PRIMAP2 Version 0.12.1

primap2 0.12.1 (2025-01-15)

primap2 is a library for compiling and analyzing climate policy datasets.

Changes

Bug Fixes

• Change URLs and names from pik-primap to primap-community. (#306)

Trivial/Internal Changes

• #304, #305

PRIMAP2 Version 0.12.0

primap2 0.12.0 (2025-01-14)

primap2 is a library for compiling and analyzing climate policy datasets.

Changes

Breaking Changes

• Harmonize parameter names for different functions. The aggregation functions now use 'sel' instead of 'filter'. (#272)
• We removed the sec_cats entry from the metadata in a dataset's attrs in the native format
  as well as the interchange format. It did not add much value, but maintaining it was work, so on balance
  we decided to remove it.
  When reading datasets from disk (from the interchange format or netcdf files), sec_cats will be ignored
  so that datasets written with earlier versions of primap2 can still be read and produce valid in-memory
  datasets. (#277)

Improvements

• Added sorting of metadata keys and data values to the interchange format on-disk files.
  This means interchange format files written with this version or higher of primap2 should
  only change if the metadata or data values change, not due to random re-ordering of
  keys. However, interchange format files written with older versions are of course
  unsorted, so most likely they will all change if just read and re-written without
  changes using this version or primap2. (#268)
• Added tests on log content and format for the pr.merge() function (#276)
• In the conversion function, disable splitting into multiple categories, instead create an aggregated category. (#291)

Bug Fixes

• The function nir_convert_df_to_long now retains NaN values instead of removing them. This is more consistent with the rest of our data reading where we keep NaN values to check that everything has been processed. (#273)
• Fix problems with downscaling where data is zero for all basket contents. (#278)

Improved Documentation

• Reintegrated and fixed the docs for {py:meth}xarray.Dataset.pr.add_aggregates_coordinates, {py:meth}xarray.DataArray.pr.add_aggregates_coordinates, and {py:meth}xarray.Dataset.pr.add_aggregates_variables. (#271)
• Added a warning that netcdf files are not reproducible. (#274)

Trivial/Internal Changes

• #270, #275, #290

PRIMAP2 Version 0.11.2

primap2 0.11.2 (2024-10-07)

primap2 is a library for compiling and analyzing climate policy datasets.

Changes

Improvements

• Added support for python 3.12.

  Started testing the lowest supported versions of dependencies. (#259)

• Added support for and required pandas 2.2.

  Switched accelerated filling functions from bottleneck to numbagg. (#261)

Bug Fixes

• Fixed handling of NaN values in {py.func}xarray.DataArray.pr.set() when existing=overwrite. (#225)

Improved Documentation

• Enhanced the API documentation. (#264)

PRIMAP2 Version 0.11.1

0.11.1

• Workaround for xarray's additional coordinate bug
• Improved a few error messages
• Disable xdoc as it throws errors
• Fixed reading the interchange format with dimensionless data (where the unit is
  an empty string).

PRIMAP2 Version 0.11.0

0.11.0

• Removed Python 3.9 support.
• Added exclude_result and exclude_input parameters to priority definitions for
  compose. They can be used to skip processing entire result timeseries or specific
  input timeseries, e.g. because of invalid data or categories.
• Added protocol for skipping strategies when they aren't applicable for
  input timeseries using the StrategyUnableToProcess exception.
• Added support for specifying the entity in priority and strategy selectors.
• Added support for specifying multiple values in priority and strategy selectors.
• Added negative selection using the primap2.Not value when using the loc
  accessor.
• Use ruff formatting instead of black formatting.
• Added a new csg sub-module which contains functions and configuration models to
  generate a composite dataset from multiple input datasets.
• add global least squares strategy
• add function to add dimension to DatasetDataFormatAccessor
• add functions to aggregate values for coordinates / dimension and entities
  to aggregation accessors
• Added metadata variables to the primap2 data format. Metadata variables describe
  the processing steps done to derive the data on a timeseries level. Also added the
  metadata classes used for the description to the public API. We support saving
  datasets with metadata variables to netcdf, but converting to the interchange format
  looses the metadata variables.
• Explicitly required supported python versions.

PRIMAP2 Version 0.10.0

0.10.0

• Fixed compatibility with latest pint and pint-xarray libraries.

PRIMAP2 Version 0.9.8

0.9.8

• add additional control over nan treatment to downscaling functionality
• Allow kwargs in gas basket summation
• use min_count=1 as default in pr.sum
• fix error message for 0-dimensional arrays in pr.merge
• fix building the documentation on readthedocs.org
• Modify unit harmonization to return native units if possible

PRIMAP2 Version 0.9.7

0.9.7

• Fix the test suite to work with Pint release 0.21.

PRIMAP2 Version 0.9.6

0.9.6

• Add dependency on openscm_units > 0.5.1 for compatibility with latest pandas.
• stop building pdf output documentation, it doesn't support SVG and isn't used much.
• Drop support for Python version 3.8 to prepare for it being dropped
  in Numpy on April 14.

PRIMAP2 Version 0.9.5

0.9.5

• pr.merge: use xarray's combine_first instead of own algorithm for better performance.
• Fix in nan handling of to_interchange_format
• made regexp_unit optional in nir_add_unit_information as intended already before
• Add support for Python 3.11