mirror of
https://github.com/microsoft/qlib.git
synced 2026-07-02 02:21:18 +08:00
Merge branch 'microsoft_main' into online_srv
This commit is contained in:
lzh222333
@@ -0,0 +1,81 @@
|
||||
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
|
||||
instruments: *market
|
||||
data_loader:
|
||||
class: QlibDataLoader
|
||||
kwargs:
|
||||
config:
|
||||
feature:
|
||||
- ["Resi($close, 15)/$close", "Std(Abs($close/Ref($close, 1)-1)*$volume, 5)/(Mean(Abs($close/Ref($close, 1)-1)*$volume, 5)+1e-12)", "Rsquare($close, 5)", "($high-$low)/$open", "Rsquare($close, 10)", "Corr($close, Log($volume+1), 5)", "Corr($close/Ref($close,1), Log($volume/Ref($volume, 1)+1), 5)", "Corr($close, Log($volume+1), 10)", "Rsquare($close, 20)", "Corr($close/Ref($close,1), Log($volume/Ref($volume, 1)+1), 60)", "Corr($close/Ref($close,1), Log($volume/Ref($volume, 1)+1), 10)", "Corr($close, Log($volume+1), 20)", "(Less($open, $close)-$low)/$open"]
|
||||
- ["RESI5", "WVMA5", "RSQR5", "KLEN", "RSQR10", "CORR5", "CORD5", "CORR10", "RSQR20", "CORD60", "CORD10", "CORR20", "KLOW"]
|
||||
label:
|
||||
- ["Ref($close, -2)/Ref($close, -1) - 1"]
|
||||
- ["LABEL0"]
|
||||
freq: day
|
||||
|
||||
learn_processors:
|
||||
- class: DropnaLabel
|
||||
- class: CSZScoreNorm
|
||||
kwargs:
|
||||
fields_group: label
|
||||
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: LGBModel
|
||||
module_path: qlib.contrib.model.gbdt
|
||||
kwargs:
|
||||
loss: mse
|
||||
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
|
||||
dataset:
|
||||
class: DatasetH
|
||||
module_path: qlib.data.dataset
|
||||
kwargs:
|
||||
handler:
|
||||
class: DataHandlerLP
|
||||
module_path: qlib.data.dataset.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
|
||||
23
examples/hyperparameter/LightGBM/Readme.md
Normal file
23
examples/hyperparameter/LightGBM/Readme.md
Normal file
@@ -0,0 +1,23 @@
|
||||
# LightGBM hyperparameter
|
||||
|
||||
## Alpha158
|
||||
First terminal
|
||||
```
|
||||
optuna create-study --study LGBM_158 --storage sqlite:///db.sqlite3
|
||||
optuna-dashboard --port 5000 --host 0.0.0.0 sqlite:///db.sqlite3
|
||||
```
|
||||
Second terminal
|
||||
```
|
||||
python hyperparameter_158.py
|
||||
```
|
||||
|
||||
## Alpha360
|
||||
First terminal
|
||||
```
|
||||
optuna create-study --study LGBM_360 --storage sqlite:///db.sqlite3
|
||||
optuna-dashboard --port 5000 --host 0.0.0.0 sqlite:///db.sqlite3
|
||||
```
|
||||
Second terminal
|
||||
```
|
||||
python hyperparameter_360.py
|
||||
```
|
||||
76
examples/hyperparameter/LightGBM/hyperparameter_158.py
Normal file
76
examples/hyperparameter/LightGBM/hyperparameter_158.py
Normal file
@@ -0,0 +1,76 @@
|
||||
import qlib
|
||||
from qlib.config import REG_CN
|
||||
from qlib.utils import exists_qlib_data, init_instance_by_config
|
||||
import optuna
|
||||
|
||||
provider_uri = "~/.qlib/qlib_data/cn_data"
|
||||
if not exists_qlib_data(provider_uri):
|
||||
print(f"Qlib data is not found in {provider_uri}")
|
||||
sys.path.append(str(scripts_dir))
|
||||
from get_data import GetData
|
||||
|
||||
GetData().qlib_data(target_dir=provider_uri, region="cn")
|
||||
qlib.init(provider_uri=provider_uri, region="cn")
|
||||
|
||||
market = "csi300"
|
||||
benchmark = "SH000300"
|
||||
|
||||
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,
|
||||
}
|
||||
dataset_task = {
|
||||
"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"),
|
||||
},
|
||||
},
|
||||
},
|
||||
}
|
||||
dataset = init_instance_by_config(dataset_task["dataset"])
|
||||
|
||||
|
||||
def objective(trial):
|
||||
task = {
|
||||
"model": {
|
||||
"class": "LGBModel",
|
||||
"module_path": "qlib.contrib.model.gbdt",
|
||||
"kwargs": {
|
||||
"loss": "mse",
|
||||
"colsample_bytree": trial.suggest_uniform("colsample_bytree", 0.5, 1),
