Windowing issues when doing "Generate features"

Question/Issue:
I imported diurnal fridge temperatures with timestamps via CSV. I then created my impuls (window size & window increase, raw data, Keras Regression). In the next step (“Raw data” tab), my data are displayed correctly, I leave the scaling at 1 and press “save parameters”. When finally trying to “generate features”, I always get this error:

Scheduling job in cluster...
Job started
Scheduling job in cluster...
Job started
Creating windows from files...
[0/0] Creating windows from files...
Error windowing Reduce of empty array with no initial value
TypeError: Reduce of empty array with no initial value
    at Array.reduce (<anonymous>)
    at createWindows (/app/node/windowing/build/window-time-series.js:107:67)
    at async /app/node/windowing/build/window-time-series.js:29:13
Application exited with code 1

Job failed (see above)

I did try to adjust window size & window increase in all combinations I could think of. I just don’t get it to run. Any hints?

Project ID:
139207

Context/Use case:
Getting first experiences; trying to make an edge-device learn when a fridge door is left open for too long.

Hi @Goldenboy,

You need to assign a label to your training data.

Thank you, that did the trick. I was not aware a missing label might produce such error.

1 Like