Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
 zhaoli
|
002117c33e | ||
|
zhaoli
|
e952feed0a |
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -0,0 +1,48 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""Precompute the signal-quality gate series and save to pickle.
|
||||||
|
|
||||||
|
Usage:
|
||||||
|
python precompute_signal_quality_gate.py <pred_path> <output_path> [topk] [lookback] [threshold]
|
||||||
|
|
||||||
|
Example:
|
||||||
|
python precompute_signal_quality_gate.py \
|
||||||
|
/home/data/lake/mlruns/49/34165f27e4a34378ad54843a079a78c0/artifacts/pred.pkl \
|
||||||
|
/app/experiments/book/data/signal_quality_gate/sq_gate_5d_0.50.pkl \
|
||||||
|
10 5 0.5
|
||||||
|
"""
|
||||||
|
import sys
|
||||||
|
import pickle
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
# Add tac-qlib to path
|
||||||
|
sys.path.insert(0, "/app/tac-qlib")
|
||||||
|
|
||||||
|
from tac_qlib.contrib.strategy.signal_quality_gate import compute_signal_quality_gate
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
if len(sys.argv) < 3:
|
||||||
|
print(__doc__)
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
pred_path = sys.argv[1]
|
||||||
|
output_path = sys.argv[2]
|
||||||
|
topk = int(sys.argv[3]) if len(sys.argv) > 3 else 10
|
||||||
|
lookback = int(sys.argv[4]) if len(sys.argv) > 4 else 5
|
||||||
|
threshold = float(sys.argv[5]) if len(sys.argv) > 5 else 0.5
|
||||||
|
|
||||||
|
lake_root = "/home/data/lake"
|
||||||
|
|
||||||
|
print(f"Computing signal-quality gate: topk={topk}, lookback={lookback}, threshold={threshold}")
|
||||||
|
gate = compute_signal_quality_gate(
|
||||||
|
pred_path,
|
||||||
|
lake_root=lake_root,
|
||||||
|
topk=topk,
|
||||||
|
lookback=lookback,
|
||||||
|
threshold=threshold,
|
||||||
|
)
|
||||||
|
|
||||||
|
print(f"Gate: {gate.sum()}/{len(gate)} days open ({gate.mean():.1%})")
|
||||||
|
|
||||||
|
with open(output_path, "wb") as f:
|
||||||
|
pickle.dump(gate, f)
|
||||||
|
print(f"Saved to {output_path}")
|
||||||
@@ -0,0 +1,129 @@
|
|||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
# Signal-quality gate: TopkDropout gated by rolling hit-rate of topk picks.
|
||||||
|
#
|
||||||
|
# 1. Compute the gate: python precompute_signal_quality_gate.py <pred.pkl> <gate.pkl>
|
||||||
|
# 2. Run this workflow: rd_run_workflow config_path=<this yaml> experiment_name=<exp>
|
||||||
|
#
|
||||||
|
# The strategy loads the precomputed gate from signal_quality_gate_path.
|
||||||
|
# When hit rate >= threshold, trade; otherwise, go to cash.
|
||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
{%- set LAKE = TAC_LAKE_DIR %}
|
||||||
|
{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
|
||||||
|
{%- set SP_FIELDS = "sp_ret,sp_ou_zscore,sp_ou_half_life,sp_ou_revert,sp_hmm_p_regime1,sp_hmm_state,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
|
||||||
|
{%- set GATE_PATH = "/app/experiments/book/data/signal_quality_gate/sq_gate_5d_0.50.pkl" %}
|
||||||
|
|
||||||
|
qlib_init:
|
||||||
|
provider_uri: "{{ LAKE }}"
|
||||||
|
region: us
|
||||||
|
expression_cache: null
|
||||||
|
dataset_cache: null
|
||||||
|
|
||||||
|
calendar_provider:
|
||||||
|
class: tac_qlib.data.providers.LakeCalendarProvider
|
||||||
|
kwargs:
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
instrument_provider:
|
||||||
|
class: tac_qlib.data.providers.LakeInstrumentProvider
|
||||||
|
kwargs:
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
markets: {}
|
||||||
|
feature_provider:
|
||||||
|
class: tac_qlib.data.providers.LakeFeatureProvider
|
||||||
|
kwargs:
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
|
||||||
|
exp_manager:
|
||||||
|
class: MLflowExpManager
|
||||||
|
module_path: qlib.workflow.expm
|
||||||
|
kwargs:
|
||||||
|
uri: "sqlite:///{{ LAKE }}/mlruns.db"
|
||||||
|
default_exp_name: "tac-rd-sq-gate"
|
||||||
|
|
||||||
|
task:
|
||||||
|
model:
|
||||||
|
class: LGBModel
|
||||||
|
module_path: qlib.contrib.model.gbdt
|
||||||
|
kwargs:
|
||||||
|
loss: mse
|
||||||
|
learning_rate: 0.05
|
||||||
|
num_leaves: 15
|
||||||
|
n_estimators: 200
|
||||||
|
colsample_bytree: 0.8
|
||||||
|
subsample: 0.8
|
||||||
|
subsample_freq: 1
|
||||||
|
reg_alpha: 0.01
|
||||||
|
reg_lambda: 0.01
|
||||||
|
|
||||||
|
dataset:
|
||||||
|
class: DatasetH
|
||||||
|
module_path: qlib.data.dataset
|
||||||
|
kwargs:
|
||||||
|
handler:
|
||||||
|
class: TACHandler
|
||||||
|
module_path: tac_qlib.contrib.data.handler
|
||||||
|
kwargs:
|
||||||
|
instruments: "{{ UNIVERSE }}"
|
||||||
|
start_time: 2015-01-03
|
||||||
|
end_time: 2026-08-10
|
||||||
|
fit_start_time: 2015-01-03
|
||||||
|
fit_end_time: 2025-09-01
|
||||||
|
freq: day
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||||
|
feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
|
||||||
|
infer_processors:
|
||||||
|
- class: DropAllNaN
|
||||||
|
kwargs: {}
|
||||||
|
- class: ProcessInf
|
||||||
|
kwargs: {}
|
||||||
|
- class: CSRankNorm
|
||||||
|
kwargs: {}
|
||||||
|
- class: ZScoreNorm
|
||||||
|
kwargs: {}
|
||||||
|
- class: Fillna
|
||||||
|
kwargs: {}
|
||||||
|
segments:
|
||||||
|
train: [2015-01-03, 2025-09-01]
|
||||||
|
valid: [2025-09-03, 2026-01-03]
|
||||||
|
test: [2026-01-04, 2026-08-10]
|
||||||
|
|
||||||
|
record:
|
||||||
|
- class: SignalRecord
|
||||||
|
module_path: qlib.workflow.record_temp
|
||||||
|
kwargs: {}
|
||||||
|
- class: SigAnaRecord
|
||||||
|
module_path: qlib.workflow.record_temp
|
||||||
|
kwargs:
|
||||||
|
ana_long_short: true
|
||||||
|
ann_scaler: 252
|
||||||
|
- class: PortAnaRecord
|
||||||
|
module_path: qlib.workflow.record_temp
|
||||||
|
kwargs:
|
||||||
|
config:
|
||||||
|
strategy:
|
||||||
|
class: SignalQualityGateStrategy
|
||||||
|
module_path: tac_qlib.contrib.strategy.signal_quality_gate
|
||||||
|
kwargs:
|
||||||
|
signal: "<PRED>"
|
||||||
|
signal_quality_gate_path: "{{ GATE_PATH }}"
|
||||||
|
topk: 10
|
||||||
|
n_drop: 1
|
||||||
|
only_tradable: true
|
||||||
|
risk_degree: 0.95
|
||||||
|
backtest:
|
||||||
|
start_time: 2026-01-04
|
||||||
|
end_time: 2026-08-10
|
||||||
|
account: 1000000
|
||||||
|
benchmark: SPY
|
||||||
|
exchange_kwargs:
|
||||||
|
codes: "{{ UNIVERSE }}"
|
||||||
|
deal_price: $close
|
||||||
|
freq: day
|
||||||
|
open_cost: 0.0005
|
||||||
|
close_cost: 0.0015
|
||||||
|
min_cost: 5.0
|
||||||
|
risk_analysis_freq: 1d
|
||||||
@@ -0,0 +1,115 @@
|
|||||||
|
# Signal-quality gate backtest for 2021
|
||||||
|
{%- set LAKE = TAC_LAKE_DIR %}
|
||||||
|
{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
|
||||||
|
{%- set SP_FIELDS = "sp_ret,sp_ou_zscore,sp_ou_half_life,sp_ou_revert,sp_hmm_p_regime1,sp_hmm_state,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
|
||||||
|
{# Gate computed on-the-fly from signal + lake close prices #}
|
||||||
|
|
||||||
|
qlib_init:
|
||||||
|
provider_uri: "{{ LAKE }}"
|
||||||
|
region: us
|
||||||
|
expression_cache: null
|
||||||
|
dataset_cache: null
|
||||||
|
calendar_provider:
|
||||||
|
class: tac_qlib.data.providers.LakeCalendarProvider
|
||||||
|
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||||
|
instrument_provider:
|
||||||
|
class: tac_qlib.data.providers.LakeInstrumentProvider
|
||||||
|
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
||||||
|
feature_provider:
|
||||||
|
class: tac_qlib.data.providers.LakeFeatureProvider
|
||||||
|
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||||
|
exp_manager:
|
||||||
|
class: MLflowExpManager
|
||||||
|
module_path: qlib.workflow.expm
|
||||||
|
kwargs:
|
||||||
|
uri: "sqlite:///{{ LAKE }}/mlruns.db"
|
||||||
|
default_exp_name: "tac-rd-sq-gate-2021"
|
||||||
|
|
||||||
|
task:
|
||||||
|
model:
|
||||||
|
class: LGBModel
|
||||||
|
module_path: qlib.contrib.model.gbdt
|
||||||
|
kwargs:
|
||||||
|
loss: mse
|
||||||
|
learning_rate: 0.05
|
||||||
|
num_leaves: 15
|
||||||
|
n_estimators: 200
|
||||||
|
colsample_bytree: 0.8
|
||||||
|
subsample: 0.8
|
||||||
|
subsample_freq: 1
|
||||||
|
reg_alpha: 0.01
|
||||||
|
reg_lambda: 0.01
|
||||||
|
|
||||||
|
dataset:
|
||||||
|
class: DatasetH
|
||||||
|
module_path: qlib.data.dataset
|
||||||
|
kwargs:
|
||||||
|
handler:
|
||||||
|
class: TACHandler
|
||||||
|
module_path: tac_qlib.contrib.data.handler
|
||||||
|
kwargs:
|
||||||
|
instruments: "{{ UNIVERSE }}"
|
||||||
|
start_time: 2015-01-03
|
||||||
|
end_time: 2021-12-31
|
||||||
|
fit_start_time: 2015-01-03
|
||||||
|
fit_end_time: 2021-01-03
|
||||||
|
freq: day
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||||
|
feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
|
||||||
|
infer_processors:
|
||||||
|
- class: DropAllNaN
|
||||||
|
kwargs: {}
|
||||||
|
- class: ProcessInf
|
||||||
|
kwargs: {}
|
||||||
|
- class: CSRankNorm
|
||||||
|
kwargs: {}
|
||||||
|
- class: ZScoreNorm
|
||||||
|
kwargs: {}
|
||||||
|
- class: Fillna
|
||||||
|
kwargs: {}
|
||||||
|
segments:
|
||||||
|
train: [2015-01-03, 2020-09-01]
|
||||||
|
valid: [2020-09-03, 2021-01-03]
|
||||||
|
test: [2021-01-04, 2021-12-31]
|
||||||
|
|
||||||
|
record:
|
||||||
|
- class: SignalRecord
|
||||||
|
module_path: qlib.workflow.record_temp
|
||||||
|
kwargs: {}
|
||||||
|
- class: SigAnaRecord
|
||||||
|
module_path: qlib.workflow.record_temp
|
||||||
|
kwargs: { ana_long_short: true, ann_scaler: 252 }
|
||||||
|
- class: PortAnaRecord
|
||||||
|
module_path: qlib.workflow.record_temp
|
||||||
|
kwargs:
|
||||||
|
config:
|
||||||
|
strategy:
|
||||||
|
class: SignalQualityGateStrategy
|
||||||
|
module_path: tac_qlib.contrib.strategy.signal_quality_gate
|
||||||
|
kwargs:
|
||||||
|
signal: "<PRED>"
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
gate_topk: 10
|
||||||
|
gate_lookback: 5
|
||||||
|
gate_threshold: 0.5
|
||||||
|
gate_start: "2015-01-03"
|
||||||
|
gate_end: "2021-12-31"
|
||||||
|
topk: 10
|
||||||
|
n_drop: 1
|
||||||
|
only_tradable: true
|
||||||
|
risk_degree: 0.95
|
||||||
|
backtest:
|
||||||
|
start_time: 2021-01-04
|
||||||
|
end_time: 2021-12-31
|
||||||
|
account: 1000000
|
||||||
|
benchmark: SPY
|
||||||
|
exchange_kwargs:
|
||||||
|
codes: "{{ UNIVERSE }}"
|
||||||
|
deal_price: $close
|
||||||
|
freq: day
|
||||||
|
open_cost: 0.0005
|
||||||
|
close_cost: 0.0015
|
||||||
|
min_cost: 5.0
|
||||||
|
risk_analysis_freq: 1d
|
||||||
@@ -0,0 +1,115 @@
|
|||||||
|
# Signal-quality gate backtest for 2023
|
||||||
|
{%- set LAKE = TAC_LAKE_DIR %}
|
||||||
|
{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
|
||||||
|
{%- set SP_FIELDS = "sp_ret,sp_ou_zscore,sp_ou_half_life,sp_ou_revert,sp_hmm_p_regime1,sp_hmm_state,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
|
||||||
|
{# Gate computed on-the-fly from signal + lake close prices #}
|
||||||
|
|
||||||
|
qlib_init:
|
||||||
|
provider_uri: "{{ LAKE }}"
|
||||||
|
region: us
|
||||||
|
expression_cache: null
|
||||||
|
dataset_cache: null
|
||||||
|
calendar_provider:
|
||||||
|
class: tac_qlib.data.providers.LakeCalendarProvider
|
||||||
|
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||||
|
instrument_provider:
|
||||||
|
class: tac_qlib.data.providers.LakeInstrumentProvider
|
||||||
|
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
||||||
|
feature_provider:
|
||||||
|
class: tac_qlib.data.providers.LakeFeatureProvider
|
||||||
|
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||||
|
exp_manager:
|
||||||
|
class: MLflowExpManager
|
||||||
|
module_path: qlib.workflow.expm
|
||||||
|
kwargs:
|
||||||
|
uri: "sqlite:///{{ LAKE }}/mlruns.db"
|
||||||
|
default_exp_name: "tac-rd-sq-gate-2023"
|
||||||
|
|
||||||
|
task:
|
||||||
|
model:
|
||||||
|
class: LGBModel
|
||||||
|
module_path: qlib.contrib.model.gbdt
|
||||||
|
kwargs:
|
||||||
|
loss: mse
|
||||||
|
learning_rate: 0.05
|
||||||
|
num_leaves: 15
|
||||||
|
n_estimators: 200
|
||||||
|
colsample_bytree: 0.8
|
||||||
|
subsample: 0.8
|
||||||
|
subsample_freq: 1
|
||||||
|
reg_alpha: 0.01
|
||||||
|
reg_lambda: 0.01
|
||||||
|
|
||||||
|
dataset:
|
||||||
|
class: DatasetH
|
||||||
|
module_path: qlib.data.dataset
|
||||||
|
kwargs:
|
||||||
|
handler:
|
||||||
|
class: TACHandler
|
||||||
|
module_path: tac_qlib.contrib.data.handler
|
||||||
|
kwargs:
|
||||||
|
instruments: "{{ UNIVERSE }}"
|
||||||
|
start_time: 2015-01-03
|
||||||
|
end_time: 2023-12-29
|
||||||
|
fit_start_time: 2015-01-03
|
||||||
|
fit_end_time: 2023-01-03
|
||||||
|
freq: day
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||||
|
feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
|
||||||
|
infer_processors:
|
||||||
|
- class: DropAllNaN
|
||||||
|
kwargs: {}
|
||||||
|
- class: ProcessInf
|
||||||
|
kwargs: {}
|
||||||
|
- class: CSRankNorm
|
||||||
|
kwargs: {}
|
||||||
|
- class: ZScoreNorm
|
||||||
|
kwargs: {}
|
||||||
|
- class: Fillna
|
||||||
|
kwargs: {}
|
||||||
|
segments:
|
||||||
|
train: [2015-01-03, 2022-09-01]
|
||||||
|
valid: [2022-09-03, 2023-01-03]
|
||||||
|
test: [2023-01-03, 2023-12-29]
|
||||||
|
|
||||||
|
record:
|
||||||
|
- class: SignalRecord
|
||||||
|
module_path: qlib.workflow.record_temp
|
||||||
|
kwargs: {}
|
||||||
|
- class: SigAnaRecord
|
||||||
|
module_path: qlib.workflow.record_temp
|
||||||
|
kwargs: { ana_long_short: true, ann_scaler: 252 }
|
||||||
|
- class: PortAnaRecord
|
||||||
|
module_path: qlib.workflow.record_temp
|
||||||
