Releases: Sbozzolo/kuibit
1.5.0
Version 1.5.0 (19 June 2024)
General
- Python 3.12 is now supported, Python 3.8.1 is required for development.
total_filesize
now errors out when directories are passed.
Features
- Added experimental support for reading OpenPMD files (with most of the heavy-lifting done by @krishivbhatia). Please, report any issue you might find.
1.4.0
Version 1.4.0 (2 May 2023)
General
- Minimum version of Python required is now 3.7.
kuibit
now explicitly follows NEP29. - Started gradual typing
- Now
SimDir
can be imported directly fromkuibit
(from kuibit import SimDir
) - Update logo to high resolution (and vector graphics)
Features
- Added linear momentum lost by gravitational waves along the x and y directions (starting from a contribution by @konrad-topolski)
- Added
Tree
data structure - Added
effective_amplitude_spectral_density
withingw_utils
(starting from a contribution by @irrationalnumbers, #27) - Added fourth order accuracy in finite differences of grid functions
- Added
copy
to gravitational and electromagnetic waves - Added
crop
andcropped
to multipole data setup_matplotlib
now takes an optional parameterrc_param_file
to configure matplotlib using a file- Added computation of linear momentum lost by electromagnetic waves
- Added
rotation180_symmetry_undo
to undo rotational symmetries in grid data - Added
cactus_twopunctures
to read metadata from TwoPunctures - Added
local_maxima
andlocal_minima
to series - Added
mean
,average
,median
,std
reductions to series and grid data - Added
ah_available
,qlm_available
toOneHorizon
- Added
tensor
module - Added support to
surface*.vtk
fromQuasiLocalMeasures
Support to VTK
variables from QuasiLocalMeasures
QuasiLocalMeasures
has an option to output its variables on the horizon. Now, kuibit
can read and parse them, so it is possible to plot horizon meshes and variables onto the mesh.
New tensor
module
kuibit.tensor
is a new module to provide high-level interfaces to work with tensorial objects. A Tensor
can be built with collections of TimeSeries
, FrequencySeries
, UniformGridData
, HierarchicalGridData
, or any other class derived from BaseNumerical
. Tensor
s support all the mathematical operations and inherit the methods from their contained object. At the moment, there are two new subclasses of Tensor
that implement additional features for vector calculus. For example, if bh_cen
is a Vector
with the time evolution of the centroid of an horizon. bh_cen.differentiated().norm()
will be a TimeSeries
with the magnitude of the coordinate velocity as a function of time (as a TimeSeries
).
Currently, the number of specialized methods in Vector
and Matrix
is not large. Nonetheless, the infrastructure is in place and adding new will be straightforward.
New cactus_twopunctures
module
TwoPunctures
creates a metadata file that stores important physical information about the initial data. The new module cactus_twopunctures
can read this information and present it as a dictionary. If sim
is a SimFactory
, sim.twopunctures
will be a dictionary-like object that has as keys the various quantities saved by TwoPunctures
and as values, their values as read from the TwoPunctures.bbh` file.
New tree
module
kuibit.tree
is a new module that can represent tree structures. At the moment, it is main use is to work with timer trees.
New hor_utils
module
kuibit.hor_utils
is a handy new module that implements common functions needed when working with binary black holes. At the moment, the functions implemented are:
compute_separation_vector
compute_separation
compute_center_of_mass
compute_angular_velocity_vector
Bug fixes
- Fix passing an empty
ah_vars
toOneHorizon
. - Fix floating-point comparison in
grid_data
. - Fix optional positional arguments to
series._local_extrema
. - Fix algorithm to compute hash for
UniformGrid
. - Make classes that should not hashed unhashable.
GravitationalWaves
now find multipole variables that containpsi4
(as opposed to being identically toPsi4
)
Detector sensitivity curves
New/updated examples
Scripts:
describe_simdir.py
interactive_timertree.py
print_available_iteration.py
optionally prints the corresponding timeplot_charge_phi1.py
plot_binary_ah_angular_velocity.py
plot_binary_ah_period.py
1.3.6
Version 1.3.6 (5 July 2022)
Bug fixes
- Fix time incorrectly read in ASCII data (thanks @AuroraDysis,
#30)
1.3.5
Version 1.3.5 (14 June 2022)
Bug fixes
- Fix str representation of multipoles
- Fix implicit plotting of
Series
formatplotlib >= 3.5.2
- Fix
test_init
intest_cactus_grid_function
1.3.4
Version 1.3.4 (22 April 2022)
General
- Improvements to documentation and docstrings
Bug fixes
- Added error in
_plot_horizon_on_plane
when the horizon cannot be plotted - Updated NumPy types (np.int -> int, np.float -> float)
- Windowing uneven signals is no longer allowed
- Correctly remove ghost zones for 1-2D HDF5 files
- Fix deprecation warning for Matplotlib 3.4
- Fix
is_masked
after removing a mask (thanks @ekwessel, #28) - Fix some information not being propagated by
grid_data_utils.merge_uniform_grids
.