|
||||
"learning_rate": trial.suggest_uniform("learning_rate", 0, 1),
|
||||
"subsample": trial.suggest_uniform("subsample", 0, 1),
|
||||
"lambda_l1": trial.suggest_loguniform("lambda_l1", 1e-8, 1e4),
|
||||
"lambda_l2": trial.suggest_loguniform("lambda_l2", 1e-8, 1e4),
|
||||
"max_depth": 10,
|
||||
"num_leaves": trial.suggest_int("num_leaves", 1, 1024),
|
||||
"feature_fraction": trial.suggest_uniform("feature_fraction", 0.4, 1.0),
|
||||
"bagging_fraction": trial.suggest_uniform("bagging_fraction", 0.4, 1.0),
|
||||
"bagging_freq": trial.suggest_int("bagging_freq", 1, 7),
|
||||
"min_data_in_leaf": trial.suggest_int("min_data_in_leaf", 1, 50),
|
||||
"min_child_samples": trial.suggest_int("min_child_samples", 5, 100),
|
||||
},
|
||||
},
|
||||
}
|
||||
|
||||
evals_result = dict()
|
||||
model = init_instance_by_config(task["model"])
|
||||
model.fit(dataset, evals_result=evals_result)
|
||||
return min(evals_result["valid"])
|
||||
|
||||
|
||||
study = optuna.Study(study_name="LGBM_158", storage="sqlite:///db.sqlite3")
|
||||
study.optimize(objective, n_jobs=6)
|
||||
76
examples/hyperparameter/LightGBM/hyperparameter_360.py
Normal file
76
examples/hyperparameter/LightGBM/hyperparameter_360.py
Normal file
@@ -0,0 +1,76 @@
|
||||
import qlib
|
||||
from qlib.config import REG_CN
|
||||
from qlib.utils import exists_qlib_data, init_instance_by_config
|
||||
import optuna
|
||||
|
||||
provider_uri = "~/.qlib/qlib_data/cn_data"
|
||||
if not exists_qlib_data(provider_uri):
|
||||
print(f"Qlib data is not found in {provider_uri}")
|
||||
sys.path.append(str(scripts_dir))
|
||||
from get_data import GetData
|
||||
|
||||
GetData().qlib_data(target_dir=provider_uri, region="cn")
|
||||
qlib.init(provider_uri=provider_uri, region="cn")
|
||||
|
||||
market = "csi300"
|
||||
benchmark = "SH000300"
|
||||
|
||||
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,
|
||||
}
|
||||
dataset_task = {
|
||||
"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"),
|
||||
},
|
||||
},
|
||||
},
|
||||
}
|
||||
dataset = init_instance_by_config(dataset_task["dataset"])
|
||||
|
||||
|
||||
def objective(trial):
|
||||
task = {
|
||||
"model": {
|
||||
"class": "LGBModel",
|
||||
"module_path": "qlib.contrib.model.gbdt",
|
||||
"kwargs": {
|
||||
"loss": "mse",
|
||||
"colsample_bytree": trial.suggest_uniform("colsample_bytree", 0.5, 1),
|
||||
"learning_rate": trial.suggest_uniform("learning_rate", 0, 1),
|
||||
"subsample": trial.suggest_uniform("subsample", 0, 1),
|
||||
"lambda_l1": trial.suggest_loguniform("lambda_l1", 1e-8, 1e4),
|
||||
"lambda_l2": trial.suggest_loguniform("lambda_l2", 1e-8, 1e4),
|
||||
"max_depth": 10,
|
||||
"num_leaves": trial.suggest_int("num_leaves", 1, 1024),
|
||||
"feature_fraction": trial.suggest_uniform("feature_fraction", 0.4, 1.0),
|
||||
"bagging_fraction": trial.suggest_uniform("bagging_fraction", 0.4, 1.0),
|
||||
"bagging_freq": trial.suggest_int("bagging_freq", 1, 7),
|
||||
"min_data_in_leaf": trial.suggest_int("min_data_in_leaf", 1, 50),
|
||||
"min_child_samples": trial.suggest_int("min_child_samples", 5, 100),
|
||||
},
|
||||
},
|
||||
}
|
||||
|
||||
evals_result = dict()
|
||||
model = init_instance_by_config(task["model"])
|
||||
model.fit(dataset, evals_result=evals_result)
|
||||
return min(evals_result["valid"])
|
||||
|
||||
|
||||
study = optuna.Study(study_name="LGBM_360", storage="sqlite:///db.sqlite3")
|
||||
study.optimize(objective, n_jobs=6)
|
||||
5
examples/hyperparameter/LightGBM/requirements.txt
Normal file
5
examples/hyperparameter/LightGBM/requirements.txt
Normal file
@@ -0,0 +1,5 @@
|
||||
pandas==1.1.2
|
||||
numpy==1.17.4
|
||||
lightgbm==3.1.0
|
||||
optuna==2.7.0
|
||||
optuna-dashboard==0.4.1
|
||||
Reference in New Issue
Block a user