From: Jérôme Benoit Date: Fri, 19 Jun 2026 14:12:11 +0000 (+0200) Subject: fix(quickadapter): align label prediction keep fraction default X-Git-Url: https://git.piment-noir.org/?a=commitdiff_plain;h=eaf298bd088773e8ac7ed1869e40a19c51aafcdb;p=freqai-strategies.git fix(quickadapter): align label prediction keep fraction default --- diff --git a/README.md b/README.md index 41f7616..14002bf 100644 --- a/README.md +++ b/README.md @@ -122,7 +122,7 @@ docker compose up -d --build | freqai.label_prediction.threshold_method | `mean` | enum {`mean`,`isodata`,`li`,`minimum`,`otsu`,`triangle`,`yen`,`median`,`soft_extremum`} | Thresholding method for prediction thresholds. | | freqai.label_prediction.soft_extremum_alpha | 12.0 | float >= 0 | Alpha for `soft_extremum` threshold method. | | freqai.label_prediction.outlier_quantile | 0.999 | float (0,1) | Quantile threshold for predictions outlier filtering. | -| freqai.label_prediction.keep_fraction | 0.5 | float (0,1] | Fraction of extrema used for thresholds. 1 uses all, lower values keep only most significant. Applies to `rank_extrema` and `rank_peaks`; ignored for `partition`. | +| freqai.label_prediction.keep_fraction | 0.0075 | float (0,1] | Fraction of extrema used for thresholds. 1 uses all, lower values keep only most significant. Applies to `rank_extrema` and `rank_peaks`; ignored for `partition`. | | _Optuna / HPO_ | | | | | freqai.optuna_hyperopt.enabled | false | bool | Enables HPO. | | freqai.optuna_hyperopt.sampler | `tpe` | enum {`tpe`,`auto`} | HPO sampler algorithm for `hp` namespace. `tpe` uses [TPESampler](https://optuna.readthedocs.io/en/stable/reference/samplers/generated/optuna.samplers.TPESampler.html) with multivariate, group, and constant_liar (when multiple workers), `auto` uses [AutoSampler](https://hub.optuna.org/samplers/auto_sampler). | diff --git a/quickadapter/user_data/strategies/LabelTransformer.py b/quickadapter/user_data/strategies/LabelTransformer.py index 8ec3a72..d1dd049 100644 --- a/quickadapter/user_data/strategies/LabelTransformer.py +++ b/quickadapter/user_data/strategies/LabelTransformer.py @@ -200,7 +200,7 @@ DEFAULTS_LABEL_PREDICTION: Final[dict[str, Any]] = { "threshold_method": SKIMAGE_THRESHOLD_METHODS[0], # "mean" "outlier_quantile": 0.999, "soft_extremum_alpha": 12.0, - "keep_fraction": 0.5, + "keep_fraction": 0.0075, }