New examples
Scripts:
plot_ah_trajectories.py
1.3.3
Version 1.3.3 (19 November 2021)
Bug fixes
- Fixed
tikzplotlib
dependency forPython 3.6
1.3.2
Version 1.3.2 (16 November 2021)
Bug fixes
- Examples with
plot_components_boundaries
now respect axes limits - Improved support to installing
mayavi
Python 3.10
is now supported (with exception ofnumba
)- Fixed parity in
reflection_symmetry_undo
1.3.1
Version 1.3.1 (4 November 2021)
Bug fixes
h5py >= 3
is now supported
1.3.0
Version 1.3.0 (28 October 2021)
SimDir
can now be cached in pickle files
kuibit
tries to do as much lazy-loading as possible. For examples, files are opened only when needed. When analyzing simulations it is useful to save the work done by kuibit
to avoid re-doing the same operations over and over. It is now possible to do this using pickle files. SimDir
can now be used as a context manager and the progresses can be loaded and saved from files. For example:
with SimDir("path_of_simulation", pickle_file="simdir.pickle") as sim:
# do operations
In this case, if pickle_file
exists, it will be loaded (ignoring all the other arguments passed to SimDir
), and it will be kept updated with the additional work done by kuibit
. If pickle_file
does not exist, the SimDir
will be created as usual as a pickle_file
will be generated.
It is important to stress that, when using pickles, no consistency check with the current state of the simulation is performed. If the simulation changes (e.g., new checkpoints are added), this will result in errors. In that case, a new pickle file must be produced.
Masked data
Numerical objects now support mask, which can be used to ignore part of the data that satisfy certain conditions (for example, to exclude the atmosphere from GRMHD computations).
Note that it is not possible to perform interpolation with masked data, so several methods will not work.
Note also that we mask only the data, not the independent coordinate (e.g., the time in TimeSeries or the spatial coordinates in the UniformGridData). In case you need masked coordinates too, you can use the mask
method to obtain an array of booleans that identifies the valid data.
Series
,UniformGridData
,HierarhicalGridData
have a new methodis_masked
.Series
,UniformGridData
,HierarhicalGridData
have a new methodmask
that identifies where data is invalid.Series
,UniformGridData
,HierarhicalGridData
have news methods to create masked data (e.g.,mask_greater
). See complete list in documentation.Series
have new methodsmask_remove
andmask_removed
to create objects without masked data.Series
have new methodsmask_apply
andmask_applyed
to create objects with a given mask (as the one obtained with themask
method).
General
SimDir
can be saved to disk with the methodsave
and read with the functionload_SimDir
. This is useful to work with a simulation that has finished.- Examples can now use pickles.
- New CI workflow: linting.
- New
First Steps
documentation page. - When a release is published, its documentation is saved to
sbozzolo.github.io/kuibit/VERSION
Features
time_at_maximum
andtime_at_minimum
inTimeSeries
can now take the optional argumentabsolute
.- Added
x_at_minimum_y
andx_at_maximum_y
toBaseNumerical
. - Added
coordinates_at_maximum
andcoordinates_at_minimum
for grid data. - Added
HierarchicalGridData.is_complex()
. - Added
tikz_clean_figure
tovisualize_matplotlib.save
, to
argparse_helper.add_figure
, and to examples. This can be used to reduce
the size of outputtikz
files. - Added
clear_cache
inOneGridFunction
. - Added
plot_contour
. - Added alias
time_found
toformation_time
in horizons. - Added
plot_components_boundaries
. - Added
ghost_zones_remove
inHierarchicalGridData
- Added
add_grid_structure_to_parser
. - Added
reflection_symmetry_undone
.
Breaking changes
- The
ignore
parameter inSimDir
has been renamed toignored_dirs
. - The
trim_ends
parameter incactus_waves
is now set toFalse
by default.
Bug fixes
plot_colorbar
does not steal axis focus anymore.- The legend in
plot_psi4_lm
was corrected. visualize_matplotlib.save
now correctly supports thefigure
argument.plot_strain_lm.py
no longer crashes whenwindow_args
is not provided.HierarchicalGridData
now owns the components.- Clear
OneGridFunction
cache ingrid_var
to avoid death by OOM. - Uniform constructor of
GridSeries
with constructors of otherSeries
. - Horizon properties now lead to valid python variable names.
New examples
Examples with --detector-num
now also accept --num-detector
as alias.
Scripts:
picklify.py
plot_1d_slice.py
plot_grid_expr.py
plot_phi_time_averaged.py
plot_gw_angular_momentum.py
print_grid_point_minmax.py