feat(dr-anticorruption): initial MVP module structure and API

modules/dr-anticorruption/Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 8000
+
+CMD ["uvicorn", "src.api.main:app", "--host", "0.0.0.0", "--port", "8000"]

modules/dr-anticorruption/README.md

@@ -1,4 +1,73 @@
-# DR Anti-Corruption
-Owner: Brian Collado
-Goal: /ingest, /risk, /graph, /brief with official DR sources.
+# DR Anti-Corruption Module (Dominican Republic)
 
+This module provides an end-to-end pipeline for detecting corruption risks in public procurement in the Dominican Republic. It ingests official sources, connects entities, calculates risk scores, and generates evidence-backed policy briefs.
+
+## 🚀 Overview
+- **Lead:** Brian Collado
+- **Scope:** DR procurement data -> Entity/Contract linking -> Risk indicators -> Evidence-linked briefs.
+- **Status:** MVP Implementation.
+
+## 📥 Inputs & 📤 Outputs
+
+### Inputs
+- **Procurement Data:** Official JSON/Excel files from DGCP (Dirección General de Contrataciones Públicas).
+- **Target Entities:** RPE (Registro de Proveedores del Estado) or company names for tailored risk analysis.
+- **Config Parameters:** Custom thresholds for activation spikes, bidder concentration, and flags for politically exposed persons (PEPs).
+
+### Outputs
+- **Risk Score:** Numerical score (0-100) indicating corruption risk.
+- **Risk Level:** Categorical risk (LOW, MEDIUM, HIGH, CRITICAL).
+- **Evidence Graph:** Relationship mapping between companies, owners, and contracts.
+- **Policy Brief:** Contextual summary of findings with citations to specific contracts or legal violations.
+
+## 🛠 How to Run
+
+### Docker (Recommended)
+The module is designed to run in a containerized environment.
+
+```bash
+docker-compose up -d
+```
+Access the API at `http://localhost:8000`.
+
+### Local Development
+1. Install dependencies:
+   ```bash
+   pip install -r requirements.txt
+   ```
+2. Run ingestion pipeline:
+   ```bash
+   python src/cli.py ingest --target all
+   ```
+3. Start the API:
+   ```bash
+   uvicorn src.api.main:app --host 0.0.0.0 --port 8000
+   ```
+
+## 🌐 API Interface (MVP)
+
+| Endpoint | Method | Description |
+| :--- | :--- | :--- |
+| `/ingest` | `POST` | Triggers background ingestion of official DR sources. |
+| `/risk` | `POST` | Returns a detailed risk report for a specific entity. |
+| `/graph` | `GET` | Returns JSON representation of the entity's network. |
+| `/brief` | `POST` | Generates a 1-page PDF/Text brief with evidence. |
+
+### Example Scenario
+**Goal:** Analyze a suspicious supplier involved in multiple "emergency" contracts.
+1. **Request:** `POST /risk` with `{"entity_id": "12345"}`.
+2. **Response:** 
+   ```json
+   {
+     "risk_score": 85.5,
+     "level": "HIGH",
+     "factors": ["Concentration of emergency contracts", "Shared ownership with public official"],
+     "evidence": ["Contract #992-2023", "Public Gazette Ref ID: X"]
+   }
+   ```
+
+## 📂 Project Structure
+- `src/api/`: FastAPI implementation.
+- `src/core/`: Risk engine, Forensic analyzers, and Brief generator.
+- `src/data/`: Data management and persistence (SQLite/Postgres).
+- `config/`: Configuration for thresholds and API keys.