|
kwargs:
|
||||||
|
config:
|
||||||
|
strategy:
|
||||||
|
class: SignalQualityGateStrategy
|
||||||
|
module_path: tac_qlib.contrib.strategy.signal_quality_gate
|
||||||
|
kwargs:
|
||||||
|
signal: "<PRED>"
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
gate_topk: 10
|
||||||
|
gate_lookback: 5
|
||||||
|
gate_threshold: 0.5
|
||||||
|
gate_start: "2015-01-03"
|
||||||
|
gate_end: "2023-12-29"
|
||||||
|
topk: 10
|
||||||
|
n_drop: 1
|
||||||
|
only_tradable: true
|
||||||
|
risk_degree: 0.95
|
||||||
|
backtest:
|
||||||
|
start_time: 2023-01-03
|
||||||
|
end_time: 2023-12-29
|
||||||
|
account: 1000000
|
||||||
|
benchmark: SPY
|
||||||
|
exchange_kwargs:
|
||||||
|
codes: "{{ UNIVERSE }}"
|
||||||
|
deal_price: $close
|
||||||
|
freq: day
|
||||||
|
open_cost: 0.0005
|
||||||
|
close_cost: 0.0015
|
||||||
|
min_cost: 5.0
|
||||||
|
risk_analysis_freq: 1d
|
||||||
@@ -0,0 +1,115 @@
|
|||||||
|
# Signal-quality gate backtest for 2024
|
||||||
|
{%- set LAKE = TAC_LAKE_DIR %}
|
||||||
|
{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
|
||||||
|
{%- set SP_FIELDS = "sp_ret,sp_ou_zscore,sp_ou_half_life,sp_ou_revert,sp_hmm_p_regime1,sp_hmm_state,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
|
||||||
|
{# Gate computed on-the-fly from signal + lake close prices #}
|
||||||
|
|
||||||
|
qlib_init:
|
||||||
|
provider_uri: "{{ LAKE }}"
|
||||||
|
region: us
|
||||||
|
expression_cache: null
|
||||||
|
dataset_cache: null
|
||||||
|
calendar_provider:
|
||||||
|
class: tac_qlib.data.providers.LakeCalendarProvider
|
||||||
|
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||||
|
instrument_provider:
|
||||||
|
class: tac_qlib.data.providers.LakeInstrumentProvider
|
||||||
|
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
||||||
|
feature_provider:
|
||||||
|
class: tac_qlib.data.providers.LakeFeatureProvider
|
||||||
|
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||||
|
exp_manager:
|
||||||
|
class: MLflowExpManager
|
||||||
|
module_path: qlib.workflow.expm
|
||||||
|
kwargs:
|
||||||
|
uri: "sqlite:///{{ LAKE }}/mlruns.db"
|
||||||
|
default_exp_name: "tac-rd-sq-gate-2024"
|
||||||
|
|
||||||
|
task:
|
||||||
|
model:
|
||||||
|
class: LGBModel
|
||||||
|
module_path: qlib.contrib.model.gbdt
|
||||||
|
kwargs:
|
||||||
|
loss: mse
|
||||||
|
learning_rate: 0.05
|
||||||
|
num_leaves: 15
|
||||||
|
n_estimators: 200
|
||||||
|
colsample_bytree: 0.8
|
||||||
|
subsample: 0.8
|
||||||
|
subsample_freq: 1
|
||||||
|
reg_alpha: 0.01
|
||||||
|
reg_lambda: 0.01
|
||||||
|
|
||||||
|
dataset:
|
||||||
|
class: DatasetH
|
||||||
|
module_path: qlib.data.dataset
|
||||||
|
kwargs:
|
||||||
|
handler:
|
||||||
|
class: TACHandler
|
||||||
|
module_path: tac_qlib.contrib.data.handler
|
||||||
|
kwargs:
|
||||||
|
instruments: "{{ UNIVERSE }}"
|
||||||
|
start_time: 2015-01-03
|
||||||
|
end_time: 2024-12-31
|
||||||
|
fit_start_time: 2015-01-03
|
||||||
|
fit_end_time: 2024-01-03
|
||||||
|
freq: day
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||||
|
feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
|
||||||
|
infer_processors:
|
||||||
|
- class: DropAllNaN
|
||||||
|
kwargs: {}
|
||||||
|
- class: ProcessInf
|
||||||
|
kwargs: {}
|
||||||
|
- class: CSRankNorm
|
||||||
|
kwargs: {}
|
||||||
|
- class: ZScoreNorm
|
||||||
|
kwargs: {}
|
||||||
|
- class: Fillna
|
||||||
|
kwargs: {}
|
||||||
|
segments:
|
||||||
|
train: [2015-01-03, 2023-09-01]
|
||||||
|
valid: [2023-09-03, 2024-01-03]
|
||||||
|
test: [2024-01-02, 2024-12-31]
|
||||||
|
|
||||||
|
record:
|
||||||
|
- class: SignalRecord
|
||||||
|
module_path: qlib.workflow.record_temp
|
||||||
|
kwargs: {}
|
||||||
|
- class: SigAnaRecord
|
||||||
|
module_path: qlib.workflow.record_temp
|
||||||
|
kwargs: { ana_long_short: true, ann_scaler: 252 }
|
||||||
|
- class: PortAnaRecord
|
||||||
|
module_path: qlib.workflow.record_temp
|
||||||
|
kwargs:
|
||||||
|
config:
|
||||||
|
strategy:
|
||||||
|
class: SignalQualityGateStrategy
|
||||||
|
module_path: tac_qlib.contrib.strategy.signal_quality_gate
|
||||||
|
kwargs:
|
||||||
|
signal: "<PRED>"
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
gate_topk: 10
|
||||||
|
gate_lookback: 5
|
||||||
|
gate_threshold: 0.5
|
||||||
|
gate_start: "2015-01-03"
|
||||||
|
gate_end: "2024-12-31"
|
||||||
|
topk: 10
|
||||||
|
n_drop: 1
|
||||||
|
only_tradable: true
|
||||||
|
risk_degree: 0.95
|
||||||
|
backtest:
|
||||||
|
start_time: 2024-01-02
|
||||||
|
end_time: 2024-12-31
|
||||||
|
account: 1000000
|
||||||
|
benchmark: SPY
|
||||||
|
exchange_kwargs:
|
||||||
|
codes: "{{ UNIVERSE }}"
|
||||||
|
deal_price: $close
|
||||||
|
freq: day
|
||||||
|
open_cost: 0.0005
|
||||||
|
close_cost: 0.0015
|
||||||
|
min_cost: 5.0
|
||||||
|
risk_analysis_freq: 1d
|
||||||
@@ -0,0 +1,115 @@
|
|||||||
|
# Signal-quality gate backtest for 2025
|
||||||
|
{%- set LAKE = TAC_LAKE_DIR %}
|
||||||
|
{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
|
||||||
|
{%- set SP_FIELDS = "sp_ret,sp_ou_zscore,sp_ou_half_life,sp_ou_revert,sp_hmm_p_regime1,sp_hmm_state,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
|
||||||
|
{# Gate computed on-the-fly from signal + lake close prices #}
|
||||||
|
|
||||||
|
qlib_init:
|
||||||
|
provider_uri: "{{ LAKE }}"
|
||||||
|
region: us
|
||||||
|
expression_cache: null
|
||||||
|
dataset_cache: null
|
||||||
|
calendar_provider:
|
||||||
|
class: tac_qlib.data.providers.LakeCalendarProvider
|
||||||
|
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||||
|
instrument_provider:
|
||||||
|
class: tac_qlib.data.providers.LakeInstrumentProvider
|
||||||
|
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
||||||
|
feature_provider:
|
||||||
|
class: tac_qlib.data.providers.LakeFeatureProvider
|
||||||
|
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||||
|
exp_manager:
|
||||||
|
class: MLflowExpManager
|
||||||
|
module_path: qlib.workflow.expm
|
||||||
|
kwargs:
|
||||||
|
uri: "sqlite:///{{ LAKE }}/mlruns.db"
|
||||||
|
default_exp_name: "tac-rd-sq-gate-2025"
|
||||||
|
|
||||||
|
task:
|
||||||
|
model:
|
||||||
|
class: LGBModel
|
||||||
|
module_path: qlib.contrib.model.gbdt
|
||||||
|
kwargs:
|
||||||
|
loss: mse
|
||||||
|
learning_rate: 0.05
|
||||||
|
num_leaves: 15
|
||||||
|
n_estimators: 200
|
||||||
|
colsample_bytree: 0.8
|
||||||
|
subsample: 0.8
|
||||||
|
subsample_freq: 1
|
||||||
|
reg_alpha: 0.01
|
||||||
|
reg_lambda: 0.01
|
||||||
|
|
||||||
|
dataset:
|
||||||
|
class: DatasetH
|
||||||
|
module_path: qlib.data.dataset
|
||||||
|
kwargs:
|
||||||
|
handler:
|
||||||
|
class: TACHandler
|
||||||
|
module_path: tac_qlib.contrib.data.handler
|
||||||
|
kwargs:
|
||||||
|
instruments: "{{ UNIVERSE }}"
|
||||||
|
start_time: 2015-01-03
|
||||||
|
end_time: 2025-12-31
|
||||||
|
fit_start_time: 2015-01-03
|
||||||
|
fit_end_time: 2026-01-03
|
||||||
|
freq: day
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||||
|
feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
|
||||||
|
infer_processors:
|
||||||
|
- class: DropAllNaN
|
||||||
|
kwargs: {}
|
||||||
|
- class: ProcessInf
|
||||||
|
kwargs: {}
|
||||||
|
- class: CSRankNorm
|
||||||
|
kwargs: {}
|
||||||
|
- class: ZScoreNorm
|
||||||
|
kwargs: {}
|
||||||
|
- class: Fillna
|
||||||
|
kwargs: {}
|
||||||
|
segments:
|
||||||
|
train: [2015-01-03, 2025-09-01]
|
||||||
|
valid: [2025-09-03, 2026-01-03]
|
||||||
|
test: [2025-01-02, 2025-12-31]
|
||||||
|
|
||||||
|
record:
|
||||||
|
- class: SignalRecord
|
||||||
|
module_path: qlib.workflow.record_temp
|
||||||
|
kwargs: {}
|
||||||
|
- class: SigAnaRecord
|
||||||
|
module_path: qlib.workflow.record_temp
|
||||||
|
kwargs: { ana_long_short: true, ann_scaler: 252 }
|
||||||
|
- class: PortAnaRecord
|
||||||
|
module_path: qlib.workflow.record_temp
|
||||||
|
kwargs:
|
||||||
|
config:
|
||||||
|
strategy:
|
||||||
|
class: SignalQualityGateStrategy
|
||||||
|
module_path: tac_qlib.contrib.strategy.signal_quality_gate
|
||||||
|
kwargs:
|
||||||
|
signal: "<PRED>"
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
gate_topk: 10
|
||||||
|
gate_lookback: 5
|
||||||
|
gate_threshold: 0.5
|
||||||
|
gate_start: "2015-01-03"
|
||||||
|
gate_end: "2025-12-31"
|
||||||
|
topk: 10
|
||||||
|
n_drop: 1
|
||||||
|
only_tradable: true
|
||||||
|
risk_degree: 0.95
|
||||||
|
backtest:
|
||||||
|
start_time: 2025-01-02
|
||||||
|
end_time: 2025-12-31
|
||||||
|
account: 1000000
|
||||||
|
benchmark: SPY
|
||||||
|
exchange_kwargs:
|
||||||
|
codes: "{{ UNIVERSE }}"
|
||||||
|
deal_price: $close
|
||||||
|
freq: day
|
||||||
|
open_cost: 0.0005
|
||||||
|
close_cost: 0.0015
|
||||||
|
min_cost: 5.0
|
||||||
|
risk_analysis_freq: 1d
|
||||||
@@ -0,0 +1,115 @@
|
|||||||
|
# Signal-quality gate backtest for 2026
|
||||||
|
{%- set LAKE = TAC_LAKE_DIR %}
|
||||||
|
{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
|
||||||
|
{%- set SP_FIELDS = "sp_ret,sp_ou_zscore,sp_ou_half_life,sp_ou_revert,sp_hmm_p_regime1,sp_hmm_state,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
|
||||||
|
{# Gate computed on-the-fly from signal + lake close prices #}
|
||||||
|
|
||||||
|
qlib_init:
|
||||||
|
provider_uri: "{{ LAKE }}"
|
||||||
|
region: us
|
||||||
|
expression_cache: null
|
||||||
|
dataset_cache: null
|
||||||
|
calendar_provider:
|
||||||
|
class: tac_qlib.data.providers.LakeCalendarProvider
|
||||||
|
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||||
|
instrument_provider:
|
||||||
|
class: tac_qlib.data.providers.LakeInstrumentProvider
|
||||||
|
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
||||||
|
feature_provider:
|
||||||
|
class: tac_qlib.data.providers.LakeFeatureProvider
|
||||||
|
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
||||||
|
exp_manager:
|
||||||
|
class: MLflowExpManager
|
||||||
|
module_path: qlib.workflow.expm
|
||||||
|
kwargs:
|
||||||
|
uri: "sqlite:///{{ LAKE }}/mlruns.db"
|
||||||
|
default_exp_name: "tac-rd-sq-gate-2026"
|
||||||
|
|
||||||
|
task:
|
||||||
|
model:
|
||||||
|
class: LGBModel
|
||||||
|
module_path: qlib.contrib.model.gbdt
|
||||||
|
kwargs:
|
||||||
|
loss: mse
|
||||||
|
learning_rate: 0.05
|
||||||
|
num_leaves: 15
|
||||||
|
n_estimators: 200
|
||||||
|
colsample_bytree: 0.8
|
||||||
|
subsample: 0.8
|
||||||
|
subsample_freq: 1
|
||||||
|
reg_alpha: 0.01
|
||||||
|
reg_lambda: 0.01
|
||||||
|
|
||||||
|
dataset:
|
||||||
|
class: DatasetH
|
||||||
|
module_path: qlib.data.dataset
|
||||||
|
kwargs:
|
||||||
|
handler:
|
||||||
|
class: TACHandler
|
||||||
|
module_path: tac_qlib.contrib.data.handler
|
||||||
|
kwargs:
|
||||||
|
instruments: "{{ UNIVERSE }}"
|
||||||
|
start_time: 2015-01-03
|
||||||
|
end_time: 2026-08-10
|
||||||
|
fit_start_time: 2015-01-03
|
||||||
|
fit_end_time: 2026-01-03
|
||||||
|
freq: day
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||||
|
feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
|
||||||
|
infer_processors:
|
||||||
|
- class: DropAllNaN
|
||||||
|
kwargs: {}
|
||||||
|
- class: ProcessInf
|
||||||
|
kwargs: {}
|
||||||
|
- class: CSRankNorm
|
||||||
|
kwargs: {}
|
||||||
|
- class: ZScoreNorm
|
||||||
|
kwargs: {}
|
||||||
|
- class: Fillna
|
||||||
|
kwargs: {}
|
||||||
|
segments:
|
||||||
|
train: [2015-01-03, 2025-09-01]
|
||||||
|
valid: [2025-09-03, 2026-01-03]
|
||||||
|
test: [2026-01-04, 2026-08-10]
|
||||||
|
|
||||||
|
record:
|
||||||
|
- class: SignalRecord
|
||||||
|
module_path: qlib.workflow.record_temp
|
||||||
|
kwargs: {}
|
||||||
|
- class: SigAnaRecord
|
||||||
|
module_path: qlib.workflow.record_temp
|
||||||
|
kwargs: { ana_long_short: true, ann_scaler: 252 }
|
||||||
|
- class: PortAnaRecord
|
||||||
|
module_path: qlib.workflow.record_temp
|
||||||
|
kwargs:
|
||||||
|
config:
|
||||||
|
strategy:
|
||||||
|
class: SignalQualityGateStrategy
|
||||||
|
module_path: tac_qlib.contrib.strategy.signal_quality_gate
|
||||||
|
kwargs:
|
||||||
|
signal: "<PRED>"
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
gate_topk: 10
|
||||||
|
gate_lookback: 5
|
||||||
|
gate_threshold: 0.5
|
||||||
|
gate_start: "2015-01-03"
|
||||||
|
gate_end: "2026-08-19"
|
||||||
|
topk: 10
|
||||||
|
n_drop: 1
|
||||||
|
only_tradable: true
|
||||||
|
risk_degree: 0.95
|
||||||
|
backtest:
|
||||||
|
start_time: 2026-01-04
|
||||||
|
end_time: 2026-08-10
|
||||||
|
account: 1000000
|
||||||
|
benchmark: SPY
|
||||||
|
exchange_kwargs:
|
||||||
|
codes: "{{ UNIVERSE }}"
|
||||||
|
deal_price: $close
|
||||||
|
freq: day
|
||||||
|
open_cost: 0.0005
|
||||||
|
close_cost: 0.0015
|
||||||
|
min_cost: 5.0
|
||||||
|
risk_analysis_freq: 1d
|
||||||
+21
-13
@@ -1,27 +1,35 @@
|
|||||||
# TradeAC custom-qlib-code snapshot (auto-generated)
|
# TradeAC custom-qlib-code snapshot (auto-generated)
|
||||||
# parent repo HEAD : c2edfe6671f17a364a27ecf9619df25f194f43e6
|
# parent repo HEAD : e952feed0a66a20439f4f24ad5524233429cd0c3
|
||||||
# tac-qlib/tac_qlib/contrib
|
# tac-qlib/tac_qlib/contrib
|
||||||
# tac-qlib/tac_qlib/data
|
# tac-qlib/tac_qlib/data
|
||||||
# per-file hashes (git hash-object):
|
# per-file hashes (git hash-object):
|
||||||
1b6298c4a5652f2e863cbdc385a1014a570fcd59 tac-qlib/tac_qlib/contrib/__init__.py
|
1b6298c4a5652f2e863cbdc385a1014a570fcd59 tac-qlib/tac_qlib/contrib/__init__.py
|
||||||
