0

I am researching the best method to use with time series. FBprophet (Python) seems like a strong option.

To prepare time series for Prophet I am thinking about using boxcox and inv_boxcox at the end

from fbprophet import Prophet
from scipy.stats import boxcox
from scipy.special import inv_boxcox

what is your opinion? Is boxcox helpful in reducing the noise of the Values?

Any tips and suggestions will be greatly appreciated

Toly
  • 2,981
  • 8
  • 25
  • 35
  • That's currently a bit broad. Could you provide some sample input and explain in more detail what you are trying to achieve? – Cleb Jun 15 '18 at 07:40
  • This is not really about the code. It is about building a time series regression and breaking it down to trend, seasonality, etc. BoxCox (and inv_boxcox) is a way to reduce the "noise" in an initial dataset (values) before running a regression (e.g. Prophet or STL). After the regression the data can be adjusted back using inv_boxcox. My question is boxcar is a way to go or are there better methods to reduce the statistical "noise" in a dataset? – Toly Jun 15 '18 at 15:15
  • Then I am not sure whether SO is the best place to ask; maybe better on [stats.stackexchange](https://stats.stackexchange.com/) or [signal processing](https://dsp.stackexchange.com/)?! – Cleb Jun 15 '18 at 15:45
  • 1
    Possibly but I am really impressed with people here who have in depth knowledge not only in Python/R coding but in statistics as well – Toly Jun 15 '18 at 16:45
  • 1
    @Cleb - just posted on Stackexchange as well. Thank you for advise – Toly Jun 15 '18 at 16:53

0 Answers0