+class TimestampedModel(models.Model):
+    created_at = models.DateTimeField(auto_now_add=True)
+    updated_at = models.DateTimeField(auto_now=True)
+
+    class Meta:
+        abstract = True
+
+
+class Institution(TimestampedModel):
+    id = models.CharField(max_length=20, primary_key=True)  # e.g., I204778367
+    name = models.CharField(max_length=255)
+    ror_id = models.CharField(max_length=100, unique=True)
+    country_code = models.CharField(max_length=2)
+    institution_type = models.CharField(max_length=50)  # funder, company, etc.
+
+    def __str__(self):
+        return self.name
+
+
+class Author(TimestampedModel):
+    id = models.CharField(max_length=20, primary_key=True)  # e.g., A5006834808
+    name = models.CharField(max_length=255)
+    orcid = models.CharField(
+        max_length=100, unique=True, null=True, blank=True)
+    h_index = models.IntegerField()
+    i10_index = models.IntegerField()
+    cited_by_count = models.IntegerField()
+    works_count = models.IntegerField()
+    mean_2yr_citedness = models.FloatField()
+
+    def __str__(self):
+        return self.name
+
+
+class Affiliation(TimestampedModel):
+    author = models.ForeignKey(
+        Author, on_delete=models.CASCADE, related_name='affiliations')
+    institution = models.ForeignKey(Institution, on_delete=models.CASCADE)
+    year = models.IntegerField()
+    is_last_known = models.BooleanField(default=False)
+
+    class Meta:
+        unique_together = ('author', 'institution', 'year')
+
+
+class Domain(TimestampedModel):
+    id = models.CharField(max_length=10, primary_key=True)  # e.g., 3
+    name = models.CharField(max_length=255)
+
+    def __str__(self):
+        return self.name
+
+
+class Field(TimestampedModel):
+    id = models.CharField(max_length=10, primary_key=True)  # e.g., 23
+    name = models.CharField(max_length=255)
+    domain = models.ForeignKey(
+        Domain, on_delete=models.CASCADE, related_name='fields')
+
+    def __str__(self):
+        return self.name
+
+
+class Subfield(TimestampedModel):
+    id = models.CharField(max_length=10, primary_key=True)  # e.g., 2304
+    name = models.CharField(max_length=255)
+    field = models.ForeignKey(
+        Field, on_delete=models.CASCADE, related_name='subfields')
+
+    def __str__(self):
+        return self.name
+
+
+class Topic(TimestampedModel):
+    id = models.CharField(max_length=20, primary_key=True)  # e.g., T13180
+    name = models.CharField(max_length=255)
+    subfield = models.ForeignKey(
+        Subfield, on_delete=models.CASCADE, related_name='topics')
+
+    def __str__(self):
+        return self.name
+
+
+class AuthorTopic(TimestampedModel):
+    author = models.ForeignKey(
+        Author, on_delete=models.CASCADE, related_name='topics')
+    topic = models.ForeignKey(Topic, on_delete=models.CASCADE)
+    count = models.IntegerField()
+    share_value = models.FloatField()
+
+    class Meta:
+        unique_together = ('author', 'topic')
+
+
+class Work(TimestampedModel):
+    id = models.CharField(max_length=20, primary_key=True)  # e.g., W123456789
+    author = models.ForeignKey(
+        Author, on_delete=models.CASCADE, related_name='works')
+    title = models.CharField(max_length=512)
+    year = models.IntegerField()
+    cited_by_count = models.IntegerField()
+
+    def __str__(self):
+        return self.title
+
+
+class AuthorYearlyStats(TimestampedModel):
+    author = models.ForeignKey(
+        Author, on_delete=models.CASCADE, related_name='yearly_stats')
+    year = models.IntegerField()
+    works_count = models.IntegerField()
+    cited_by_count = models.IntegerField()
+
+    class Meta:
+        unique_together = ('author', 'year')
+
+
+class Concept(TimestampedModel):
+    id = models.CharField(max_length=20, primary_key=True)  # e.g., C41008148
+    name = models.CharField(max_length=255)
+    wikidata_url = models.URLField(null=True, blank=True)
+    level = models.IntegerField()
+    score = models.FloatField()
+
+    def __str__(self):
+        return f"{self.name} ({self.id})"
+
+
+class AuthorConcept(models.Model):
+    author = models.ForeignKey(
+        Author, on_delete=models.CASCADE, related_name='concepts')
+    concept = models.ForeignKey(Concept, on_delete=models.CASCADE)
+    level = models.IntegerField(null=True, blank=True)
+    score = models.FloatField(null=True, blank=True)
+
+    class Meta:
+        unique_together = ('author', 'concept')

