diff options
| -rw-r--r-- | README.md | 3 | ||||
| -rw-r--r-- | lib/functions.py | 8 | ||||
| -rw-r--r-- | lib/paramfit.py | 8 |
3 files changed, 16 insertions, 3 deletions
@@ -133,8 +133,9 @@ The following variables may be set to alter the behaviour of dfatool components. | `DFATOOL_LMT_MIN_SAMPLES_LEAF` | 0.0 .. **0.1** .. 1.0, 3 .. *n* | Minimum samples that each leaf of a split candidate must contain. A value below 1.0 specifies a ratio of the total number of training samples. A value above 1 specifies an absolute number of samples. | | `DFATOOL_LMT_MAX_BINS` | 10 .. **120** | Number of bins used to determine optimal split. LMT default: 25. | | `DFATOOL_LMT_CRITERION` | **mse**, rmse, mae, poisson | Error metric to use when selecting best split. | -| `DFATOOL_ULS_ERROR_METRIC` | **ssr**, rmsd, mae, … | Error metric to use when selecting best-fitting function during unsupervised least squares (ULS) regression. Least squares regression itself minimzes root mean square deviation (rmsd), hence the equivalent (but partitioning-compatible) sum of squared residuals (ssr) is the default. Supports all metrics accepted by `--error-metric`. | +| `DFATOOL_ULS_ERROR_METRIC` | **ssr**, rmsd, **mae**, … | Error metric to use when selecting best-fitting function during unsupervised least squares (ULS) regression. By default, least squares regression minimzes root mean square deviation (rmsd), hence the equivalent (but partitioning-compatible) sum of squared residuals (ssr) is the default. If `DFATOOL_ULS_LOSS_FUNCTION` is set to another value than linear, the default is mean absolute error (mae). Supports all metrics accepted by `--error-metric`. | | `DFATOOL_ULS_FUNCTIONS` | a,b,… | List of function templates to use in ULS. Default: all supported functions. | +| `DFATOOL_ULS_LOSS_FUNCTION` | **linear**', soft\_l1, … | Loss function for least squares fitting, see `scipy.optimize.least_squares#loss` documentation. | | `DFATOOL_ULS_MIN_DISTINCT_VALUES` | 2 .. **3** .. *n* | Minimum number of unique values a parameter must take to be eligible for ULS | | `DFATOOL_ULS_SKIP_CODEPENDENT_CHECK` | **0**, 1 | Do not detect and remove co-dependent features in ULS. | | `DFATOOL_ULS_MIN_BOUND` | **-∞** .. *n* | Lower bound for ULS regression variables. Setting it to 0 can often be beneficial. | diff --git a/lib/functions.py b/lib/functions.py index 35b04ef..b76814b 100644 --- a/lib/functions.py +++ b/lib/functions.py @@ -27,6 +27,7 @@ dfatool_rmt_relevance_threshold = float( os.getenv("DFATOOL_RMT_RELEVANCE_THRESHOLD", "0.5") ) +dfatool_uls_loss_fun = os.getenv("DFATOOL_ULS_LOSS_FUNCTION", "linear") dfatool_uls_min_bound = float(os.getenv("DFATOOL_ULS_MIN_BOUND", -np.inf)) if dfatool_preproc_relevance_method == "mi": @@ -1692,7 +1693,11 @@ class FOLFunction(SKLearnRegressionFunction): self.model_args = list(np.ones((num_vars))) try: res = optimize.least_squares( - error_function, self.model_args, args=(fit_parameters, data), xtol=2e-15 + error_function, + self.model_args, + args=(fit_parameters, data), + xtol=2e-15, + loss=dfatool_uls_loss_fun, ) except ValueError as err: logger.warning(f"Fit failed: {err} (function: {self.model_function})") @@ -1955,6 +1960,7 @@ class AnalyticFunction(ModelFunction): self.model_args, args=(X, Y), xtol=2e-15, + loss=dfatool_uls_loss_fun, bounds=(lower_bounds, upper_bounds), ) except ValueError as err: diff --git a/lib/paramfit.py b/lib/paramfit.py index 000aa9c..84eba2b 100644 --- a/lib/paramfit.py +++ b/lib/paramfit.py @@ -16,9 +16,14 @@ from .utils import ( ) logger = logging.getLogger(__name__) -best_fit_metric = os.getenv("DFATOOL_ULS_ERROR_METRIC", "ssr") +dfatool_uls_loss_fun = os.getenv("DFATOOL_ULS_LOSS_FUNCTION", "linear") dfatool_uls_min_bound = float(os.getenv("DFATOOL_ULS_MIN_BOUND", -np.inf)) +if dfatool_uls_loss_fun == "linear": + best_fit_metric = os.getenv("DFATOOL_ULS_ERROR_METRIC", "ssr") +else: + best_fit_metric = os.getenv("DFATOOL_ULS_ERROR_METRIC", "mae") + class ParamFit: """ @@ -222,6 +227,7 @@ def _try_fits( ini, args=(X, Y), xtol=2e-15, + loss=dfatool_uls_loss_fun, bounds=param_function.bounds, ) except FloatingPointError as e: |