Icon

Day5 Analytics - Cost Prediction with PyCaret

Day5 Analytics - Cost Prediction with PyCaret
Model Predictions captured for Integrated Deployment Data Pre-Processing for Integrated DeploymentTrain/Test Split for machine learning Model Training (PyCaret)Leverage the 'Conda Environment Propagation' node if needed to supportmultiple environments in a single workflow! Average Cost Estimation Method Enter Service Request Data Save Integrated Deployment Workflow for predictions against new data Compare PyCaret prediction to Average Cost estimationMean Absolute Error as the comparison metric (smaller MAE means theprediction is closer to the actual cost) This workflow demonstrates the application of PyCaret Automated Machine learning within KNIME, using KNIME's integrated deployment capability.The goal is to predict a service request cost better than a simple average method, and the results are compared using Mean Absolute Error at a category level.The deployed workflow will predict costs for unseen data.This model is part 1 of a multi-part blog series by Day5 Analytics, demonstrating deployment of powerful technologies for enterprise success. Visit www.day5analytics.com formore.Note: PyCaret requires a python environment with pycaret installed, and the environment available within KNIME (search 'Machine Learning in KNIME with PyCaret' on Medium) Test/train splitCalculate Average Price per serviceJoin Service Average price with Cost CalculateAbsolute errorCalculate MAE per Service typeCalculateAbsolute errorCalculate MAEper Service typeRight click View Interactive TablesRemove datetime columnPre-ProcessingStartPre-ProcessingEndMake PredictionStartMake PredictionEndCollect CapturedPre-Processingand PredictionWorkflowsEncodeCategoricalVariablesPyCaret PredictorCategoricalVariables returnedNumber to CategoryWrite CapturedWorkflowsCreate Data Partitioning GroupBy Joiner Math Formula GroupBy Math Formula GroupBy Cost PredictionComparison Column Filter CaptureWorkflow Start CaptureWorkflow End CaptureWorkflow Start CaptureWorkflow End Workflow Combiner Category To Number Python Predictor Number ToCategory (Apply) Number ToCategory (Apply) Workflow Writer PyCaret Learner Table Creator Model Predictions captured for Integrated Deployment Data Pre-Processing for Integrated DeploymentTrain/Test Split for machine learning Model Training (PyCaret)Leverage the 'Conda Environment Propagation' node if needed to supportmultiple environments in a single workflow! Average Cost Estimation Method Enter Service Request Data Save Integrated Deployment Workflow for predictions against new data Compare PyCaret prediction to Average Cost estimationMean Absolute Error as the comparison metric (smaller MAE means theprediction is closer to the actual cost) This workflow demonstrates the application of PyCaret Automated Machine learning within KNIME, using KNIME's integrated deployment capability.The goal is to predict a service request cost better than a simple average method, and the results are compared using Mean Absolute Error at a category level.The deployed workflow will predict costs for unseen data.This model is part 1 of a multi-part blog series by Day5 Analytics, demonstrating deployment of powerful technologies for enterprise success. Visit www.day5analytics.com formore.Note: PyCaret requires a python environment with pycaret installed, and the environment available within KNIME (search 'Machine Learning in KNIME with PyCaret' on Medium) Test/train splitCalculate Average Price per serviceJoin Service Average price with Cost CalculateAbsolute errorCalculate MAE per Service typeCalculateAbsolute errorCalculate MAEper Service typeRight click View Interactive TablesRemove datetime columnPre-ProcessingStartPre-ProcessingEndMake PredictionStartMake PredictionEndCollect CapturedPre-Processingand PredictionWorkflowsEncodeCategoricalVariablesPyCaret PredictorCategoricalVariables returnedNumber to CategoryWrite CapturedWorkflowsCreate Data Partitioning GroupBy Joiner Math Formula GroupBy Math Formula GroupBy Cost PredictionComparison Column Filter CaptureWorkflow Start CaptureWorkflow End CaptureWorkflow Start CaptureWorkflow End Workflow Combiner Category To Number Python Predictor Number ToCategory (Apply) Number ToCategory (Apply) Workflow Writer PyCaret Learner Table Creator

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: prabh
Created at: 2021-01-20
On NodePit since: 2021-08-31
Last update: 2024-04-24
Created with KNIME version: v4.3.3
Tags: machine learningPyCaretPythonIntegrated DeploymentCapture Workflow

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

Try NodePit Runner!