This is part of a TEDx-Project; their Blog about this Contest and nostradamIQ's Blog entery!
See the Pitch!
The idea is to make the world a safe place by making nostradamIQ-prediction more efficient. This will also lead to a nice tool for visualizing all kinds of natural phenomena, easily searchable with a timescale and choosable info-layers. The core-feature, though, is going to be a layer showing the probability for natural disasters determined by learning time and location based sequences and utilizing other tools like detecting anomal abnormal behavior, preassure and temperature anomalies and (hopefully) combining all to one useful and accurate prediction tool to help local governments and organisations to focus research and prepare for possible nostradamIQs.
"There are only patterns, patterns on top of patterns, patterns that affect other patterns. Patterns hidden by patterns. Patterns within patterns. If you watch close, history does nothing but repeat itself." -Someone smart
- NuPIC
- Redis running locally
- Python, and dependencies
- Google Maps Javascript API Key
- Possibly:
- Cerebro2
- MySQLdb
Include your API-Keys in webapp/API_KEYS.py (MAPS_API_KEY=< your API_KEY>)
-
Start redis
$ redis-server
-
Start
run.py$ python run.py
-
Start webapp
$ cd webapp $ python serve.py -
Open http://localhost:8080 in browser
Include your API-Keys in webapp/API_KEYS.py (MAPS_API_KEY=< your API_KEY>) Download and install Docker client, Virtualbox, and Vagrant, and then:
source env.sh
vagrant up
docker build -t nostradamIQ .
docker run --name nostradamIQ-redis -d -p 0.0.0.0:6379:6379 redis
docker run \
--name nostradamIQ-server \
--link nostradamIQ-redis:broker \
-e REDIS_HOST=broker \
-d \
-p 0.0.0.0:8080:8080 \
-w /opt/numenta/nostradamIQ/webapp \
nostradamIQ \
python serve.py
docker run \
--link nostradamIQ-redis:broker \
-e REDIS_HOST=broker \
nostradamIQ \
python run.py
Redis, the nostradamIQ web service, and the nostradamIQ entry point are now running in separate containers in a vm. You should be able to access the web service in a browser at http://localhost:8080
Thanks to the NuPIC-Community, Austin, Lab75 and many more for help!