Compare commits
17
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 zhaoli
|
130484e4b8 | ||
|
zhaoli
|
22a57a81c6 | ||
|
zhaoli
|
513fcdf344 | ||
|
zhaoli
|
202589fc3e | ||
|
zhaoli
|
3ded27e5f9 | ||
|
zhaoli
|
125be7b96f | ||
|
zhaoli
|
20857f76be | ||
|
zhaoli
|
9c0cf096f8 | ||
|
zhaoli
|
80c7230e17 | ||
|
zhaoli
|
07e78c2bd9 | ||
|
zhaoli
|
e09ab7f05a | ||
|
zhaoli
|
337f6e17d8 | ||
|
zhaoli
|
7fad62a4ef | ||
|
zhaoli
|
f9ef005e9a | ||
|
zhaoli
|
c09997c7e2 | ||
|
zhaoli
|
32477c7bb8 | ||
|
zhaoli
|
e657c58758 |
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -1,48 +0,0 @@
|
|||||||
#!/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}")
|
|
||||||
@@ -1,115 +0,0 @@
|
|||||||
# 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
|
|
||||||
@@ -1,115 +0,0 @@
|
|||||||
# 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
|
|
||||||
+16
-20
@@ -1,35 +1,31 @@
|
|||||||
# TradeAC custom-qlib-code snapshot (auto-generated)
|
# TradeAC custom-qlib-code snapshot (auto-generated)
|
||||||
# parent repo HEAD : e952feed0a66a20439f4f24ad5524233429cd0c3
|
# parent repo HEAD : 22a57a81c62aa2d99f9362a50b52fb4c0d82d1c2
|
||||||
# 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
|
||||||
861592c63edd6a0853a9cb174b5970435b135fc8 tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
|
b419ee55ed455a1c45423d1c9025ca5cc0a98576 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
|
||||||
5c547a2ef92e075e550fe6d01508a2f1d3f536bc tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
|
2f6c67620aa2f9e6aaaef3369361d9b3eac3d6ca tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
|
||||||
4f656130d167e79dcaaeb7783a121f0b36852374 tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
|
fdd5923a70a399e8680913593ff111641947898e 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
|
||||||
b1489f2fc0dee85f0a4f90b2e6ad545ed9c8967b tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
|
08dec87ccdf6bb5d2cf611ca3032a4280aaab8cf tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
|
||||||
121ef237da1df1b8e21a561c3ad0db200b901339 tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
|
6fb61946ea9a83dfb560de3717f5fbf482c4c00e tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
|
||||||
74d0da348cbcc3700c96b6f4fe4391488e61efc5 tac-qlib/tac_qlib/contrib/model/__pycache__/rank_gbdt.cpython-312.pyc
|
3e80f2e08b661ddd2f58ffe5a6196063fa41ae51 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
|
||||||
2c2f167b693f4366a769998e3c9d4804f29e31e0 tac-qlib/tac_qlib/contrib/strategy/__init__.py
|
c4ef84ffda2a611262412fe1127689c667f3d0c1 tac-qlib/tac_qlib/contrib/strategy/__init__.py
|
||||||
f9cd9ab729e3248542ccc490af7adc2e51c71914 tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
|
6ad10c2ebe37c16417e67c7aeb731ad1fcb6da2f tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
|
||||||
cd3133cfbd2556b25c106e39ae97fb128df0e326 tac-qlib/tac_qlib/contrib/strategy/__pycache__/ic_gate.cpython-312.pyc
|
8d684b3216b040071d9ee4fa920a0e0c7486d278 tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
|
||||||
6dd1c568a2961842793674390d5abffd1a0e71b8 tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
|
896ef74ae47bcd1ed388e1e5d9c8d70c28097fe9 tac-qlib/tac_qlib/contrib/strategy/kelly_dropout.py
|
||||||
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
|
5b9acfb4340111b204249add7760bd53c6ae03f1 tac-qlib/tac_qlib/contrib/strategy/regime_gate.py
|
||||||
16ab80b731aab6d8bb818525615d77c2d1fcb0c8 tac-qlib/tac_qlib/contrib/strategy/signal_quality_gate.py
|
aa1ee880d52ceb5821d65973962099c2254f710a tac-qlib/tac_qlib/contrib/strategy/top_bottom.py
|
||||||
fe60bacdfedd48617863be31f24b7c7daebfac5a tac-qlib/tac_qlib/contrib/strategy/weekly_rebalance.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
|
||||||
316bf4aa160cc8d15929ea648be03f4b4999667d tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
|
7c4e6c345fad1978efe8860c0d977d0c02d6f8d9 tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
|
||||||
554a3f29d181b64effbf49a8161b32e7f93d8d3e tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
|
99e602392d51663cb06d5c425000b1ed1e5a916b tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
|
||||||
8b47f6d78ac046b6b7b2fb07bd7f3382773ffb73 tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc
|
020dcdcf288e4832c8cf2386351f78d5ceb4fe13 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.
@@ -1,11 +1,13 @@
|
|||||||
from .ic_gate import ICGateTopkDropoutStrategy # noqa: F401
|
from .kelly_dropout import FractionalKellyDropoutStrategy # noqa: F401
|
||||||
from .optimal_stop import OptimalStopControl # noqa: F401
|
from .optimal_stop import OptimalStopControl # noqa: F401
|
||||||
from .regime_gate import RegimeGateTopkDropoutStrategy # noqa: F401
|
from .regime_gate import RegimeGateDropoutStrategy # noqa: F401
|
||||||
|
from .top_bottom import TopBottomDropoutStrategy # noqa: F401
|
||||||
from .weekly_rebalance import WeeklyRebalanceDropoutStrategy # noqa: F401
|
from .weekly_rebalance import WeeklyRebalanceDropoutStrategy # noqa: F401
|
||||||
|
|
||||||
__all__ = [
|
__all__ = [
|
||||||
"ICGateTopkDropoutStrategy",
|
|
||||||
"OptimalStopControl",
|
"OptimalStopControl",
|
||||||
"RegimeGateTopkDropoutStrategy",
|
"FractionalKellyDropoutStrategy",
|
||||||
"WeeklyRebalanceDropoutStrategy",
|
"WeeklyRebalanceDropoutStrategy",
|
||||||
|
"TopBottomDropoutStrategy",
|
||||||
|
"RegimeGateDropoutStrategy",
|
||||||
]
|
]
|
||||||
|
|||||||
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.
@@ -1,117 +0,0 @@
|
|||||||
"""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 +1,201 @@
|
|||||||
|
"""Fractional-Kelly dropout strategy for cross-sectional signals.
|
||||||
|
|
||||||
|
Sizing rule variant of ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy``:
|
||||||
|
the topk/n_drop SELECTION is identical to the reference, but the buy size is
|
||||||
|
proportional to the score MAGNITUDE (edge) instead of equal-weight, capped at a
|
||||||
|
fraction ``cap_frac`` of the equal-weight notional so a single name cannot
|
||||||
|
over-concentrate the book.
|
||||||
|
|
||||||
|
``cap_frac`` is the fraction of the equal-weight per-name notional that a top
|
||||||
|
signal can deploy at most (e.g. 0.5 = at most half the equal-weight size).
|
||||||
|
Names whose score is below the median of the buy set get a proportionally
|
||||||
|
smaller slice; the residual stays in cash (that is the point of the rule:
|
||||||
|
throw away less edge per name, deploy less capital when conviction is low).
|
||||||
|
"""
|
||||||
|
|
||||||
|
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__ = ["FractionalKellyDropoutStrategy"]
|
||||||
|
|
||||||
|
DEFAULT_CAP_FRAC = 0.5
|
||||||
|
|
||||||
|
|
||||||
|
class FractionalKellyDropoutStrategy(TopkDropoutStrategy):
|
||||||
|
"""TopkDropout selection with score-magnitude (fractional-Kelly) sizing.
