liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-11 14:56:55 +08:00
Code Activity

add test/config.py

Browse Source
This commit is contained in:
zhupr
2021-05-28 13:24:47 +08:00
parent 0a4e241608
commit 98eacf8f88
21 changed files with 246 additions and 637 deletions
Download Patch File Download Diff File Expand all files Collapse all files

65
tests/test_contrib_workflow.py
View File

@@ -1,73 +1,22 @@
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
import sys
import shutil
import unittest
from pathlib import Path
import qlib
from qlib.config import C
from qlib.contrib.workflow import MultiSegRecord, SignalMseRecord
from qlib.utils import init_instance_by_config, flatten_dict
from qlib.workflow import R
from qlib.tests import TestAutoData
market = "csi300"
benchmark = "SH000300"
###################################
# train model
###################################
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,
}
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"),
},
},
},
}
from qlib.tests.config import CSI300_GBDT_TASK
def train_multiseg():
model = init_instance_by_config(task["model"])
dataset = init_instance_by_config(task["dataset"])
model = init_instance_by_config(CSI300_GBDT_TASK["model"])
dataset = init_instance_by_config(CSI300_GBDT_TASK["dataset"])
with R.start(experiment_name="workflow"):
R.log_params(**flatten_dict(task))
R.log_params(**flatten_dict(CSI300_GBDT_TASK))
model.fit(dataset)
recorder = R.get_recorder()
sr = MultiSegRecord(model, dataset, recorder)
@@ -77,10 +26,10 @@ def train_multiseg():
def train_mse():
model = init_instance_by_config(task["model"])
dataset = init_instance_by_config(task["dataset"])
model = init_instance_by_config(CSI300_GBDT_TASK["model"])
dataset = init_instance_by_config(CSI300_GBDT_TASK["dataset"])
with R.start(experiment_name="workflow"):
R.log_params(**flatten_dict(task))
R.log_params(**flatten_dict(CSI300_GBDT_TASK))
model.fit(dataset)
recorder = R.get_recorder()
sr = SignalMseRecord(recorder, model=model, dataset=dataset)