Data migration and normalization pipeline for the cihjml (Centro de Investigaciones Históricas José María Arboleda Llorente).
This repository processes and normalizes archival collection data, including:
- Date normalization and validation
- Geographic entity recognition and gazetteer matching
- Collection metadata processing
- Data quality diagnostics
procesar.py- Main processing pipelinecorrector.py- Data correction modules (dates, places, collections, entities)datenormalizer.py- Date parsing and standardizationdiagnostics.py- Data quality checksent_reconocimiento.py- Entity recognitiongazeetter.py/lugares.py- Geographic place matching
pip install -r requirements.txtInput/output CSV files are stored in the data/ directory.