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
|
||||||
|
forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
|
||||||
|
cap_frac : max buy notional as a fraction of the equal-weight notional.
|
||||||
|
"""
|
||||||
|
|
||||||
|
def __init__(self, *, topk, n_drop, cap_frac: float = DEFAULT_CAP_FRAC, **kwargs):
|
||||||
|
super().__init__(topk=topk, n_drop=n_drop, **kwargs)
|
||||||
|
self.cap_frac = cap_frac
|
||||||
|
|
||||||
|
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)
|
||||||
|
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)
|
||||||
|
|
||||||
|
# ---- fractional-Kelly sizing --------------------------------------
|
||||||
|
# equal-weight notional (reference baseline)
|
||||||
|
eq_notional = cash * self.risk_degree / len(buy)
|
||||||
|
buy_scores = pred_score.reindex(buy).astype(float)
|
||||||
|
lo, hi = buy_scores.min(), buy_scores.max()
|
||||||
|
if hi == lo:
|
||||||
|
w = pd.Series(1.0, index=buy_scores.index)
|
||||||
|
else:
|
||||||
|
w = (buy_scores - lo) / (hi - lo) # [0,1] edge magnitude
|
||||||
|
w = w.clip(lower=0.0)
|
||||||
|
w_max = w.max()
|
||||||
|
w = w / w_max if w_max > 0 else w # max == 1.0
|
||||||
|
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
|
||||||
|
)
|
||||||
|
notional = eq_notional * min(self.cap_frac, float(w.get(code, 0.0)))
|
||||||
|
buy_amount = notional / 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)
|
||||||
@@ -1,215 +1,231 @@
|
|||||||
"""Regime-gate TopkDropout strategy.
|
"""HMM-regime overlay TopkDropout strategy.
|
||||||
|
|
||||||
Subclass of ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy`` that
|
Regime-gate overlay on ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy``:
|
||||||
holds the book (issues NO orders) while a regime detector says the market is in
|
selection and sizing are identical to the reference, but a name is only BOUGHT
|
||||||
an unfavorable state. When the gate is open it behaves exactly like the
|
(entry gate) when its per-symbol HMM regime posterior ``sp_hmm_p_regime1`` on
|
||||||
reference TopkDropoutStrategy.
|
the signal date is >= ``regime_threshold``; otherwise it is held in cash instead
|
||||||
|
of being opened.
|
||||||
|
|
||||||
Three detector types are supported (all causal — no lookahead):
|
The regime posterior is read from the lake feature provider on the fly via
|
||||||
|
``qlib.data.D.features`` (field ``$sp_hmm_p_regime1``) for the signal window, so
|
||||||
|
no regime column needs to enter the model's ``feature_fields`` — the gate is a
|
||||||
|
pure overlay (book ch.01: regime flags regressed as model features, survived
|
||||||
|
only as an overlay). The HMM itself was fit with ``fit_end=<train end>`` when
|
||||||
|
the lake features were backfilled, so there is no lookahead.
|
||||||
|
|
||||||
* ``dispersion``: cross-sectional standard deviation of 22-day rolling returns
|
Names already held are NOT force-sold when the regime turns unfavourable
|
||||||
across the universe. Gate closes when CS dispersion < threshold (low
|
(entry gate only, matching the queue-10 design).
|
||||||
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
|
from __future__ import annotations
|
||||||
|
|
||||||
|
from typing import List
|
||||||
|
|
||||||
|
import numpy as np
|
||||||
import pandas as pd
|
import pandas as pd
|
||||||
|
|
||||||
from qlib.backtest.decision import TradeDecisionWO
|
from qlib.backtest import Order
|
||||||
|
from qlib.backtest.decision import OrderDir, TradeDecisionWO
|
||||||
from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
|
from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
|
||||||
|
|
||||||
__all__ = ["RegimeGateTopkDropoutStrategy", "compute_regime_gate"]
|
try:
|
||||||
|
from qlib.data import D
|
||||||
|
except ImportError: # pragma: no cover - qlib always present in this stack
|
||||||
|
D = None
|
||||||
|
|
||||||
|
__all__ = ["RegimeGateDropoutStrategy"]
|
||||||
|
|
||||||
|
DEFAULT_REGIME_THRESHOLD = 0.5
|
||||||
|
REGIME_FIELD = "$sp_hmm_p_regime1"
|
||||||
|
|
||||||
|
|
||||||
class RegimeGateTopkDropoutStrategy(TopkDropoutStrategy):
|
class RegimeGateDropoutStrategy(TopkDropoutStrategy):
|
||||||
"""TopkDropout with a regime-gate circuit breaker.
|
"""TopkDropout with an HMM-regime entry gate on buy candidates.
|
||||||
|
|
||||||
Parameters
|
Parameters
|
||||||
----------
|
----------
|
||||||
topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
|
topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
|
||||||
forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
|
forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
|
||||||
regime_gate : pd.Series — precomputed per-date gate (bool indexed by
|
regime_threshold : minimum ``sp_hmm_p_regime1`` posterior required to open a
|
||||||
datetime). True = trade allowed, False = no orders. Missing dates
|
new position (default 0.5).
|
||||||
default to open (trade allowed).
|
|
||||||
"""
|
"""
|
||||||
|
|
||||||
def __init__(self, *, regime_gate=None, **kwargs):
|
def __init__(self, *, topk, n_drop, regime_threshold: float = DEFAULT_REGIME_THRESHOLD, **kwargs):
|
||||||
super().__init__(**kwargs)
|
super().__init__(topk=topk, n_drop=n_drop, **kwargs)
|
||||||
self._regime_gate = regime_gate
|
self.regime_threshold = regime_threshold
|
||||||
|
|
||||||
def _gate_open(self, trade_start_time) -> bool:
|
def _regime_for(self, codes, pred_start, pred_end) -> pd.Series:
|
||||||
if self._regime_gate is None:
|
"""Return {code: sp_hmm_p_regime1} for the signal window (last day)."""
|
||||||
return True
|
if D is None:
|
||||||
ts = pd.Timestamp(trade_start_time)
|
return pd.Series(dtype=float)
|
||||||
known = self._regime_gate[self._regime_gate.index <= ts]
|
try:
|
||||||
if len(known):
|
df = D.features(list(codes), [REGIME_FIELD], start_time=pred_start, end_time=pred_end, freq="day")
|
||||||
return bool(known.iloc[-1])
|
except Exception: # noqa: BLE001 - a regime read failure should gate open, not crash
|
||||||
return True # default open if no history yet
|
return pd.Series(dtype=float)
|
||||||
|
if df is None or len(df) == 0:
|
||||||
|
return pd.Series(dtype=float)
|
||||||
|
# df index is MultiIndex (datetime, instrument); take the last day's values
|
||||||
|
df = df.reset_index()
|
||||||
|
ts_col = "datetime" if "datetime" in df.columns else df.columns[0]
|
||||||
|
sym_col = "instrument" if "instrument" in df.columns else df.columns[1]
|
||||||
|
last_ts = df[ts_col].max()
|
||||||
|
last = df[df[ts_col] == last_ts]
|
||||||
|
out = {}
|
||||||
|
for _, row in last.iterrows():
|
||||||
|
sym = str(row[sym_col]).split("/")[-1].upper()
|
||||||
|
val = row.iloc[-1]
|
||||||
|
out[sym] = float(val) if val == val else np.nan
|
||||||
|
return pd.Series(out)
|
||||||
|
|
||||||
def generate_trade_decision(self, execute_result=None):
|
def generate_trade_decision(self, execute_result=None):
|
||||||
|
import copy
|
||||||
|
|
||||||
trade_step = self.trade_calendar.get_trade_step()
|
trade_step = self.trade_calendar.get_trade_step()
|
||||||
trade_start_time, _ = self.trade_calendar.get_step_time(trade_step)
|
trade_start_time, trade_end_time = self.trade_calendar.get_step_time(trade_step)
|
||||||
if not self._gate_open(trade_start_time):
|
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)
|
return TradeDecisionWO([], self)
|
||||||
return super().generate_trade_decision(execute_result)
|
|
||||||
|
|
||||||
|
if self.only_tradable:
|
||||||
|
|
||||||
# ---------------------------------------------------------------------------
|
def get_first_n(li, n, reverse=False):
|
||||||
# Precomputation helper
|
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 compute_regime_gate(
|
def get_last_n(li, n):
|
||||||
detector: str,
|
return get_first_n(li, n, reverse=True)
|
||||||
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
|
def filter_stock(li):
|
||||||
----------
|
return [
|
||||||
detector : str — ``"dispersion"``, ``"vol"``, or ``"hmm"``.
