Changelogs » Aict-tools

Aict-tools

0.20.0

* aict-tools can now apply models stored using onnx or pmml. However, application  of models stored to pickle is still the fastest option for most models.

0.19.0

* Fixing the configuration of the output names. These can now be set using `output_name: ` in the models section
* Use onnxruntime v1.0

0.18.3

* Fix modification of input file timestamp in copy runs
* All but the `apply_` scripts should now not modify their input filestamps now

0.18.2

* Fix for apply_cuts: modification date of input file is not modified anymore

0.18.1

* Add support for most sklearn models, before only `sklearn.ensemble` was supported

0.18.0

* Update to sklearn ~0.21.0, use joblib directly (fixes sklearn's DeprecationWarning)
* Improve feature importance plot
* Add citing instructions

0.17.0

* Enable zenodo doi
* Refactored IO, removed the already sparse support for csv completely
* Testing pmml on travis
* Improved log output

Merged PRs:

* ade81cb Merge pull request 78 from fact-project/tables_compability
* b6a41f3 Merge pull request 87 from fact-project/logging
* c087f54 Merge pull request 88 from fact-project/enable_pmml
* f930c2a Merge pull request 89 from fact-project/zenodo

0.16.3

Add optional support for serializing models into the onnx format.

0.16.1

Switch from pyyaml to ruamel.yaml

0.16.0

* Add random source position sampling for theta calculation in `fact_to_dl3`
* Write the samplefraction into files created by `split_data` and copy it in `fact_to_dl3` if present

Merged PRs

* Merge pull request 81 from fact-project/add_sample_fraction
* Merge pull request 80 from fact-project/random_source

0.14.0

Add chunked version of `split_data` for single telescope h5py files to deal with larger than memory files.

0.13.1

* Add long description and classifiers for PyPI

0.13.0

* Publish to PyPI
* Require scikit-learn 0.20.*
* Fix progress bars

0.12.4

Fixes an issue where files would not get opened in read-only mode essentially breaking make files.

0.12.3


      

0.12.2


      

0.12.1


      

0.12.0

The module and all executables got renamed to `aict_tools` and `aict_train_...` and `aict_apply_...`

0.11.0


      

0.10.0

* Configuration was completely refactored, check the examples folder, especially `full_config.yaml`

* Added executable `klaas_fact_to_dl3` to apply all three models and calculate ra/dec and theta in one go.

* First support for multiple telescopes (cta)

0.9.0


      

0.8.1

We forgot to merge a PR apparently. This times source dependent features are actually removed.

0.8.0


      

0.7.4


      

0.7.3


      

0.7.1


      

0.7.0

This allows setting random seeds to be used everywhere. The split_data script can now keep together telescope events that belong to the same array-wide event.

0.6.0

* The disp regressor does not calculate theta anymore, to make analysis more flexibel
* Output columns are now `source_x_prediction`, `source_y_prediction` and `disp_prediction`
* `klaas_split_data` and `klaas_apply_cuts`  use h5py by default
* Switch to sklearn 0.19.0

0.4.0

This release features two new klaas scripts


klaas_train_disp_regressor
klaas_apply_disp_regressor

To train models to predict the origin of gamma rays

0.1.1

This release fixes the helptext in the `klaas_apply_separation_model` command line utility and fixes the matplotlib depenedency to at least 2.0 for plotting bias and resolution.