Version 3.2.3

Issue 27: Remove invalid escape sequences from docstrings.

Version 3.2.2

05 Nov 2024 version 3.2.2
Adapt to numpy-2 and pertaining Scipy, Astropy and MatplotLib

V.3.2.1

• 27 March 2024 version 3.2.1
  
  A lot of fairly small stuff.
  • status changed to Alpha for some newer additions
  • Priors:
    • Adapt to input arrays
    • Made limited and/or circular
    • Proper integral when limited
  • Engines:
    • Add bestCheck and bestBoost
    • Minor restructoring
  • Models:
    • Minor restructoring and renaming
    • setLimits() replaced by setPrior() in RepeatingModel
    • provide for more dimensions of outputs in derivative
  • Problems:
    • toString() method restructured
  • Walker and WalkerList:
    • Add logPrior attribute
    • Change in inheritance reporting
  • PhantomCollection:
    • getList() method
  • NestedSampler:
    • Add repiter attribute: report every repiter when verbose=2
    • Add bestBoost
  • ModelDistribution:
    • put internal sample() method in try-except block
  • Tools:
    • subclassof() method
    • printclass finetuning
  • Test and documentation. Update.

Version 3.2.0

• 31 Aug 2023 version 3.2.0

• The new class, PhantomCollection is part of NestedSampler. It contains a sorted
  WalkerList, in which all valid positions are collected, proper walkers
  and phantoms. Each iteration the phantoms with log likelihood lower than the
  low limit for that iteration, are removed. The PhantomCollection is used
  to get a better estimate on the size of the bounding box for the walkers and
  to obtain starting positions for new walkers. In general the PhantomCollection
  contains an order of magnitude more items than the WalkerList itself.
• NestedSampler has a new stopping criterion. It also stops when the log of the
  relative contribution to the logZ (evidence) integral is less than -tolerance (=12).
• FootballModel: new class. Model to estimate strengths of football teams in
  several key parameters.
• Address PhantomCollection and add **kwargs in all Engines
• Quadratic (in stead of linear) interpolation on edge in GalileanEngine
• Unnormalized Gauss prior changed into a normalized one
• Some documentation issues
• More dimensional arrays in LogFactorial
• str() method in NestedSolver and PhantomSampler
• Avoid numeric instabilities in sqrt in SampleList
• New tools in Tools
• More construction options in WalkerList
• New example: Uefa2022.ipynb
• New tests: TestPhantomCollection, TestFootballModel
• Adaptations in existing tests
• Reran all tests and examples

Version 3.1.1

What's new.

• 18 Jan 2023 version 3.1.1
  • remode GaussPriorNew from init.py

Version 3.1.0

What's new.

• 18 Jan 2023 version 3.1.0 (still working on the same update)

  • Implementing accuracy in fitters and samplers
  • Update of documentation
  • More tests

• 19 Nov 2022 version 3.1.0

  • Gauss2dErrorDistribution: New Class to handle correlated errors in X and Y
  • ErrorDistribution and GaussErrorDistribution : adaptation for covariant errors.
  • Small updates and corrections and removal of unused methods
  • Added / corrected version information and documentation issues
  • Rerun all examples and added tests

Version 3.0.1

05 Apr 2022 version 3.0.1:
Addressing issue #18: UserModel does not work for multiple dimensions.

Version 3.0.0

• New classes: AstropyModel and UserModel
• New class: NeuralNetUtilities
• New classes: NestedSolver, OrderProblem, SalesmanProblem, DistanceCostFunction
• New classes: OrderEngine, MoveEngine, SwitchEngine, LoopEngine, ShuffleEngine
• New classes: ReverseEngine, NearEngine, StartOrderEngine
• Make pipe work for more dimensional output | input
• Test harnesses for the new classes
• New examples for AstropyModel, UserModel and SalesmanProblem
• Update existing examples to improve coverage of pytest
• update Manual

Version 2.8.1

Cleanup in Plotter
Documentation issues; Replaced style.md by code-style.md
Correcting error on Windows system

Version 2.8.0

• 29 Oct 2021 version 2.8.0
  • New class: BernoulliErrorDistribution and SoftMaxModel, tests, examples and data
  • Adaptations To BernoulliED in some other classes
  • Multi-dim input and output issues
  • Updated some other tests and examples
  • Documentation and other small issues.