Skip to content
Snippets Groups Projects

Repository graph

You can move around the graph by using the arrow keys.
Select Git revision
  • 313-allow-non-monotonic-window-lead-times-in-helpers-statistics-py-ahead_names-definition
  • 414-include-crps-analysis-and-other-ens-verif-methods-or-plots
  • IntelliO3-ts
  • Kleinert_et_al_2022_Representing
  • develop protected
  • develop_IntelliO3-ts
  • enxhi_issue460_remove_TOAR-I_access
  • falco_issue271_feat_add-cdc-database-datahandler
  • felix_PaperVersion
  • felix_TF2_merge_test_sectorial_skill_scores
  • felix_issue267-create-wrf-chem-data-handler
  • felix_issue287_tech-wrf-datahandler-should-inherit-from-singlestationdatahandler
  • felix_issue303-wrf-dh-major-minor
  • felix_issue319-toar-statistics4wrf-dh
  • felix_issue400_feat-include-tf-probability
  • felix_issue411-feat_include-postprocessing-for-bnns
  • felix_issue412-create-ens-predictions-for-bnns
  • felix_issue420-datahandler-with-multiple-stats-per-variable
  • felix_issue_365-tech-set-ci-cd-artifact-expire-time
  • lukas_issue363_feat_calculate-toar-metrics-on-hourly-forecasts
  • v2.4.0 protected
  • v2.3.0 protected
  • v2.2.0 protected
  • v2.1.0 protected
  • Kleinert_etal_2022_initial_submission
  • v2.0.0 protected
  • v1.5.0 protected
  • v1.4.0 protected
  • v1.3.0 protected
  • v1.2.1 protected
  • v1.2.0 protected
  • v1.1.0 protected
  • IntelliO3-ts-v1.0_R1-submit
  • v1.0.0 protected
  • v0.12.2 protected
  • v0.12.1 protected
  • v0.12.0 protected
  • v0.11.0 protected
  • v0.10.0 protected
  • IntelliO3-ts-v1.0_initial-submit
40 results
Created with Raphaël 2.2.017Aug16141312119643227Jul26232221201918161587542130Jun2928232221181728May27262522212019181764329Apr282721201918161514131211109876131Mar302926252322181716151211109854326Feb2524232219181716151211108432129Jan272120191818Dec1716151110987+1 on every contingency cellupdate HPC.req add tzwhere==3.0.3first runthrough of toarstats and lazyadded fake_retrieve_db_data to test if retrieve_db_data is causing PicklingError - it still occurs, thus added dill.detect.trace(True)check system by hostname in run scripttransformation is now called, when do_legendre_reduction=False - transformation dict is tuple with options for inputadded methods descriptions and renamed calculate_legendre_transformation to proper *_reductionremoved confusing shape parameters in get_legendre_fit() and fixed dask computation graph creationdebugging in postprocessing_plottingFixed errortried to fix PicklingError - changed derieve_db_data into staticmethod, no open(...) in initFor debugging on HPCMerge branch 'release_v1.4.0' into 'develop'reverted last commitFixed the problem in _load_competitors in post_processing and postprocessing_plotting, reverted the workaround in statisticsWorkaround in statistics.py, climatological_skill_scoresrefactor time zone handlingupdate run_wrf.py and run_wrf_dh_sector.py in order to use toarstatsmove _force_dask_comp to absract dh and include input_output_sampling4toarstatsinclude first impl of toarstatisticsfurther testing if any np.nan is in first_param and det() calculation using da.map_blocks(np.linalg.det,...)fixed tuple dask problem caused by dask_array direct assignment of guess_mat = da.full(...) -> guess_mat = np.full(...)merged origin/master into branchdask_delayed.compute()[0], because get_legendre_fit evaluation now results in a tuple returndask_delayed.compute()[0], because get_legendre_fit evaluation now results in a tuple returndask_delayed.compute[0](), because get_legendre_fit evaluation now results in a tuple returnchanged np. to da. in get_legendre_fit()print experiment configReverting the changesvincent_issue31…vincent_issue318-workaround-to-get-resultsReverting the changesBefore making new branchupdate MyLuongAttentionLSTMModelresorted dealing with self.variables, so self.history only contains input vars. Minor tweaks to legendre transformation. New switches for transformation (standardization, normalization if not Legendre)Updated run-scripts for hdfmlAdded bias and titles to PlotOversamplingContingencyMerge branch 'felix_issue287_tech-wrf-datahandler-should-inherit-from-singlestationdatahandler' of ssh://gitlab.version.fz-juelich.de:10022/esde/machine-learning/mlair into felix_issue287_tech-wrf-datahandler-should-inherit-from-singlestationdatahandlerupdate MyLSTMModelAdd new model class MyLuongAttentionLSTMModel based on https://levelup.gitconnected.com/building-seq2seq-lstm-with-luong-attention-in-keras-for-time-series-forecasting-1ee00958decbGives ValueError if window_lead_time of competitors and model dont matchMade PlotOversamplingContingency get min and max_threshold