|
si
|
||||||
threshold : float — for ``dispersion``: min CS dispersion to allow trading.
|
for si in li
|
||||||
For ``hmm``: min HMM posterior to allow trading.
|
if self.trade_exchange.is_stock_tradable(
|
||||||
Ignored for ``vol`` (uses ``vol_low``/``vol_high`` band instead).
|
stock_id=si, start_time=trade_start_time, end_time=trade_end_time
|
||||||
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
|
else:
|
||||||
-------
|
|
||||||
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)
|
def get_first_n(li, n):
|
||||||
symbols = _universe_symbols(cfg)
|
return list(li)[:n]
|
||||||
close_df, vol_df = _load_daily_bars(symbols, cfg, start, end)
|
|
||||||
if close_df.empty:
|
|
||||||
return pd.Series(dtype=bool)
|
|
||||||
|
|
||||||
if detector == "dispersion":
|
def get_last_n(li, n):
|
||||||
return _dispersion_gate(close_df, threshold)
|
return list(li)[-n:]
|
||||||
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 filter_stock(li):
|
||||||
|
return li
|
||||||
|
|
||||||
def _universe_symbols(cfg) -> list:
|
current_temp: "object" = copy.deepcopy(self.trade_position)
|
||||||
"""Read symbols from the lake symbols.parquet."""
|
sell_order_list: List[Order] = []
|
||||||
import pathlib
|
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
|
||||||
|
|
||||||
sp = cfg.lake_root / "symbols.parquet"
|
if self.method_buy == "top":
|
||||||
if sp.exists():
|
today = get_first_n(
|
||||||
df = pd.read_parquet(sp)
|
pred_score[~pred_score.index.isin(last)].sort_values(ascending=False).index,
|
||||||
col = "symbol" if "symbol" in df.columns else df.columns[0]
|
self.n_drop + self.topk - len(last),
|
||||||
return sorted(df[col].astype(str).str.upper().tolist())
|
)
|
||||||
return []
|
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))
|
||||||
def _load_daily_bars(symbols, cfg, start, end):
|
n = self.n_drop + self.topk - len(last)
|
||||||
"""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:
|
try:
|
||||||
df = pd.read_parquet(p)
|
today = np.random.choice(candi, n, replace=False)
|
||||||
except Exception:
|
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)]
|
||||||
|
|
||||||
|
# ---- regime gate -----------------------------------------------------
|
||||||
|
if buy:
|
||||||
|
regime = self._regime_for(buy, pred_start_time, pred_end_time)
|
||||||
|
gated = [c for c in buy if regime.get(c, np.nan) >= self.regime_threshold]
|
||||||
|
else:
|
||||||
|
gated = []
|
||||||
|
|
||||||
|
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
|
continue
|
||||||
if hmm_field not in df.columns:
|
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(gated) == 0:
|
||||||
|
return TradeDecisionWO(sell_order_list, self)
|
||||||
|
|
||||||
|
value = cash * self.risk_degree / len(gated)
|
||||||
|
for code in gated:
|
||||||
|
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
|
continue
|
||||||
tcol = df["t"] if "t" in df.columns else df["date"]
|
buy_price = self.trade_exchange.get_deal_price(
|
||||||
ts = pd.to_datetime(tcol)
|
stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=OrderDir.BUY
|
||||||
s = pd.Series(df[hmm_field].values, index=ts, name=sym)
|
)
|
||||||
s = s.loc[start:end].dropna()
|
buy_amount = value / buy_price
|
||||||
if len(s) > 0:
|
factor = self.trade_exchange.get_factor(
|
||||||
all_posteriors[sym] = s
|
stock_id=code, start_time=trade_start_time, end_time=trade_end_time
|
||||||
break
|
)
|
||||||
if not all_posteriors:
|
buy_amount = self.trade_exchange.round_amount_by_trade_unit(buy_amount, factor)
|
||||||
# no HMM features found — default open
|
buy_order = Order(
|
||||||
idx = pd.date_range(start, end, freq="B")
|
stock_id=code,
|
||||||
return pd.Series(True, index=idx)
|
amount=buy_amount,
|
||||||
post_df = pd.DataFrame(all_posteriors)
|
start_time=trade_start_time,
|
||||||
cs_mean = post_df.mean(axis=1)
|
end_time=trade_end_time,
|
||||||
gate = cs_mean >= threshold
|
direction=Order.BUY,
|
||||||
return gate
|
)
|
||||||
|
buy_order_list.append(buy_order)
|
||||||
|
|
||||||
|
return TradeDecisionWO(sell_order_list + buy_order_list, self)
|
||||||
@@ -1,301 +0,0 @@
|
|||||||
"""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 +1,169 @@
|
|||||||
|
"""Market-neutral top/bottom long-short strategy for cross-sectional signals.
|
||||||
|
|
||||||
|
Captures the cross-sectional long-short spread net of costs: buys the top-ranked
|
||||||
|
``topk`` names and shorts the bottom-ranked ``topk`` names, equal-weight per
|
||||||
|
side, sized to ``risk_degree`` of total value per side. Rebalances daily to the
|
||||||
|
current rank (dropout-free: the book converges to the latest top/bottom sets).
|
||||||
|
|
||||||
|
The long and short legs use equal notional per side (gross exposure ~2x
|
||||||
|
``risk_degree`` of NAV, i.e. approximately market neutral before transaction
|
||||||
|
costs). Benchmark neutrality (SPY beta ~ 0) is the secondary sanity metric.
|
||||||
|
"""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
from typing import List
|
||||||
|
|
||||||
|
import copy
|
||||||
|
|
||||||
|
import pandas as pd
|
||||||
|
|
||||||
|
from qlib.backtest import Order
|
||||||
|
from qlib.backtest.decision import OrderDir, TradeDecisionWO
|
||||||
|
from qlib.contrib.strategy.signal_strategy import BaseSignalStrategy
|
||||||
|
|
||||||
|
__all__ = ["TopBottomDropoutStrategy"]
|
||||||
|
|
||||||
|
DEFAULT_SHORT_LEG = True
|
||||||
|
DEFAULT_REBALANCE_DAILY = True
|
||||||
|
|
||||||
|
|
||||||
|
class TopBottomDropoutStrategy(BaseSignalStrategy):
|
||||||
|
"""Long top-k / short bottom-k equal-weight market-neutral book.
|
||||||
|
|
||||||
|
Parameters
|
||||||
|
----------
|
||||||
|
topk : number of names on each side (long top-k and short bottom-k).
|
||||||
|
short_leg : whether to open the short side (if False, long-only topk).
|
||||||
|
rebalance_daily : if True rebalance to current rank every day; else keep
|
||||||
|
positions and only refresh on score changes (dropout-style).
|
||||||
|
risk_degree : fraction of total value deployed per side.
