From d9d0ba80a6bbde11f51b178b44d43c94ae022c9c Mon Sep 17 00:00:00 2001 From: =?utf8?q?J=C3=A9r=C3=B4me=20Benoit?= Date: Sat, 22 Nov 2025 12:38:29 +0100 Subject: [PATCH] perf(qav3)!: add amplitude zigzag threshold excess to reservals labeling HPO objectives MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Signed-off-by: Jérôme Benoit --- .opencode/command/openspec-proposal.md | 1 + README.md | 138 +++++++++--------- quickadapter/user_data/config-template.json | 2 +- .../freqaimodels/QuickAdapterRegressorV3.py | 20 ++- 4 files changed, 85 insertions(+), 76 deletions(-) diff --git a/.opencode/command/openspec-proposal.md b/.opencode/command/openspec-proposal.md index 096770e..9282a4f 100644 --- a/.opencode/command/openspec-proposal.md +++ b/.opencode/command/openspec-proposal.md @@ -16,6 +16,7 @@ $ARGUMENTS - Keep changes tightly scoped to the requested outcome. - Refer to `openspec/AGENTS.md` (located inside the `openspec/` directory—run `ls openspec` or `openspec update` if you don't see it) if you need additional OpenSpec conventions or clarifications. - Identify any vague or ambiguous details and ask the necessary follow-up questions before editing files. +- Do not write any code during the proposal stage. Only create design documents (proposal.md, tasks.md, design.md, and spec deltas). Implementation happens in the apply stage after approval. **Steps** diff --git a/README.md b/README.md index e3fbeb4..3d2c959 100644 --- a/README.md +++ b/README.md @@ -35,75 +35,75 @@ docker compose up -d --build ### Configuration tunables -| Path | Default | Type / Range | Description | -| ---------------------------------------------------- | ----------------- | -------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| _Protections_ | | | | -| estimated_trade_duration_candles | 48 | int >= 1 | Heuristic for StoplossGuard tuning. | -| _Leverage_ | | | | -| leverage | proposed_leverage | float [1.0, max_leverage] | Leverage. Fallback to proposed_leverage for the pair. | -| _Exit pricing_ | | | | -| exit_pricing.trade_price_target | `moving_average` | enum {`moving_average`,`interpolation`,`weighted_interpolation`} | Trade NATR computation method. | -| exit_pricing.thresholds_calibration.decline_quantile | 0.90 | float (0,1) | PnL decline quantile threshold. | -| _Reversal confirmation_ | | | | -| reversal_confirmation.lookback_period | 0 | int >= 0 | Prior confirming candles; 0 = none. | -| reversal_confirmation.decay_ratio | 0.5 | float (0,1] | Geometric per-candle relaxation factor. | -| reversal_confirmation.min_natr_ratio_percent | 0.0095 | float [0,1] | Lower bound fraction for volatility adjusted reversal threshold. | -| reversal_confirmation.max_natr_ratio_percent | 0.2 | float [0,1] | Upper bound fraction (>= lower bound) for volatility adjusted reversal threshold. | -| _Regressor model_ | | | | -| freqai.regressor | `xgboost` | enum {`xgboost`,`lightgbm`} | Machine learning regressor algorithm. | -| _Extrema smoothing_ | | | | -| freqai.extrema_smoothing.method | `gaussian` | enum {`gaussian`,`kaiser`,`triang`,`smm`,`sma`} | Extrema smoothing kernel (smm=simple moving median, sma=simple moving average). | -| freqai.extrema_smoothing.window | 5 | int >= 3 | Window size for extrema smoothing. | -| freqai.extrema_smoothing.beta | 8.0 | float > 0 | Kaiser kernel shape parameter. | -| _Extrema weighting_ | | | | -| freqai.extrema_weighting.strategy | `none` | enum {`none`,`amplitude`,`amplitude_excess`} | Extrema weighting source: unweighted (`none`), swing amplitude (`amplitude`), or volatility-adjusted swing amplitude (`amplitude_excess`). | -| freqai.extrema_weighting.normalization | `minmax` | enum {`minmax`,`zscore`,`l1`,`l2`,`robust`,`softmax`,`tanh`,`rank`,`none`} | Normalization method for weights. | -| freqai.extrema_weighting.gamma | 1.0 | float (0,10] | Contrast exponent applied after normalization (>1 emphasizes extremes, 0 0 | Temperature parameter