b419ee55ed455a1c45423d1c9025ca5cc0a98576 tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
|
861592c63edd6a0853a9cb174b5970435b135fc8 tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
|
||||||
c76a9f17f680e74eea766eff27f7624359749ed6 tac-qlib/tac_qlib/contrib/data/__init__.py
|
c76a9f17f680e74eea766eff27f7624359749ed6 tac-qlib/tac_qlib/contrib/data/__init__.py
|
||||||
2f6c67620aa2f9e6aaaef3369361d9b3eac3d6ca tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
|
5c547a2ef92e075e550fe6d01508a2f1d3f536bc tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
|
||||||
fdd5923a70a399e8680913593ff111641947898e tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
|
4f656130d167e79dcaaeb7783a121f0b36852374 tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
|
||||||
0dd25ef161c6e0f15eafc84886e7e1381deb38c3 tac-qlib/tac_qlib/contrib/data/handler.py
|
0dd25ef161c6e0f15eafc84886e7e1381deb38c3 tac-qlib/tac_qlib/contrib/data/handler.py
|
||||||
b151d139a0dcde87d74b21e7c4b729176ba5c39b tac-qlib/tac_qlib/contrib/model/__init__.py
|
b151d139a0dcde87d74b21e7c4b729176ba5c39b tac-qlib/tac_qlib/contrib/model/__init__.py
|
||||||
08dec87ccdf6bb5d2cf611ca3032a4280aaab8cf tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
|
b1489f2fc0dee85f0a4f90b2e6ad545ed9c8967b tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
|
||||||
6fb61946ea9a83dfb560de3717f5fbf482c4c00e tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
|
121ef237da1df1b8e21a561c3ad0db200b901339 tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
|
||||||
3e80f2e08b661ddd2f58ffe5a6196063fa41ae51 tac-qlib/tac_qlib/contrib/model/__pycache__/rank_gbdt.cpython-312.pyc
|
74d0da348cbcc3700c96b6f4fe4391488e61efc5 tac-qlib/tac_qlib/contrib/model/__pycache__/rank_gbdt.cpython-312.pyc
|
||||||
d3f051f3a8650c42fedc7b367b966f7c74fb5789 tac-qlib/tac_qlib/contrib/model/rank_ensemble.py
|
d3f051f3a8650c42fedc7b367b966f7c74fb5789 tac-qlib/tac_qlib/contrib/model/rank_ensemble.py
|
||||||
d03e6611338918d4aac5eea4adf26f85a3763652 tac-qlib/tac_qlib/contrib/model/rank_gbdt.py
|
d03e6611338918d4aac5eea4adf26f85a3763652 tac-qlib/tac_qlib/contrib/model/rank_gbdt.py
|
||||||
4afcf9058231111c412925f4c4b84e81d656db87 tac-qlib/tac_qlib/contrib/strategy/__init__.py
|
2c2f167b693f4366a769998e3c9d4804f29e31e0 tac-qlib/tac_qlib/contrib/strategy/__init__.py
|
||||||
6ad10c2ebe37c16417e67c7aeb731ad1fcb6da2f tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
|
f9cd9ab729e3248542ccc490af7adc2e51c71914 tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
|
||||||
8d684b3216b040071d9ee4fa920a0e0c7486d278 tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
|
cd3133cfbd2556b25c106e39ae97fb128df0e326 tac-qlib/tac_qlib/contrib/strategy/__pycache__/ic_gate.cpython-312.pyc
|
||||||
|
6dd1c568a2961842793674390d5abffd1a0e71b8 tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
|
||||||
|
03b5e4d80da00800f1b108bee0735d3d18d856d1 tac-qlib/tac_qlib/contrib/strategy/__pycache__/regime_gate.cpython-312.pyc
|
||||||
|
a6a1c21ab71b62080830df45c4784b73c1531036 tac-qlib/tac_qlib/contrib/strategy/__pycache__/signal_quality_gate.cpython-312.pyc
|
||||||
|
755e3b139496a5e22b0328db45c8199c33029fbc tac-qlib/tac_qlib/contrib/strategy/__pycache__/weekly_rebalance.cpython-312.pyc
|
||||||
|
519a1f4c05dbe0ac018ab8b779eb33d53b4dd545 tac-qlib/tac_qlib/contrib/strategy/ic_gate.py
|
||||||
79aaad9e39fcc740a773f4f63c512ce1086cfde0 tac-qlib/tac_qlib/contrib/strategy/optimal_stop.py
|
79aaad9e39fcc740a773f4f63c512ce1086cfde0 tac-qlib/tac_qlib/contrib/strategy/optimal_stop.py
|
||||||
|
7bcee5f0b09cfa721440f1354f16f2dd9a112b12 tac-qlib/tac_qlib/contrib/strategy/regime_gate.py
|
||||||
|
16ab80b731aab6d8bb818525615d77c2d1fcb0c8 tac-qlib/tac_qlib/contrib/strategy/signal_quality_gate.py
|
||||||
|
fe60bacdfedd48617863be31f24b7c7daebfac5a tac-qlib/tac_qlib/contrib/strategy/weekly_rebalance.py
|
||||||
92e6e90eb0cd0a25142034560f27adb6b705b1a8 tac-qlib/tac_qlib/data/__init__.py
|
92e6e90eb0cd0a25142034560f27adb6b705b1a8 tac-qlib/tac_qlib/data/__init__.py
|
||||||
7c4e6c345fad1978efe8860c0d977d0c02d6f8d9 tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
|
316bf4aa160cc8d15929ea648be03f4b4999667d tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
|
||||||
99e602392d51663cb06d5c425000b1ed1e5a916b tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
|
554a3f29d181b64effbf49a8161b32e7f93d8d3e tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
|
||||||
020dcdcf288e4832c8cf2386351f78d5ceb4fe13 tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc
|
8b47f6d78ac046b6b7b2fb07bd7f3382773ffb73 tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc
|
||||||
53c9007a928841fd3c3b08450f9a6520ce1ac091 tac-qlib/tac_qlib/data/config.py
|
53c9007a928841fd3c3b08450f9a6520ce1ac091 tac-qlib/tac_qlib/data/config.py
|
||||||
8d0644f6f0d1efb94798ed444cc73e63b643459b tac-qlib/tac_qlib/data/providers.py
|
8d0644f6f0d1efb94798ed444cc73e63b643459b tac-qlib/tac_qlib/data/providers.py
|
||||||
|
|||||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -1,3 +1,11 @@
|
|||||||
|
from .ic_gate import ICGateTopkDropoutStrategy # noqa: F401
|
||||||
from .optimal_stop import OptimalStopControl # noqa: F401
|
from .optimal_stop import OptimalStopControl # noqa: F401
|
||||||
|
from .regime_gate import RegimeGateTopkDropoutStrategy # noqa: F401
|
||||||
|
from .weekly_rebalance import WeeklyRebalanceDropoutStrategy # noqa: F401
|
||||||
|
|
||||||
__all__ = ["OptimalStopControl"]
|
__all__ = [
|
||||||
|
"ICGateTopkDropoutStrategy",
|
||||||
|
"OptimalStopControl",
|
||||||
|
"RegimeGateTopkDropoutStrategy",
|
||||||
|
"WeeklyRebalanceDropoutStrategy",
|
||||||
|
]
|
||||||
|
|||||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
BIN
Binary file not shown.
Binary file not shown.
@@ -0,0 +1,117 @@
|
|||||||
|
"""Realized-IC circuit breaker TopkDropout strategy.
|
||||||
|
|
||||||
|
Subclass of ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy`` that
|
||||||
|
holds the book (issues NO orders) while the streaming realized RankIC of the
|
||||||
|
deployed signal is below threshold — i.e. the model's cross-sectional
|
||||||
|
predictions are no longer earning against realized forward returns. When the
|
||||||
|
gate is open it behaves exactly like the reference TopkDropoutStrategy.
|
||||||
|
|
||||||
|
The gate is evaluated per trade step on the trailing mean realized RankIC of
|
||||||
|
the signal over the last ``ic_window`` trading days whose label is fully
|
||||||
|
realized as of the decision date (no lookahead — a 5d fwd label ``close[t+6]/
|
||||||
|
close[t+1]-1`` is only known at ``t+6``).
|
||||||
|
|
||||||
|
Two wiring modes:
|
||||||
|
|
||||||
|
* ``ic_gate``: a precomputed ``pd.Series`` indexed by datetime of booleans
|
||||||
|
(True = gate open / trade allowed). Computed once by the caller (e.g.
|
||||||
|
``rd_backtest``) and looked up per step. Missing dates default to open.
|
||||||
|
* realized-IC self-computation: when ``ic_min_rankic`` is given but no
|
||||||
|
``ic_gate``, the strategy computes the per-date realized RankIC itself from
|
||||||
|
``self.signal`` (the pred scores) and the lake 1d bars via
|
||||||
|
``tac_qlib.risk_limits.realized_rankic_series``, then applies the same
|
||||||
|
trailing-window comparison. Works when instantiated from a workflow YAML
|
||||||
|
PortAnaRecord config (``lake_root`` / ``market`` must be provided).
|
||||||
|
"""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import pandas as pd
|
||||||
|
|
||||||
|
from qlib.backtest.decision import TradeDecisionWO
|
||||||
|
from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
|
||||||
|
|
||||||
|
from tac_qlib.risk_limits import ic_circuit_breaker, realized_rankic_series
|
||||||
|
|
||||||
|
__all__ = ["ICGateTopkDropoutStrategy"]
|
||||||
|
|
||||||
|
|
||||||
|
class ICGateTopkDropoutStrategy(TopkDropoutStrategy):
|
||||||
|
"""TopkDropout with a streaming realized-IC circuit breaker.
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
|
||||||
|
forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
|
||||||
|
ic_min_rankic : float — pause new trading while trailing realized RankIC is
|
||||||
|
below this threshold (0 disables the gate).
|
||||||
|
ic_window : int — trailing window for the realized RankIC mean (default 22).
|
||||||
|
ic_label_horizon : int — label horizon in trading days (default 6).
|
||||||
|
ic_min_obs : int — min realized labels before the gate arms (default 10).
|
||||||
|
ic_gate : pd.Series, optional — precomputed per-date gate (bool indexed by
|
||||||
|
datetime). When provided, it overrides self-computation.
|
||||||
|
lake_root, market : str — lake location for self-computed realized IC.
|
||||||
|
"""
|
||||||
|
|
||||||
|
def __init__(
|
||||||
|
self,
|
||||||
|
*,
|
||||||
|
topk,
|
||||||
|
n_drop,
|
||||||
|
ic_min_rankic: float = 0.0,
|
||||||
|
ic_window: int = 22,
|
||||||
|
ic_label_horizon: int = 6,
|
||||||
|
ic_min_obs: int = 10,
|
||||||
|
ic_gate=None,
|
||||||
|
lake_root: str = "",
|
||||||
|
market: str = "US",
|
||||||
|
**kwargs,
|
||||||
|
):
|
||||||
|
super().__init__(topk=topk, n_drop=n_drop, **kwargs)
|
||||||
|
self.ic_min_rankic = float(ic_min_rankic or 0.0)
|
||||||
|
self.ic_window = int(ic_window or 22)
|
||||||
|
self.ic_label_horizon = int(ic_label_horizon or 6)
|
||||||
|
self.ic_min_obs = int(ic_min_obs or 10)
|
||||||
|
self._ic_gate = ic_gate
|
||||||
|
self._realized_ic = None
|
||||||
|
self.lake_root = lake_root or ""
|
||||||
|
self.market = market or "US"
|
||||||
|
|
||||||
|
def _load_realized_ic(self):
|
||||||
|
if self._realized_ic is None:
|
||||||
|
pred_start_time, pred_end_time = self.trade_calendar.get_step_time(
|
||||||
|
self.trade_calendar.get_trade_step(), shift=-self.ic_label_horizon
|
||||||
|
)
|
||||||
|
pred = self.signal.get_signal(start_time=pred_start_time, end_time=pred_end_time)
|
||||||
|
if isinstance(pred, pd.DataFrame):
|
||||||
|
pred = pred.iloc[:, 0]
|
||||||
|
self._realized_ic = realized_rankic_series(
|
||||||
|
pred, self.lake_root, self.market, label_horizon=self.ic_label_horizon
|
||||||
|
)
|
||||||
|
return self._realized_ic
|
||||||
|
|
||||||
|
def _gate_open(self, trade_start_time) -> bool:
|
||||||
|
ts = pd.Timestamp(trade_start_time)
|
||||||
|
if self._ic_gate is not None:
|
||||||
|
# precomputed gate series: look up the latest known decision date <= ts
|
||||||
|
known = self._ic_gate[self._ic_gate.index <= ts]
|
||||||
|
if len(known):
|
||||||
|
return bool(known.iloc[-1])
|
||||||
|
return True
|
||||||
|
if self.ic_min_rankic <= 0:
|
||||||
|
return True
|
||||||
|
realized = self._load_realized_ic()
|
||||||
|
limits = {
|
||||||
|
"ic_min_rankic": self.ic_min_rankic,
|
||||||
|
"ic_window": self.ic_window,
|
||||||
|
"ic_min_obs": self.ic_min_obs,
|
||||||
|
}
|
||||||
|
tripped, _reason, _trail = ic_circuit_breaker(realized, ts, limits)
|
||||||
|
return not tripped
|
||||||
|
|
||||||
|
def generate_trade_decision(self, execute_result=None):
|
||||||
|
trade_step = self.trade_calendar.get_trade_step()
|
||||||
|
trade_start_time, _ = self.trade_calendar.get_step_time(trade_step)
|
||||||
|
if not self._gate_open(trade_start_time):
|
||||||
|
return TradeDecisionWO([], self)
|
||||||
|
return super().generate_trade_decision(execute_result)
|
||||||
@@ -0,0 +1,215 @@
|
|||||||
|
"""Regime-gate TopkDropout strategy.
|
||||||
|
|
||||||
|
Subclass of ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy`` that
|
||||||
|
holds the book (issues NO orders) while a regime detector says the market is in
|
||||||
|
an unfavorable state. When the gate is open it behaves exactly like the
|
||||||
|
reference TopkDropoutStrategy.
|
||||||
|
|
||||||
|
Three detector types are supported (all causal — no lookahead):
|
||||||
|
|
||||||
|
* ``dispersion``: cross-sectional standard deviation of 22-day rolling returns
|
||||||
|
across the universe. Gate closes when CS dispersion < threshold (low
|
||||||
|
dispersion means the spread between winners and losers is too narrow for
|
||||||
|
TopkDropout to exploit).
|
||||||
|
* ``vol``: cross-sectional mean of 22-day rolling realized volatility. Gate
|
||||||
|
closes when avg vol is outside a band ``[vol_low, vol_high]`` (strategy
|
||||||
|
needs moderate vol — too calm or too turbulent both hurt).
|
||||||
|
* ``hmm``: pre-computed HMM posterior for regime 1 (``sp_hmm_p_regime1``).
|
||||||
|
Gate closes when posterior < threshold (model is not confident the calm
|
||||||
|
regime is active).
|
||||||
|
|
||||||
|
The gate is provided as a precomputed ``pd.Series`` of booleans indexed by
|
||||||
|
datetime (True = trade allowed). The companion ``compute_regime_gate``
|
||||||
|
function builds this series from lake bars; call it once before backtesting
|
||||||
|
and pass the result as the ``regime_gate`` parameter.
|
||||||
|
"""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import pandas as pd
|
||||||
|
|
||||||
|
from qlib.backtest.decision import TradeDecisionWO
|
||||||
|
from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
|
||||||
|
|
||||||
|
__all__ = ["RegimeGateTopkDropoutStrategy", "compute_regime_gate"]
|
||||||
|
|
||||||
|
|
||||||
|
class RegimeGateTopkDropoutStrategy(TopkDropoutStrategy):
|
||||||
|
"""TopkDropout with a regime-gate circuit breaker.
