This is a series of scripts for translating categorical values from spanish to english This repository contains the following files:
- DATA/: In this folder all the source files sould be placed
- requirements.txt: This file contains all the library requirements for running the translation
- settings.py: Contains all the value mappings from spanish to english
- transformer.py: This is the execution script of the EREN dataset translation
- Have Python 3.7 installed
- Install python requirements
pip install -r requirements.txt
- Create DATA repository and download the following files and put them in DATA folder:
- Regional Administration Consumer centers name this file as
centros-de-consumo-energetico-de-la-administracion-autonoma-de-castilla-y-leon.csv
- Electricity consumption of the Regional Administration buildings name this file as
consumo-de-electricidad-en-centros-de-la-administracion-autonomica-de-castilla-y.csv
- Natural gas consumption of the Regional Administration buildings name this file as
consumo-de-gas-en-centros-de-la-administracion-autonomica-de-castilla-y-leon.csv
- Diesel consumption in education, health and culture centres of the Regional Administration of Castilla y León name this file as
consumo-de-gasoil-en-centros-de-educacion-y-sanidad-de-la-administracion-autonom.csv
- Energy efficiency certificates name this file as
certificados-de-eficiencia-energetica.csv
- Hourly electricity consumption in hospitals name this file as
consumos-horarios-en-hospitales.csv
- Regional Administration Consumer centers name this file as
- Put the EREN datasets to DATA/ directory
- Execute this command for installing python requirements:
pip install -r requirements.txt
- Execute this script:
python transformer.py
The translated datasets will be generated to the OUTPUT/ folder