for softmax normalization (lower values sharpen distribution, higher values flatten it). | -| freqai.extrema_weighting.tanh_scale | 1.0 | float > 0 | Scale parameter for tanh normalization. | -| freqai.extrema_weighting.tanh_gain | 1.0 | float > 0 | Gain parameter for tanh normalization. | -| freqai.extrema_weighting.robust_quantiles | [0.25, 0.75] | list[float] where 0 <= q_low < q_high <= 1 | Quantile range for robust normalization. | -| freqai.extrema_weighting.rank_method | `average` | enum {`average`,`min`,`max`,`dense`,`ordinal`} | Ranking method for rank normalization. | -| _Feature parameters_ | | | | -| freqai.feature_parameters.label_period_candles | min/max midpoint | int >= 1 | Zigzag labeling NATR horizon. | -| freqai.feature_parameters.min_label_period_candles | 12 | int >= 1 | Minimum labeling NATR horizon used for reversals labeling HPO. | -| freqai.feature_parameters.max_label_period_candles | 24 | int >= 1 | Maximum labeling NATR horizon used for reversals labeling HPO. | -| freqai.feature_parameters.label_natr_ratio | min/max midpoint | float > 0 | Zigzag labeling NATR ratio. | -| freqai.feature_parameters.min_label_natr_ratio | 9.0 | float > 0 | Minimum labeling NATR ratio used for reversals labeling HPO. | -| freqai.feature_parameters.max_label_natr_ratio | 12.0 | float > 0 | Maximum labeling NATR ratio used for reversals labeling HPO. | -| freqai.feature_parameters.label_frequency_candles | `auto` | int >= 2 \| `auto` | Reversals labeling frequency. `auto` = max(2, 2 \* number of whitelisted pairs). | -| freqai.feature_parameters.label_metric | `euclidean` | string (supported: `euclidean`,`minkowski`,`cityblock`,`chebyshev`,`mahalanobis`,`seuclidean`,`jensenshannon`,`sqeuclidean`,...) | Metric used in distance calculations to ideal point. | -| freqai.feature_parameters.label_weights | [0.5,0.5] | list[float] | Per-objective weights used in distance calculations to ideal point. First objective is the median swing amplitude of Zigzag reversals (reversals quality). Second objective is the number of detected reversals. | -| freqai.feature_parameters.label_p_order | `None` | float | p-order used by Minkowski / power-mean calculations (optional). | -| freqai.feature_parameters.label_medoid_metric | `euclidean` | string | Metric used with `medoid`. | -| freqai.feature_parameters.label_kmeans_metric | `euclidean` | string | Metric used for k-means clustering. | -| freqai.feature_parameters.label_kmeans_selection | `min` | enum {`min`,`medoid`} | Strategy to select trial in the best kmeans cluster. | -| freqai.feature_parameters.label_kmedoids_metric | `euclidean` | string | Metric used for k-medoids clustering. | -| freqai.feature_parameters.label_kmedoids_selection | `min` | enum {`min`,`medoid`} | Strategy to select trial in the best k-medoids cluster. | -| freqai.feature_parameters.label_knn_metric | `minkowski` | string | Distance metric for KNN. | -| freqai.feature_parameters.label_knn_p_order | `None` | float | p-order for KNN Minkowski metric distance. (optional) | -| freqai.feature_parameters.label_knn_n_neighbors | 5 | int >= 1 | Number of neighbors for KNN. | -| _Predictions extrema_ | | | | -| freqai.predictions_extrema.selection_method | `rank` | enum {`rank`,`values`,`partition`} | Extrema selection method. `values` uses reversal values, `rank` uses ranked extrema values, `partition` uses sign-based partitioning. | -| freqai.predictions_extrema.thresholds_smoothing | `mean` | enum {`mean`,`isodata`,`li`,`minimum`,`otsu`,`triangle`,`yen`,`median`,`soft_extremum`} | Thresholding method for prediction thresholds smoothing. | -| freqai.predictions_extrema.thresholds_alpha | 12.0 | float > 0 | Alpha for `soft_extremum`. | -| freqai.predictions_extrema.threshold_outlier | 0.999 | float (0,1) | Quantile threshold for predictions outlier filtering. | -| _Optuna / HPO_ | | | | -| freqai.optuna_hyperopt.enabled | true | bool | Enables