liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-06 04:20:57 +08:00
Code Activity

Merge branch 'main' into online_srv

Browse Source
This commit is contained in:
lzh222333
2021-03-23 11:20:02 +08:00
committed by GitHub
parent 84d5318bda 2b74b4dfa4
commit d66d4ec93d
74 changed files with 3035 additions and 1020 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/benchmarks/DoubleEnsemble/README.md Normal file
View File

@@ -0,0 +1,4 @@
# DoubleEnsemble
* DoubleEnsemble is an ensemble framework leveraging learning trajectory based sample reweighting and shuffling based feature selection, to solve both the low signal-to-noise ratio and increasing number of features problems. They identify the key samples based on the training dynamics on each sample and elicit key features based on the ablation impact of each feature via shuffling. The model is applicable to a wide range of base models, capable of extracting complex patterns, while mitigating the overfitting and instability issues for financial market prediction.
* This code used in Qlib is implemented by ourselves.
* Paper: DoubleEnsemble: A New Ensemble Method Based on Sample Reweighting and Feature Selection for Financial Data Analysis [https://arxiv.org/pdf/2010.01265.pdf](https://arxiv.org/pdf/2010.01265.pdf).

3
examples/benchmarks/DoubleEnsemble/requirements.txt Normal file
View File

@@ -0,0 +1,3 @@
pandas==1.1.2
numpy==1.17.4
lightgbm==3.1.0

90
examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha158.yaml Normal file
View File

@@ -0,0 +1,90 @@
qlib_init:
provider_uri: "~/.qlib/qlib_data/cn_data"
region: cn
market: &market csi300
benchmark: &benchmark SH000300
data_handler_config: &data_handler_config
start_time: 2008-01-01
end_time: 2020-08-01
fit_start_time: 2008-01-01
fit_end_time: 2014-12-31
instruments: *market
port_analysis_config: &port_analysis_config
strategy:
class: TopkDropoutStrategy
module_path: qlib.contrib.strategy.strategy
kwargs:
topk: 50
n_drop: 5
backtest:
verbose: False
limit_threshold: 0.095
account: 100000000
benchmark: *benchmark
deal_price: close
open_cost: 0.0005
close_cost: 0.0015
min_cost: 5
task:
model:
class: DEnsembleModel
module_path: qlib.contrib.model.double_ensemble
kwargs:
base_model: "gbm"
loss: mse
num_models: 6
enable_sr: True
enable_fs: True
alpha1: 1
alpha2: 1
bins_sr: 10
bins_fs: 5
decay: 0.5
sample_ratios:
- 0.8
- 0.7
- 0.6
- 0.5
- 0.4
sub_weights:
- 1
- 0.2
- 0.2
- 0.2
- 0.2
- 0.2
epochs: 28
colsample_bytree: 0.8879
learning_rate: 0.2
subsample: 0.8789
lambda_l1: 205.6999
lambda_l2: 580.9768
max_depth: 8
num_leaves: 210
num_threads: 20
verbosity: -1
dataset:
class: DatasetH
module_path: qlib.data.dataset
kwargs:
handler:
class: Alpha158
module_path: qlib.contrib.data.handler
kwargs: *data_handler_config
segments:
train: [2008-01-01, 2014-12-31]
valid: [2015-01-01, 2016-12-31]
test: [2017-01-01, 2020-08-01]
record:
- class: SignalRecord
module_path: qlib.workflow.record_temp
kwargs: {}
- class: SigAnaRecord
module_path: qlib.workflow.record_temp
kwargs:
ana_long_short: False
ann_scaler: 252
- class: PortAnaRecord
module_path: qlib.workflow.record_temp
kwargs:
config: *port_analysis_config

97
examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha360.yaml Normal file
View File

@@ -0,0 +1,97 @@
qlib_init:
provider_uri: "~/.qlib/qlib_data/cn_data"
region: cn
market: &market csi300
benchmark: &benchmark SH000300
data_handler_config: &data_handler_config
start_time: 2008-01-01
end_time: 2020-08-01
fit_start_time: 2008-01-01
fit_end_time: 2014-12-31
instruments: *market
infer_processors: []
learn_processors:
- class: DropnaLabel
- class: CSRankNorm
kwargs:
fields_group: label
label: ["Ref($close, -2) / Ref($close, -1) - 1"]
port_analysis_config: &port_analysis_config
strategy:
class: TopkDropoutStrategy
module_path: qlib.contrib.strategy.strategy
kwargs:
topk: 50
n_drop: 5
backtest:
verbose: False
limit_threshold: 0.095
account: 100000000
benchmark: *benchmark
deal_price: close
open_cost: 0.0005
close_cost: 0.0015
min_cost: 5
task:
model:
class: DEnsembleModel
module_path: qlib.contrib.model.double_ensemble
kwargs:
base_model: "gbm"
loss: mse
num_models: 6
enable_sr: True
enable_fs: True
alpha1: 1
alpha2: 1
bins_sr: 10
bins_fs: 5
decay: 0.5
sample_ratios:
- 0.8
- 0.7
- 0.6
- 0.5
- 0.4
sub_weights:
- 1
- 0.2
- 0.2
- 0.2
- 0.2
- 0.2
epochs: 136
colsample_bytree: 0.8879
learning_rate: 0.0421
subsample: 0.8789
lambda_l1: 205.6999
lambda_l2: 580.9768
max_depth: 8
num_leaves: 210
num_threads: 20
verbosity: -1
dataset:
class: DatasetH
module_path: qlib.data.dataset
kwargs:
handler:
class: Alpha360
module_path: qlib.contrib.data.handler
kwargs: *data_handler_config
segments:
train: [2008-01-01, 2014-12-31]
valid: [2015-01-01, 2016-12-31]
test: [2017-01-01, 2020-08-01]
record:
- class: SignalRecord
module_path: qlib.workflow.record_temp
kwargs: {}
- class: SigAnaRecord
module_path: qlib.workflow.record_temp
kwargs:
ana_long_short: False
ann_scaler: 252
- class: PortAnaRecord
module_path: qlib.workflow.record_temp
kwargs:
config: *port_analysis_config

2
examples/benchmarks/LSTM/workflow_config_lstm_Alpha158.yaml
View File

@@ -29,7 +29,7 @@ data_handler_config: &data_handler_config
- class: CSRankNorm
kwargs:
fields_group: label
label: ["Ref($close, -2) / Ref($close, -1) - 1"]
label: ["Ref($close, -2) / Ref($close, -1) - 1"]
port_analysis_config: &port_analysis_config
strategy:

4
examples/benchmarks/README.md
View File

@@ -16,6 +16,7 @@ The numbers shown below demonstrate the performance of the entire `workflow` of
| LSTM (Sepp Hochreiter, et al.) | Alpha360 | 0.0443±0.01 | 0.3401±0.05| 0.0536±0.01 | 0.4248±0.05 | 0.0627±0.03 | 0.8441±0.48| -0.0882±0.03 |
| ALSTM (Yao Qin, et al.) | Alpha360 | 0.0493±0.01 | 0.3778±0.06| 0.0585±0.00 | 0.4606±0.04 | 0.0513±0.03 | 0.6727±0.38| -0.1085±0.02 |
| GATs (Petar Velickovic, et al.) | Alpha360 | 0.0475±0.00 | 0.3515±0.02| 0.0592±0.00 | 0.4585±0.01 | 0.0876±0.02 | 1.1513±0.27| -0.0795±0.02 |
| DoubleEnsemble (Chuheng Zhang, et al.) | Alpha360 | 0.0407±0.00| 0.3053±0.00 | 0.0490±0.00 | 0.3840±0.00 | 0.0380±0.02 | 0.5000±0.21 | -0.0984±0.02 |
## Alpha158 dataset
| Model Name | Dataset | IC | ICIR | Rank IC | Rank ICIR | Annualized Return | Information Ratio | Max Drawdown |
@@ -25,11 +26,12 @@ The numbers shown below demonstrate the performance of the entire `workflow` of
| XGBoost (Tianqi Chen, et al.) | Alpha158 | 0.0481±0.00 | 0.3659±0.00| 0.0495±0.00 | 0.4033±0.00 | 0.1111±0.00 | 1.2915±0.00| -0.0893±0.00 |
| LightGBM (Guolin Ke, et al.) | Alpha158 | 0.0475±0.00 | 0.3979±0.00| 0.0485±0.00 | 0.4123±0.00 | 0.1143±0.00 | 1.2744±0.00| -0.0800±0.00 |
| MLP | Alpha158 | 0.0358±0.00 | 0.2738±0.03| 0.0425±0.00 | 0.3221±0.01 | 0.0836±0.02 | 1.0323±0.25| -0.1127±0.02 |
| TabNet with pretrain (Sercan O. Arikm et al) | Alpha158 | 0.0344±0.00|0.205±0.11|0.0398±0.00 |0.3479±0.01|0.0827±0.02|1.1141±0.32 |-0.0925±0.02 |
| TFT (Bryan Lim, et al.) | Alpha158 (with selected 20 features) | 0.0343±0.00 | 0.2071±0.02| 0.0107±0.00 | 0.0660±0.02 | 0.0623±0.02 | 0.5818±0.20| -0.1762±0.01 |
| GRU (Kyunghyun Cho, et al.) | Alpha158 (with selected 20 features) | 0.0311±0.00 | 0.2418±0.04| 0.0425±0.00 | 0.3434±0.02 | 0.0330±0.02 | 0.4805±0.30| -0.1021±0.02 |
| LSTM (Sepp Hochreiter, et al.) | Alpha158 (with selected 20 features) | 0.0312±0.00 | 0.2394±0.04| 0.0418±0.00 | 0.3324±0.03 | 0.0298±0.02 | 0.4198±0.33| -0.1348±0.03 |
| ALSTM (Yao Qin, et al.) | Alpha158 (with selected 20 features) | 0.0385±0.01 | 0.3022±0.06| 0.0478±0.00 | 0.3874±0.04 | 0.0486±0.03 | 0.7141±0.45| -0.1088±0.03 |
| GATs (Petar Velickovic, et al.) | Alpha158 (with selected 20 features) | 0.0349±0.00 | 0.2511±0.01| 0.0457±0.00 | 0.3537±0.01 | 0.0578±0.02 | 0.8221±0.25| -0.0824±0.02 |
| DoubleEnsemble (Chuheng Zhang, et al.) | Alpha158 | 0.0544±0.00 | 0.4338±0.01 | 0.0523±0.00 | 0.4257±0.01 | 0.1253±0.01 | 1.4105±0.14 | -0.0902±0.01 |
- The selected 20 features are based on the feature importance of a lightgbm-based model.
- The base model of DoubleEnsemble is LGBM.