|
||||||
|
"""
|
||||||
|
|
||||||
|
def __init__(
|
||||||
|
self,
|
||||||
|
*,
|
||||||
|
topk: int = 10,
|
||||||
|
short_leg: bool = DEFAULT_SHORT_LEG,
|
||||||
|
rebalance_daily: bool = DEFAULT_REBALANCE_DAILY,
|
||||||
|
**kwargs,
|
||||||
|
):
|
||||||
|
super().__init__(**kwargs)
|
||||||
|
self.topk = topk
|
||||||
|
self.short_leg = short_leg
|
||||||
|
self.rebalance_daily = rebalance_daily
|
||||||
|
self._prev_longs = set()
|
||||||
|
self._prev_shorts = set()
|
||||||
|
|
||||||
|
def generate_trade_decision(self, execute_result=None):
|
||||||
|
trade_step = self.trade_calendar.get_trade_step()
|
||||||
|
trade_start_time, trade_end_time = self.trade_calendar.get_step_time(trade_step)
|
||||||
|
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 or len(pred_score) == 0:
|
||||||
|
return TradeDecisionWO([], self)
|
||||||
|
|
||||||
|
# rank all names; topk longs and topk shorts
|
||||||
|
ranked = pred_score.sort_values(ascending=False)
|
||||||
|
longs = list(ranked.index[: self.topk])
|
||||||
|
shorts = list(ranked.index[-self.topk :]) if self.short_leg else []
|
||||||
|
|
||||||
|
current_temp: "object" = copy.deepcopy(self.trade_position)
|
||||||
|
current_codes = set(current_temp.get_stock_list())
|
||||||
|
holdings = {c: current_temp for c in current_codes if abs(current_temp.get_stock_amount(c)) > 1e-6}
|
||||||
|
|
||||||
|
sell_orders: List[Order] = []
|
||||||
|
buy_orders: List[Order] = []
|
||||||
|
|
||||||
|
def _tradable(code, direction):
|
||||||
|
try:
|
||||||
|
return self.trade_exchange.is_stock_tradable(
|
||||||
|
stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=direction
|
||||||
|
)
|
||||||
|
except TypeError:
|
||||||
|
return self.trade_exchange.is_stock_tradable(
|
||||||
|
stock_id=code, start_time=trade_start_time, end_time=trade_end_time
|
||||||
|
)
|
||||||
|
|
||||||
|
# determine target set (long/short)
|
||||||
|
target_longs = set(longs)
|
||||||
|
target_shorts = set(shorts)
|
||||||
|
|
||||||
|
# close positions not in the target book
|
||||||
|
for code in list(holdings):
|
||||||
|
if code in target_longs or code in target_shorts:
|
||||||
|
continue
|
||||||
|
amt = abs(current_temp.get_stock_amount(code))
|
||||||
|
o = Order(
|
||||||
|
stock_id=code,
|
||||||
|
amount=amt,
|
||||||
|
start_time=trade_start_time,
|
||||||
|
end_time=trade_end_time,
|
||||||
|
direction=Order.SELL if code in target_longs else Order.SELL,
|
||||||
|
)
|
||||||
|
if self.trade_exchange.check_order(o):
|
||||||
|
sell_orders.append(o)
|
||||||
|
self.trade_exchange.deal_order(o, position=current_temp)
|
||||||
|
|
||||||
|
# equal-weight notional per side
|
||||||
|
total_value = current_temp.get_cash()
|
||||||
|
for code, pos in holdings.items():
|
||||||
|
if code in target_longs or code in target_shorts:
|
||||||
|
mark = self.trade_exchange.get_deal_price(
|
||||||
|
stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=Order.SELL
|
||||||
|
)
|
||||||
|
if mark is not None and mark == mark:
|
||||||
|
total_value += abs(current_temp.get_stock_amount(code)) * mark
|
||||||
|
|
||||||
|
side_notional = total_value * self.risk_degree / max(1, self.topk)
|
||||||
|
|
||||||
|
for code in longs:
|
||||||
|
if code in holdings and abs(current_temp.get_stock_amount(code)) > 1e-6:
|
||||||
|
continue
|
||||||
|
px = self.trade_exchange.get_deal_price(
|
||||||
|
stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=Order.BUY
|
||||||
|
)
|
||||||
|
if px is None or px != px or px <= 0:
|
||||||
|
continue
|
||||||
|
amount = side_notional / px
|
||||||
|
factor = self.trade_exchange.get_factor(
|
||||||
|
stock_id=code, start_time=trade_start_time, end_time=trade_end_time
|
||||||
|
)
|
||||||
|
amount = self.trade_exchange.round_amount_by_trade_unit(amount, factor)
|
||||||
|
o = Order(
|
||||||
|
stock_id=code,
|
||||||
|
amount=amount,
|
||||||
|
start_time=trade_start_time,
|
||||||
|
end_time=trade_end_time,
|
||||||
|
direction=Order.BUY,
|
||||||
|
)
|
||||||
|
if self.trade_exchange.check_order(o):
|
||||||
|
buy_orders.append(o)
|
||||||
|
|
||||||
|
if self.short_leg:
|
||||||
|
for code in shorts:
|
||||||
|
if code in holdings and abs(current_temp.get_stock_amount(code)) > 1e-6:
|
||||||
|
continue
|
||||||
|
px = self.trade_exchange.get_deal_price(
|
||||||
|
stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=Order.SELL
|
||||||
|
)
|
||||||
|
if px is None or px != px or px <= 0:
|
||||||
|
continue
|
||||||
|
amount = side_notional / px
|
||||||
|
factor = self.trade_exchange.get_factor(
|
||||||
|
stock_id=code, start_time=trade_start_time, end_time=trade_end_time
|
||||||
|
)
|
||||||
|
amount = self.trade_exchange.round_amount_by_trade_unit(amount, factor)
|
||||||
|
o = Order(
|
||||||
|
stock_id=code,
|
||||||
|
amount=amount,
|
||||||
|
start_time=trade_start_time,
|
||||||
|
end_time=trade_end_time,
|
||||||
|
direction=Order.SELL,
|
||||||
|
)
|
||||||
|
if self.trade_exchange.check_order(o):
|
||||||
|
sell_orders.append(o)
|
||||||
|
|
||||||
|
return TradeDecisionWO(sell_orders + buy_orders, self)
