Workflow
Introduction
- Data
- Loading
- Processing
- Slicing
- Model
- Training and inference
- Saving and loading
- Evaluation
- Forcast signal analysis
- Backtest
Complete Example
qlib_init:
provider_uri: "~/.qlib/qlib_data/cn_data"
region: cn
market: &market csi300
benchmark: &benchmark SH000300
# data handler config process the data. Diveided into 2 parts: data fitting and data processing.
# This config will be used in dataset.
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
signal: <PRED>
backtest:
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: 0.0421
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: 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: PortAnaRecord
module_path: qlib.workflow.record_temp
kwargs:
config: *port_analysis_config
run the workflow
qrun configuration.yaml
# or run under debug mode
python -m pdb qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml
Tips
qrun will be placed in your $PATH directory when installing
Qlib
.The symbol & in yaml file stands for an anchor of a field, which is useful when another fields include this parameter as part of the value. Taking the configuration file above as an example, users can directly change the value of market and benchmark without traversing the entire configuration file.
Configuration follows the designe of init_instance_by_config
. The following yaml and code are equivalent.
model:
class: LGBModel
module_path: qlib.contrib.model.gbdt
kwargs:
loss: mse
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
from qlib.contrib.model.gbdt import LGBModel
kwargs = {
"loss": "mse" ,
"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,
}
LGBModel(kwargs)