core/schema.py

@@ -0,0 +1,194 @@
+import graphene
+from graphene_django import DjangoObjectType
+from graphene_django.filter import DjangoFilterConnectionField
+from .models import (
+    Institution, Author, Affiliation, Domain, Field,
+    Subfield, Topic, AuthorTopic, Work, AuthorYearlyStats,
+    Concept, AuthorConcept
+)
+
+
+# === GraphQL Types ===
+class InstitutionType(DjangoObjectType):
+    class Meta:
+        model = Institution
+        fields = "__all__"
+        filter_fields = {
+            'id': ['exact', 'icontains'],
+            'name': ['icontains', 'iexact'],
+            'ror_id': ['exact'],
+            'country_code': ['exact'],
+            'institution_type': ['exact'],
+        }
+        interfaces = (graphene.relay.Node,)
+
+
+class AuthorType(DjangoObjectType):
+    class Meta:
+        model = Author
+        fields = "__all__"
+        filter_fields = {
+            'id': ['exact', 'icontains'],
+            'name': ['icontains'],
+            'orcid': ['exact'],
+            'h_index': ['exact', 'gte', 'lte'],
+            'cited_by_count': ['gte', 'lte'],
+            'works_count': ['gte', 'lte'],
+        }
+        interfaces = (graphene.relay.Node,)
+
+
+class AffiliationType(DjangoObjectType):
+    class Meta:
+        model = Affiliation
+        fields = "__all__"
+        filter_fields = {
+            'author__id': ['exact'],
+            'institution__id': ['exact'],
+            'year': ['exact', 'gte', 'lte'],
+            'is_last_known': ['exact'],
+        }
+        interfaces = (graphene.relay.Node,)
+
+
+class DomainType(DjangoObjectType):
+    class Meta:
+        model = Domain
+        fields = "__all__"
+        filter_fields = ['id', 'name']
+        interfaces = (graphene.relay.Node,)
+
+
+class FieldType(DjangoObjectType):
+    class Meta:
+        model = Field
+        fields = "__all__"
+        filter_fields = {
+            'id': ['exact'],
+            'name': ['icontains'],
+            'domain__id': ['exact'],
+        }
+        interfaces = (graphene.relay.Node,)
+
+
+class SubfieldType(DjangoObjectType):
+    class Meta:
+        model = Subfield
+        fields = "__all__"
+        filter_fields = {
+            'id': ['exact'],
+            'name': ['icontains'],
+            'field__id': ['exact'],
+        }
+        interfaces = (graphene.relay.Node,)
+
+
+class TopicType(DjangoObjectType):
+    class Meta:
+        model = Topic
+        fields = "__all__"
+        filter_fields = {
+            'id': ['exact'],
+            'name': ['icontains'],
+            'subfield__id': ['exact'],
+        }
+        interfaces = (graphene.relay.Node,)
+
+
+class AuthorTopicType(DjangoObjectType):
+    class Meta:
+        model = AuthorTopic
+        fields = "__all__"
+        filter_fields = {
+            'author__id': ['exact'],
+            'topic__id': ['exact'],
+        }
+        interfaces = (graphene.relay.Node,)
+
+
+class WorkType(DjangoObjectType):
+    class Meta:
+        model = Work
+        fields = "__all__"
+        filter_fields = {
+            'id': ['exact'],
+            'title': ['icontains'],
+            'author__id': ['exact'],
+            'year': ['exact', 'gte', 'lte'],
+            'cited_by_count': ['gte', 'lte'],
+        }
+        interfaces = (graphene.relay.Node,)
+
+
+class AuthorYearlyStatsType(DjangoObjectType):
+    class Meta:
+        model = AuthorYearlyStats
+        fields = "__all__"
+        filter_fields = {
+            'author__id': ['exact'],
+            'year': ['exact'],
+            'works_count': ['gte', 'lte'],
+        }
+        interfaces = (graphene.relay.Node,)
+
+
+class ConceptType(DjangoObjectType):
+    class Meta:
+        model = Concept
+        fields = "__all__"
+        filter_fields = ['id', 'name', 'level', 'score']
+        interfaces = (graphene.relay.Node,)
+
+
+class AuthorConceptType(DjangoObjectType):
+    class Meta:
+        model = AuthorConcept
+        fields = "__all__"
+        filter_fields = {
+            'author__id': ['exact'],
+            'concept__id': ['exact'],
+        }
+        interfaces = (graphene.relay.Node,)
+
+
+# === Query with Filtered Connections ===
+class Query(graphene.ObjectType):
+    institution = graphene.relay.Node.Field(InstitutionType)
+    all_institutions = DjangoFilterConnectionField(InstitutionType)
+
+    author = graphene.relay.Node.Field(AuthorType)
+    all_authors = DjangoFilterConnectionField(AuthorType)
+
+    affiliation = graphene.relay.Node.Field(AffiliationType)
+    all_affiliations = DjangoFilterConnectionField(AffiliationType)
+
+    domain = graphene.relay.Node.Field(DomainType)
+    all_domains = DjangoFilterConnectionField(DomainType)
+
+    field = graphene.relay.Node.Field(FieldType)
+    all_fields = DjangoFilterConnectionField(FieldType)
+
+    subfield = graphene.relay.Node.Field(SubfieldType)
+    all_subfields = DjangoFilterConnectionField(SubfieldType)
+
+    topic = graphene.relay.Node.Field(TopicType)
+    all_topics = DjangoFilterConnectionField(TopicType)
+
+    author_topic = graphene.relay.Node.Field(AuthorTopicType)
+    all_author_topics = DjangoFilterConnectionField(AuthorTopicType)
+
+    work = graphene.relay.Node.Field(WorkType)
+    all_works = DjangoFilterConnectionField(WorkType)
+
+    author_yearly_stats = graphene.relay.Node.Field(AuthorYearlyStatsType)
+    all_author_yearly_stats = DjangoFilterConnectionField(
+        AuthorYearlyStatsType)
+
+    concept = graphene.relay.Node.Field(ConceptType)
+    all_concepts = DjangoFilterConnectionField(ConceptType)
+
+    author_concept = graphene.relay.Node.Field(AuthorConceptType)
+    all_author_concepts = DjangoFilterConnectionField(AuthorConceptType)
+
+
+schema = graphene.Schema(query=Query)

