Burrobot is a prototype of conversational agent popularly known as chatbot that will interact with users using Artificial Intelligence and NLP techniques integrated into Facebook Messenger network.
En caso de que la bandera de DB se encuentre en verdadero y no se pueda establecer una conexión con la base de datos, cambiarla a falso para prevenir errores.
By the moment the mongo helper class in the scraper module doesn't validate if the document trying to insert already exists, implement this functionality, if the document's message id already exists (not _id, this _id it's created by mongo) only update the message not re-insert it.
Configure a logger for topics modeling, this logger must sent it's output a tmp file named topic.log and each element must be a LDA output that will be plotted.
Create the initial configuration for the NLP project.
The NLP project must be able to take the information retrivered from scraper (mongodb or file system storage) and clean that data, make exploratory analysis, get the most related topics, use analizers like gensim, etc., by the moment an initial configuration is enough.
The introduction must have the following information.
1.- Presentación.
2.- Motivación.
3.- Planteamiento del problema.
4.- Objetivos.
5.- Objetivo general.
6.- Objetivo especifico.
7.- Estado del arte.
8.- Descripción del documento.
Prepare the Python's scraper initial configuration for downloading messages from Facebook and retrieve linguistic information.
1.- Create a folder for the scraper program.
2.- Upload pipenv file with dependencies.
3.- Pipenv file must include development dependencies.
4.- Add README.md for a proper configuration and an explanation of how to execute the program.