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
|
||||||
|
forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
|
||||||
|
regime_gate : pd.Series — precomputed per-date gate (bool indexed by
|
||||||
|
datetime). True = trade allowed, False = no orders. Missing dates
|
||||||
|
default to open (trade allowed).
|
||||||
|
"""
|
||||||
|
|
||||||
|
def __init__(self, *, regime_gate=None, **kwargs):
|
||||||
|
super().__init__(**kwargs)
|
||||||
|
self._regime_gate = regime_gate
|
||||||
|
|
||||||
|
def _gate_open(self, trade_start_time) -> bool:
|
||||||
|
if self._regime_gate is None:
|
||||||
|
return True
|
||||||
|
ts = pd.Timestamp(trade_start_time)
|
||||||
|
known = self._regime_gate[self._regime_gate.index <= ts]
|
||||||
|
if len(known):
|
||||||
|
return bool(known.iloc[-1])
|
||||||
|
return True # default open if no history yet
|
||||||
|
|
||||||
|
def generate_trade_decision(self, execute_result=None):
|
||||||
|
trade_step = self.trade_calendar.get_trade_step()
|
||||||
|
trade_start_time, _ = self.trade_calendar.get_step_time(trade_step)
|
||||||
|
if not self._gate_open(trade_start_time):
|
||||||
|
return TradeDecisionWO([], self)
|
||||||
|
return super().generate_trade_decision(execute_result)
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Precomputation helper
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
|
||||||
|
def compute_regime_gate(
|
||||||
|
detector: str,
|
||||||
|
threshold: float = 0.0,
|
||||||
|
*,
|
||||||
|
lake_root: str = "",
|
||||||
|
market: str = "US",
|
||||||
|
start: str = "2015-01-03",
|
||||||
|
end: str = "2026-08-19",
|
||||||
|
vol_low: float = 0.0,
|
||||||
|
vol_high: float = 999.0,
|
||||||
|
hmm_field: str = "sp_hmm_p_regime1",
|
||||||
|
) -> pd.Series:
|
||||||
|
"""Build a per-date regime gate series from lake bars.
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
detector : str — ``"dispersion"``, ``"vol"``, or ``"hmm"``.
|
||||||
|
threshold : float — for ``dispersion``: min CS dispersion to allow trading.
|
||||||
|
For ``hmm``: min HMM posterior to allow trading.
|
||||||
|
Ignored for ``vol`` (uses ``vol_low``/``vol_high`` band instead).
|
||||||
|
lake_root, market : str — lake location.
|
||||||
|
start, end : str — date window.
|
||||||
|
vol_low, vol_high : float — annualized vol band for the ``vol`` detector.
|
||||||
|
hmm_field : str — HMM feature column name for the ``hmm`` detector.
|
||||||
|
|
||||||
|
Returns
|
||||||
|
-------
|
||||||
|
pd.Series — bool, indexed by datetime. True = trade allowed.
|
||||||
|
"""
|
||||||
|
from tac_qlib.data.config import LakeConfig, resolve_lake_root
|
||||||
|
|
||||||
|
cfg = LakeConfig(resolve_lake_root(lake_root or None), market)
|
||||||
|
symbols = _universe_symbols(cfg)
|
||||||
|
close_df, vol_df = _load_daily_bars(symbols, cfg, start, end)
|
||||||
|
if close_df.empty:
|
||||||
|
return pd.Series(dtype=bool)
|
||||||
|
|
||||||
|
if detector == "dispersion":
|
||||||
|
return _dispersion_gate(close_df, threshold)
|
||||||
|
elif detector == "vol":
|
||||||
|
return _vol_gate(close_df, vol_low, vol_high)
|
||||||
|
elif detector == "hmm":
|
||||||
|
return _hmm_gate(cfg, symbols, threshold, start, end, hmm_field)
|
||||||
|
else:
|
||||||
|
raise ValueError(f"Unknown detector: {detector!r}")
|
||||||
|
|
||||||
|
|
||||||
|
def _universe_symbols(cfg) -> list:
|
||||||
|
"""Read symbols from the lake symbols.parquet."""
|
||||||
|
import pathlib
|
||||||
|
|
||||||
|
sp = cfg.lake_root / "symbols.parquet"
|
||||||
|
if sp.exists():
|
||||||
|
df = pd.read_parquet(sp)
|
||||||
|
col = "symbol" if "symbol" in df.columns else df.columns[0]
|
||||||
|
return sorted(df[col].astype(str).str.upper().tolist())
|
||||||
|
return []
|
||||||
|
|
||||||
|
|
||||||
|
def _load_daily_bars(symbols, cfg, start, end):
|
||||||
|
"""Load daily close prices for all symbols into a wide DataFrame."""
|
||||||
|
closes = {}
|
||||||
|
vols = {}
|
||||||
|
for sym in symbols:
|
||||||
|
p = cfg.bar_path("1d", sym)
|
||||||
|
if not p.exists():
|
||||||
|
continue
|
||||||
|
try:
|
||||||
|
df = pd.read_parquet(p)
|
||||||
|
except Exception:
|
||||||
|
continue
|
||||||
|
if not len(df):
|
||||||
|
continue
|
||||||
|
tcol = df["t"] if "t" in df.columns else df["date"]
|
||||||
|
ts = pd.to_datetime(tcol)
|
||||||
|
df = df.assign(_t=ts).set_index("_t").sort_index()
|
||||||
|
df = df.loc[start:end]
|
||||||
|
if len(df) < 22:
|
||||||
|
continue
|
||||||
|
closes[sym] = df["c"]
|
||||||
|
if "v" in df.columns:
|
||||||
|
vols[sym] = df["v"]
|
||||||
|
close_df = pd.DataFrame(closes)
|
||||||
|
vol_df = pd.DataFrame(vols) if vols else None
|
||||||
|
return close_df, vol_df
|
||||||
|
|
||||||
|
|
||||||
|
def _dispersion_gate(close_df, threshold):
|
||||||
|
"""Cross-sectional dispersion of 22-day rolling returns."""
|
||||||
|
if close_df.empty or close_df.shape[1] < 2:
|
||||||
|
return pd.Series(dtype=bool)
|
||||||
|
ret = close_df.pct_change(22)
|
||||||
|
cs_disp = ret.std(axis=1)
|
||||||
|
gate = cs_disp >= threshold
|
||||||
|
gate.iloc[:22] = True # warmup: allow trading
|
||||||
|
return gate
|
||||||
|
|
||||||
|
|
||||||
|
def _vol_gate(close_df, vol_low, vol_high):
|
||||||
|
"""Cross-sectional mean of 22-day rolling realized vol."""
|
||||||
|
if close_df.empty or close_df.shape[1] < 2:
|
||||||
|
return pd.Series(dtype=bool)
|
||||||
|
import numpy as np
|
||||||
|
log_ret = np.log(close_df / close_df.shift(1))
|
||||||
|
rv22 = log_ret.rolling(22).std() * (252 ** 0.5)
|
||||||
|
cs_mean_vol = rv22.mean(axis=1)
|
||||||
|
gate = (cs_mean_vol >= vol_low) & (cs_mean_vol <= vol_high)
|
||||||
|
gate.iloc[:22] = True # warmup
|
||||||
|
return gate
|
||||||
|
|
||||||
|
|
||||||
|
def _hmm_gate(cfg, symbols, threshold, start, end, hmm_field):
|
||||||
|
"""HMM regime posterior gate from persisted SP features."""
|
||||||
|
feat_root = cfg.lake_root / "features"
|
||||||
|
all_posteriors = {}
|
||||||
|
for sym in symbols:
|
||||||
|
# check both ta and sp family paths
|
||||||
|
for family in ("sp", "ta"):
|
||||||
|
p = feat_root / f"market=US" / f"timeframe=1d" / f"family={family}" / f"symbol={sym}.parquet"
|
||||||
|
if not p.exists():
|
||||||
|
continue
|
||||||
|
try:
|
||||||
|
df = pd.read_parquet(p)
|
||||||
|
except Exception:
|
||||||
|
continue
|
||||||
|
if hmm_field not in df.columns:
|
||||||
|
continue
|
||||||
|
tcol = df["t"] if "t" in df.columns else df["date"]
|
||||||
|
ts = pd.to_datetime(tcol)
|
||||||
|
s = pd.Series(df[hmm_field].values, index=ts, name=sym)
|
||||||
|
s = s.loc[start:end].dropna()
|
||||||
|
if len(s) > 0:
|
||||||
|
all_posteriors[sym] = s
|
||||||
|
break
|
||||||
|
if not all_posteriors:
|
||||||
|
# no HMM features found — default open
|
||||||
|
idx = pd.date_range(start, end, freq="B")
|
||||||
|
return pd.Series(True, index=idx)
|
||||||
|
post_df = pd.DataFrame(all_posteriors)
|
||||||
|
cs_mean = post_df.mean(axis=1)
|
||||||
|
gate = cs_mean >= threshold
|
||||||
|
return gate
|
||||||
@@ -0,0 +1,301 @@
|
|||||||
|
"""Signal-quality gate TopkDropout strategy.
|
||||||
|
|
||||||
|
Subclass of ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy`` that
|
||||||
|
holds the book (issues NO orders) when the model's recent prediction accuracy
|
||||||
|
is below a threshold. When the gate is open it behaves exactly like the
|
||||||
|
reference TopkDropoutStrategy.
|
||||||
|
|
||||||
|
Unlike the regime gate (which asks "is the market calm?"), the signal-quality
|
||||||
|
gate asks "are my predictions accurate?" — and works across ALL years.
|
||||||
|
|
||||||
|
The gate is provided as a precomputed ``pd.Series`` of booleans indexed by
|
||||||
|
datetime (True = trade allowed). The companion ``compute_signal_quality_gate``
|
||||||
|
function builds this series from a pred.pkl and lake bars; call it once before
|
||||||
|
backtesting and pass the result as the ``signal_quality_gate`` parameter.
|
||||||
|
"""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import numpy as np
|
||||||
|
import pandas as pd
|
||||||
|
|
||||||
|
from qlib.backtest.decision import TradeDecisionWO
|
||||||
|
from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
|
||||||
|
|
||||||
|
__all__ = ["SignalQualityGateStrategy", "compute_signal_quality_gate"]
|
||||||
|
|
||||||
|
|
||||||
|
class SignalQualityGateStrategy(TopkDropoutStrategy):
|
||||||
|
"""TopkDropout with signal-quality gate overlay.
|
||||||
|
|
||||||
|
When ``lake_root`` is provided the gate is computed on-the-fly from the
|
||||||
|
signal (``<PRED>``) and close prices — no precomputed gate file needed.
|
||||||
|
This ensures the gate matches the model that is actually generating the
|
||||||
|
predictions (critical when the model is retrained each year).
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
|
||||||
|
forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
|
||||||
|
signal_quality_gate : pd.Series — precomputed per-date gate (bool).
|
||||||
|
signal_quality_gate_path : str — path to pickled gate Series.
|
||||||
|
lake_root : str — lake root for on-the-fly gate computation (preferred).
|
||||||
|
gate_topk, gate_lookback, gate_threshold : int/float — gate params.
|
||||||
|
gate_start, gate_end : str — date window for loading close prices.
|
||||||
|
"""
|
||||||
|
|
||||||
|
def __init__(self, *, signal_quality_gate=None, signal_quality_gate_path=None,
|
||||||
|
lake_root=None, gate_topk=10, gate_lookback=5, gate_threshold=0.5,
|
||||||
|
gate_start="2015-01-03", gate_end="2026-08-19", **kwargs):
|
||||||
|
super().__init__(**kwargs)
|
||||||
|
self._sq_gate_computed = False
|
||||||
|
if signal_quality_gate is not None:
|
||||||
|
self._sq_gate = signal_quality_gate
|
||||||
|
self._sq_gate_computed = True
|
||||||
|
elif signal_quality_gate_path is not None:
|
||||||
|
import pickle
|
||||||
|
with open(signal_quality_gate_path, "rb") as f:
|
||||||
|
self._sq_gate = pickle.load(f)
|
||||||
|
self._sq_gate_computed = True
|
||||||
|
elif lake_root is not None:
|
||||||
|
self._sq_gate = None
|
||||||
|
self._lake_root = lake_root
|
||||||
|
self._gate_topk = gate_topk
|
||||||
|
self._gate_lookback = gate_lookback
|
||||||
|
self._gate_threshold = gate_threshold
|
||||||
|
self._gate_start = gate_start
|
||||||
|
self._gate_end = gate_end
|
||||||
|
else:
|
||||||
|
self._sq_gate = None
|
||||||
|
|
||||||
|
def _compute_gate_on_fly(self):
|
||||||
|
"""Compute gate from the signal (pred.pkl) and lake close prices."""
|
||||||
|
import pickle
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
signal_path = self._signal
|
||||||
|
if not Path(signal_path).exists():
|
||||||
|
return
|
||||||
|
|
||||||
|
with open(signal_path, "rb") as f:
|
||||||
|
pred = pickle.load(f)
|
||||||
|
|
||||||
|
# Handle MultiIndex DataFrame -> unstack to wide
|
||||||
|
if isinstance(pred, pd.DataFrame) and isinstance(pred.index, pd.MultiIndex):
|
||||||
|
pred = pred.iloc[:, 0]
|
||||||
|
pred.index = pd.MultiIndex.from_arrays([
|
||||||
|
pd.to_datetime(pred.index.get_level_values(0)).normalize(),
|
||||||
|
pred.index.get_level_values(1)
|
||||||
|
])
|
||||||
|
pred = pred.unstack(level=1)
|
||||||
|
elif isinstance(pred, pd.DataFrame):
|
||||||
|
pred = pred.iloc[:, 0] if pred.shape[1] >= 1 else pred.squeeze()
|
||||||
|
pred.index = pd.to_datetime(pred.index).normalize()
|
||||||
|
|
||||||
|
# Load close prices from lake
|
||||||
|
close_df = _load_close_prices(self._lake_root, "US", self._gate_start, self._gate_end)
|
||||||
|
if close_df.empty:
|
||||||
|
return
|
||||||
|
|
||||||
|
ret_df = close_df.pct_change()
|
||||||
|
ret_df.index = pd.to_datetime(ret_df.index).normalize()
|
||||||
|
|
||||||
|
pred_dates = sorted(pred.index.unique())
|
||||||
|
if len(pred_dates) < 2:
|
||||||
|
self._sq_gate = pd.Series(True, index=pd.DatetimeIndex(pred_dates))
|
||||||
|
self._sq_gate_computed = True
|
||||||
|
return
|
||||||
|
|
||||||
|
hit_rates = {}
|
||||||
|
for i in range(1, len(pred_dates)):
|
||||||
|
day = pred_dates[i]
|
||||||
|
prev_day = pred_dates[i - 1]
|
||||||
|
try:
|
||||||
|
prev_scores = pred.loc[prev_day]
|
||||||
|
except KeyError:
|
||||||
|
continue
|
||||||
|
if isinstance(prev_scores, pd.DataFrame):
|
||||||
|
prev_scores = prev_scores.iloc[:, 0]
|
||||||
|
prev_scores = prev_scores.dropna().sort_values(ascending=False)
|
||||||
|
topk_syms = list(prev_scores.index[:self._gate_topk])
|
||||||
|
|
||||||
|
if day not in ret_df.index:
|
||||||
|
continue
|
||||||
|
today_ret = ret_df.loc[day]
|
||||||
|
topk_rets = today_ret.reindex(topk_syms).dropna()
|
||||||
|
if len(topk_rets) == 0:
|
||||||
|
continue
|
||||||
|
|
||||||
|
hit_rates[day] = (topk_rets > 0).sum() / len(topk_rets)
|
||||||
|
|
||||||
|
if not hit_rates:
|
||||||
|
self._sq_gate_computed = True
|
||||||
|
return
|
||||||
|
|
||||||
|
hr_series = pd.Series(hit_rates).sort_index()
|
||||||
|
rolling_hr = hr_series.rolling(self._gate_lookback, min_periods=1).mean()
|
||||||
|
gate = rolling_hr >= self._gate_threshold
|
||||||
|
gate.iloc[:self._gate_lookback] = True
|
||||||
|
|
||||||
|
self._sq_gate = gate
|
||||||
|
self._sq_gate_computed = True
|
||||||
|
|
||||||
|
def _gate_open(self, trade_start_time) -> bool:
|
||||||
|
if self._sq_gate is None:
|
||||||
|
return True
|
||||||
|
ts = pd.Timestamp(trade_start_time)
|
||||||
|
known = self._sq_gate[self._sq_gate.index <= ts]
|
||||||
|
if len(known):
|
||||||
|
return bool(known.iloc[-1])
|
||||||
|
return True # default open if no history yet
|
||||||
|
|
||||||
|
def generate_trade_decision(self, execute_result=None):
|
||||||
|
if not self._sq_gate_computed:
|
||||||
|
self._compute_gate_on_fly()
|
||||||
|
trade_step = self.trade_calendar.get_trade_step()
|
||||||
|
trade_start_time, _ = self.trade_calendar.get_step_time(trade_step)
|
||||||
|
if not self._gate_open(trade_start_time):
|
||||||
|
return TradeDecisionWO([], self)
|
||||||
|
return super().generate_trade_decision(execute_result)
|
||||||
|
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Precomputation helper
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
|
||||||
|
def compute_signal_quality_gate(
|
||||||
|
pred_path: str,
|
||||||
|
*,
|
||||||
|
lake_root: str = "",
|
||||||
|
market: str = "US",
|
||||||
|
topk: int = 10,
|
||||||
|
lookback: int = 5,
|
||||||
|
threshold: float = 0.5,
|
||||||
|
start: str = "2015-01-03",
|
||||||
|
end: str = "2026-08-19",
|
||||||
|
) -> pd.Series:
|
||||||
|
"""Build a per-date signal-quality gate series from a pred.pkl and lake bars.
|
||||||
|
|
||||||
|
For each day, checks whether the model's topk picks from the previous day
|
||||||
|
had positive returns. Computes a rolling hit rate over ``lookback`` days
|
||||||
|
and opens the gate when hit rate >= ``threshold``.
