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 2.2.023Nov2221191817161512119843229Oct28272625222120191815141312118765427Sep241413987632131Aug30272625242322212019181716141312119643227Jul26232221201918161587542130Jun2928232221181728May27262522212019181764329Apr282721201918161514131211109876neg_1_to_1_normalization returns 0 when all values are 0 now, this helps produce more robust dimension reduction results. PCA independent run_pca_reduction now has window history creation included.PCA independent run script added and errors fixedmany new tests for filtersstation selections now choosable as parser argadded stations selection directory with pickle data containing stations listsremoved 'method':None in transformation_dictdefault CDC_DB_FILENAME changedadd metadata to wrfdhadded dummy loading for preprocessed_lazy_data method, nrw_low_alt_stations selection temporarly as default, transformation_dict has now a 'method:None for target data (maybe runs better in postprocessing)new tests for filter methodsadded also pytest-covpipepline finished successfully, therefore disable tests from scratch for "standard" commits, /close #340add pytest-html and check only by enabling tests from scratchapply some refac on filter calculationMerge branch '331-upgrade-code-to-tensorflow-v2' into 'develop'Merge branch 'lukas_issue331_test_tf2_on_local_system_and_hdfml' into '331-upgrade-code-to-tensorflow-v2'uncluded test related packages in requirements, removed outdated requirements filesadded gres:gpu to script template for hdfmlfixed self.meta is loaded as well, when lazy_preprocessed_data is loadedfixed if no lazy_preprocessed_data is found, make_input_target() is executedupdate ready to run testrunning load_lazy_preprocessed_data excludes lazy_preprocessing, because loading of input and target is not necessary thenupdate test for train resumingparser args are popped after evaluation, because experiment_date and experiment_name are passes via parser_args into the Workflow()added n_epochs to parser arguments and transformation_input_target_dict as global varparser arguments are not handled correctly in main()added window_history_size as parser argumentadded lazy preprocessing and pca reduction as parser arguments for sbatchfix for uncompiled model when resuming training from epoch differing from 0added missing packages, try on other systemsseparate directory for lazy_preprocessed_data, now initialized in CDCDataHandler initMerge branch 'develop' into 'lukas_issue331_test_tf2_on_local_system_and_hdfml'Merge branch 'master' into 'develop'Merge branch '331-upgrade-code-to-tensorflow-v2' into 'lukas_issue331_test_tf2_on_local_system_and_hdfml'explanation on lazy_preprocessed and lazy_data difference and more accurate names for functionsexplanation on lazy_preprocessed and lazy_data difference and more accurate names for functionstransformation_input_dict = None if do_pca_reduction = True. So input does not get transformed when pca reduction is applied alreadylazy_preprocessing enabled againtrain_start & _end removed in run_mtfalco.py, because it should not be edited manually (unless val & test are edited as well. client.close() in pca_reductionfix in training_monitoring.py if validation is not available