Icon

Group3_​Deployment_​Model

Group 3 Deployment Model
Group 3. Deployment Challenge: Predict Results using REST APIGoal: Create a model deployment workflow. Execute it using the Call Workflow (Table Based) node or an external tool such as Postman or Curl.Datasets: In data/1_Input/Group3, you'll find the BestModel.model file, which contains a random forest model.Suggested Steps:- Read the BestModel.model file from disk. This allows the model to be updated by a separate workflow that can be run according to a schedule. (Model Reader node)- Predict the departure delay for the data coming from the Container Input (Table) node (Random Forest Predictor node)- Convert the predicted data into JSON format (Table to JSON node)- Output the data with the Container Output (Table) node- Execute the Group3_Call_Workflow locally (Group3_Call_Workflow workflow)Optional Steps:- Deploy the workflow Group3_Deployment_Model, Group3_Call_Workflow and the data folder to KNIME Server. Keep the same structure between the workflows and the datafolder!- Execute the Group3_Call_Workflow workflow on KNIME ServerReference workflow available on the EXAMPLES Server at: 50_Applications/27_Deployment_Options/03_Model_Deployment_as_REST_APIAnd on KNIME Hub:https://kni.me/w/CWUSI19hdVidihQy Optional input directly forwarded to the output of the node, unless overwritten by supplying a table via the REST API ContainerInput (Table) Table Reader Group 3. Deployment Challenge: Predict Results using REST APIGoal: Create a model deployment workflow. Execute it using the Call Workflow (Table Based) node or an external tool such as Postman or Curl.Datasets: In data/1_Input/Group3, you'll find the BestModel.model file, which contains a random forest model.Suggested Steps:- Read the BestModel.model file from disk. This allows the model to be updated by a separate workflow that can be run according to a schedule. (Model Reader node)- Predict the departure delay for the data coming from the Container Input (Table) node (Random Forest Predictor node)- Convert the predicted data into JSON format (Table to JSON node)- Output the data with the Container Output (Table) node- Execute the Group3_Call_Workflow locally (Group3_Call_Workflow workflow)Optional Steps:- Deploy the workflow Group3_Deployment_Model, Group3_Call_Workflow and the data folder to KNIME Server. Keep the same structure between the workflows and the datafolder!- Execute the Group3_Call_Workflow workflow on KNIME ServerReference workflow available on the EXAMPLES Server at: 50_Applications/27_Deployment_Options/03_Model_Deployment_as_REST_APIAnd on KNIME Hub:https://kni.me/w/CWUSI19hdVidihQy Optional input directly forwarded to the output of the node, unless overwritten by supplying a table via the REST API ContainerInput (Table) Table Reader

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: Vincenzo
Created at: 2017-08-23
On NodePit since: 2021-04-15
Last update: 2024-05-02
Created with KNIME version: v4.3.1
Tags: DeploymentSchedulingModelPredictionJSONRESTExternal ApplicationKNIME Server

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!