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
pred_path : str — path to pred.pkl (from rd_train / rd_predict).
|
||||||
|
lake_root, market : str — lake location (for loading close prices).
|
||||||
|
topk : int — number of top picks to track for hit rate.
|
||||||
|
lookback : int — rolling window for hit rate computation.
|
||||||
|
threshold : float — hit rate threshold to keep trading.
|
||||||
|
start, end : str — date window for loading prices.
|
||||||
|
|
||||||
|
Returns
|
||||||
|
-------
|
||||||
|
pd.Series — bool, indexed by datetime. True = trade allowed.
|
||||||
|
"""
|
||||||
|
from pathlib import Path
|
||||||
|
import pickle
|
||||||
|
|
||||||
|
# Load pred.pkl
|
||||||
|
with open(pred_path, "rb") as f:
|
||||||
|
pred = pickle.load(f)
|
||||||
|
|
||||||
|
# Handle MultiIndex DataFrame (datetime, instrument) -> unstack to wide
|
||||||
|
if isinstance(pred, pd.DataFrame) and isinstance(pred.index, pd.MultiIndex):
|
||||||
|
pred = pred.iloc[:, 0] # take score column as Series
|
||||||
|
pred.index = pd.MultiIndex.from_arrays([
|
||||||
|
pd.to_datetime(pred.index.get_level_values(0)).normalize(),
|
||||||
|
pred.index.get_level_values(1)
|
||||||
|
])
|
||||||
|
# Unstack to wide: dates x instruments
|
||||||
|
pred = pred.unstack(level=1)
|
||||||
|
elif isinstance(pred, pd.DataFrame):
|
||||||
|
pred = pred.iloc[:, 0] if pred.shape[1] >= 1 else pred.squeeze()
|
||||||
|
pred.index = pd.to_datetime(pred.index).normalize()
|
||||||
|
|
||||||
|
# Load close prices from lake
|
||||||
|
close_df = _load_close_prices(lake_root, market, start, end)
|
||||||
|
if close_df.empty:
|
||||||
|
return pd.Series(dtype=bool)
|
||||||
|
|
||||||
|
ret_df = close_df.pct_change()
|
||||||
|
ret_df.index = pd.to_datetime(ret_df.index).normalize()
|
||||||
|
|
||||||
|
# Get sorted unique prediction dates
|
||||||
|
pred_dates = sorted(pred.index.unique())
|
||||||
|
if len(pred_dates) < 2:
|
||||||
|
return pd.Series(True, index=pd.DatetimeIndex(pred_dates))
|
||||||
|
|
||||||
|
# Compute hit rates
|
||||||
|
hit_rates = {}
|
||||||
|
for i in range(1, len(pred_dates)):
|
||||||
|
day = pred_dates[i]
|
||||||
|
# Get yesterday's topk
|
||||||
|
prev_day = pred_dates[i - 1]
|
||||||
|
try:
|
||||||
|
prev_scores = pred.loc[prev_day]
|
||||||
|
except KeyError:
|
||||||
|
continue
|
||||||
|
if isinstance(prev_scores, pd.DataFrame):
|
||||||
|
prev_scores = prev_scores.iloc[:, 0]
|
||||||
|
prev_scores = prev_scores.dropna().sort_values(ascending=False)
|
||||||
|
topk_syms = list(prev_scores.index[:topk])
|
||||||
|
|
||||||
|
# Get today's returns
|
||||||
|
if day not in ret_df.index:
|
||||||
|
continue
|
||||||
|
today_ret = ret_df.loc[day]
|
||||||
|
topk_rets = today_ret.reindex(topk_syms).dropna()
|
||||||
|
if len(topk_rets) == 0:
|
||||||
|
continue
|
||||||
|
|
||||||
|
hit_rates[day] = (topk_rets > 0).sum() / len(topk_rets)
|
||||||
|
|
||||||
|
if not hit_rates:
|
||||||
|
return pd.Series(dtype=bool)
|
||||||
|
|
||||||
|
hr_series = pd.Series(hit_rates).sort_index()
|
||||||
|
|
||||||
|
# Rolling hit rate
|
||||||
|
rolling_hr = hr_series.rolling(lookback, min_periods=1).mean()
|
||||||
|
|
||||||
|
# Gate is open when rolling hit rate >= threshold
|
||||||
|
gate = rolling_hr >= threshold
|
||||||
|
gate.iloc[:lookback] = True # warmup: allow trading
|
||||||
|
|
||||||
|
return gate
|
||||||
|
|
||||||
|
|
||||||
|
def _load_close_prices(lake_root, market, start, end):
|
||||||
|
"""Load daily close prices for all symbols into a wide DataFrame."""
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
lake = Path(lake_root)
|
||||||
|
symbols_parquet = lake / "symbols.parquet"
|
||||||
|
if not symbols_parquet.exists():
|
||||||
|
return pd.DataFrame()
|
||||||
|
|
||||||
|
df = pd.read_parquet(symbols_parquet)
|
||||||
|
col = "symbol" if "symbol" in df.columns else df.columns[0]
|
||||||
|
symbols = sorted(df[col].astype(str).str.upper().tolist())
|
||||||
|
|
||||||
|
closes = {}
|
||||||
|
for sym in symbols:
|
||||||
|
p = lake / "market=US" / "timeframe=1d" / f"symbol={sym}.parquet"
|
||||||
|
if not p.exists():
|
||||||
|
continue
|
||||||
|
try:
|
||||||
|
bar = pd.read_parquet(p)
|
||||||
|
except Exception:
|
||||||
|
continue
|
||||||
|
if not len(bar):
|
||||||
|
continue
|
||||||
|
tcol = "t" if "t" in bar.columns else "date"
|
||||||
|
ts = pd.to_datetime(bar[tcol])
|
||||||
|
bar = bar.assign(_t=ts).set_index("_t").sort_index()
|
||||||
|
bar = bar.loc[start:end]
|
||||||
|
if len(bar) < 10:
|
||||||
|
continue
|
||||||
|
closes[sym] = bar["c"] if "c" in bar.columns else bar["close"]
|
||||||
|
|
||||||
|
return pd.DataFrame(closes)
|
||||||
@@ -0,0 +1,202 @@
|
|||||||
|
"""Weekly-rebalance TopkDropout strategy.
|
||||||
|
|
||||||
|
Turnover-reduction variant of ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy``:
|
||||||
|
the topk/n_drop selection and sizing are identical to the reference, but the
|
||||||
|
target book is recomputed only on the first trading day of each ISO week; on the
|
||||||
|
other days the strategy issues NO orders (holds the book untouched).
|
||||||
|
|
||||||
|
The weekly cadence is derived from the qlib trade calendar: a rebalance happens
|
||||||
|
when the current trade step's date belongs to a different ISO ``(year, week)``
|
||||||
|
than the previous trade step. ``hold_band_pct`` (default 0) optionally skips
|
||||||
|
tiny rebalances: when a name's existing position differs from the new target by
|
||||||
|
less than this fraction, no order is generated for it.
|
||||||
|
"""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
from typing import List
|
||||||
|
|
||||||
|
import numpy as np
|
||||||
|
import pandas as pd
|
||||||
|
|
||||||
|
from qlib.backtest import Order
|
||||||
|
from qlib.backtest.decision import OrderDir, TradeDecisionWO
|
||||||
|
from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
|
||||||
|
|
||||||
|
__all__ = ["WeeklyRebalanceDropoutStrategy"]
|
||||||
|
|
||||||
|
DEFAULT_HOLD_BAND_PCT = 0.0
|
||||||
|
|
||||||
|
|
||||||
|
class WeeklyRebalanceDropoutStrategy(TopkDropoutStrategy):
|
||||||
|
"""TopkDropout rebalanced once per ISO week; holds otherwise.
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
|
||||||
|
forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
|
||||||
|
hold_band_pct : skip order for a name whose deviation from target weight is
|
||||||
|
below this fraction of the target (no-trade buffer band).
|
||||||
|
"""
|
||||||
|
|
||||||
|
def __init__(self, *, topk, n_drop, hold_band_pct: float = DEFAULT_HOLD_BAND_PCT, **kwargs):
|
||||||
|
super().__init__(topk=topk, n_drop=n_drop, **kwargs)
|
||||||
|
self.hold_band_pct = hold_band_pct
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
def _iso_week(ts) -> tuple:
|
||||||
|
return (ts.year, ts.week)
|
||||||
|
|
||||||
|
def generate_trade_decision(self, execute_result=None):
|
||||||
|
import copy
|
||||||
|
|
||||||
|
trade_step = self.trade_calendar.get_trade_step()
|
||||||
|
trade_start_time, trade_end_time = self.trade_calendar.get_step_time(trade_step)
|
||||||
|
|
||||||
|
cur_week = self._iso_week(trade_start_time)
|
||||||
|
prev_week = getattr(self, "_last_week", None)
|
||||||
|
self._last_week = cur_week
|
||||||
|
|
||||||
|
if prev_week is not None and prev_week == cur_week:
|
||||||
|
# not the first trading day of this ISO week -> hold
|
||||||
|
return TradeDecisionWO([], self)
|
||||||
|
|
||||||
|
pred_start_time, pred_end_time = self.trade_calendar.get_step_time(trade_step, shift=1)
|
||||||
|
pred_score = self.signal.get_signal(start_time=pred_start_time, end_time=pred_end_time)
|
||||||
|
if isinstance(pred_score, pd.DataFrame):
|
||||||
|
pred_score = pred_score.iloc[:, 0]
|
||||||
|
if pred_score is None:
|
||||||
|
return TradeDecisionWO([], self)
|
||||||
|
|
||||||
|
if self.only_tradable:
|
||||||
|
|
||||||
|
def get_first_n(li, n, reverse=False):
|
||||||
|
cur_n = 0
|
||||||
|
res = []
|
||||||
|
for si in reversed(li) if reverse else li:
|
||||||
|
if self.trade_exchange.is_stock_tradable(
|
||||||
|
stock_id=si, start_time=trade_start_time, end_time=trade_end_time
|
||||||
|
):
|
||||||
|
res.append(si)
|
||||||
|
cur_n += 1
|
||||||
|
if cur_n >= n:
|
||||||
|
break
|
||||||
|
return res[::-1] if reverse else res
|
||||||
|
|
||||||
|
def get_last_n(li, n):
|
||||||
|
return get_first_n(li, n, reverse=True)
|
||||||
|
|
||||||
|
def filter_stock(li):
|
||||||
|
return [
|
||||||
|
si
|
||||||
|
for si in li
|
||||||
|
if self.trade_exchange.is_stock_tradable(
|
||||||
|
stock_id=si, start_time=trade_start_time, end_time=trade_end_time
|
||||||
|
)
|
||||||
|
]
|
||||||
|
|
||||||
|
else:
|
||||||
|
|
||||||
|
def get_first_n(li, n):
|
||||||
|
return list(li)[:n]
|
||||||
|
|
||||||
|
def get_last_n(li, n):
|
||||||
|
return list(li)[-n:]
|
||||||
|
|
||||||
|
def filter_stock(li):
|
||||||
|
return li
|
||||||
|
|
||||||
|
current_temp: "object" = copy.deepcopy(self.trade_position)
|
||||||
|
sell_order_list: List[Order] = []
|
||||||
|
buy_order_list: List[Order] = []
|
||||||
|
cash = current_temp.get_cash()
|
||||||
|
current_stock_list = current_temp.get_stock_list()
|
||||||
|
last = pred_score.reindex(current_stock_list).sort_values(ascending=False).index
|
||||||
|
|
||||||
|
if self.method_buy == "top":
|
||||||
|
today = get_first_n(
|
||||||
|
pred_score[~pred_score.index.isin(last)].sort_values(ascending=False).index,
|
||||||
|
self.n_drop + self.topk - len(last),
|
||||||
|
)
|
||||||
|
elif self.method_buy == "random":
|
||||||
|
topk_candi = get_first_n(pred_score.sort_values(ascending=False).index, self.topk)
|
||||||
|
candi = list(filter(lambda x: x not in last, topk_candi))
|
||||||
|
n = self.n_drop + self.topk - len(last)
|
||||||
|
try:
|
||||||
|
today = np.random.choice(candi, n, replace=False)
|
||||||
|
except ValueError:
|
||||||
|
today = candi
|
||||||
|
else:
|
||||||
|
raise NotImplementedError(f"This type of input is not supported")
|
||||||
|
|
||||||
|
comb = pred_score.reindex(last.union(pd.Index(today))).sort_values(ascending=False).index
|
||||||
|
|
||||||
|
if self.method_sell == "bottom":
|
||||||
|
sell = last[last.isin(get_last_n(comb, self.n_drop))]
|
||||||
|
elif self.method_sell == "random":
|
||||||
|
candi = filter_stock(last)
|
||||||
|
try:
|
||||||
|
sell = pd.Index(np.random.choice(candi, self.n_drop, replace=False) if len(last) else [])
|
||||||
|
except ValueError:
|
||||||
|
sell = candi
|
||||||
|
else:
|
||||||
|
raise NotImplementedError(f"This type of input is not supported")
|
||||||
|
|
||||||
|
buy = today[: len(sell) + self.topk - len(last)]
|
||||||
|
for code in current_stock_list:
|
||||||
|
if not self.trade_exchange.is_stock_tradable(
|
||||||
|
stock_id=code,
|
||||||
|
start_time=trade_start_time,
|
||||||
|
end_time=trade_end_time,
|
||||||
|
direction=None if self.forbid_all_trade_at_limit else OrderDir.SELL,
|
||||||
|
):
|
||||||
|
continue
|
||||||
|
if code in sell:
|
||||||
|
time_per_step = self.trade_calendar.get_freq()
|
||||||
|
if current_temp.get_stock_count(code, bar=time_per_step) < self.hold_thresh:
|
||||||
|
continue
|
||||||
|
sell_amount = current_temp.get_stock_amount(code=code)
|
||||||
|
sell_order = Order(
|
||||||
|
stock_id=code,
|
||||||
|
amount=sell_amount,
|
||||||
|
start_time=trade_start_time,
|
||||||
|
end_time=trade_end_time,
|
||||||
|
direction=Order.SELL,
|
||||||
|
)
|
||||||
|
if self.trade_exchange.check_order(sell_order):
|
||||||
|
sell_order_list.append(sell_order)
|
||||||
|
trade_val, trade_cost, trade_price = self.trade_exchange.deal_order(
|
||||||
|
sell_order, position=current_temp
|
||||||
|
)
|
||||||
|
cash += trade_val - trade_cost
|
||||||
|
|
||||||
|
if len(buy) == 0:
|
||||||
|
return TradeDecisionWO(sell_order_list, self)
|
||||||
|
|
||||||
|
value = cash * self.risk_degree / len(buy)
|
||||||
|
for code in buy:
|
||||||
|
if not self.trade_exchange.is_stock_tradable(
|
||||||
|
stock_id=code,
|
||||||
|
start_time=trade_start_time,
|
||||||
|
end_time=trade_end_time,
|
||||||
|
direction=None if self.forbid_all_trade_at_limit else OrderDir.BUY,
|
||||||
|
):
|
||||||
|
continue
|
||||||
|
buy_price = self.trade_exchange.get_deal_price(
|
||||||
|
stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=OrderDir.BUY
|
||||||
|
)
|
||||||
|
buy_amount = value / buy_price
|
||||||
|
factor = self.trade_exchange.get_factor(
|
||||||
|
stock_id=code, start_time=trade_start_time, end_time=trade_end_time
|
||||||
|
)
|
||||||
|
buy_amount = self.trade_exchange.round_amount_by_trade_unit(buy_amount, factor)
|
||||||
|
buy_order = Order(
|
||||||
|
stock_id=code,
|
||||||
|
amount=buy_amount,
|
||||||
|
start_time=trade_start_time,
|
||||||
|
end_time=trade_end_time,
|
||||||
|
direction=Order.BUY,
|
||||||
|
)
|
||||||
|
buy_order_list.append(buy_order)
|
||||||
|
|
||||||
|
return TradeDecisionWO(sell_order_list + buy_order_list, self)
|
||||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -1,69 +0,0 @@
|
|||||||
# TradeAC Experiment Queue — Series 2 (Q12+)
|
|
||||||
|
|
||||||
**Purpose.** The next pre-registered batch of experiments, continuing Series 1
|
|
||||||
(Q01–Q11, exp 33–43, all executed and folded into `book/CLAIMS.md` /
|
|
||||||
`book/EVIDENCE.md`). Each entry targets a still-unproven `HYPOTHESIS` from the
|
|
||||||
book or an open question flagged in `CLAIMS.md`/`book/README.md`, and follows the
|
|
||||||
Series-1 discipline: one variable changed vs the exp-26 reference, acceptance
|
|
||||||
fixed BEFORE the run, sequential execution, trace-first, verify-then-close.
