No description, website, or topics provided.
Switch branches/tags
Nothing to show
Clone or download
Latest commit cb7a22a Jan 3, 2018
Permalink
Failed to load latest commit information.
data first commit Dec 27, 2017
project first commit Dec 27, 2017
src/main/scala/org/jpioug/template first commit Dec 27, 2017
.gitignore first commit Dec 27, 2017
LICENSE.txt first commit Dec 27, 2017
README.md update doc Dec 27, 2017
build.sbt first commit Dec 27, 2017
docker-compose.yml first commit Dec 27, 2017
eda.ipynb update analysis Jan 3, 2018
engine.json first commit Dec 27, 2017
run.sh first commit Dec 27, 2017
template.json first commit Dec 27, 2017
train.py first commit Dec 27, 2017

README.md

PredictionIO Template: House Prices

Overview

This repository is PredictionIO Template for House Prices: Advanced Regression Techniques on Kaggle.

Dataset

Download train.csv and test.csv from Data and put them to data directory.

Requirement

  • Docker

Getting Started

Run Jupyter

PIO_MODE=jupyter docker-compose up --abort-on-container-exit

Open eda.ipynb at Jupyter Notebook page(http://localhost:8888/).

Run Train Steps on Docker

train mode executes create-app, import-data, build and train process.

PIO_MODE=train docker-compose up --abort-on-container-exit

Run Deploy Step on Docker

deploy mode starts Rest API on Docker container.

PIO_MODE=deploy docker-compose up --abort-on-container-exit

and then check a prediction:

curl -s -H "Content-Type: application/json" -d '{"attr0":5.1,"attr1":3.5,"attr2":1.4,"attr3":0.2}' http://localhost:8000/queries.json