briandesilva
commented
3 years ago Unfortunately we don't currently have any built-in methods with the functionality you're suggesting. I'm also unaware of any functions for grouping sensors. I think your best bet is probably to implement a custom method. You could write a function that maps from the expanded sensor index (0 to 1999) to the original sensor index (0 to 19). Then you could apply this function to selected_sensors. A few ideas for how to proceed from there:
- Pick the first k unique sensors to appear
- Of the top n features, choose the k which appear most often
- Use the individual sensor "saliences" (from the
sensor_coef_attribute) to help decide which sensors to use, e.g. sum up the saliences across features for each sensor and select the k sensors with the highest scores. See theupdate_sensorssource code for examples of how to work withsensor_coef_.
Dear team,
Firstly, many thanks for your fantastic work on SSPOC and also for providing this package. This is indeed a beneficial resource.
I am currently using PySensors to find the minimal sensors required for a classification task. However, instead of running this directly on the actual sensor count, I intend to input the extracted features and then select the number of sensors.
Specifically, I have data from 20 sensors, and I calculate 100 features/sensor. This results in a matrix with 2000 columns. In other words, the SSPOC algorithm treats this as a problem with 2000 sensors. While the _'selectedsensors' lists the particular feature that can be traced back to the corresponding sensor. I would be grateful if you could please link me to any inbuilt function for grouping the sensors or any other voting mechanism that I may use or implement?
Thanks a lot for your time.