Transform: SKIL Transform Wrapper for for preprocessing (transform)...

In SkymindIO/skilr: Train, deploy and manage your R models with SKIL

Description

SKIL Transform Wrapper for for preprocessing (transform) steps. Currently only supports 'TransformProcess' instances from pydatavec or their serialized versions (JSON format).

Usage

Transform(transform = NULL, transform_id = NULL,
  transform_type = "CSV", name = NULL, version = NULL,
  experiment = NULL, labels = "", verbose = FALSE, create = TRUE)

Arguments

transform:	pydatavec.TransformProcess or TransformProcess JSON
transform_id:	integer. Unique id for the transform. If 'None', a unique id will be generated.
transform_type:	Type of the SKIL transform. Choose from "CSV", "image" or "array"
name:	string. Name for the transform.
version:	integer. Version of the transform. Defaults to 1.
experiment:	'Experiment' instance. If 'None', an 'Experiment' object will be created internally.
labels:	string. Labels associated with the workspace, useful for searching (comma separated).
verbose:	boolean. If 'True', prints api response.
create:	boolean. Internal. Do not use.

Examples

## Not run: 
library(skilr)

# Creating a SKIL experiment
skil  <- Skil(host='localhost', port=9008, user_id='admin', password='admin')
ws    <- Workspace(skil, name='test_workspace')
exp   <- Experiment(ws, name='test_experiment')
trans <- Transform(transform="iris.json", name="my_pydatavec_transform", experiment=exp)


## End(Not run)

SkymindIO/skilr documentation built on May 26, 2019, 1:42 a.m.