summaryrefslogtreecommitdiff
path: root/lib/parameters.py
AgeCommit message (Expand)AuthorLines
2024-03-07RMT: support mutual information-based parameter relevanceBirte Kristina Friesel-0/+26
2024-03-07DFATOOL_RMT_IGNORE_IRRELEVANT_PARAMS=1 → DFATOOL_RMT_RELEVANCE_METHOD=std_b...Birte Kristina Friesel-21/+12
2024-03-06Add LightGBM supportBirte Kristina Friesel-0/+18
2024-02-26add RMT_SUBMODEL=cartBirte Kristina Friesel-2/+8
2024-02-22Support Symbolic Regression rather than ULS in RMT leavesBirte Kristina Friesel-15/+26
2024-02-22Replace DFATOOL_RMT_FUNCTION_LEAVES=0 with DFATOOL_RMT_SUBMODEL=staticBirte Kristina Friesel-4/+5
2024-02-21make SymbolicRegressionFunction inherit from SKLearnRegressionFunctionBirte Kristina Friesel-23/+27
2024-02-21rename build_dtree to build_rmtBirte Kristina Friesel-6/+6
2024-02-21Rename DFATOOL_FIT_LINEAR_ONLY=1 to DFATOOL_SUBMODEL=folBirte Kristina Friesel-1/+1
2024-02-21Rename DFATOOL_DTREE_* to DFATOOL_RMT_*Birte Kristina Friesel-6/+6
2024-02-21build_dtree: there is no need to explicitly pass param_values and dataBirte Kristina Friesel-4/+2
2024-02-21Replace DFATOOL_FIT_FOL with DFATOOL_MODEL=folBirte Kristina Friesel-35/+40
2024-02-21move (de)cart, lmt, xgb model generation into separate ModelAttribute functionsBirte Kristina Friesel-80/+80
2024-02-21Move CART/LMT/XGB fitting into the respective modulesBirte Kristina Friesel-207/+34
2024-02-20Re-add (very very basic, for now) Symbolic Regression supportBirte Kristina Friesel-0/+26
2024-02-19FOLFunction: Do not redundantly pass param_names to constructor.Birte Kristina Friesel-2/+1
2024-02-19categorial → categoricalBirte Kristina Friesel-7/+7
2024-02-12unfuck param_names / feature_names handlingBirte Kristina Friesel-83/+29
2024-02-09CART.to_json: support function argumentsBirte Kristina Friesel-0/+1
2024-02-09LMT export: set paramIndex; use correct parameterNames in analytic nodesBirte Kristina Friesel-1/+6
2024-02-06Add ScalarSplitFunction support for manual scalar splits in RMTBirte Kristina Friesel-1/+1
2024-02-02ModelAttribute.from_json: Set mean/median from static modelBirte Kristina Friesel-0/+2
2024-01-29LMT: Fix DFATOOL_LMT_MIN_SAMPLES_LEAF default valueBirte Kristina Friesel-1/+3
2024-01-25Use LMT algorithm defaults for max depth and min samples leaf.Birte Kristina Friesel-3/+3
2024-01-25XGB: switch to XGBoost defaultsBirte Kristina Friesel-8/+62
2024-01-25LMT: Tailor hyper-parameters towards higher accuracy (and longer training time)Birte Kristina Friesel-1/+54
2024-01-24Use separate /hyper/ hierarchy for hyper-parameter exportBirte Kristina Friesel-3/+0
2024-01-23Allow --skip-param-stats to be used in FIT_FOL modeBirte Kristina Friesel-3/+10
2024-01-22Support LUT model independent of --skip-param-statsBirte Kristina Friesel-1/+6
2024-01-19Store n_samples in all relevant ModelFunction instancesBirte Kristina Friesel-5/+12
2024-01-19dataref export: include XGB hyper-parametersBirte Kristina Friesel-1/+4
2024-01-19optionally store n_samples in ModelFunctionBirte Kristina Friesel-7/+16
2024-01-19Remove unused ModelAttribute.split code; splits are handled via SplitFunctionBirte Kristina Friesel-80/+34
2024-01-19parameters: nitsBirte Kristina Friesel-4/+6
2024-01-19assertionsBirte Kristina Friesel-1/+4
2024-01-18Rename DFATOOL_{'' → ULS_}SKIP_CODEPENDENT_CHECKBirte Kristina Friesel-1/+1
2024-01-18build_dtree: do not ignore codependent parametersBirte Kristina Friesel-2/+7
2024-01-18parameters: ModelAttribute: remane .ignore_param to .ignore_codependent_paramBirte Kristina Friesel-12/+14
2024-01-17Disable DFATOOL_DTREE_IGNORE_IRRELEVANT_PARAMS by defaultBirte Kristina Friesel-2/+2
2024-01-17dtree irrelevant param detection nits; still not working properlyBirte Kristina Friesel-5/+5
2024-01-17Stop splitting if there is no split that reduces lossBirte Kristina Friesel-1/+3
2024-01-16build_dtree: add another assertion for good measureBirte Kristina Friesel-4/+2
2024-01-16Add LMT support for --export-json / ModelAttribute.to_jsonBirte Kristina Friesel-1/+5
2024-01-15improve(?) loss_ignore_scalar implementation: more opportunities for FFSBirte Kristina Friesel-6/+44
2024-01-15dtraa loss_ignore_scalar: calculate unsuitable params for each nodeBirte Kristina Friesel-2/+20
2024-01-15dtree: replace condition by assertionBirte Kristina Friesel-11/+11
2024-01-15decrease non-debug verbosityBirte Kristina Friesel-6/+2
2024-01-12Expose DFATOOL_ULS_MIN_DISTINCT_VALUES training hyper-parameterBirte Kristina Friesel-1/+5
2024-01-12It's THRESHOLD, not TRESHOLD. Oops.Birte Kristina Friesel-2/+2
2024-01-11Add helper function missing in previous commit.Birte Kristina Friesel-3/+22
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-25 19:18:15 +0000