core/tests.py

@@ -0,0 +1,3 @@
+from django.test import TestCase
+
+# Create your tests here.

core/views.py

@@ -0,0 +1,3 @@
+from django.shortcuts import render
+
+# Create your views here.

manage.py

@@ -0,0 +1,22 @@
+#!/usr/bin/env python
+"""Django's command-line utility for administrative tasks."""
+import os
+import sys
+
+
+def main():
+    """Run administrative tasks."""
+    os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'BridgeMentor.settings')
+    try:
+        from django.core.management import execute_from_command_line
+    except ImportError as exc:
+        raise ImportError(
+            "Couldn't import Django. Are you sure it's installed and "
+            "available on your PYTHONPATH environment variable? Did you "
+            "forget to activate a virtual environment?"
+        ) from exc
+    execute_from_command_line(sys.argv)
+
+
+if __name__ == '__main__':
+    main()

populate_user.py

@@ -0,0 +1,177 @@
+from django.utils.timezone import make_aware, is_naive
+from django.utils.dateparse import parse_datetime
+from tqdm import tqdm
+import glob
+import json
+from core.models import (
+    Author, Institution, Affiliation, Domain, Field, Subfield, Topic, AuthorTopic, AuthorYearlyStats, Concept, AuthorConcept
+)
+from urllib.parse import urlparse
+
+
+def parse_id_from_url(url):
+    try:
+        return urlparse(url).path.strip('/').split('/')[-1]
+    except Exception as e:
+        print(f"Error parsing URL {url}: {e}")
+        breakpoint()
+
+
+def add_author(user_info, updated_date):
+    author_id = parse_id_from_url(user_info["id"])
+    author, _ = Author.objects.update_or_create(
+        id=author_id,
+        defaults={
+            "name": max(user_info['display_name_alternatives'], key=lambda name: len(name)),
+            "orcid": parse_id_from_url(user_info["orcid"]) if user_info.get("orcid") else None,
+            "h_index": user_info["summary_stats"]["h_index"],
+            "i10_index": user_info["summary_stats"]["i10_index"],
+            "cited_by_count": user_info["cited_by_count"],
+            "works_count": user_info["works_count"],
+            "mean_2yr_citedness": user_info["summary_stats"]["2yr_mean_citedness"]
+        }
+    )
+    author.updated_at = updated_date
+    author.save(update_fields=["updated_at"])
+    return author
+
+
+def add_institution(inst_data):
+    inst_id = parse_id_from_url(inst_data["id"])
+    inst, _ = Institution.objects.update_or_create(
+        id=inst_id,
+        defaults={
+            "name": inst_data["display_name"],
+            "ror_id": parse_id_from_url(inst_data["ror"]),
+            "country_code": 'N/A' or inst_data.get("country_code"),
+            "institution_type": inst_data["type"]
+        }
+    )
+    return inst
+
+
+def add_affiliations(author, affiliations, last_known_insts):
+    last_known_ids = {parse_id_from_url(
+        inst["id"]) for inst in last_known_insts}
+    for aff in affiliations:
+        institution = add_institution(aff["institution"])
+        for year in aff["years"]:
+            Affiliation.objects.update_or_create(
+                author=author,
+                institution=institution,
+                year=year,
+                defaults={"is_last_known": institution.id in last_known_ids}
+            )
+
+
+def add_hierarchy(domain_data):
+    domain_id = parse_id_from_url(domain_data["id"])
+    domain, _ = Domain.objects.update_or_create(
+        id=domain_id, defaults={"name": domain_data["display_name"]})
+    return domain
+
+
+def add_field(field_data, domain_data):
+    domain = add_hierarchy(domain_data)
