Icon

3. Time_​Series_​no_​flowvars

Time Series Analysis with Machine Learning

This workflow shows an example of time series analysis using the pre-packaged metanodes Time Series Auto-Prediction Training and Time Series Auto-Prediction Predictor.

After reading the time series of the number of visitor to a web site, we want to predict today's number of visitory given the number of visitors in the past N=5 days.

Here we use the Linear Regression, but any other numerical prediction algorithm would have worked as well.

Workflow: Time_Series This workflow shows an example of time series analysis using some of the pre-packaged components in "00_Components/TimeSeries" on the EXAMPLES server..After reading the time series of the number of visitor to a web site, we want to predict next day's number of visitors given thenumber of visitors in the past N=7 days.Here we use the Linear Regression, but any other numerical prediction algorithm would have worked as well. Preliminary steps Dealing with Seasonality Training and Testing Rebuilding the signal Lag Value= 7remove missing valuessort by ascending timeLag Value = 7daily numberof visitors"allow for short lines"must be enabledtake from the topLag Value= 7from x(t) to: x(t), x(t-1), x(t-2), ..., x(t-lag)lag =Nfrom x(t) to: x(t), x(t-1), x(t-2), ..., x(t-lag)lag = NNode 238on predictionson no visitors Inspect Seasonality clean and sorttime series Remove Seasonality Line Plot CSV Reader Partitioning Remove Seasonality Lag Column Linear RegressionLearner Lag Column RegressionPredictor Reshape data Reshape data Return Seasonality Line Plot Return Seasonality Numeric Scorer Workflow: Time_Series This workflow shows an example of time series analysis using some of the pre-packaged components in "00_Components/TimeSeries" on the EXAMPLES server..After reading the time series of the number of visitor to a web site, we want to predict next day's number of visitors given thenumber of visitors in the past N=7 days.Here we use the Linear Regression, but any other numerical prediction algorithm would have worked as well. Preliminary steps Dealing with Seasonality Training and Testing Rebuilding the signal Lag Value= 7remove missing valuessort by ascending timeLag Value = 7daily numberof visitors"allow for short lines"must be enabledtake from the topLag Value= 7from x(t) to: x(t), x(t-1), x(t-2), ..., x(t-lag)lag =Nfrom x(t) to: x(t), x(t-1), x(t-2), ..., x(t-lag)lag = NNode 238on predictionson no visitors Inspect Seasonality clean and sorttime series Remove Seasonality Line Plot CSV Reader Partitioning Remove Seasonality Lag Column Linear RegressionLearner Lag Column RegressionPredictor Reshape data Reshape data Return Seasonality Line Plot Return Seasonality Numeric Scorer

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: rosy
Created at: 2014-09-29
On NodePit since: 2023-01-23
Last update: 2024-04-27
Created with KNIME version: v4.4.0
Tags: BooksKNIME Advanced LuckTime SeriesTime Series AnalysisMachine LearningAuto-RegressionARLinear Regression

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

Try NodePit Runner!