Skip to content
forked from zrnsm/pyloess

loess smoother / stl seasonal trend decomposition, originally from scipy.sandbox.pyloess

License

Notifications You must be signed in to change notification settings

jcrotinger/pyloess

 
 

Repository files navigation

pyloess: a numpy wrapper to lowess and stl.

Build with Conda

  • Install Conda
  • Create conda environment; e.g: $ conda create -n pyloess python=3.6 gfortran_osx-64 gcc numpy
  • Activate environment: $ source activate pyloess
  • Clean: $ rm -rf build/*
  • Install: $ python setup.py install

NOTE: On recent version of MacOS you may have to manually install the C include files as some Mojave patches apparently delete them and xcode-select --install no longer re-installs them. I found this helpful.

  • Sanity check:
$ python
>>> from pyloess import stl

From original readme:

LOWESS

The initial file is available at: http://netlib.bell-labs.com/netlib/go/lowess.f.gz Simple to double precision conversion by Pierre GERARD-MARCHANT, 2007/03.

STL

The initial file is available at: http://netlib.bell-labs.com/netlib/a/stl.gz Simple to double precision conversion by Pierre GERARD-MARCHANT, 2007/03.

About

loess smoother / stl seasonal trend decomposition, originally from scipy.sandbox.pyloess

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 56.0%
  • Fortran 33.5%
  • C 10.3%
  • Other 0.2%