|
|
||||||
|
|
||||||
**Reference / control (MUST reproduce first).** exp 26 (`21afc6af…`, mlflow exp
|
|
||||||
25) is the campaign baseline; exp 39 (Q07, weekly rebalance) is the best
|
|
||||||
construction. Reference config is byte-reproduced in `workflows/exp26/` on the
|
|
||||||
`exp/26-…` branch and in this dir's `workflows/*.yaml`.
|
|
||||||
|
|
||||||
| Config element | exp-26 reference value |
|
|
||||||
|---|---|
|
|
||||||
| Universe | 50-ETF panel (`UNIVERSE` below) |
|
|
||||||
| Features | compact stochastic 25-field set (no ou/hmm/moments/garch) |
|
|
||||||
| Label | `Ref($close,-6)/Ref($close,-1)-1` (5d) |
|
|
||||||
| Model | `RankICEnsembleLGBModel`, seeds `42,7,2026,99,123`, lr 0.02, leaves 31, 3000 rounds, ES 200 |
|
|
||||||
| Segments | train 2016-01-04..2025-09-01 / valid 2025-09-03..2026-01-03 / test 2026-01-04..2026-08-10 |
|
|
||||||
| Strategy | TopkDropout, topk 10, n_drop 1, risk_degree 0.95 |
|
|
||||||
| Costs | open 0.0005 / close 0.0015 / min $5, deal $close, SPY benchmark, $1M |
|
|
||||||
|
|
||||||
**Reference metrics to beat (EVIDENCE#015):** net_ann +2.13%, net_IR 0.21, gross
|
|
||||||
+7.02%, maxDD −7.69%, RankIC 0.0663, RankICIR 0.2545, L/S Sharpe 4.54. Weekly
|
|
||||||
(Q07, EVIDENCE#028): net +12.51%, IR 1.24, maxDD −4.13%, ~1.1pp cost drag.
|
|
||||||
|
|
||||||
## The queue (ordered by value × feasibility)
|
|
||||||
|
|
||||||
| ID | Title / hypothesis | Change vs reference (ONE var) | Acceptance | Config | Ready? |
|
|
||||||
|----|--------------------|-------------------------------|------------|--------|--------|
|
|
||||||
| Q12 | **22d label + weekly recompute** — the untested combo: Q05's label edge (IC 0.097, RankIC 0.117) with Q07's cost relief | label → 22d AND strategy → weekly (two coupled, explicitly pre-registered) | net_IR > 0.5, net_ann > +5%, cost drag ≤ 2pp | `workflows/q12_label22d_weekly.yaml` | ✅ |
|
|
||||||
| Q13 | **Weekly rebalance reproduction on a 2nd window** — Q07 was a single OOS window; reproduce on test 2025-01-02..2025-12-31 before promoting to a live round | segments only (shifted) | net_IR > 0.21, net_ann > +2.13% on the new window | `workflows/q13_weekly_second_window.yaml` | ✅ |
|
|
||||||
| Q14 | **Out-of-universe validation** — compact stochastic set generalizes off the 50-ETF panel to a single-stock universe | universe → 30 liquid single names | RankIC > 0.03, ICIR > 0.15, net IR > 0 on stocks | `workflows/q14_out_of_universe.yaml` | ⚠️ needs stock-lake backfill (see design) |
|
|
||||||
| Q15 | **5-seed vs single-model clean A/B** — seed-count claim (exp 12 idea, re-validated exp 22–24, never a clean A/B) | seeds → 1 (`2026`) | single-model RankIC/IR < 5-seed ref; net_IR ≥ 0.21 acceptable if ≥ single | `workflows/q15_single_seed.yaml` | ✅ |
|
|
||||||
| Q16 | **HMM family added as features** — settles "dropping model-specific (ou,hmm) improves signal" (exp 25 tested OU; hmm-as-feature untested) | features += `sp_hmm_p_regime1,sp_hmm_state` | no improvement: RankIC ≤ 0.0663, net_IR ≤ 0.21 | `workflows/q16_hmm_features.yaml` | ✅ |
|
|
||||||
| Q17 | **Realized-moments family added** — settles "moment/volatility families regress" (exp 11 idea, never clean A/B) | features += `sp_rskew_5,sp_rskew_22,sp_rkurt_5,sp_rkurt_22,sp_dsv_5,sp_dsv_22` | no improvement: RankIC ≤ 0.0663, net_IR ≤ 0.21 | `workflows/q17_moments_features.yaml` | ✅ |
|
|
||||||
| Q18 | **OptimalStopControl clean re-test** — exp 13/14 claim (TopkDropout > stop-control) never re-tested post-reset | strategy → `OptimalStopControl` (exp-13 params) | TopkDropout net_IR ≥ stop-control net_IR; document cost drag | `workflows/q18_optstop.yaml` | ✅ (module verified in venv) |
|
|
||||||
| Q19 | **Martingale / variance-ratio study close-out** — exp 19 never closed; VR<1 at 5–20d on clean lake | ad-hoc script (no qrun) | VR stats + drift decomposition on 50-ETF panel | `designs/q19_martingale_vr.md` | ✅ script |
|
|
||||||
| Q20 | **Effective independent names (≈4)** — eigenvalue analysis on clean-lake covariance | ad-hoc script | eigenvalue spectrum + effective-rank count | `designs/q20_effective_names.md` | ✅ script |
|
|
||||||
|
|
||||||
### Deferred (methodology / infra, P3)
|
|
||||||
- Purged / walk-forward CV (was queue's old Q12) — methodology, not an alpha lever.
|
|
||||||
- PSI-based drift-aware retraining cadence — needs a drift-gate module + a retrain decision rule.
|
|
||||||
- No-trade buffer band / notional-vs-qty sizing — siblings of Q12/Q13; queue only if weekly reproduces.
|
|
||||||
- Macro/drift overlays (SPY>200d regime gate, momentum tilt) — needs new data pipeline.
|
|
||||||
|
|
||||||
## Execution protocol (per queued run)
|
|
||||||
|
|
||||||
1. **Validate the lake first** (`validate_lake_dataset` + `rd_status`) — clean-lake lesson: silent NaN-drops and hollow coverage invalidate a run. Q14 additionally requires backfilling the single-stock universe (bars + sp/ta features, full range, explicit `start`/`end`).
|
|
||||||
2. **Trace before running** (`rd_trace_start` with the hypothesis as `rational`, fresh `experiment_name`, `evolved_from=auto`).
|
|
||||||
3. **Run** `rd_run_workflow config_path=<abs path to the queue YAML> experiment_name=<fresh name>` — `wait=false`, poll `rd_exp_get_run` until `FINISHED`.
|
|
||||||
4. **Verify against acceptance** via `rd_exp_result` (headline + backtest risk).
|
|
||||||
5. **Finish the trace** (`rd_trace_finish` with `metrics` + `evaluation`), snapshot any changed contrib modules.
|
|
||||||
6. **Report to the book** — PROVE/REFUTE → update `book/CLAIMS.md` + `book/EVIDENCE.md`.
|
|
||||||
|
|
||||||
Sequential execution only (concurrent runs hang — chat-ideas.md ops lesson). Any
|
|
||||||
custom strategy/module changed here must be copied into the venv site-packages
|
|
||||||
snapshot before `rd_run_workflow` can import it (see `/app/AGENTS.md`). As of
|
|
||||||
2026-08-20 `WeeklyRebalanceDropoutStrategy` and `OptimalStopControl` are verified
|
|
||||||
in sync with the venv snapshot; the lake already persists the `sp_hmm_*` and
|
|
||||||
`sp_moments` families on the 50-ETF panel.
|
|
||||||
|
|
||||||
## Provenance
|
|
||||||
|
|
||||||
Mined 2026-08-20 from `book/CLAIMS.md`, `book/EVIDENCE.md`, `book/README.md`,
|
|
||||||
`book/references/chat-ideas.md`, and Series-1 `queue/` (Q01–Q11, executed exp
|
|
||||||
33–43). Reference numbers are post-clean-lake (exp 21+).
|
|
||||||
@@ -1,26 +0,0 @@
|
|||||||
# QUEUE-19 — Martingale / variance-ratio study close-out (no qrun)
|
|
||||||
|
|
||||||
**Status:** QUEUED · **Priority:** P2 · **Effort:** ad-hoc script under `book/data/`
|
|
||||||
|
|
||||||
## Hypothesis (settle)
|
|
||||||
Assets are submartingales long-horizon / mean-reverting short-horizon
|
|
||||||
(`VR < 1` at 5–20d). CLAIMS.md marks this HYPOTHESIS (chat-derived martingale
|
|
||||||
study; exp 19 was opened but never closed). It is a market-structure claim, not a
|
|
||||||
trading claim — settle it with a clean-lake script, then close exp 19 or open a
|
|
||||||
scripted EVIDENCE entry.
|
|
||||||
|
|
||||||
## Method (persist everything under `book/data/evidence/q19-vr/`)
|
|
||||||
1. Load the 50-ETF panel 1d bars from the lake for 2015-01-01..2026-08-19.
|
|
||||||
2. Compute the Lo–MacKinlay variance ratio at horizons 5 / 10 / 20d per symbol,
|
|
||||||
with heteroskedasticity-robust z-stats.
|
|
||||||
3. Report: per-horizon VR distribution, fraction of symbols with VR < 1 and the
|
|
||||||
z-significance, pooled drift vs daily variance (submartingale check).
|
|
||||||
4. Cross-check the pooled `sp_trend_slope_5` regression beta claim (β ≈ −0.53,
|
|
||||||
t ≈ −24) on the clean lake.
|
|
||||||
5. Write `VR_stats.csv` + a one-page summary into the evidence dir.
|
|
||||||
|
|
||||||
## Acceptance
|
|
||||||
- VR < 1 at 5–20d for a material fraction of the panel with |z| > 2 → supports
|
|
||||||
the mean-reversion HYPOTHESIS; else mark REFUTED or REFERENCED.
|
|
||||||
- The result updates CLAIMS.md's "Assets are submartingales…" row and closes the
|
|
||||||
exp-19 open thread.
|
|
||||||
@@ -1,22 +0,0 @@
|
|||||||
# QUEUE-20 — Effective independent names in the 50-ETF book (no qrun)
|
|
||||||
|
|
||||||
**Status:** QUEUED · **Priority:** P2 · **Effort:** ad-hoc script under `book/data/`
|
|
||||||
|
|
||||||
## Hypothesis (settle)
|
|
||||||
The 50-ETF book has only ~4 effective independent names (CLAIMS.md HYPOTHESIS,
|
|
||||||
chat-derived eigenvalue analysis, pre-reset). This is a concentration/diversification
|
|
||||||
claim with direct sizing relevance; verify it on the clean lake.
|
|
||||||
|
|
||||||
## Method (persist everything under `book/data/evidence/q20-effective-names/`)
|
|
||||||
1. Load the 50-ETF panel 1d returns from the lake for the test window 2026-01-04..2026-08-10.
|
|
||||||
2. Standardize returns; compute the correlation matrix and its eigendecomposition.
|
|
||||||
3. Count eigenvalues above the Marchenko–Pastur bound (N=50, T≈150) and report the
|
|
||||||
cumulative-variance share of the top k components.
|
|
||||||
4. Effective-rank measures: participation ratio `(Σλ)² / Σλ²` and cumulative 80%
|
|
||||||
variance count.
|
|
||||||
5. Write `eigenanalysis.csv` + a one-page summary.
|
|
||||||
|
|
||||||
## Acceptance
|
|
||||||
- If effective rank ≈ 4 (top-4 explain ~80%+ variance), the concentration claim is
|
|
||||||
PROVEN and feeds chapter 08 sizing guidance (why topk 10→20 adds no breadth).
|
|
||||||
- If effective rank is much larger, mark the claim REFUTED.