modules/dr-anticorruption/config/config.yaml

@@ -0,0 +1,189 @@
+data:
+  dir: data
+
+logging:
+  level: INFO
+  file: ingestion.log
+
+dgcp:
+  base_url: https://datosabiertos.dgcp.gob.do/api-dgcp/v1
+  rate_limit_delay: 0.2
+  max_retries: 5
+  timeout_connect: 10
+  timeout_read: 30
+
+risk:
+  thresholds:
+    critical: 75
+    high: 50
+    medium: 25
+  new_company_years: ['2024', '2025', '2026']
+  hub_density_high: 20
+  hub_density_medium: 5
+
+forensics:
+  versatility_threshold: 2
+  activation_concentration: 0.6
+  activation_min_contracts: 10
+  activation_30d_max: 10
+
+keywords:
+  industries:
+    medical:
+      - salud
+      - hospital
+      - medico
+      - farmacia
+      - medicamento
+      - laboratorio
+      - reactivo
+      - clinico
+      - quirurgico
+      - insumo
+      - oxigeno
+      - suero
+      - pastillas
+      - jarabe
+      - sonda
+      - jeringa
+      - hilo
+      - cateter
+      - guante
+      - mascarilla
+      - sutura
+      - antibiotico
+      - analgesico
+    construction:
+      - obra
+      - construc
+      - ingenier
+      - remodelacion
+      - mantenimiento fisico
+      - reparacion
+      - pintura
+      - cemento
+      - varilla
+      - ferreteria
+      - asfalt
+      - acero
+      - edific
+      - tuberia
+      - electrico
+      - plomeria
+    food:
+      - aliment
+      - comida
+      - desayuno
+      - almuerzo
+      - catering
+      - buffet
+      - cocina
+      - bebida
+      - picadera
+      - refrigerio
+      - pan
+      - agua
+      - jugo
+      - cafe
+      - botella
+    it:
+      - computadora
+      - laptop
+      - toner
+      - papel
+      - oficina
+      - software
+      - licencia
+      - informatica
+      - tecnologia
+      - impresora
+      - cartucho
+      - redes
+      - internet
+      - disco duro
+      - ups
+      - monitor
+      - cable
+    transport:
+      - transporte
+      - vehiculo
+      - combustible
+      - taller
+      - repuesto
+      - goma
+      - bateria
+      - neumatico
+      - chofer
+      - camion
+      - guagua
+      - motor
+      - mecanic
+      - aceite
+      - lubricante
+      - freno
+    cleaning:
+      - limpieza
+      - aseo
+      - fumigacion
+      - conserje
+      - desechos
+      - basura
+      - jardineria
+      - desinfeccion
+      - lavado
+      - detergente
+      - escoba
+      - suape
+    event:
+      - evento
+      - publicidad
+      - impresion
+      - montaje
+      - sonido
+      - banner
+      - rotulo
+      - regalo
+      - bono
+  risk_news:
+    - corrupcion
+    - soborno
+    - fraude
+    - peculado
+    - lavado de activos
+    - estafa
+    - investigacion
+    - imputado
+    - acusado
+    - irregularidad
+    - sobrevaluacion
+    - vinculado
+    - testaferro
+    - clonacion
+  investigative:
+    - Nuria
+    - Alicia Ortega
+    - Acento
+    - SIN
+  whistleblowers:
+    - somos pueblo
+    - tolentino
+    - cavada
+    - espresate
+
+api:
+  host: 0.0.0.0
+  port: 8000
+
+news:
+  region: DO
+  language: es-419
+  lookback_years: 5
+
+minio:
+  endpoint: http://localhost:9000
+  access_key: minioadmin
+  secret_key: minioadmin
+  bucket: s3-raw
+
+postgres:
+  dsn: postgresql://postgres:postgres@localhost:5432/datalake

modules/dr-anticorruption/docker-compose.yml

@@ -0,0 +1,58 @@
+version: '3.8'
+
+services:
+  api:
+    build: .
+    ports:
+      - "8000:8000"
+    volumes:
+      - .:/app
+    environment:
+      - PYTHONPATH=/app/src
+    command: uvicorn src.api.main:app --host 0.0.0.0 --port 8000 --reload
+    depends_on:
+      - redis
+      - postgres
+      - minio
+  redis:
+    image: redis:alpine
+    ports:
+      - "6379:6379"
+    volumes:
+      - redis_data:/data
+  postgres:
+    image: postgres:15
+    environment:
+      POSTGRES_DB: datalake
+      POSTGRES_USER: postgres
+      POSTGRES_PASSWORD: postgres
+    ports:
+      - "5432:5432"
+    volumes:
+      - postgres_data:/var/lib/postgresql/data
+    healthcheck:
+      test: [ "CMD-SHELL", "pg_isready -U postgres -d datalake" ]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+  minio:
+    image: quay.io/minio/minio:latest
+    command: server /data --console-address ":9001"
+    environment:
+      MINIO_ROOT_USER: minioadmin
+      MINIO_ROOT_PASSWORD: minioadmin
+    ports:
+      - "9000:9000"
+      - "9001:9001"
+    volumes:
+      - minio_data:/data
+    healthcheck:
+      test: [ "CMD", "curl", "-f", "http://localhost:9000/minio/health/live" ]
+      interval: 30s
+      timeout: 20s
+      retries: 3
+
+volumes:
+  redis_data:
+  postgres_data:
+  minio_data:

modules/dr-anticorruption/pyproject.toml

@@ -0,0 +1,51 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "dr-anticorruption"
+version = "0.2.0"
+description = "Anti-corruption analysis platform for DR procurement data"
+readme = "README.md"
+requires-python = ">=3.11"
+dependencies = [
+    "fastapi==0.115.0",
+    "uvicorn[standard]==0.32.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest==8.3.3",
+    "pytest-cov==5.0.0",
+    "black==24.8.0",
+    "isort==5.13.2",
+    "mypy==1.11.2",
+    "types-requests==2.32.0.202409.1",
+]
+
+[tool.black]
+line-length = 88
+target-version = ['py311']
+
+[tool.isort]
+profile = "black"
+line_length = 88
+
+[tool.mypy]
+python_version = "3.11"
+warn_return_any = true
+warn_unused_configs = true
+disallow_untyped_defs = true
+disallow_incomplete_defs = true
+
+[tool.pytest.ini_options]
+addopts = "-ra --strict-markers --strict-config --cov=src --cov-report=html --cov-report=term-missing"
+testpaths = ["tests"]
+markers = [
+    "slow: Marks tests as slow",
+    "integration: Integration tests"
+]
+
+[tool.setuptools.packages.find]
+where = ["src"]
+namespaces = false