+    field_id = parse_id_from_url(field_data["id"])
+    field, _ = Field.objects.update_or_create(
+        id=field_id, defaults={
+            "name": field_data["display_name"], "domain": domain}
+    )
+    return field
+
+
+def add_subfield(subfield_data, field_data, domain_data):
+    field = add_field(field_data, domain_data)
+    subfield_id = parse_id_from_url(subfield_data["id"])
+    subfield, _ = Subfield.objects.update_or_create(
+        id=subfield_id, defaults={
+            "name": subfield_data["display_name"], "field": field}
+    )
+    return subfield
+
+
+def add_topic(author, topic_data, topic_share_map):
+    topic_id = parse_id_from_url(topic_data["id"])
+    subfield = add_subfield(
+        topic_data["subfield"], topic_data["field"], topic_data["domain"])
+    topic, _ = Topic.objects.update_or_create(
+        id=topic_id, defaults={
+            "name": topic_data["display_name"], "subfield": subfield}
+    )
+    share_value = topic_share_map.get(topic_id, 0)
+    AuthorTopic.objects.update_or_create(
+        author=author, topic=topic, defaults={
+            "count": topic_data["count"], "share_value": share_value}
+    )
+
+
+def add_topic_shares(topic_share_list):
+    return {parse_id_from_url(topic["id"]): topic["value"] for topic in topic_share_list}
+
+
+def add_yearly_stats(author, stats):
+    for stat in stats:
+        AuthorYearlyStats.objects.update_or_create(
+            author=author,
+            year=stat["year"],
+            defaults={
+                "works_count": stat["works_count"],
+                "cited_by_count": stat["cited_by_count"]
+            }
+        )
+
+
+def add_concepts(author, concepts):
+    for concept in concepts:
+        concept_id = parse_id_from_url(concept["id"])
+        obj, _ = Concept.objects.update_or_create(
+            id=concept_id,
+            defaults={
+                "name": concept["display_name"],
+                "wikidata_url": concept.get("wikidata"),
+                "level": concept["level"],
+                "score": concept["score"]
+            }
+        )
+        AuthorConcept.objects.update_or_create(
+            author=author,
+            concept=obj,
+            defaults={
+                "level": concept["level"],
+                "score": concept["score"]
+            }
+        )
+
+
+def populate_user(user_info):
+    author_id = parse_id_from_url(user_info["id"])
+    updated_date = parse_datetime(user_info["updated_date"])
+    author = Author.objects.filter(id=author_id).first()
+    if is_naive(updated_date):
+        updated_date = make_aware(updated_date)
+    if author and (author.updated_at >= updated_date):
+        return
+    author = add_author(user_info, updated_date)
+    add_affiliations(
+        author, user_info["affiliations"], user_info["last_known_institutions"])
+    topic_share_map = add_topic_shares(user_info["topic_share"])
+    for topic in user_info["topics"]:
+        add_topic(author, topic, topic_share_map)
+    add_yearly_stats(author, user_info["counts_by_year"])
+    add_concepts(author, user_info["x_concepts"])
+
+
+# Call this function to load data
+# populate_user(user_info)
+
+jsons = "/Users/sgautam/Documents/BridgeMentor/C41008148_authors"
+for page, json_file in tqdm(enumerate(glob.glob(f"{jsons}/*.json"))):
+    with open(json_file, "r") as file:
+        user_infos = json.load(file)['results']
+        for user_info in tqdm(user_infos, leave=False):
+            populate_user(user_info)
+            print(f"{page}-{user_info['display_name']}")
+
+# python manage.py shell
+# from populate_user import populate_user