HPO. | -| freqai.optuna_hyperopt.sampler | `tpe` | enum {`tpe`,`auto`} | HPO sampler algorithm. `tpe` uses TPESampler with multivariate and group, `auto` uses AutoSampler. | -| freqai.optuna_hyperopt.storage | `file` | enum {`file`,`sqlite`} | HPO storage backend. | -| freqai.optuna_hyperopt.continuous | true | bool | Continuous HPO. | -| freqai.optuna_hyperopt.warm_start | true | bool | Warm start HPO with previous best value(s). | -| freqai.optuna_hyperopt.n_startup_trials | 15 | int >= 0 | HPO startup trials. | -| freqai.optuna_hyperopt.n_trials | 50 | int >= 1 | Maximum HPO trials. | -| freqai.optuna_hyperopt.n_jobs | CPU threads / 4 | int >= 1 | Parallel HPO workers. | -| freqai.optuna_hyperopt.timeout | 7200 | int >= 0 | HPO wall-clock timeout in seconds. | -| freqai.optuna_hyperopt.label_candles_step | 1 | int >= 1 | Step for Zigzag NATR horizon search space. | -| freqai.optuna_hyperopt.train_candles_step | 10 | int >= 1 | Step for training sets size search space. | -| freqai.optuna_hyperopt.space_reduction | false | bool | Enable/disable HPO search space reduction based on previous best parameters. | -| freqai.optuna_hyperopt.expansion_ratio | 0.4 | float [0,1] | HPO search space expansion ratio. | -| freqai.optuna_hyperopt.min_resource | 3 | int >= 1 | Minimum resource per Hyperband pruner rung. | -| freqai.optuna_hyperopt.seed | 1 | int >= 0 | HPO RNG seed. | +| Path | Default | Type / Range | Description | +| ---------------------------------------------------- | ----------------- | -------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | +| _Protections_ | | | | +| estimated_trade_duration_candles | 48 | int >= 1 | Heuristic for StoplossGuard tuning. | +| _Leverage_ | | | | +| leverage | proposed_leverage | float [1.0, max_leverage] | Leverage. Fallback to proposed_leverage for the pair. | +| _Exit pricing_ | | | | +| exit_pricing.trade_price_target | `moving_average` | enum {`moving_average`,`interpolation`,`weighted_interpolation`} | Trade NATR computation method. | +| exit_pricing.thresholds_calibration.decline_quantile | 0.90 | float (0,1) | PnL decline quantile threshold. | +| _Reversal confirmation_ | | | | +| reversal_confirmation.lookback_period | 0 | int >= 0 | Prior confirming candles; 0 = none. | +| reversal_confirmation.decay_ratio | 0.5 | float (0,1] | Geometric per-candle relaxation factor. | +| reversal_confirmation.min_natr_ratio_percent | 0.0095 | float [0,1] | Lower bound fraction for volatility adjusted reversal threshold. | +| reversal_confirmation.max_natr_ratio_percent | 0.2 | float [0,1] | Upper bound fraction (>= lower bound) for volatility adjusted reversal threshold. | +| _Regressor model_ | | | | +| freqai.regressor | `xgboost` | enum {`xgboost`,`lightgbm`} | Machine learning regressor algorithm. | +| _Extrema smoothing_ | | | | +| freqai.extrema_smoothing.method | `gaussian` | enum {`gaussian`,`kaiser`,`triang`,`smm`,`sma`} | Extrema smoothing kernel (smm=simple moving median, sma=simple moving average). | +| freqai.extrema_smoothing.window | 5 | int >= 3 | Window size for extrema smoothing. | +| freqai.extrema_smoothing.beta | 8.0 | float > 0 | Kaiser kernel shape parameter. | +| _Extrema weighting_ | | | | +| freqai.extrema_weighting.strategy | `none` | enum {`none`,`amplitude`,`amplitude_excess`} | Extrema weighting source: unweighted (`none`), swing amplitude (`amplitude`), or volatility-adjusted swing amplitude (`amplitude_excess`). | +| freqai.extrema_weighting.normalization | `minmax` | enum {`minmax`,`zscore`,`l1`,`l2`,`robust`,`softmax`,`tanh`,`rank`,`none`} | Normalization method for weights. | +| freqai.extrema_weighting.gamma | 1.0 | float (0,10] | Contrast exponent applied after normalization (>1 emphasizes extremes, 0 0 | Temperature parameter for softmax normalization (lower values sharpen distribution, higher values flatten it). | +| freqai.extrema_weighting.tanh_scale | 1.0 | float > 0 | Scale parameter