The following two figures show raw data and filtered data recorded in a measurement. I have used SciPy's Savizky-Golay filter with window_length = 6 and polyorder of 3 to obtain the second plot. One can see, that the filtration has distorted the endpoints. Also bumps seen in the raw data is not completely gone either, one or two being clearly visible.

I have the following questions:

1. How do I supress the boundary effects?

2. I would like to know is it recommended to apply the Sav-Gol filter to data taken in a measurement or is it meant for some other purposes.

3. Are there any other filtration methods that you know of that can be better in cases such as this?

4. Can journal publishers object to data filtered in this way as it might distort original data points that are nighbouring to noisy data points?

I would appreciate any help on this.

Edit: Somehow the inline images are not showing. Here are the hyperlinks. Plot of raw data: https://imgbox.com/2BEovRgY Result of Sav-Gol filter: https://imgbox.com/Et0AOu3P

The following two figures show raw data and filtered data recorded in a measurement. I have used SciPy's Savizky-Golay filter with window_length = 6 and polyorder of 3 to obtain the second plot. One can see, that the filtration has distorted the endpoints. Also bumps seen in the raw data is not completely gone either, one or two being clearly visible.

I have the following questions:

1. How do I supress the boundary effects?

2. I would like to know is it recommended to apply the Sav-Gol filter to data taken in a measurement or is it meant for some other purposes.

3. Are there any other filtration methods that you know of that can be better in cases such as this?

4. Can journal publishers object to data filtered in this way as it might distort original data points that are nighbouring to noisy data points?

I would appreciate any help on this.

Plot of raw data:

Result of Sav-Gol filter: