liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-10 06:20:57 +08:00
Code Activity

add docs & fix reinit of datatset

Browse Source
This commit is contained in:
bxdd
2021-02-03 08:57:31 +00:00
committed by you-n-g
parent c71b645777
commit 4ed8b8e233
4 changed files with 96 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
examples/highfreq/README.md Normal file
View File

@@ -0,0 +1,28 @@
# High-Frequency Dataset
This dataset is an example for RL high frequency trading.
## Get High-Frequency Data
Get high-frequency data by running the following command:
```bash
python workflow.py get_data
```
## Dump & Reload & Reinitialize the Dataset
The High-Frequency Dataset is implemented as `qlib.data.dataset.DatasetH` in the `workflow.py`. `DatatsetH` is the subclass of `qlib.utils.serial.Serializable`, which supports being dumped in or loaded from disk in `pickle` format.
### About Reinitialization
After reloading `Dataset` from disk, `Qlib` also support reinitialize the dataset. It means that users can reset some config of `Dataset` or `DataHandler` such as `instruments`, `start_time`, `end_time` and `segmens`, etc.
The example is given in `workflow.py`, users can run the code as follows.
### Run the Code
Run the example by running the following command:
```bash
python workflow.py dump_and_load_dataset
```

0
examples/highfreq/__init__.py
View File

45
examples/highfreq/workflow.py
View File

@@ -9,7 +9,7 @@ import qlib
import pickle
import numpy as np
import pandas as pd
from qlib.config import HIGH_FREQ_CONFIG
from qlib.config import REG_CN, HIGH_FREQ_CONFIG
from qlib.contrib.model.gbdt import LGBModel
from qlib.contrib.data.handler import Alpha158
from qlib.contrib.strategy.strategy import TopkDropoutStrategy
@@ -26,7 +26,6 @@ from qlib.tests.data import GetData
from highfreq_ops import get_calendar_day, DayLast, FFillNan, BFillNan, Date, Select, IsNull
class HighfreqWorkflow(object):
SPEC_CONF = {"custom_ops": [DayLast, FFillNan, BFillNan, Date, Select, IsNull], "expression_cache": None}
@@ -123,8 +122,7 @@ class HighfreqWorkflow(object):
backtest_train, backtest_test = dataset_backtest.prepare(["train", "test"])
print(backtest_train, backtest_test)
del xtrain, xtest
del backtest_train, backtest_test
return
def dump_and_load_dataset(self):
"""dump and load dataset state on disk"""
@@ -146,18 +144,39 @@ class HighfreqWorkflow(object):
dataset_backtest = pickle.load(file_dataset_backtest)
self._prepare_calender_cache()
##=============reload_dataset=============
dataset.init(init_type=DataHandlerLP.IT_LS)
dataset_backtest.init()
##=============reinit dataset=============
dataset.init(
handler_kwargs = {
"init_type" : DataHandlerLP.IT_LS,
"start_time" : "2021-01-19 00:00:00",
"end_time" : "2021-01-25 16:00:00",
},
segment_kwargs = {
"test": (
"2021-01-19 00:00:00",
"2021-01-25 16:00:00",
),
}
)
dataset_backtest.init(
handler_kwargs = {
"start_time" : "2021-01-19 00:00:00",
"end_time" : "2021-01-25 16:00:00",
},
segment_kwargs = {
"test": (
"2021-01-19 00:00:00",
"2021-01-25 16:00:00",
),
}
)
##=============get data=============
xtrain, xtest = dataset.prepare(["train", "test"])
backtest_train, backtest_test = dataset_backtest.prepare(["train", "test"])
xtest = dataset.prepare(["test"])
backtest_test = dataset_backtest.prepare(["test"])
print(xtrain, xtest)
print(backtest_train, backtest_test)
del xtrain, xtest
del backtest_train, backtest_test
print(xtest, backtest_test)
return
if __name__ == "__main__":