Skip to content

This microservice will be the one in charge of retriving the ML predictions from the trained models

License

Notifications You must be signed in to change notification settings

Skydipper/GeoPredictor

Repository files navigation

GeoPredictor

Receives a geoJson/geostore id, a model and generates a prediction.

Lists all models and allows filtering by datasetID, type, architecture...

Working Postman collection with endpoints

The knowledge sorce came from this medium article

For the AI part of the project the knowledge came from https://github.com/Skydipper/CNN-tests

development

You will need to have installed docker and docker-compose;

You will need to have control tower and geostore up and running.

Don't forget to populate your .env file with the requirements

run sh geopredictor.sh develop

After pgadmin is up and running you can http://0.0.0.0:16543/ to load into pg-admin. In order to connect with the DB you should create server connection with network as the hostname, the port, username and password that you seted up on your .env file

For the microservice endpoint you should be able to access http://0.0.0.0:6868/ or if working with CT http://0.0.0.0:9000/v1/model

In order to populate the DB you will need to update the data as you need on the /data folder. You will need to connect to the postgres container. To do so: docker exec -it geo-postgres-compose /bin/bash cd /data_import sh import_data.sh To export the DB: pg_dump -U postgres geopredictor > geopredictor.pgsql

Tests

TODO

Deployment

TODO

About

This microservice will be the one in charge of retriving the ML predictions from the trained models

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published