rf-pool-classifier

A GBDX task that trains a random forest classifier to classify polygons of arbitrary geometry into those that contain swimming pools and those that do not.

Run

Here we run a sample execution of the rf-pool-classifier task. Sample inputs are provided on S3 in the locations specified below.

In a Python terminal create a GBDX interface and specify the task input location:

from gbdxtools import Interface
from os.path import join
import uuid

gbdx = Interface()

input_location = 's3://gbd-customer-data/32cbab7a-4307-40c8-bb31-e2de32f940c2/platform-stories/rf-pool-classifier/'

Create a task instance and set the required inputs:

rf_task = gbdx.Task('rf-pool-classifier')
rf_task.inputs.image = join(input_location, 'image')
rf_task.inputs.geojson = join(input_location, 'geojson')
rf_task.inputs.n_estimators = "1000"

Create a single-task workflow object and define where the output data should be saved.

workflow = gbdx.Workflow([rf_task])
random_str = str(uuid.uuid4())
output_location = join('platform-stories/trial-runs', random_str)

workflow.savedata(rf_task.outputs.trained_classifier, output_location)

Execute the workflow and monitor its status as follows:
```
workflow.execute()
workflow.status
```

Input Ports

GBDX input ports can only be of "Directory" or "String" type. Booleans, integers and floats are passed to the task as strings, e.g., "True", "10", "0.001".

Name	Type	Description	Required
image	directory	Contains the image strip where the polygons are found.	True
geojson	directory	Contains a geojson with labeled polygons. Each polygon has the properties feature_id, image_id, and class_name (either 'No swimming pool' or 'Swimming pool')	True
n_estimators	string	Number of trees to use in the random forest classifier. Defaults to 100.	False

Output Ports

Name	Type	Description
trained_classifier	directory	Contains the file 'classifier.pkl' which is the trained random forest classifier.

Development

Build the Docker Image

You need to install Docker.

Clone the repository:

git clone https://github.com/platformstories/rf-pool-classifier

Then

cd rf-pool-classifier
docker build -t rf-pool-classifier .

Try out locally

Create a container in interactive mode and mount the sample input under /mnt/work/input/:

docker run --rm -v full/path/to/sample-input:/mnt/work/input -it rf-pool-classifier

Then, within the container:

python /rf-pool-classifier.py

Docker Hub

docker login

Tag your image using your username and push it to DockerHub:

docker tag rf-pool-classifier yourusername/rf-pool-classifier
docker push yourusername/rf-pool-classifier

The image name should be the same as the image name under containerDescriptors in rf-pool-classifier.json.

Alternatively, you can link this repository to a Docker automated build. Every time you push a change to the repository, the Docker image gets automatically updated.

Register on GBDX

In a Python terminal:

from gbdxtools import Interface
gbdx=Interface()
gbdx.task_registry.register(json_filename="rf-pool-classifier-definition.json")

Note: If you change the task image, you need to reregister the task with a higher version number in order for the new image to take effect. Keep this in mind especially if you use Docker automated build.

PlatformStories/rf-pool-classifier