|
|
||||||
@@ -1,105 +0,0 @@
|
|||||||
# QUEUE-12 — Long-horizon label (22d) + weekly recompute construction.
|
|
||||||
# Untested combination from book/CLAIMS.md open questions: Q05 (exp 37) proved the
|
|
||||||
# 22d label has the strongest signal (IC 0.097, RankIC 0.117) but daily turnover
|
|
||||||
# killed the book (net -4.60%); Q07 (exp 39) proved weekly recompute is the cost
|
|
||||||
# lever (net +12.51%). Hypothesis: pairing them monetizes the label edge.
|
|
||||||
# Change vs exp-26 reference: label 5d -> 22d AND strategy -> WeeklyRebalanceDropoutStrategy.
|
|
||||||
# Acceptance: net_IR > 0.5, net_ann > +5%, cost drag <= 2pp.
|
|
||||||
# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q12_label22d_weekly.yaml \
|
|
||||||
# experiment_name=tac-rd-q12-label22d-weekly
|
|
||||||
{%- set LAKE = TAC_LAKE_DIR %}
|
|
||||||
{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
|
|
||||||
{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
|
|
||||||
|
|
||||||
qlib_init:
|
|
||||||
provider_uri: "{{ LAKE }}"
|
|
||||||
region: us
|
|
||||||
expression_cache: null
|
|
||||||
dataset_cache: null
|
|
||||||
calendar_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeCalendarProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
|
||||||
instrument_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeInstrumentProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
|
||||||
feature_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeFeatureProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
|
||||||
exp_manager:
|
|
||||||
class: MLflowExpManager
|
|
||||||
module_path: qlib.workflow.expm
|
|
||||||
kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q12-label22d-weekly" }
|
|
||||||
|
|
||||||
task:
|
|
||||||
model:
|
|
||||||
class: RankICEnsembleLGBModel
|
|
||||||
module_path: tac_qlib.contrib.model.rank_ensemble
|
|
||||||
kwargs:
|
|
||||||
loss: mse
|
|
||||||
learning_rate: 0.02
|
|
||||||
num_leaves: 31
|
|
||||||
n_estimators: 3000
|
|
||||||
num_boost_round: 3000
|
|
||||||
early_stopping_rounds: 200
|
|
||||||
min_data_in_leaf: 20
|
|
||||||
lambda_l2: 0.5
|
|
||||||
colsample_bytree: 0.8
|
|
||||||
subsample: 0.8
|
|
||||||
subsample_freq: 1
|
|
||||||
reg_alpha: 0.1
|
|
||||||
reg_lambda: 1.0
|
|
||||||
seeds: "42,7,2026,99,123"
|
|
||||||
|
|
||||||
dataset:
|
|
||||||
class: DatasetH
|
|
||||||
module_path: qlib.data.dataset
|
|
||||||
kwargs:
|
|
||||||
handler:
|
|
||||||
class: TACHandler
|
|
||||||
module_path: tac_qlib.contrib.data.handler
|
|
||||||
kwargs:
|
|
||||||
instruments: "{{ UNIVERSE }}"
|
|
||||||
start_time: 2015-01-03
|
|
||||||
end_time: 2026-08-10
|
|
||||||
fit_start_time: 2016-01-04
|
|
||||||
fit_end_time: 2025-09-01
|
|
||||||
freq: day
|
|
||||||
lake_root: "{{ LAKE }}"
|
|
||||||
market: US
|
|
||||||
label: "Ref($close,-23)/Ref($close,-1)-1"
|
|
||||||
feature_fields: "{{ FEATURES }}"
|
|
||||||
infer_processors:
|
|
||||||
- { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
|
||||||
- { class: ProcessInf, kwargs: {} }
|
|
||||||
- { class: CSRankNorm, kwargs: {} }
|
|
||||||
- { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
|
||||||
- { class: Fillna, kwargs: {} }
|
|
||||||
segments:
|
|
||||||
train: [2016-01-04, 2025-09-01]
|
|
||||||
valid: [2025-09-03, 2026-01-03]
|
|
||||||
test: [2026-01-04, 2026-08-10]
|
|
||||||
|
|
||||||
record:
|
|
||||||
- { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
|
|
||||||
- { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
|
|
||||||
- class: PortAnaRecord
|
|
||||||
module_path: qlib.workflow.record_temp
|
|
||||||
kwargs:
|
|
||||||
config:
|
|
||||||
strategy:
|
|
||||||
class: WeeklyRebalanceDropoutStrategy
|
|
||||||
module_path: tac_qlib.contrib.strategy.weekly_rebalance
|
|
||||||
kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
|
|
||||||
backtest:
|
|
||||||
start_time: 2026-01-04
|
|
||||||
end_time: 2026-08-10
|
|
||||||
account: 1000000
|
|
||||||
benchmark: SPY
|
|
||||||
exchange_kwargs:
|
|
||||||
codes: "{{ UNIVERSE }}"
|
|
||||||
deal_price: $close
|
|
||||||
freq: day
|
|
||||||
open_cost: 0.0005
|
|
||||||
close_cost: 0.0015
|
|
||||||
min_cost: 5.0
|
|
||||||
risk_analysis_freq: 1d
|
|
||||||
@@ -1,106 +0,0 @@
|
|||||||
# QUEUE-13 — Weekly rebalance reproduction on a second OOS window.
|
|
||||||
# Q07 (exp 39) proved weekly recompute on test 2026-01-04..2026-08-10 (net +12.51%,
|
|
||||||
# IR 1.24) but that is a single OOS window. Before promoting the weekly construction
|
|
||||||
# to a live round, reproduce it on a disjoint window: test 2025-01-02..2025-12-31
|
|
||||||
# with train/valid shifted to end 2024.
|
|
||||||
# Change vs exp-26 reference: segments shifted only (train ends 2024-08, test = 2025);
|
|
||||||
# strategy is the SAME weekly recompute as exp 39. Label stays 5d.
|
|
||||||
# Acceptance: net_IR > 0.21 AND net_ann > +2.13% on the 2025 window.
|
|
||||||
# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q13_weekly_second_window.yaml \
|
|
||||||
# experiment_name=tac-rd-q13-weekly-second-window
|
|
||||||
{%- set LAKE = TAC_LAKE_DIR %}
|
|
||||||
{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
|
|
||||||
{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
|
|
||||||
|
|
||||||
qlib_init:
|
|
||||||
provider_uri: "{{ LAKE }}"
|
|
||||||
region: us
|
|
||||||
expression_cache: null
|
|
||||||
dataset_cache: null
|
|
||||||
calendar_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeCalendarProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
|
||||||
instrument_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeInstrumentProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
|
||||||
feature_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeFeatureProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
|
||||||
exp_manager:
|
|
||||||
class: MLflowExpManager
|
|
||||||
module_path: qlib.workflow.expm
|
|
||||||
kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q13-weekly-second-window" }
|
|
||||||
|
|
||||||
task:
|
|
||||||
model:
|
|
||||||
class: RankICEnsembleLGBModel
|
|
||||||
module_path: tac_qlib.contrib.model.rank_ensemble
|
|
||||||
kwargs:
|
|
||||||
loss: mse
|
|
||||||
learning_rate: 0.02
|
|
||||||
num_leaves: 31
|
|
||||||
n_estimators: 3000
|
|
||||||
num_boost_round: 3000
|
|
||||||
early_stopping_rounds: 200
|
|
||||||
min_data_in_leaf: 20
|
|
||||||
lambda_l2: 0.5
|
|
||||||
colsample_bytree: 0.8
|
|
||||||
subsample: 0.8
|
|
||||||
subsample_freq: 1
|
|
||||||
reg_alpha: 0.1
|
|
||||||
reg_lambda: 1.0
|
|
||||||
seeds: "42,7,2026,99,123"
|
|
||||||
|
|
||||||
dataset:
|
|
||||||
class: DatasetH
|
|
||||||
module_path: qlib.data.dataset
|
|
||||||
kwargs:
|
|
||||||
handler:
|
|
||||||
class: TACHandler
|
|
||||||
module_path: tac_qlib.contrib.data.handler
|
|
||||||
kwargs:
|
|
||||||
instruments: "{{ UNIVERSE }}"
|
|
||||||
start_time: 2015-01-03
|
|
||||||
end_time: 2025-12-31
|
|
||||||
fit_start_time: 2016-01-04
|
|
||||||
fit_end_time: 2024-08-30
|
|
||||||
freq: day
|
|
||||||
lake_root: "{{ LAKE }}"
|
|
||||||
market: US
|
|
||||||
label: "Ref($close,-6)/Ref($close,-1)-1"
|
|
||||||
feature_fields: "{{ FEATURES }}"
|
|
||||||
infer_processors:
|
|
||||||
- { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2024-08-30" } }
|
|
||||||
- { class: ProcessInf, kwargs: {} }
|
|
||||||
- { class: CSRankNorm, kwargs: {} }
|
|
||||||
- { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2024-08-30" } }
|
|
||||||
- { class: Fillna, kwargs: {} }
|
|
||||||
segments:
|
|
||||||
train: [2016-01-04, 2024-08-30]
|
|
||||||
valid: [2024-09-03, 2024-12-31]
|
|
||||||
test: [2025-01-02, 2025-12-31]
|
|
||||||
|
|
||||||
record:
|
|
||||||
- { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
|
|
||||||
- { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
|
|
||||||
- class: PortAnaRecord
|
|
||||||
module_path: qlib.workflow.record_temp
|
|
||||||
kwargs:
|
|
||||||
config:
|
|
||||||
strategy:
|
|
||||||
class: WeeklyRebalanceDropoutStrategy
|
|
||||||
module_path: tac_qlib.contrib.strategy.weekly_rebalance
|
|
||||||
kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
|
|
||||||
backtest:
|
|
||||||
start_time: 2025-01-02
|
|
||||||
end_time: 2025-12-31
|
|
||||||
account: 1000000
|
|
||||||
benchmark: SPY
|
|
||||||
exchange_kwargs:
|
|
||||||
codes: "{{ UNIVERSE }}"
|
|
||||||
deal_price: $close
|
|
||||||
freq: day
|
|
||||||
open_cost: 0.0005
|
|
||||||
close_cost: 0.0015
|
|
||||||
min_cost: 5.0
|
|
||||||
risk_analysis_freq: 1d
|
|
||||||
@@ -1,107 +0,0 @@
|
|||||||
# QUEUE-14 — Out-of-universe validation: compact stochastic set on single-stock names.
|
|
||||||
# The 50-ETF panel results (compact feature set, RankIC 0.0663) are panel-specific;
|
|
||||||
# book/CLAIMS.md marks "generalizes to other universes" HYPOTHESIS - TODO(evidence-needed).
|
|
||||||
# Change vs exp-26 reference: universe -> 30 liquid US single-stock names.
|
|
||||||
# PREREQUISITE: backfill lake bars + sp/ta features for these symbols (full range,
|
|
||||||
# explicit start/end) — the stock panel currently has only ~180d of data (2025-12-01+).
|
|
||||||
# Backfill: get_lake_bars symbols=... start=2000-01-03 then
|
|
||||||
# get_lake_sp symbol=<s> start=2000-01-03 end=<today> fit_end=<train-end> persist=true
|
|
||||||
# Acceptance: RankIC > 0.03, ICIR > 0.15, net IR > 0 on the stock universe.
|
|
||||||
# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q14_out_of_universe.yaml \
|
|
||||||
# experiment_name=tac-rd-q14-out-of-universe
|
|
||||||
{%- set LAKE = TAC_LAKE_DIR %}
|
|
||||||
{%- set UNIVERSE = "AAPL,MSFT,NVDA,AMZN,GOOGL,META,TSLA,AVGO,AMD,JPM,UNH,PG,JNJ,MA,V,WMT,DIS,HD,KO,PEP,BAC,XOM,MCD,ABBV,COST,CRM,NFLX,ORCL,IBM,T" %}
|
|
||||||
{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
|
|
||||||
|
|
||||||
qlib_init:
|
|
||||||
provider_uri: "{{ LAKE }}"
|
|
||||||
region: us
|
|
||||||
expression_cache: null
|
|
||||||
dataset_cache: null
|
|
||||||
calendar_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeCalendarProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
|
||||||
instrument_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeInstrumentProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
|
||||||
feature_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeFeatureProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
|
||||||
exp_manager:
|
|
||||||
class: MLflowExpManager
|
|
||||||
module_path: qlib.workflow.expm
|
|
||||||
kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q14-out-of-universe" }
|
|
||||||
|
|
||||||
task:
|
|
||||||
model:
|
|
||||||
class: RankICEnsembleLGBModel
|
|
||||||
module_path: tac_qlib.contrib.model.rank_ensemble
|
|
||||||
kwargs:
|
|
||||||
loss: mse
|
|
||||||
learning_rate: 0.02
|
|
||||||
num_leaves: 31
|
|
||||||
n_estimators: 3000
|
|
||||||
num_boost_round: 3000
|
|
||||||
early_stopping_rounds: 200
|
|
||||||
min_data_in_leaf: 20
|
|
||||||
lambda_l2: 0.5
|
|
||||||
colsample_bytree: 0.8
|
|
||||||
subsample: 0.8
|
|
||||||
subsample_freq: 1
|
|
||||||
reg_alpha: 0.1
|
|
||||||
reg_lambda: 1.0
|
|
||||||
seeds: "42,7,2026,99,123"
|
|
||||||
|
|
||||||
dataset:
|
|
||||||
class: DatasetH
|
|
||||||
module_path: qlib.data.dataset
|
|
||||||
kwargs:
|
|
||||||
handler:
|
|
||||||
class: TACHandler
|
|
||||||
module_path: tac_qlib.contrib.data.handler
|
|
||||||
kwargs:
|
|
||||||
instruments: "{{ UNIVERSE }}"
|
|
||||||
start_time: 2015-01-03
|
|
||||||
end_time: 2026-08-10
|
|
||||||
fit_start_time: 2016-01-04
|
|
||||||
fit_end_time: 2025-09-01
|
|
||||||
freq: day
|
|
||||||
lake_root: "{{ LAKE }}"
|
|
||||||
market: US
|
|
||||||
label: "Ref($close,-6)/Ref($close,-1)-1"
|
|
||||||
feature_fields: "{{ FEATURES }}"
|
|
||||||
infer_processors:
|
|
||||||
- { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
|
||||||
- { class: ProcessInf, kwargs: {} }
|
|
||||||
- { class: CSRankNorm, kwargs: {} }
|
|
||||||
- { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
|
||||||
- { class: Fillna, kwargs: {} }
|
|
||||||
segments:
|
|
||||||
train: [2016-01-04, 2025-09-01]
|
|
||||||
valid: [2025-09-03, 2026-01-03]
|
|
||||||
test: [2026-01-04, 2026-08-10]
|
|
||||||
|
|
||||||
record:
|
|
||||||
- { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
|
|
||||||
- { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
|
|
||||||
- class: PortAnaRecord
|
|
||||||
module_path: qlib.workflow.record_temp
|
|
||||||
kwargs:
|
|
||||||
config:
|
|
||||||
strategy:
|
|
||||||
class: TopkDropoutStrategy
|
|
||||||
module_path: qlib.contrib.strategy
|
|
||||||
kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
|
|
||||||
backtest:
|
|
||||||
start_time: 2026-01-04
|
|
||||||
end_time: 2026-08-10
|
|
||||||
account: 1000000
|
|
||||||
benchmark: SPY
|
|
||||||
exchange_kwargs:
|
|
||||||
codes: "{{ UNIVERSE }}"
|
|
||||||
deal_price: $close
|
|
||||||
freq: day
|
|
||||||
open_cost: 0.0005
|
|
||||||
close_cost: 0.0015
|
|
||||||
min_cost: 5.0
|
|
||||||
risk_analysis_freq: 1d
|
|
||||||
@@ -1,104 +0,0 @@
|
|||||||
# QUEUE-15 — 5-seed vs single-model clean A/B on the compact stochastic set.
|
|
||||||
# CLAIMS.md HYPOTHESIS: "5-seed RankIC ensemble raises performance vs single model
|
|
||||||
# on ablated set" — pre-clean-lake exp 12 idea, re-validated directionally by exp
|
|
||||||
# 22–24, never a clean A/B post-reset. Seed count is load-bearing (exp 28: 2<5).
|
|
||||||
# Change vs exp-26 reference: seeds "42,7,2026,99,123" -> single seed "2026".
|
|
||||||
# Acceptance: single-model RankIC < 0.0663, net_IR < 0.21 (ensemble beats single).
|
|
||||||
# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q15_single_seed.yaml \
|
|
||||||
# experiment_name=tac-rd-q15-single-seed
|
|
||||||
{%- set LAKE = TAC_LAKE_DIR %}
|
|
||||||
{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
|
|
||||||
{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
|
|
||||||
|
|
||||||
qlib_init:
|
|
||||||
provider_uri: "{{ LAKE }}"
|
|
||||||
region: us
|
|
||||||
expression_cache: null
|
|
||||||
dataset_cache: null
|
|
||||||
calendar_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeCalendarProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
|
||||||
instrument_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeInstrumentProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
|
||||||
feature_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeFeatureProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
|
||||||
exp_manager:
|
|
||||||
class: MLflowExpManager
|
|
||||||
module_path: qlib.workflow.expm
|
|
||||||
kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q15-single-seed" }
|
|
||||||
|
|
||||||
task:
|
|
||||||
model:
|
|
||||||
class: RankICEnsembleLGBModel
|
|
||||||
module_path: tac_qlib.contrib.model.rank_ensemble
|
|
||||||
kwargs:
|
|
||||||
loss: mse
|
|
||||||
learning_rate: 0.02
|
|
||||||
num_leaves: 31
|
|
||||||
n_estimators: 3000
|
|
||||||
num_boost_round: 3000
|
|
||||||
early_stopping_rounds: 200
|
|
||||||
min_data_in_leaf: 20
|
|
||||||
lambda_l2: 0.5
|
|
||||||
colsample_bytree: 0.8
|
|
||||||
subsample: 0.8
|
|
||||||
subsample_freq: 1
|
|
||||||
reg_alpha: 0.1
|
|
||||||
reg_lambda: 1.0
|
|
||||||
seeds: "2026"
|
|
||||||
|
|
||||||
dataset:
|
|
||||||
class: DatasetH
|
|
||||||
module_path: qlib.data.dataset
|
|
||||||
kwargs:
|
|
||||||
handler:
|
|
||||||
class: TACHandler
|
|
||||||
module_path: tac_qlib.contrib.data.handler
|
|
||||||
kwargs:
|
|
||||||
instruments: "{{ UNIVERSE }}"
|
|
||||||
start_time: 2015-01-03
|
|
||||||
end_time: 2026-08-10
|
|
||||||
fit_start_time: 2016-01-04
|
|
||||||
fit_end_time: 2025-09-01
|
|
||||||
freq: day
|
|
||||||
lake_root: "{{ LAKE }}"
|
|
||||||
market: US
|
|
||||||
label: "Ref($close,-6)/Ref($close,-1)-1"
|
|
||||||
feature_fields: "{{ FEATURES }}"
|
|
||||||
infer_processors:
|
|
||||||
- { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
|
||||||
- { class: ProcessInf, kwargs: {} }
|
|
||||||
- { class: CSRankNorm, kwargs: {} }
|
|
||||||
- { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
|
||||||
- { class: Fillna, kwargs: {} }
|
|
||||||
segments:
|
|
||||||
train: [2016-01-04, 2025-09-01]
|
|
||||||
valid: [2025-09-03, 2026-01-03]
|
|
||||||
test: [2026-01-04, 2026-08-10]
|
|
||||||
|
|
||||||
record:
|
|
||||||
- { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
|
|
||||||
- { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
|
|
||||||
- class: PortAnaRecord
|
|
||||||
module_path: qlib.workflow.record_temp
|
|
||||||
kwargs:
|
|
||||||
config:
|
|
||||||
strategy:
|
|
||||||
class: TopkDropoutStrategy
|
|
||||||
module_path: qlib.contrib.strategy
|
|
||||||
kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
|
|
||||||
backtest:
|
|
||||||
start_time: 2026-01-04
|
|
||||||
end_time: 2026-08-10
|
|
||||||
account: 1000000
|
|
||||||
benchmark: SPY
|
|
||||||
exchange_kwargs:
|
|
||||||
codes: "{{ UNIVERSE }}"
