mcup package

Submodules

mcup.config module

config.py

Setting for the package and pregenerated data.

mcup.config.linear_fun(x, c)[source]

mcup.data_generator module

data_generator.py

Data generation for testing.

class mcup.data_generator.DataGenerator(fun, data_len, boundaries, seed=None, dtype=<class 'numpy.float64'>, params=None)[source]

Bases: object

add_noise_x(const_err=None, stat_error=None)[source]

[summary]

Parameters:
  • const_err ([type], optional) – [description]. Defaults to None.
  • stat_error ([type], optional) – [description]. Defaults to None.
Returns:

[description]
Return type:

[type]
add_noise_y(const_err=None, stat_error=None)[source]

[summary]

Parameters:
  • const_err ([type], optional) – [description]. Defaults to None.
  • stat_error ([type], optional) – [description]. Defaults to None.
Returns:

[description]
Return type:

[type]

mcup.mcup module

mcup.py

The core module of MCUP package.

class mcup.mcup.Measurement(x=None, y=None, x_err=None, y_err=None)[source]

Bases: object

An example docstring for a class definition.

evaluate_params(iter_num=None, rtol=0.0001, atol=0.0001, num_diff=False)[source]
set_data(x=None, y=None, x_err=None, y_err=None)[source]

[summary]

Parameters:
  • x ([type], optional) – [description]. Defaults to None.
  • y ([type], optional) – [description]. Defaults to None.
  • x_err ([type], optional) – [description]. Defaults to None.
  • y_err ([type], optional) – [description]. Defaults to None.
Raises:
  • AssertionError – [description]
  • AssertionError – [description]
set_function(fun, params)[source]

mcup.pee module

pee.py

Parameter error estimator functionality.

mcup.pee.parameter_error_estimator(fun, x_data, y_data, x_err, y_err, w_0, iter_num=None, rtol=None, atol=None, method=None, jac=None, hess=None, hessp=None, bounds=None, constraints=(), tol=None, callback=None, options=None)[source]

This function takes input data and input error and than samples in each iteration data from given normal distribution. Input function fun will be used in the definition of cost function for least squares. Cost functions is optimized using scipy.optimize.minimize function. Argument iter_num or rtol, atol has to be set in order to run least squares.

Parameters:
  • fun ([type]) – [description]
  • x_data ([type]) – [description]
  • y_data ([type]) – [description]
  • x_err ([type]) – [description]
  • y_err ([type]) – [description]
  • w_0 ([type]) – [description]
  • iter_num (int, optional) – [description]. Defaults to 1000.
  • method ([type], optional) – [description]. Defaults to None.
  • jac ([type], optional) – [description]. Defaults to None.
  • hess ([type], optional) – [description]. Defaults to None.
  • hessp ([type], optional) – [description]. Defaults to None.
  • bounds ([type], optional) – [description]. Defaults to None.
  • constraints (tuple, optional) – [description]. Defaults to ().
  • tol ([type], optional) – [description]. Defaults to None.
  • callback ([type], optional) – [description]. Defaults to None.
  • options ([type], optional) – [description]. Defaults to None.

mcup.utils module

utils.py

Utilities for the package.

mcup.utils.local_numpy_seed(seed)[source]

Set temporal seed for numpy package with local scope.

Parameters:seed ([int]) – Seed for numpy package.

Module contents

__init__ file for project.