for tanh normalization. | +| freqai.extrema_weighting.tanh_gain | 1.0 | float > 0 | Gain parameter for tanh normalization. | +| freqai.extrema_weighting.robust_quantiles | [0.25, 0.75] | list[float] where 0 <= q_low < q_high <= 1 | Quantile range for robust normalization. | +| freqai.extrema_weighting.rank_method | `average` | enum {`average`,`min`,`max`,`dense`,`ordinal`} | Ranking method for rank normalization. | +| _Feature parameters_ | | | | +| freqai.feature_parameters.label_period_candles | min/max midpoint | int >= 1 | Zigzag labeling NATR horizon. | +| freqai.feature_parameters.min_label_period_candles | 12 | int >= 1 | Minimum labeling NATR horizon used for reversals labeling HPO. | +| freqai.feature_parameters.max_label_period_candles | 24 | int >= 1 | Maximum labeling NATR horizon used for reversals labeling HPO. | +| freqai.feature_parameters.label_natr_ratio | min/max midpoint | float > 0 | Zigzag labeling NATR ratio. | +| freqai.feature_parameters.min_label_natr_ratio | 9.0 | float > 0 | Minimum labeling NATR ratio used for reversals labeling HPO. | +| freqai.feature_parameters.max_label_natr_ratio | 12.0 | float > 0 | Maximum labeling NATR ratio used for reversals labeling HPO. | +| freqai.feature_parameters.label_frequency_candles | `auto` | int >= 2 \| `auto` | Reversals labeling frequency. `auto` = max(2, 2 \* number of whitelisted pairs). | +| freqai.feature_parameters.label_metric | `euclidean` | string (supported: `euclidean`,`minkowski`,`cityblock`,`chebyshev`,`mahalanobis`,`seuclidean`,`jensenshannon`,`sqeuclidean`,...) | Metric used in distance calculations to ideal point. | +| freqai.feature_parameters.label_weights | [0.5,0.5,0.5] | list[float] | Per-objective weights used in distance calculations to ideal point. First objective is the number of detected reversals. Second objective is the median swing amplitude of Zigzag reversals (reversals quality). Third objective is the median volatility-adjusted swing amplitude (amplitude_excess). | +| freqai.feature_parameters.label_p_order | `None` | float | p-order used by Minkowski / power-mean calculations (optional). | +| freqai.feature_parameters.label_medoid_metric | `euclidean` | string | Metric used with `medoid`. | +| freqai.feature_parameters.label_kmeans_metric | `euclidean` | string | Metric used for k-means clustering. | +| freqai.feature_parameters.label_kmeans_selection | `min` | enum {`min`,`medoid`} | Strategy to select trial in the best kmeans cluster. | +| freqai.feature_parameters.label_kmedoids_metric | `euclidean` | string | Metric used for k-medoids clustering. | +| freqai.feature_parameters.label_kmedoids_selection | `min` | enum {`min`,`medoid`} | Strategy to select trial in the best k-medoids cluster. | +| freqai.feature_parameters.label_knn_metric | `minkowski` | string | Distance metric for KNN. | +| freqai.feature_parameters.label_knn_p_order | `None` | float | p-order for KNN Minkowski metric distance. (optional) | +| freqai.feature_parameters.label_knn_n_neighbors | 5 | int >= 1 | Number of neighbors for KNN. | +| _Predictions extrema_ | | | | +| freqai.predictions_extrema.selection_method | `rank` | enum {`rank`,`values`,`partition`} | Extrema selection method. `values` uses reversal values, `rank` uses ranked extrema values, `partition` uses sign-based partitioning. | +| freqai.predictions_extrema.thresholds_smoothing | `mean` | enum {`mean`,`isodata`,`li`,`minimum`,`otsu`,`triangle`,`yen`,`median`,`soft_extremum`} | Thresholding method for prediction thresholds smoothing. | +| freqai.predictions_extrema.thresholds_alpha | 12.0 | float > 0 | Alpha for `soft_extremum`. | +| freqai.predictions_extrema.threshold_outlier | 0.999 | float (0,1) | Quantile threshold for predictions outlier filtering. | +| _Optuna / HPO_ | | | | +| freqai.optuna_hyperopt.enabled | true | bool | Enables HPO. | +| freqai.optuna_hyperopt.sampler | `tpe` | enum {`tpe`,`auto`} | HPO