|
||||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -1,44 +1,76 @@
|
|||||||
# Signal-quality gate backtest for 2026
|
# QUEUE-me
|
||||||
|
# HMM regime overlay (Q10): identical TopkDropout selection, entry gated on sp_hmm_p_regime1 >= 0.5.
|
||||||
|
# Acceptance: net_max_drawdown < 7.69% AND net_IR >= 0.21. No regime column enters feature_fields.
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
{%- set LAKE = TAC_LAKE_DIR %}
|
{%- 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 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 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" %}
|
||||||
{# Gate computed on-the-fly from signal + lake close prices #}
|
|
||||||
|
|
||||||
qlib_init:
|
qlib_init:
|
||||||
provider_uri: "{{ LAKE }}"
|
provider_uri: "{{ LAKE }}"
|
||||||
region: us
|
region: us
|
||||||
expression_cache: null
|
expression_cache: null
|
||||||
dataset_cache: null
|
dataset_cache: null
|
||||||
|
|
||||||
calendar_provider:
|
calendar_provider:
|
||||||
class: tac_qlib.data.providers.LakeCalendarProvider
|
class: tac_qlib.data.providers.LakeCalendarProvider
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
kwargs:
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
instrument_provider:
|
instrument_provider:
|
||||||
class: tac_qlib.data.providers.LakeInstrumentProvider
|
class: tac_qlib.data.providers.LakeInstrumentProvider
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
kwargs:
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
markets: {}
|
||||||
feature_provider:
|
feature_provider:
|
||||||
class: tac_qlib.data.providers.LakeFeatureProvider
|
class: tac_qlib.data.providers.LakeFeatureProvider
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
kwargs:
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
|
||||||
exp_manager:
|
exp_manager:
|
||||||
class: MLflowExpManager
|
class: MLflowExpManager
|
||||||
module_path: qlib.workflow.expm
|
module_path: qlib.workflow.expm
|
||||||
kwargs:
|
kwargs:
|
||||||
uri: "sqlite:///{{ LAKE }}/mlruns.db"
|
uri: "sqlite:///{{ LAKE }}/mlruns.db"
|
||||||
default_exp_name: "tac-rd-sq-gate-2026"
|
default_exp_name: "tac-rd-q10-regime"
|
||||||
|
|
||||||
task:
|
task:
|
||||||
model:
|
model:
|
||||||
class: LGBModel
|
class: RankICEnsembleLGBModel
|
||||||
module_path: qlib.contrib.model.gbdt
|
module_path: tac_qlib.contrib.model.rank_ensemble
|
||||||
kwargs:
|
kwargs:
|
||||||
loss: mse
|
loss: mse
|
||||||
learning_rate: 0.05
|
learning_rate: 0.02
|
||||||
num_leaves: 15
|
num_leaves: 31
|
||||||
n_estimators: 200
|
n_estimators: 3000
|
||||||
|
num_boost_round: 3000
|
||||||
|
early_stopping_rounds: 200
|
||||||
|
min_data_in_leaf: 20
|
||||||
|
lambda_l2: 0.5
|
||||||
colsample_bytree: 0.8
|
colsample_bytree: 0.8
|
||||||
subsample: 0.8
|
subsample: 0.8
|
||||||
subsample_freq: 1
|
subsample_freq: 1
|
||||||
reg_alpha: 0.01
|
reg_alpha: 0.1
|
||||||
reg_lambda: 0.01
|
reg_lambda: 1.0
|
||||||
|
seeds: "42,7,2026,99,123"
|
||||||
|
parallel: 5
|
||||||
|
|
||||||
dataset:
|
dataset:
|
||||||
class: DatasetH
|
class: DatasetH
|
||||||
@@ -51,13 +83,13 @@ task:
|
|||||||
instruments: "{{ UNIVERSE }}"
|
instruments: "{{ UNIVERSE }}"
|
||||||
start_time: 2015-01-03
|
start_time: 2015-01-03
|
||||||
end_time: 2026-08-10
|
end_time: 2026-08-10
|
||||||
fit_start_time: 2015-01-03
|
fit_start_time: 2016-01-04
|
||||||
fit_end_time: 2026-01-03
|
fit_end_time: 2025-09-01
|
||||||
freq: day
|
freq: day
|
||||||
lake_root: "{{ LAKE }}"
|
lake_root: "{{ LAKE }}"
|
||||||
market: US
|
market: US
|
||||||
label: "Ref($close,-6)/Ref($close,-1)-1"
|
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||||
feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
|
feature_fields: "{{ FEATURES }}"
|
||||||
infer_processors:
|
infer_processors:
|
||||||
- class: DropAllNaN
|
- class: DropAllNaN
|
||||||
kwargs: {}
|
kwargs: {}
|
||||||
@@ -70,7 +102,7 @@ task:
|
|||||||
- class: Fillna
|
- class: Fillna
|
||||||
kwargs: {}
|
kwargs: {}
|
||||||
segments:
|
segments:
|
||||||
train: [2015-01-03, 2025-09-01]
|
train: [2016-01-04, 2025-09-01]
|
||||||
valid: [2025-09-03, 2026-01-03]
|
valid: [2025-09-03, 2026-01-03]
|
||||||
test: [2026-01-04, 2026-08-10]
|
test: [2026-01-04, 2026-08-10]
|
||||||
|
|
||||||
@@ -80,26 +112,23 @@ task:
|
|||||||
kwargs: {}
|
kwargs: {}
|
||||||
- class: SigAnaRecord
|
- class: SigAnaRecord
|
||||||
module_path: qlib.workflow.record_temp
|
module_path: qlib.workflow.record_temp
|
||||||
kwargs: { ana_long_short: true, ann_scaler: 252 }
|
kwargs:
|
||||||
|
ana_long_short: true
|
||||||
|
ann_scaler: 252
|
||||||
- class: PortAnaRecord
|
- class: PortAnaRecord
|
||||||
module_path: qlib.workflow.record_temp
|
module_path: qlib.workflow.record_temp
|
||||||
kwargs:
|
kwargs:
|
||||||
config:
|
config:
|
||||||
strategy:
|
strategy:
|
||||||
class: SignalQualityGateStrategy
|
class: RegimeGateDropoutStrategy
|
||||||
module_path: tac_qlib.contrib.strategy.signal_quality_gate
|
module_path: tac_qlib.contrib.strategy.regime_gate
|
||||||
kwargs:
|
kwargs:
|
||||||
signal: "<PRED>"
|
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
|
topk: 10
|
||||||
n_drop: 1
|
n_drop: 1
|
||||||
only_tradable: true
|
only_tradable: true
|
||||||
risk_degree: 0.95
|
risk_degree: 0.95
|
||||||
|
regime_threshold: 0.5
|
||||||
backtest:
|
backtest:
|
||||||
start_time: 2026-01-04
|
start_time: 2026-01-04
|
||||||
end_time: 2026-08-10
|
end_time: 2026-08-10
|
||||||
+23
-19
@@ -1,16 +1,16 @@
|
|||||||
# -----------------------------------------------------------------------------
|
# -----------------------------------------------------------------------------
|
||||||
# Signal-quality gate: TopkDropout gated by rolling hit-rate of topk picks.
|
# ABLATION A (baseline): LightGBM with RankIC early-stopping on the 50-ETF SP-5d
|
||||||
|
# panel, using ALL 24 sp_* feature columns (ou,hmm,jump,har,trend,hurst,
|
||||||
|
# signature). Copy of the canonical workflow_lgb_sp5d_rankic.yaml with a
|
||||||
|
# distinct experiment name so the ablation runs are isolated.
|
||||||
#
|
#
|
||||||
# 1. Compute the gate: python precompute_signal_quality_gate.py <pred.pkl> <gate.pkl>
|
# Run:
|
||||||
# 2. Run this workflow: rd_run_workflow config_path=<this yaml> experiment_name=<exp>
|
# rd_run_workflow config_path=tac-qlib/workflows/ablate_baseline_all_sp_fields.yaml \
|
||||||
#
|
# experiment_name=tac-rd-rank-ablate
|
||||||
# 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 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 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 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:
|
qlib_init:
|
||||||
provider_uri: "{{ LAKE }}"
|
provider_uri: "{{ LAKE }}"
|
||||||
@@ -40,22 +40,27 @@ qlib_init:
|
|||||||
module_path: qlib.workflow.expm
|
module_path: qlib.workflow.expm
|
||||||
kwargs:
|
kwargs:
|
||||||
uri: "sqlite:///{{ LAKE }}/mlruns.db"
|
uri: "sqlite:///{{ LAKE }}/mlruns.db"
|
||||||
default_exp_name: "tac-rd-sq-gate"
|
default_exp_name: "tac-rd-rank-ablate"
|
||||||
|
|
||||||
task:
|
task:
|
||||||
model:
|
model:
|
||||||
class: LGBModel
|
class: RankICLGBModel
|
||||||
module_path: qlib.contrib.model.gbdt
|
module_path: tac_qlib.contrib.model.rank_gbdt
|
||||||
kwargs:
|
kwargs:
|
||||||
loss: mse
|
loss: mse
|
||||||
learning_rate: 0.05
|
learning_rate: 0.02
|
||||||
num_leaves: 15
|
num_leaves: 31
|
||||||
n_estimators: 200
|
n_estimators: 3000
|
||||||
|
num_boost_round: 3000
|
||||||
|
early_stopping_rounds: 200
|
||||||
|
min_data_in_leaf: 20
|
||||||
|
lambda_l2: 0.5
|
||||||
colsample_bytree: 0.8
|
colsample_bytree: 0.8
|
||||||
subsample: 0.8
|
subsample: 0.8
|
||||||
subsample_freq: 1
|
subsample_freq: 1
|
||||||
reg_alpha: 0.01
|
reg_alpha: 0.1
|
||||||
reg_lambda: 0.01
|
reg_lambda: 1.0
|
||||||
|
seed: 42
|
||||||
|
|
||||||
dataset:
|
dataset:
|
||||||
class: DatasetH
|
class: DatasetH
|
||||||
@@ -105,13 +110,12 @@ task:
|
|||||||
kwargs:
|
kwargs:
|
||||||
config:
|
config:
|
||||||
strategy:
|
strategy:
|
||||||
class: SignalQualityGateStrategy
|
class: TopkDropoutStrategy
|
||||||
module_path: tac_qlib.contrib.strategy.signal_quality_gate
|
module_path: qlib.contrib.strategy
|
||||||
kwargs:
|
kwargs:
|
||||||
signal: "<PRED>"
|
signal: "<PRED>"
|
||||||
signal_quality_gate_path: "{{ GATE_PATH }}"
|
|
||||||
topk: 10
|
topk: 10
|
||||||
n_drop: 1
|
n_drop: 2
|
||||||
only_tradable: true
|
only_tradable: true
|
||||||
risk_degree: 0.95
|
risk_degree: 0.95
|
||||||
backtest:
|
backtest:
