liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-10 22:36:55 +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

22
tests/dataset_tests/test_datalayer.py
View File

@@ -1,26 +1,10 @@
import sys
from pathlib import Path
import qlib
from qlib.data import D
from qlib.config import REG_CN
import unittest
import numpy as np
from qlib.utils import exists_qlib_data
from qlib.data import D
from qlib.tests import TestAutoData
class TestDataset(unittest.TestCase):
@classmethod
def setUpClass(cls) -> None:
# use default data
provider_uri = "~/.qlib/qlib_data/cn_data_simple" # target_dir
if not exists_qlib_data(provider_uri):
print(f"Qlib data is not found in {provider_uri}")
sys.path.append(str(Path(__file__).resolve().parent.parent.parent.joinpath("scripts")))
from get_data import GetData
GetData().qlib_data(name="qlib_data_simple", target_dir=provider_uri)
qlib.init(provider_uri=provider_uri, region=REG_CN)
class TestDataset(TestAutoData):
def testCSI300(self):
close_p = D.features(D.instruments("csi300"), ["$close"])
size = close_p.groupby("datetime").size()

66
tests/test_all_pipeline.py
View File

@@ -12,55 +12,7 @@ from qlib.utils import init_instance_by_config, flatten_dict
from qlib.workflow import R
from qlib.workflow.record_temp import SignalRecord, SigAnaRecord, PortAnaRecord
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, CSI300_BENCH
port_analysis_config = {
"strategy": {
@@ -75,7 +27,7 @@ port_analysis_config = {
"verbose": False,
"limit_threshold": 0.095,
"account": 100000000,
"benchmark": benchmark,
"benchmark": CSI300_BENCH,
"deal_price": "close",
"open_cost": 0.0005,
"close_cost": 0.0015,
@@ -96,15 +48,15 @@ def train():
"""
# model initiaiton
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"])
# To test __repr__
print(dataset)
print(R)
# start exp
with R.start(experiment_name="workflow"):
R.log_params(**flatten_dict(task))
R.log_params(**flatten_dict(CSI300_GBDT_TASK))
model.fit(dataset)
# prediction
@@ -137,12 +89,12 @@ def train_with_sigana():
performance: dict
model performance
"""
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"])
# start exp
with R.start(experiment_name="workflow_with_sigana"):
R.log_params(**flatten_dict(task))
R.log_params(**flatten_dict(CSI300_GBDT_TASK))
model.fit(dataset)
# predict and calculate ic and ric
@@ -171,7 +123,7 @@ def fake_experiment():
default_uri = R.get_uri()
current_uri = "file:./temp-test-exp-mag"
with R.start(experiment_name="fake_workflow_for_expm", uri=current_uri):
R.log_params(**flatten_dict(task))
R.log_params(**flatten_dict(CSI300_GBDT_TASK))
current_uri_to_check = R.get_uri()
default_uri_to_check = R.get_uri()

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)

5
tests/test_get_data.py
View File

@@ -1,16 +1,13 @@
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
import sys
import shutil
import unittest
from pathlib import Path
sys.path.append(str(Path(__file__).resolve().parent.parent.joinpath("scripts")))
from get_data import GetData
import qlib
from qlib.data import D
from qlib.tests.data import GetData
DATA_DIR = Path(__file__).parent.joinpath("test_get_data")
SOURCE_DIR = DATA_DIR.joinpath("source")

5
tests/test_register_ops.py
View File

@@ -1,17 +1,12 @@
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
import sys
import unittest
import numpy as np
import qlib
from qlib.data import D
from qlib.data.ops import ElemOperator, PairOperator
from qlib.config import REG_CN
from qlib.utils import exists_qlib_data
from qlib.tests import TestAutoData
from qlib.tests.data import GetData
class Diff(ElemOperator):