requirements.txt

@@ -0,0 +1,3 @@
+django==4.2.20
+graphene-django
+django-filter

scrap_openalex.py

@@ -0,0 +1,38 @@
+import os
+import requests
+import json
+from time import sleep
+
+# Base API URL
+BASE_URL = "https://api.openalex.org/authors"
+FILTER = "last_known_institutions.country_code:NO,x_concepts.id:C41008148"
+PER_PAGE = 200
+TOTAL_RESULTS = 86500
+TOTAL_PAGES = (TOTAL_RESULTS + PER_PAGE - 1) // PER_PAGE  # Ceiling division
+
+# Output directory
+OUTPUT_DIR = "C41008148_authors"
+os.makedirs(OUTPUT_DIR, exist_ok=True)
+
+# Loop through pages
+for page in range(50, TOTAL_PAGES + 1):
+    url = f"{BASE_URL}?filter={FILTER}&per-page={PER_PAGE}&page={page}"
+    try:
+        print(f"Fetching page {page}...")
+        response = requests.get(url)
+        response.raise_for_status()
+        data = response.json()
+
+        filename = os.path.join(OUTPUT_DIR, f"{page:010}.json")
+        # skip if exists
+        if os.path.exists(filename):
+            print(f"File {filename} already exists, skipping...")
+            continue
+        with open(filename, 'w', encoding='utf-8') as f:
+            json.dump(data, f, ensure_ascii=False, indent=2)
+        sleep(1)  # Rate-limiting to avoid hitting the server too hard
+    except Exception as e:
+        print(f"Error on page {page}: {e}")
+        break
+
+print("Download complete.")