sklearn.ensemble.GradientBoostingClassifierand upload it to the Hydrosphere cluster.
requirements.txtis a list of Python dependencies used during the process of building model image.
serving.yamlis a resource definition that describes how model should be built and uploaded to Hydrosphere platform.
train.pyis used to generate a
model.joblibwhich is loaded from
func_main.pyduring model serving.
python train.pyto generate
func_main.pyis a script which serves requests and produces responses.
hs applyfrom the command line.
FOOenvironment variable with value
with_replicaswas successful by calling
kubectl get deployment -A -o wideand checking the
with_hpawas successful you should get a list of all created Horizontal Pod Autoscaler Resources. You can do so by calling
kubectl get hpa -A
kubectl exec my-model-1-tumbling-star -it /bin/bashand then execute the
printenvcommand which prints ann system variables.