|
||||||
+48
-29
@@ -1,44 +1,67 @@
|
|||||||
# Signal-quality gate backtest for 2025
|
# -----------------------------------------------------------------------------
|
||||||
|
# ABLATION B (generic-only): same panel/model as the baseline, but feature
|
||||||
|
# fields restricted to the model-free / generic stochastic-process families
|
||||||
|
# (jump,har,trend,hurst,signature). Drops the model-specific ou (OU/AR-1
|
||||||
|
# half-life) and hmm (2-state regime) families to test whether the generic
|
||||||
|
# families alone dominate the rank dimension.
|
||||||
|
#
|
||||||
|
# Run:
|
||||||
|
# rd_run_workflow config_path=tac-qlib/workflows/ablate_generic_only_sp_fields.yaml \
|
||||||
|
# experiment_name=tac-rd-rank-ablate
|
||||||
|
# -----------------------------------------------------------------------------
|
||||||
{%- set LAKE = TAC_LAKE_DIR %}
|
{%- 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 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 SP_FIELDS = "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" %}
|
||||||
{# Gate computed on-the-fly from signal + lake close prices #}
|
|
||||||
|
|
||||||
qlib_init:
|
qlib_init:
|
||||||
provider_uri: "{{ LAKE }}"
|
provider_uri: "{{ LAKE }}"
|
||||||
region: us
|
region: us
|
||||||
expression_cache: null
|
expression_cache: null
|
||||||
dataset_cache: null
|
dataset_cache: null
|
||||||
|
|
||||||
calendar_provider:
|
calendar_provider:
|
||||||
class: tac_qlib.data.providers.LakeCalendarProvider
|
class: tac_qlib.data.providers.LakeCalendarProvider
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
kwargs:
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
instrument_provider:
|
instrument_provider:
|
||||||
class: tac_qlib.data.providers.LakeInstrumentProvider
|
class: tac_qlib.data.providers.LakeInstrumentProvider
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
kwargs:
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
markets: {}
|
||||||
feature_provider:
|
feature_provider:
|
||||||
class: tac_qlib.data.providers.LakeFeatureProvider
|
class: tac_qlib.data.providers.LakeFeatureProvider
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
kwargs:
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
|
||||||
exp_manager:
|
exp_manager:
|
||||||
class: MLflowExpManager
|
class: MLflowExpManager
|
||||||
module_path: qlib.workflow.expm
|
module_path: qlib.workflow.expm
|
||||||
kwargs:
|
kwargs:
|
||||||
uri: "sqlite:///{{ LAKE }}/mlruns.db"
|
uri: "sqlite:///{{ LAKE }}/mlruns.db"
|
||||||
default_exp_name: "tac-rd-sq-gate-2025"
|
default_exp_name: "tac-rd-rank-ablate"
|
||||||
|
|
||||||
task:
|
task:
|
||||||
model:
|
model:
|
||||||
class: LGBModel
|
class: RankICLGBModel
|
||||||
module_path: qlib.contrib.model.gbdt
|
module_path: tac_qlib.contrib.model.rank_gbdt
|
||||||
kwargs:
|
kwargs:
|
||||||
loss: mse
|
loss: mse
|
||||||
learning_rate: 0.05
|
learning_rate: 0.02
|
||||||
num_leaves: 15
|
num_leaves: 31
|
||||||
n_estimators: 200
|
n_estimators: 3000
|
||||||
|
num_boost_round: 3000
|
||||||
|
early_stopping_rounds: 200
|
||||||
|
min_data_in_leaf: 20
|
||||||
|
lambda_l2: 0.5
|
||||||
colsample_bytree: 0.8
|
colsample_bytree: 0.8
|
||||||
subsample: 0.8
|
subsample: 0.8
|
||||||
subsample_freq: 1
|
subsample_freq: 1
|
||||||
reg_alpha: 0.01
|
reg_alpha: 0.1
|
||||||
reg_lambda: 0.01
|
reg_lambda: 1.0
|
||||||
|
seed: 42
|
||||||
|
|
||||||
dataset:
|
dataset:
|
||||||
class: DatasetH
|
class: DatasetH
|
||||||
@@ -50,9 +73,9 @@ task:
|
|||||||
kwargs:
|
kwargs:
|
||||||
instruments: "{{ UNIVERSE }}"
|
instruments: "{{ UNIVERSE }}"
|
||||||
start_time: 2015-01-03
|
start_time: 2015-01-03
|
||||||
end_time: 2025-12-31
|
end_time: 2026-08-10
|
||||||
fit_start_time: 2015-01-03
|
fit_start_time: 2015-01-03
|
||||||
fit_end_time: 2026-01-03
|
fit_end_time: 2025-09-01
|
||||||
freq: day
|
freq: day
|
||||||
lake_root: "{{ LAKE }}"
|
lake_root: "{{ LAKE }}"
|
||||||
market: US
|
market: US
|
||||||
@@ -72,7 +95,7 @@ task:
|
|||||||
segments:
|
segments:
|
||||||
train: [2015-01-03, 2025-09-01]
|
train: [2015-01-03, 2025-09-01]
|
||||||
valid: [2025-09-03, 2026-01-03]
|
valid: [2025-09-03, 2026-01-03]
|
||||||
test: [2025-01-02, 2025-12-31]
|
test: [2026-01-04, 2026-08-10]
|
||||||
|
|
||||||
record:
|
record:
|
||||||
- class: SignalRecord
|
- class: SignalRecord
|
||||||
@@ -80,29 +103,25 @@ task:
|
|||||||
kwargs: {}
|
kwargs: {}
|
||||||
- class: SigAnaRecord
|
- class: SigAnaRecord
|
||||||
module_path: qlib.workflow.record_temp
|
module_path: qlib.workflow.record_temp
|
||||||
kwargs: { ana_long_short: true, ann_scaler: 252 }
|
kwargs:
|
||||||
|
ana_long_short: true
|
||||||
|
ann_scaler: 252
|
||||||
- class: PortAnaRecord
|
- class: PortAnaRecord
|
||||||
module_path: qlib.workflow.record_temp
|
module_path: qlib.workflow.record_temp
|
||||||
kwargs:
|
kwargs:
|
||||||
config:
|
config:
|
||||||
strategy:
|
strategy:
|
||||||
class: SignalQualityGateStrategy
|
class: TopkDropoutStrategy
|
||||||
module_path: tac_qlib.contrib.strategy.signal_quality_gate
|
module_path: qlib.contrib.strategy
|
||||||
kwargs:
|
kwargs:
|
||||||
signal: "<PRED>"
|
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
|
topk: 10
|
||||||
n_drop: 1
|
n_drop: 2
|
||||||
only_tradable: true
|
only_tradable: true
|
||||||
risk_degree: 0.95
|
risk_degree: 0.95
|
||||||
backtest:
|
backtest:
|
||||||
start_time: 2025-01-02
|
start_time: 2026-01-04
|
||||||
end_time: 2025-12-31
|
end_time: 2026-08-10
|
||||||
account: 1000000
|
account: 1000000
|
||||||
benchmark: SPY
|
benchmark: SPY
|
||||||
exchange_kwargs:
|
exchange_kwargs:
