summaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorLines
2022-02-18move --log-level and --info to cli.pyDaniel Friesel-25/+18
2022-02-18add show_model_size optionDaniel Friesel-0/+30
2022-02-10only load kconfig / kconfiglib when requiredDaniel Friesel-2/+1
2022-02-09allow dtree relevant parameter detection to be disabledDaniel Friesel-9/+32
2022-02-07SplitFunction: Use mean of children for predicting unknown valuesDaniel Friesel-4/+10
2022-02-04use O(n) instead of O(2^m) iterator in _mean_std_by_param. Oops.Daniel Friesel-20/+16
2022-02-04update tests for 8c118d357ad873349a2ae00ccf9bcd093c448df0Daniel Friesel-25/+25
2022-02-02build_dtree: improve debug outputDaniel Friesel-7/+7
2022-02-02build_dtree: ignore codependent parametersDaniel Friesel-0/+1
2022-02-01dref export: static and analytic function ≙ single-node treeDaniel Friesel-0/+3
2022-01-31update tests for 063b277b32e8bdde5ce04efdf236c7821c79a3daDaniel Friesel-17/+17
2022-01-31RMT generation: only split on relevant variablesDaniel Friesel-3/+19
2022-01-31ParamStats: Remove unused can_be_fitted functionDaniel Friesel-30/+0
Has been superseded by ModelAttribute.all_relevant_parameters_are_none_or_numeric
2022-01-31LMT generation: Catch LinAlg errors (e.g. during SVD), fall back to staticDaniel Friesel-1/+6
2022-01-31allow parameter values to be adjusted before modelingDaniel Friesel-0/+55
(e.g. to ensure they're positive)
2022-01-28PTAModel: Add force_tree optionDaniel Friesel-2/+59
2022-01-27export dataref entries with deterministic orderDaniel Friesel-2/+2
2022-01-27add LMT support via https://github.com/cerlymarco/linear-treeDaniel Friesel-0/+2962
2022-01-26Add tree attribute export for XGBoostDaniel Friesel-10/+32
2022-01-21add depth / #nodes accessor to sklearn CART modelDaniel Friesel-2/+28
2022-01-21"if np.std(data) < 0". real galaxy brain condition right there.Daniel Friesel-1/+1
2022-01-21parameters: fix xgb model dumpDaniel Friesel-2/+3
2022-01-18optionally export xgboost modelDaniel Friesel-0/+3
2022-01-18loader: gracefully handle uncreatable cache directoryDaniel Friesel-0/+6
2022-01-17build_tree: oops. properly set staticfunctionDaniel Friesel-2/+4
2022-01-17XGBoost: add env variables for num regressors and max depthDaniel Friesel-8/+14
2022-01-17CART, XGBoost: Fall back to StaticFunction if no parameters are availableDaniel Friesel-0/+10
2022-01-17XGBoost: Input data must be two-dimensionalDaniel Friesel-1/+1
2022-01-14fix categorial-to-scalar handler for categorial values unseen during trainingDaniel Friesel-1/+1
2022-01-10SKLearnRegressionFunction: handle unseen params in categorial_to_index modeDaniel Friesel-2/+13
2022-01-06README: Document XGBoostDaniel Friesel-0/+1
2022-01-06param_to_ndarray: remove debug outputDaniel Friesel-3/+0
2022-01-06perform categorial→scalar conversion based on env varDaniel Friesel-2/+7
2022-01-06sklearn (CART, XGBoost): support mapping of categorial parameter values to ↵Daniel Friesel-10/+36
scalar indexes
2022-01-06test: adjust validator usage for 2c5bcd77f2c952cc5269ca3e4b6e0a7323ebd085Daniel Friesel-2/+2
2022-01-06add preliminary xgboost supportDaniel Friesel-1/+27
2022-01-06add xv data to dref exportDaniel Friesel-3/+3
2022-01-05store decision tree attributes of xv models in dataref exportDaniel Friesel-9/+57
2022-01-05cross validation: return intermediate models used for XVDaniel Friesel-20/+28
These are interesting for statistics, e.g. to determine the average dtree size
2022-01-05README: document sklearn cartDaniel Friesel-0/+2
2021-12-23model: add sklearn CART support (CART with scalar features)Daniel Friesel-3/+91
2021-12-03dtree: switch to ssr lossDaniel Friesel-12/+13
2021-12-03model: fix parameter counts in dataref exportDaniel Friesel-1/+3
2021-12-03model: Remove temporary ResKIL accuracy/power modeling hackDaniel Friesel-7/+0
2021-12-03optionally ignore scalar parameters during dtree split generationDaniel Friesel-16/+68
2021-12-01add ParamType helper classDaniel Friesel-13/+48
2021-12-01model: Add MAPE exportDaniel Friesel-0/+12
2021-12-01move some standard arguments to cli helper classDaniel Friesel-40/+24
2021-11-24validation: add SMAPE outputDaniel Friesel-2/+3
2021-11-23add parameter-aware cross validationDaniel Friesel-3/+52