sampler algorithm. `tpe` uses TPESampler with multivariate and group, `auto` uses AutoSampler. | +| freqai.optuna_hyperopt.storage | `file` | enum {`file`,`sqlite`} | HPO storage backend. | +| freqai.optuna_hyperopt.continuous | true | bool | Continuous HPO. | +| freqai.optuna_hyperopt.warm_start | true | bool | Warm start HPO with previous best value(s). | +| freqai.optuna_hyperopt.n_startup_trials | 15 | int >= 0 | HPO startup trials. | +| freqai.optuna_hyperopt.n_trials | 50 | int >= 1 | Maximum HPO trials. | +| freqai.optuna_hyperopt.n_jobs | CPU threads / 4 | int >= 1 | Parallel HPO workers. | +| freqai.optuna_hyperopt.timeout | 7200 | int >= 0 | HPO wall-clock timeout in seconds. | +| freqai.optuna_hyperopt.label_candles_step | 1 | int >= 1 | Step for Zigzag NATR horizon search space. | +| freqai.optuna_hyperopt.train_candles_step | 10 | int >= 1 | Step for training sets size search space. | +| freqai.optuna_hyperopt.space_reduction | false | bool | Enable/disable HPO search space reduction based on previous best parameters. | +| freqai.optuna_hyperopt.expansion_ratio | 0.4 | float [0,1] | HPO search space expansion ratio. | +| freqai.optuna_hyperopt.min_resource | 3 | int >= 1 | Minimum resource per Hyperband pruner rung. | +| freqai.optuna_hyperopt.seed | 1 | int >= 0 | HPO RNG seed. | ## ReforceXY diff --git a/quickadapter/user_data/config-template.json b/quickadapter/user_data/config-template.json index cb1cf1b..4654272 100644 --- a/quickadapter/user_data/config-template.json +++ b/quickadapter/user_data/config-template.json @@ -144,7 +144,7 @@ "include_timeframes": ["5m", "15m", "1h", "4h"], "label_period_candles": 18, "label_metric": "euclidean", - "label_weights": [0.5, 0.5], + "label_weights": [0.5, 0.5, 0.5], "include_shifted_candles": 6, "DI_threshold": 10, "weight_factor": 0.9, diff --git a/quickadapter/user_data/freqaimodels/QuickAdapterRegressorV3.py b/quickadapter/user_data/freqaimodels/QuickAdapterRegressorV3.py index 7f75046..c27ab15 100644 --- a/quickadapter/user_data/freqaimodels/QuickAdapterRegressorV3.py +++ b/quickadapter/user_data/freqaimodels/QuickAdapterRegressorV3.py @@ -260,7 +260,7 @@ class QuickAdapterRegressorV3(BaseRegressionModel): for pair in self.pairs: self._optuna_hp_value[pair] = -1 self._optuna_train_value[pair] = -1 - self._optuna_label_values[pair] = [-1, -1] + self._optuna_label_values[pair] = [-1, -1, -1] self._optuna_hp_params[pair] = ( self.optuna_load_best_params( pair, QuickAdapterRegressorV3._OPTUNA_NAMESPACES[0] @@ -633,6 +633,7 @@ class QuickAdapterRegressorV3(BaseRegressionModel): directions=[ optuna.study.StudyDirection.MAXIMIZE, optuna.study.StudyDirection.MAXIMIZE, + optuna.study.StudyDirection.MAXIMIZE, ], ), ) @@ -2081,7 +2082,7 @@ def label_objective( max_label_period_candles: int = 24, min_label_natr_ratio: float = 9.0, max_label_natr_ratio: float = 12.0, -) -> tuple[float, int]: +) -> tuple[int, float, float]: min_label_period_candles, max_label_period_candles, candles_step = ( get_min_max_label_period_candles( fit_live_predictions_candles, @@ -2107,15 +2108,22 @@ def label_objective( df = df.iloc[-(max(2, int(label_period_cycles)) * label_period_candles) :] if df.empty: - return -np.inf, 0 + return 0, 0.0, 0.0 - _, pivots_values, _, pivots_amplitudes, _ = zigzag( + _, pivots_values, _, pivots_amplitudes, pivots_amplitude_excesses = zigzag( df, natr_period=label_period_candles, natr_ratio=label_natr_ratio, ) - median_amplitude = np.nanmedian(pivots_amplitudes) + median_amplitude = np.nanmedian(np.asarray(pivots_amplitudes, dtype=float)) if not np.isfinite(median_amplitude): median_amplitude = 0.0 - return median_amplitude, len(pivots_values) + + median_amplitude_excess = np.nanmedian( + np.asarray(pivots_amplitude_excesses, dtype=float) + ) + if not np.isfinite(median_amplitude_excess): + median_amplitude_excess = 0.0 + + return len(pivots_values), median_amplitude, median_amplitude_excess -- 2.43.0