What’s new in revision 0.6.1

These are the changes in SpectroChemPy-0.6.1. See Release notes for a full changelog including other versions of SpectroChemPy.

Breaking changes

This version introduce a full refactoring of the Spectrochempy analysis functions. See the examples in order to understand the changes.

• For a rapid transition note that calling the analysis function is now done in two steps. When before, one was writing

  # change log level
  scp.set_loglevel("INFO")
  # init the MCRALS object and fit the model on X dataset using a guess.
  mcr = scp.MCRALS(X, guess, tol=0.001)
  # use the MCRALS object attributes
  mcr.C.T.plot()
  mcr.St.plot()
  

  now one would write:

  # init the MCRALS object
  mcr = scp.MCRALS(log_level="INFO", tol=0.001)
  # fit the model on X dataset using a guess.
  mcr.fit(X, guess)
  # use the MCRALS object attributes
  mcr.C.T.plot()
  mcr.St.plot()
  

Deprecations

• Analysis object methods such as reconstruct and reduce are now deprecated. Use inverse_transform and transform,instead, in line with the method naming in sklearn.