|
||||||
@@ -0,0 +1,141 @@
|
|||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
# ISOLATION: multi-seed RankIC ensemble, ablate-B generic-only feature set.
|
||||||
|
#
|
||||||
|
# Isolates the ensemble effect on the SP-5d rank signal. Same panel, segments,
|
||||||
|
# history (full backfilled 2016+) and feature set as the exp-9 ablate-B winner
|
||||||
|
# (generic-only sp_* families: jump,har,trend,hurst,signature), but replaces the
|
||||||
|
# single RankICLGBModel with a 5-seed RankICEnsembleLGBModel (42,7,2026,99,123)
|
||||||
|
# that averages per-day predictions.
|
||||||
|
#
|
||||||
|
# Differs from exp-15 (tac-rd-rank-ensemble, mlflow exp 15) ONLY by dropping the
|
||||||
|
# TA subset (rsi_14,roc_10,macd_hist,willr_14,atr_14) and the inter-asset xr_*
|
||||||
|
# features, so any change vs exp-15 is attributable to the feature set alone,
|
||||||
|
# and any change vs exp-9 is attributable to the ensemble + full history alone.
|
||||||
|
#
|
||||||
|
# Run:
|
||||||
|
# rd_run_workflow config_path=experiments/workflows/exp12_isolation_ensemble.yaml \
|
||||||
|
# experiment_name=tac-rd-rank-ensemble-isolated
|
||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
{%- 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_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-rank-ensemble-isolated"
|
||||||
|
|
||||||
|
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: 2026-08-14
|
||||||
|
fit_start_time: 2016-01-04
|
||||||
|
fit_end_time: 2025-09-01
|
||||||
|
freq: day
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||||
|
feature_fields: "$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: [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: 2
|
||||||
|
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 +1,141 @@
|
|||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
# EXP 18 - Risk-limit control: reference model + TopkDropout baseline (A).
|
||||||
|
#
|
||||||
|
# Signal/model identical to the reference (tac-rd-rank-ensemble-isolated,
|
||||||
|
# run 0cea66d9...): RankICEnsembleLGBModel (parallel, 5 seeds) on the 50-ETF
|
||||||
|
# SP-5d panel, test 2026-01-04..2026-08-10. This workflow reproduces the
|
||||||
|
# unconstrained TopkDropout baseline net-of-cost so the risk-limited variant
|
||||||
|
# (same pred, liquidity/size/concentration caps) can be compared 1:1.
|
||||||
|
#
|
||||||
|
# The risk_limits spec itself is applied via rd_backtest / rd_strategy_targets
|
||||||
|
# (tool-level param, not a YAML key); this run records the unconstrained
|
||||||
|
# baseline that the limit A/B is measured against.
|
||||||
|
#
|
||||||
|
# Run:
|
||||||
|
# rd_run_workflow config_path=experiments/workflows/exp18-risk-limit/a_baseline.yaml \
|
||||||
|
# experiment_name=tac-rd-risk-limit
|
||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
{%- 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_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:///{{ LAKE }}/mlruns.db"
|
||||||
|
default_exp_name: "tac-rd-risk-limit"
|
||||||
|
|
||||||
|
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"
|
||||||
|
parallel: 5
|
||||||
|
|
||||||
|
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: 2026-08-14
|
||||||
|
fit_start_time: 2016-01-04
|
||||||
|
fit_end_time: 2025-09-01
|
||||||
|
freq: day
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||||
|
feature_fields: "$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: [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: 2
|
||||||
|
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 +1,135 @@
|
|||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
|
||||||
|
#
|
||||||
|
# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
|
||||||
|
# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
|
||||||
|
# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
|
||||||
|
#
|
||||||
|
# Run:
|
||||||
|
# rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
|
||||||
|
# experiment_name=tac-rd-risk-limit
|
||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
{%- 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_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:///{{ LAKE }}/mlruns.db"
|
||||||
|
default_exp_name: "tac-rd-risk-limit"
|
||||||
|
|
||||||
|
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"
|
||||||
|
parallel: 5
|
||||||
|
|
||||||
|
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: 2026-08-14
|
||||||
|
fit_start_time: 2016-01-04
|
||||||
|
fit_end_time: 2025-09-01
|
||||||
|
freq: day
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||||
|
feature_fields: "$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: [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: 2
|
||||||
|
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 +1,135 @@
|
|||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
|
||||||
|
#
|
||||||
|
# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
|
||||||
|
# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
|
||||||
|
# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
|
||||||
|
#
|
||||||
|
# Run:
|
||||||
|
# rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
|
||||||
|
# experiment_name=tac-rd-risk-limit
|
||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
{%- 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_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:///{{ LAKE }}/mlruns.db"
|
||||||
|
default_exp_name: "tac-rd-risk-limit"
|
||||||
|
|
||||||
|
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"
|
||||||
|
parallel: 1
|
||||||
|
|
||||||
|
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: 2026-08-14
|
||||||
|
fit_start_time: 2016-01-04
|
||||||
|
fit_end_time: 2025-09-01
|
||||||
|
freq: day
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||||
|
feature_fields: "$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: [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: 2
|
||||||
|
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
|
||||||
+52
-32
@@ -1,44 +1,68 @@
|
|||||||
# Signal-quality gate backtest for 2023
|
# -----------------------------------------------------------------------------
|
||||||
|
# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
|
||||||
|
#
|
||||||
|
# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
|
||||||
|
# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
|
||||||
|
# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
|
||||||
|
#
|
||||||
|
# Run:
|
||||||
|
# rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
|
||||||
|
# experiment_name=tac-rd-risk-limit
|
||||||
|
# -----------------------------------------------------------------------------
|
||||||
{%- set LAKE = TAC_LAKE_DIR %}
|
{%- 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 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 SP_FIELDS = "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" %}
|
||||||
{# Gate computed on-the-fly from signal + lake close prices #}
|
|
||||||
|
|
||||||
qlib_init:
|
qlib_init:
|
||||||
provider_uri: "{{ LAKE }}"
|
provider_uri: "{{ LAKE }}"
|
||||||
region: us
|
region: us
|
||||||
expression_cache: null
|
expression_cache: null
|
||||||
dataset_cache: null
|
dataset_cache: null
|
||||||
|
|
||||||
calendar_provider:
|
calendar_provider:
|
||||||
class: tac_qlib.data.providers.LakeCalendarProvider
|
class: tac_qlib.data.providers.LakeCalendarProvider
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
kwargs:
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
instrument_provider:
|
instrument_provider:
|
||||||
class: tac_qlib.data.providers.LakeInstrumentProvider
|
class: tac_qlib.data.providers.LakeInstrumentProvider
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
|
kwargs:
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
markets: {}
|
||||||
feature_provider:
|
feature_provider:
|
||||||
class: tac_qlib.data.providers.LakeFeatureProvider
|
class: tac_qlib.data.providers.LakeFeatureProvider
|
||||||
kwargs: { lake_root: "{{ LAKE }}", market: US }
|
kwargs:
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
|
||||||
exp_manager:
|
exp_manager:
|
||||||
class: MLflowExpManager
|
class: MLflowExpManager
|
||||||
module_path: qlib.workflow.expm
|
module_path: qlib.workflow.expm
|
||||||
kwargs:
|
kwargs:
|
||||||
uri: "sqlite:///{{ LAKE }}/mlruns.db"
|
uri: "sqlite:///{{ LAKE }}/mlruns.db"
|
||||||
default_exp_name: "tac-rd-sq-gate-2023"
|
default_exp_name: "tac-rd-risk-limit"
|
||||||
|
|
||||||
task:
|
task:
|
||||||
model:
|
model:
|
||||||
class: LGBModel
|
class: RankICEnsembleLGBModel
