Fix bug in split_data

Merge pull request #46 from fact-project/fix_subsamples_in_split

Fix subsamples in split

Warn about removed columns in disp_regressor

v0.7.1

Merge pull request #43 from fact-project/jebuss-theta-needs-to-be-cal…

Improvements to reproducibility and some early multi-telescope support

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.

Improve Disp Regressor, update scikit-learn version, use h5py by default

• 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

Disp Regressor

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

Fix Helptexts And Dependencies

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.

First Release

Merge pull request #1 from fact-project/adapt_to_erna

Adapt to erna