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 2.2.031Aug30272625242322212019181716141312119643227Jul26232221201918161587542130Jun2928232221181728May27262522212019181764329Apr282721201918161514131211109876131Mar302926252322181716151211109854326Feb2524232219181716151211108432129Jan27added debug printsadded error handling, /close #32Merge branch 'lukas_issue325_refac_split-overwriting-of-lazy-data-and-raw-data' into 'develop'station in cdc dh __init__() fixedstation is now also processed in cdc datahandler before super.__init__()nan fraction messages changed to logging.debug()applied split of overwrite parameters, /close #325Merge remote-tracking branch 'origin/develop' into falco_issue271_feat_add-cdc-database-datahandlerrun_mt_falco with standard config againprint all stations in statusremove self.input_data and self.target_data after make_samples()dill.dump(..., protocol=4) for the _store method to avoid failures when big data (>4GB) is stored.interpolation_limite = 24 and uncommented nan value evaluation by varsMerge branch 'lukas_issue324_bug_fix-problem-in-multiply-extremes' into 'develop'added upsampled histogramfixed bug in multiply extremesinterpolation_limit set to 10disabled rea6 vars containing >40% nan: ['REA6_SWDIFDS_RAD', 'REA6_TMAX_2M', 'REA6_TMIN_2M', 'REA6_SOBS_RAD', 'REA6_SWDIRS_RAD']nan check logging.info per variableMerge branch 'lukas_issue321_bug_too-big-data-for-memory' into 'develop'Merge branch 'lukas_issue322_refac_reduce-communication-in-multiprocessing' into 'lukas_issue321_bug_too-big-data-for-memory'Merge branch 'vincent_324-fix-problem-in-multiply-extremes' into 'develop'Fix multiply_extremesnan fraction in logging.info for input after make_history_window and after transformationown version of lazy save and load with input and target data seperation, _data not included to save space and because it is not used afterwardsadded protocol number for pickling commandsopen statement wasn't committed entirelynew reference return strategy to reduce communication amount in multiprocessing, /close #322 after test on HPC systemsFix in the default_data_handler.py in multiply_extremescalculate_legendre_reduction now has proper working dask map functionality - use_multiprocessing disabled for legendre - minor structural changes for data pathesadded missing statementadd another fix to use raw input data for climate filterreset decode_cf to open_mfdataset methodrestructuring of the calculate_legendre_reduction to a map function approach instead of the timedim loop - changed juwels data_dir to /p/scratch/Fixed finetuning, allowed correct learning_rateMerge branch 'falco_issue323-raise-valueerror-in-remove_nan-if-data-is-nan-only' into falco_issue271_feat_add-cdc-database-datahandlerremoved unnecessary line in remove_nan()Merge branch 'falco_issue323-raise-valueerror-in-remove_nan-if-data-is-nan-only' into falco_issue271_feat_add-cdc-database-datahandlerValueErrors raised when timeseries (history, label or observation) only consists of NaNproper stations enumeration (list sorted), removed unnecessary prints, added proper start and end paramter in run script