BIN
examples/benchmarks/TabNet/pretrain/best.model
View File

Binary file not shown.

3
examples/benchmarks/TabNet/workflow_config_TabNet_Alpha158.yaml
View File

@@ -44,6 +44,7 @@ task:
class: TabnetModel
module_path: qlib.contrib.model.pytorch_tabnet
kwargs:
d_feat: 158
pretrain: True
dataset:
class: DatasetH
@@ -55,7 +56,7 @@ task:
kwargs: *data_handler_config
segments:
pretrain: [2008-01-01, 2014-12-31]
pretrain_validation: [2015-01-01, 2020-08-01]
pretrain_validation: [2015-01-01, 2016-12-31]
train: [2008-01-01, 2014-12-31]
valid: [2015-01-01, 2016-12-31]
test: [2017-01-01, 2020-08-01]

75
examples/benchmarks/TabNet/workflow_config_TabNet_Alpha360.yaml Normal file
View File

@@ -0,0 +1,75 @@
qlib_init:
provider_uri: "~/.qlib/qlib_data/cn_data"
region: cn
market: &market csi300
benchmark: &benchmark SH000300
data_handler_config: &data_handler_config
start_time: 2008-01-01
end_time: 2020-08-01
fit_start_time: 2008-01-01
fit_end_time: 2014-12-31
instruments: *market
infer_processors:
- class: RobustZScoreNorm
kwargs:
fields_group: feature
clip_outlier: true
- class: Fillna
kwargs:
fields_group: feature
learn_processors:
- class: DropnaLabel
- class: CSRankNorm
kwargs:
fields_group: label
label: ["Ref($close, -2) / Ref($close, -1) - 1"]
port_analysis_config: &port_analysis_config
strategy:
class: TopkDropoutStrategy
module_path: qlib.contrib.strategy.strategy
kwargs:
topk: 50
n_drop: 5
backtest:
verbose: False
limit_threshold: 0.095
account: 100000000
benchmark: *benchmark
deal_price: close
open_cost: 0.0005
close_cost: 0.0015
min_cost: 5
task:
model:
class: TabnetModel
module_path: qlib.contrib.model.pytorch_tabnet
kwargs:
d_feat: 360
pretrain: True
dataset:
class: DatasetH
module_path: qlib.data.dataset
kwargs:
handler:
class: Alpha360
module_path: qlib.contrib.data.handler
kwargs: *data_handler_config
segments:
pretrain: [2008-01-01, 2014-12-31]
pretrain_validation: [2015-01-01, 2016-12-31]
train: [2008-01-01, 2014-12-31]
valid: [2015-01-01, 2016-12-31]
test: [2017-01-01, 2020-08-01]
record:
- class: SignalRecord
module_path: qlib.workflow.record_temp
kwargs: {}
- class: SigAnaRecord
module_path: qlib.workflow.record_temp
kwargs:
ana_long_short: False
ann_scaler: 252
- class: PortAnaRecord
module_path: qlib.workflow.record_temp
kwargs:
config: *port_analysis_config