|
|
||||||
deal_price: $close
|
|
||||||
freq: day
|
|
||||||
open_cost: 0.0005
|
|
||||||
close_cost: 0.0015
|
|
||||||
min_cost: 5.0
|
|
||||||
risk_analysis_freq: 1d
|
|
||||||
@@ -1,105 +0,0 @@
|
|||||||
# QUEUE-16 — HMM family added as model features to the compact set.
|
|
||||||
# CLAIMS.md HYPOTHESIS: "Dropping model-specific feature families (ou, hmm)
|
|
||||||
# improves the rank signal" — exp 25 cleanly tested OU (adding it hurts: IC 0.0511->0.0343);
|
|
||||||
# hmm-as-features has NOT been clean A/B'd post-reset (exp 42 tested hmm as an entry
|
|
||||||
# GATE overlay, refuted). This run adds the hmm family columns to the compact set.
|
|
||||||
# Change vs exp-26 reference: features += sp_hmm_p_regime1, sp_hmm_state.
|
|
||||||
# Acceptance (prune-hypothesis): no improvement — RankIC <= 0.0663, net_IR <= 0.21.
|
|
||||||
# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q16_hmm_features.yaml \
|
|
||||||
# experiment_name=tac-rd-q16-hmm-features
|
|
||||||
{%- set LAKE = TAC_LAKE_DIR %}
|
|
||||||
{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
|
|
||||||
{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sp_hmm_p_regime1,sp_hmm_state" %}
|
|
||||||
|
|
||||||
qlib_init:
|
|
||||||
provider_uri: "{{ LAKE }}"
|
|
||||||
region: us
|
|
||||||
expression_cache: null
|
|
||||||
dataset_cache: null
|
|
||||||
calendar_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeCalendarProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
|
||||||
instrument_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeInstrumentProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
|
||||||
feature_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeFeatureProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
|
||||||
exp_manager:
|
|
||||||
class: MLflowExpManager
|
|
||||||
module_path: qlib.workflow.expm
|
|
||||||
kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q16-hmm-features" }
|
|
||||||
|
|
||||||
task:
|
|
||||||
model:
|
|
||||||
class: RankICEnsembleLGBModel
|
|
||||||
module_path: tac_qlib.contrib.model.rank_ensemble
|
|
||||||
kwargs:
|
|
||||||
loss: mse
|
|
||||||
learning_rate: 0.02
|
|
||||||
num_leaves: 31
|
|
||||||
n_estimators: 3000
|
|
||||||
num_boost_round: 3000
|
|
||||||
early_stopping_rounds: 200
|
|
||||||
min_data_in_leaf: 20
|
|
||||||
lambda_l2: 0.5
|
|
||||||
colsample_bytree: 0.8
|
|
||||||
subsample: 0.8
|
|
||||||
subsample_freq: 1
|
|
||||||
reg_alpha: 0.1
|
|
||||||
reg_lambda: 1.0
|
|
||||||
seeds: "42,7,2026,99,123"
|
|
||||||
|
|
||||||
dataset:
|
|
||||||
class: DatasetH
|
|
||||||
module_path: qlib.data.dataset
|
|
||||||
kwargs:
|
|
||||||
handler:
|
|
||||||
class: TACHandler
|
|
||||||
module_path: tac_qlib.contrib.data.handler
|
|
||||||
kwargs:
|
|
||||||
instruments: "{{ UNIVERSE }}"
|
|
||||||
start_time: 2015-01-03
|
|
||||||
end_time: 2026-08-10
|
|
||||||
fit_start_time: 2016-01-04
|
|
||||||
fit_end_time: 2025-09-01
|
|
||||||
freq: day
|
|
||||||
lake_root: "{{ LAKE }}"
|
|
||||||
market: US
|
|
||||||
label: "Ref($close,-6)/Ref($close,-1)-1"
|
|
||||||
feature_fields: "{{ FEATURES }}"
|
|
||||||
infer_processors:
|
|
||||||
- { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
|
||||||
- { class: ProcessInf, kwargs: {} }
|
|
||||||
- { class: CSRankNorm, kwargs: {} }
|
|
||||||
- { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
|
||||||
- { class: Fillna, kwargs: {} }
|
|
||||||
segments:
|
|
||||||
train: [2016-01-04, 2025-09-01]
|
|
||||||
valid: [2025-09-03, 2026-01-03]
|
|
||||||
test: [2026-01-04, 2026-08-10]
|
|
||||||
|
|
||||||
record:
|
|
||||||
- { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
|
|
||||||
- { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
|
|
||||||
- class: PortAnaRecord
|
|
||||||
module_path: qlib.workflow.record_temp
|
|
||||||
kwargs:
|
|
||||||
config:
|
|
||||||
strategy:
|
|
||||||
class: TopkDropoutStrategy
|
|
||||||
module_path: qlib.contrib.strategy
|
|
||||||
kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
|
|
||||||
backtest:
|
|
||||||
start_time: 2026-01-04
|
|
||||||
end_time: 2026-08-10
|
|
||||||
account: 1000000
|
|
||||||
benchmark: SPY
|
|
||||||
exchange_kwargs:
|
|
||||||
codes: "{{ UNIVERSE }}"
|
|
||||||
deal_price: $close
|
|
||||||
freq: day
|
|
||||||
open_cost: 0.0005
|
|
||||||
close_cost: 0.0015
|
|
||||||
min_cost: 5.0
|
|
||||||
risk_analysis_freq: 1d
|
|
||||||
@@ -1,105 +0,0 @@
|
|||||||
# QUEUE-17 — Realized-moments family added to the compact set.
|
|
||||||
# CLAIMS.md HYPOTHESIS: "Adding moment/volatility families regresses the signal"
|
|
||||||
# (idea: pre-clean-lake exp 11). M1 momentum bundle (exp 29) and M3 GARCH (exp 31)
|
|
||||||
# were refuted post-reset; the realized-moments family (sp_rskew/sp_rkurt/sp_dsv)
|
|
||||||
# has NOT been clean A/B'd. This run adds the moments columns to the compact set.
|
|
||||||
# Change vs exp-26 reference: features += sp_rskew_5,sp_rskew_22,sp_rkurt_5,sp_rkurt_22,sp_dsv_5,sp_dsv_22.
|
|
||||||
# Acceptance (prune-hypothesis): no improvement — RankIC <= 0.0663, net_IR <= 0.21.
|
|
||||||
# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q17_moments_features.yaml \
|
|
||||||
# experiment_name=tac-rd-q17-moments-features
|
|
||||||
{%- set LAKE = TAC_LAKE_DIR %}
|
|
||||||
{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
|
|
||||||
{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sp_rskew_5,sp_rskew_22,sp_rkurt_5,sp_rkurt_22,sp_dsv_5,sp_dsv_22" %}
|
|
||||||
|
|
||||||
qlib_init:
|
|
||||||
provider_uri: "{{ LAKE }}"
|
|
||||||
region: us
|
|
||||||
expression_cache: null
|
|
||||||
dataset_cache: null
|
|
||||||
calendar_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeCalendarProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
|
||||||
instrument_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeInstrumentProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
|
||||||
feature_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeFeatureProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
|
||||||
exp_manager:
|
|
||||||
class: MLflowExpManager
|
|
||||||
module_path: qlib.workflow.expm
|
|
||||||
kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q17-moments-features" }
|
|
||||||
|
|
||||||
task:
|
|
||||||
model:
|
|
||||||
class: RankICEnsembleLGBModel
|
|
||||||
module_path: tac_qlib.contrib.model.rank_ensemble
|
|
||||||
kwargs:
|
|
||||||
loss: mse
|
|
||||||
learning_rate: 0.02
|
|
||||||
num_leaves: 31
|
|
||||||
n_estimators: 3000
|
|
||||||
num_boost_round: 3000
|
|
||||||
early_stopping_rounds: 200
|
|
||||||
min_data_in_leaf: 20
|
|
||||||
lambda_l2: 0.5
|
|
||||||
colsample_bytree: 0.8
|
|
||||||
subsample: 0.8
|
|
||||||
subsample_freq: 1
|
|
||||||
reg_alpha: 0.1
|
|
||||||
reg_lambda: 1.0
|
|
||||||
seeds: "42,7,2026,99,123"
|
|
||||||
|
|
||||||
dataset:
|
|
||||||
class: DatasetH
|
|
||||||
module_path: qlib.data.dataset
|
|
||||||
kwargs:
|
|
||||||
handler:
|
|
||||||
class: TACHandler
|
|
||||||
module_path: tac_qlib.contrib.data.handler
|
|
||||||
kwargs:
|
|
||||||
instruments: "{{ UNIVERSE }}"
|
|
||||||
start_time: 2015-01-03
|
|
||||||
end_time: 2026-08-10
|
|
||||||
fit_start_time: 2016-01-04
|
|
||||||
fit_end_time: 2025-09-01
|
|
||||||
freq: day
|
|
||||||
lake_root: "{{ LAKE }}"
|
|
||||||
market: US
|
|
||||||
label: "Ref($close,-6)/Ref($close,-1)-1"
|
|
||||||
feature_fields: "{{ FEATURES }}"
|
|
||||||
infer_processors:
|
|
||||||
- { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
|
||||||
- { class: ProcessInf, kwargs: {} }
|
|
||||||
- { class: CSRankNorm, kwargs: {} }
|
|
||||||
- { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
|
||||||
- { class: Fillna, kwargs: {} }
|
|
||||||
segments:
|
|
||||||
train: [2016-01-04, 2025-09-01]
|
|
||||||
valid: [2025-09-03, 2026-01-03]
|
|
||||||
test: [2026-01-04, 2026-08-10]
|
|
||||||
|
|
||||||
record:
|
|
||||||
- { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
|
|
||||||
- { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
|
|
||||||
- class: PortAnaRecord
|
|
||||||
module_path: qlib.workflow.record_temp
|
|
||||||
kwargs:
|
|
||||||
config:
|
|
||||||
strategy:
|
|
||||||
class: TopkDropoutStrategy
|
|
||||||
module_path: qlib.contrib.strategy
|
|
||||||
kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
|
|
||||||
backtest:
|
|
||||||
start_time: 2026-01-04
|
|
||||||
end_time: 2026-08-10
|
|
||||||
account: 1000000
|
|
||||||
benchmark: SPY
|
|
||||||
exchange_kwargs:
|
|
||||||
codes: "{{ UNIVERSE }}"
|
|
||||||
deal_price: $close
|
|
||||||
freq: day
|
|
||||||
open_cost: 0.0005
|
|
||||||
close_cost: 0.0015
|
|
||||||
min_cost: 5.0
|
|
||||||
risk_analysis_freq: 1d
|
|
||||||
@@ -1,106 +0,0 @@
|
|||||||
# QUEUE-18 — OptimalStopControl clean re-test vs TopkDropout (exp 13/14 claim).
|
|
||||||
# CLAIMS.md HYPOTHESIS: "TopkDropout beats stochastic-control OptimalStopControl on
|
|
||||||
# the ensemble signal" — exp 13/14 were pre-clean-lake; never re-tested post-reset.
|
|
||||||
# Same compact signal as the exp-26 reference; ONLY the strategy changes to
|
|
||||||
# OptimalStopControl with exp-13 params (entry 0.85 / exit 0.7 / hold 10 / sl -0.08).
|
|
||||||
# PREREQUISITE: tac_qlib/contrib/strategy/optimal_stop.py must be synced to the venv
|
|
||||||
# site-packages snapshot before running (see /app/AGENTS.md).
|
|
||||||
# Acceptance: TopkDropout net_IR >= stop-control net_IR; document cost drag of both.
|
|
||||||
# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q18_optstop.yaml \
|
|
||||||
# experiment_name=tac-rd-q18-optstop
|
|
||||||
{%- set LAKE = TAC_LAKE_DIR %}
|
|
||||||
{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
|
|
||||||
{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
|
|
||||||
|
|
||||||
qlib_init:
|
|
||||||
provider_uri: "{{ LAKE }}"
|
|
||||||
region: us
|
|
||||||
expression_cache: null
|
|
||||||
dataset_cache: null
|
|
||||||
calendar_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeCalendarProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
|
||||||
instrument_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeInstrumentProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
|
||||||
feature_provider:
|
|
||||||
class: tac_qlib.data.providers.LakeFeatureProvider
|
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
|
||||||
exp_manager:
|
|
||||||
class: MLflowExpManager
|
|
||||||
module_path: qlib.workflow.expm
|
|
||||||
kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q18-optstop" }
|
|
||||||
|
|
||||||
task:
|
|
||||||
model:
|
|
||||||
class: RankICEnsembleLGBModel
|
|
||||||
module_path: tac_qlib.contrib.model.rank_ensemble
|
|
||||||
kwargs:
|
|
||||||
loss: mse
|
|
||||||
learning_rate: 0.02
|
|
||||||
num_leaves: 31
|
|
||||||
n_estimators: 3000
|
|
||||||
num_boost_round: 3000
|
|
||||||
early_stopping_rounds: 200
|
|
||||||
min_data_in_leaf: 20
|
|
||||||
lambda_l2: 0.5
|
|
||||||
colsample_bytree: 0.8
|
|
||||||
subsample: 0.8
|
|
||||||
subsample_freq: 1
|
|
||||||
reg_alpha: 0.1
|
|
||||||
reg_lambda: 1.0
|
|
||||||
seeds: "42,7,2026,99,123"
|
|
||||||
|
|
||||||
dataset:
|
|
||||||
class: DatasetH
|
|
||||||
module_path: qlib.data.dataset
|
|
||||||
kwargs:
|
|
||||||
handler:
|
|
||||||
class: TACHandler
|
|
||||||
module_path: tac_qlib.contrib.data.handler
|
|
||||||
kwargs:
|
|
||||||
instruments: "{{ UNIVERSE }}"
|
|
||||||
start_time: 2015-01-03
|
|
||||||
end_time: 2026-08-10
|
|
||||||
fit_start_time: 2016-01-04
|
|
||||||
fit_end_time: 2025-09-01
|
|
||||||
freq: day
|
|
||||||
lake_root: "{{ LAKE }}"
|
|
||||||
market: US
|
|
||||||
label: "Ref($close,-6)/Ref($close,-1)-1"
|
|
||||||
feature_fields: "{{ FEATURES }}"
|
|
||||||
infer_processors:
|
|
||||||
- { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
|
||||||
- { class: ProcessInf, kwargs: {} }
|
|
||||||
- { class: CSRankNorm, kwargs: {} }
|
|
||||||
- { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
|
|
||||||
- { class: Fillna, kwargs: {} }
|
|
||||||
segments:
|
|
||||||
train: [2016-01-04, 2025-09-01]
|
|
||||||
valid: [2025-09-03, 2026-01-03]
|
|
||||||
test: [2026-01-04, 2026-08-10]
|
|
||||||
|
|
||||||
record:
|
|
||||||
- { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
|
|
||||||
- { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
|
|
||||||
- class: PortAnaRecord
|
|
||||||
module_path: qlib.workflow.record_temp
|
|
||||||
kwargs:
|
|
||||||
config:
|
|
||||||
strategy:
|
|
||||||
class: OptimalStopControl
|
|
||||||
module_path: tac_qlib.contrib.strategy.optimal_stop
|
|
||||||
kwargs: { signal: "<PRED>", topk: 10, entry_pct: 0.85, exit_pct: 0.7, max_hold_days: 10, min_hold_days: 2, sl: -0.08 }
|
|
||||||
backtest:
|
|
||||||
start_time: 2026-01-04
|
|
||||||
end_time: 2026-08-10
|
|
||||||
account: 1000000
|
|
||||||
benchmark: SPY
|
|
||||||
exchange_kwargs:
|
|
||||||
codes: "{{ UNIVERSE }}"
|
|
||||||
deal_price: $close
|
|
||||||
freq: day
|
|
||||||
open_cost: 0.0005
|
|
||||||
close_cost: 0.0015
|
|
||||||
min_cost: 5.0
|
|
||||||
risk_analysis_freq: 1d
|
|
||||||
Reference in New Issue
Block a user