|
||||||
module_path: qlib.contrib.model.gbdt
|
module_path: tac_qlib.contrib.model.rank_ensemble
|
||||||
kwargs:
|
kwargs:
|
||||||
loss: mse
|
loss: mse
|
||||||
learning_rate: 0.05
|
learning_rate: 0.02
|
||||||
num_leaves: 15
|
num_leaves: 31
|
||||||
n_estimators: 200
|
n_estimators: 3000
|
||||||
|
num_boost_round: 3000
|
||||||
|
early_stopping_rounds: 200
|
||||||
|
min_data_in_leaf: 20
|
||||||
|
lambda_l2: 0.5
|
||||||
colsample_bytree: 0.8
|
colsample_bytree: 0.8
|
||||||
subsample: 0.8
|
subsample: 0.8
|
||||||
subsample_freq: 1
|
subsample_freq: 1
|
||||||
reg_alpha: 0.01
|
reg_alpha: 0.1
|
||||||
reg_lambda: 0.01
|
reg_lambda: 1.0
|
||||||
|
seeds: "42,7"
|
||||||
|
parallel: 2
|
||||||
|
|
||||||
dataset:
|
dataset:
|
||||||
class: DatasetH
|
class: DatasetH
|
||||||
@@ -50,9 +74,9 @@ task:
|
|||||||
kwargs:
|
kwargs:
|
||||||
instruments: "{{ UNIVERSE }}"
|
instruments: "{{ UNIVERSE }}"
|
||||||
start_time: 2015-01-03
|
start_time: 2015-01-03
|
||||||
end_time: 2023-12-29
|
end_time: 2026-08-14
|
||||||
fit_start_time: 2015-01-03
|
fit_start_time: 2016-01-04
|
||||||
fit_end_time: 2023-01-03
|
fit_end_time: 2025-09-01
|
||||||
freq: day
|
freq: day
|
||||||
lake_root: "{{ LAKE }}"
|
lake_root: "{{ LAKE }}"
|
||||||
market: US
|
market: US
|
||||||
@@ -70,9 +94,9 @@ task:
|
|||||||
- class: Fillna
|
- class: Fillna
|
||||||
kwargs: {}
|
kwargs: {}
|
||||||
segments:
|
segments:
|
||||||
train: [2015-01-03, 2022-09-01]
|
train: [2016-01-04, 2025-09-01]
|
||||||
valid: [2022-09-03, 2023-01-03]
|
valid: [2025-09-03, 2026-01-03]
|
||||||
test: [2023-01-03, 2023-12-29]
|
test: [2026-01-04, 2026-08-10]
|
||||||
|
|
||||||
record:
|
record:
|
||||||
- class: SignalRecord
|
- class: SignalRecord
|
||||||
@@ -80,29 +104,25 @@ task:
|
|||||||
kwargs: {}
|
kwargs: {}
|
||||||
- class: SigAnaRecord
|
- class: SigAnaRecord
|
||||||
module_path: qlib.workflow.record_temp
|
module_path: qlib.workflow.record_temp
|
||||||
kwargs: { ana_long_short: true, ann_scaler: 252 }
|
kwargs:
|
||||||
|
ana_long_short: true
|
||||||
|
ann_scaler: 252
|
||||||
- class: PortAnaRecord
|
- class: PortAnaRecord
|
||||||
module_path: qlib.workflow.record_temp
|
module_path: qlib.workflow.record_temp
|
||||||
kwargs:
|
kwargs:
|
||||||
config:
|
config:
|
||||||
strategy:
|
strategy:
|
||||||
class: SignalQualityGateStrategy
|
class: TopkDropoutStrategy
|
||||||
module_path: tac_qlib.contrib.strategy.signal_quality_gate
|
module_path: qlib.contrib.strategy
|
||||||
kwargs:
|
kwargs:
|
||||||
signal: "<PRED>"
|
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
|
topk: 10
|
||||||
n_drop: 1
|
n_drop: 2
|
||||||
only_tradable: true
|
only_tradable: true
|
||||||
risk_degree: 0.95
|
risk_degree: 0.95
|
||||||
backtest:
|
backtest:
|
||||||
start_time: 2023-01-03
|
start_time: 2026-01-04
|
||||||
end_time: 2023-12-29
|
end_time: 2026-08-10
|
||||||
account: 1000000
|
account: 1000000
|
||||||
benchmark: SPY
|
benchmark: SPY
|
||||||
exchange_kwargs:
|
exchange_kwargs:
|
||||||
@@ -0,0 +1,136 @@
|
|||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
|
||||||
|
#
|
||||||
|
# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
|
||||||
|
# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
|
||||||
|
# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
|
||||||
|
#
|
||||||
|
# Run:
|
||||||
|
# rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
|
||||||
|
# experiment_name=tac-rd-risk-limit
|
||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
{%- 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_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:///{{ LAKE }}/mlruns.db"
|
||||||
|
default_exp_name: "tac-rd-risk-limit"
|
||||||
|
|
||||||
|
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"
|
||||||
|
parallel: 5
|
||||||
|
|
||||||
|
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: 2026-08-14
|
||||||
|
fit_start_time: 2016-01-04
|
||||||
|
fit_end_time: 2025-09-01
|
||||||
|
freq: day
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||||
|
feature_fields: "$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: [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: MomentumGateTopk
|
||||||
|
module_path: tac_qlib.contrib.strategy.momentum_gate
|
||||||
|
kwargs:
|
||||||
|
signal: "<PRED>"
|
||||||
|
topk: 10
|
||||||
|
n_drop: 2
|
||||||
|
min_momentum: 0.0
|
||||||
|
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 +1,138 @@
|
|||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
|
||||||
|
#
|
||||||
|
# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
|
||||||
|
# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
|
||||||
|
# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
|
||||||
|
#
|
||||||
|
# Run:
|
||||||
|
# rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
|
||||||
|
# experiment_name=tac-rd-risk-limit
|
||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
{%- 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_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:///{{ LAKE }}/mlruns.db"
|
||||||
|
default_exp_name: "tac-rd-risk-limit"
|
||||||
|
|
||||||
|
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"
|
||||||
|
parallel: 5
|
||||||
|
|
||||||
|
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: 2026-08-14
|
||||||
|
fit_start_time: 2016-01-04
|
||||||
|
fit_end_time: 2025-09-01
|
||||||
|
freq: day
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||||
|
feature_fields: "$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: [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: HmmRiskTopk
|
||||||
|
module_path: tac_qlib.contrib.strategy.hmm_risk
|
||||||
|
kwargs:
|
||||||
|
signal: "<PRED>"
|
||||||
|
topk: 10
|
||||||
|
n_drop: 2
|
||||||
|
hmm_pause_pct: 0.70
|
||||||
|
drawdown_pause_pct: 8.0
|
||||||
|
liquidity_floor_adv: 5000000
|
||||||
|
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 +1,137 @@
|
|||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
|
||||||
|
#
|
||||||
|
# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
|
||||||
|
# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
|
||||||
|
# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
|
||||||
|
#
|
||||||
|
# Run:
|
||||||
|
# rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
|
||||||
|
# experiment_name=tac-rd-risk-limit
|
||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
{%- 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_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:///{{ LAKE }}/mlruns.db"
|
||||||
|
default_exp_name: "tac-rd-risk-limit"
|
||||||
|
|
||||||
|
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"
|
||||||
|
weight_mode: rolling_ic
|
||||||
|
rolling_ic_window: 21
|
||||||
|
parallel: 5
|
||||||
|
|
||||||
|
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: 2026-08-14
|
||||||
|
fit_start_time: 2016-01-04
|
||||||
|
fit_end_time: 2025-09-01
|
||||||
|
freq: day
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||||
|
feature_fields: "$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: [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: 2
|
||||||
|
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 +1,135 @@
|
|||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
|
||||||
|
#
|
||||||
|
# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
|
||||||
|
# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
|
||||||
|
# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
|
||||||
|
#
|
||||||
|
# Run:
|
||||||
|
# rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
|
||||||
|
# experiment_name=tac-rd-risk-limit
|
||||||
|
# -----------------------------------------------------------------------------
|
||||||
|
{%- 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_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,sma_3,ema_3" %}
|
||||||
|
|
||||||
|
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-risk-limit"
|
||||||
|
|
||||||
|
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"
|
||||||
|
parallel: 5
|
||||||
|
|
||||||
|
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: 2026-08-14
|
||||||
|
fit_start_time: 2016-01-04
|
||||||
|
fit_end_time: 2025-09-01
|
||||||
|
freq: day
|
||||||
|
lake_root: "{{ LAKE }}"
|
||||||
|
market: US
|
||||||
|
label: "Ref($close,-6)/Ref($close,-1)-1"
|
||||||
|
feature_fields: "$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: [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: 2
|
||||||
|
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
|
||||||
Reference in New Issue
Block a user