Hi I would like to ask, how is it I am able to create a linear regression tables based on for my case power usage over time?
Could you give an example input (xlsx file, etc.) and expand on what you would like as final output?
I went to the KNIME hub and found a workflow which may interest you:
This workflow builds an auto-regressive model to predict energy usage. The first week of the time series is used as a template for seasonality correction: the data are differenced by subtracting the values in the same hour in the previous week from the current values. Only past time series are used for prediction. No other external time series/data used. The regression model can be either a linear or a polynomial regression model.
So initially my data set is based of a 10min interval over the course of 2 months
I am required to append my data set with a 1hr interval and select only 1 day from the 2 months to be used for linear regression with another observation ( energy consumption etc).
Hi there is a linear regression learner and predictor node. So you can preprocess your data the way you need it then split it and feed the training data to the learner node. I would also take a look at @victor_palacios link as it might be a better option for you.
In general always attach sample data so it’s easier for all the smart guys and girls here to help.
Thanks, I have looked through it, just trying to figure it out right now. This is my data set, where I’m trying to create a linear regression along with the appliances over time stamp
@Daniel_Weikert, I have tried the steps you mentioned previously but I have many missing values. So regarding that how do I go about it? Im sorry but I am really new to knime.
I do not necessarily think this is a KNIME specific question, rather Statistics or ML.
Missing Values could be imputed, dropped,… You can take a look at the Missing Value Node for that
br and take care
This topic was automatically closed 182 days after the last reply. New replies are no longer allowed.