liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-06-06 05:51:17 +08:00
Code Activity

solve conflict

Browse Source
This commit is contained in:
bxdd
2021-06-01 17:46:47 +08:00
parent a183d8a631 4ff0c4fb0f
commit 04fff8ca36
31 changed files with 606 additions and 765 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
examples/highfreq/workflow.py
View File

@@ -1,24 +1,13 @@
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
import sys
import fire
from pathlib import Path
import qlib
import pickle
import numpy as np
import pandas as pd
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
from qlib.contrib.evaluate import (
backtest as normal_backtest,
risk_analysis,
)
from qlib.utils import init_instance_by_config, exists_qlib_data
from qlib.utils import init_instance_by_config
from qlib.data.dataset.handler import DataHandlerLP
from qlib.data.ops import Operators
from qlib.data.data import Cal
@@ -96,9 +85,7 @@ class HighfreqWorkflow:
# use yahoo_cn_1min data
QLIB_INIT_CONFIG = {**HIGH_FREQ_CONFIG, **self.SPEC_CONF}
provider_uri = QLIB_INIT_CONFIG.get("provider_uri")
if not exists_qlib_data(provider_uri):
print(f"Qlib data is not found in {provider_uri}")
GetData().qlib_data(target_dir=provider_uri, interval="1min", region=REG_CN)
GetData().qlib_data(target_dir=provider_uri, interval="1min", region=REG_CN, exists_skip=True)
qlib.init(**QLIB_INIT_CONFIG)
def _prepare_calender_cache(self):

58
examples/hyperparameter/LightGBM/hyperparameter_158.py
View File

@@ -1,46 +1,9 @@
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"])
from qlib.config import REG_CN
from qlib.utils import init_instance_by_config
from qlib.tests.config import CSI300_DATASET_CONFIG
from qlib.tests.data import GetData
def objective(trial):
@@ -65,12 +28,19 @@ def objective(trial):
},
},
}
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)
if __name__ == "__main__":
provider_uri = "~/.qlib/qlib_data/cn_data"
GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
qlib.init(provider_uri=provider_uri, region="cn")
dataset = init_instance_by_config(CSI300_DATASET_CONFIG)
study = optuna.Study(study_name="LGBM_158", storage="sqlite:///db.sqlite3")
study.optimize(objective, n_jobs=6)

57
examples/hyperparameter/LightGBM/hyperparameter_360.py
View File

@@ -1,46 +1,11 @@
import qlib
from qlib.config import REG_CN
from qlib.utils import exists_qlib_data, init_instance_by_config
import optuna
from qlib.config import REG_CN
from qlib.utils import init_instance_by_config
from qlib.tests.data import GetData
from qlib.tests.config import get_dataset_config, CSI300_MARKET, DATASET_ALPHA360_CLASS
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"])
DATASET_CONFIG = get_dataset_config(market=CSI300_MARKET, dataset_class=DATASET_ALPHA360_CLASS)
def objective(trial):
@@ -72,5 +37,13 @@ def objective(trial):
return min(evals_result["valid"])
study = optuna.Study(study_name="LGBM_360", storage="sqlite:///db.sqlite3")
study.optimize(objective, n_jobs=6)
if __name__ == "__main__":
provider_uri = "~/.qlib/qlib_data/cn_data"
GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
qlib.init(provider_uri=provider_uri, region=REG_CN)
dataset = init_instance_by_config(DATASET_CONFIG)
study = optuna.Study(study_name="LGBM_360", storage="sqlite:///db.sqlite3")
study.optimize(objective, n_jobs=6)

32
examples/model_interpreter/feature.py Normal file
View File

@@ -0,0 +1,32 @@
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
import qlib
from qlib.config import REG_CN
from qlib.utils import init_instance_by_config
from qlib.tests.data import GetData
from qlib.tests.config import CSI300_GBDT_TASK
if __name__ == "__main__":
# use default data
provider_uri = "~/.qlib/qlib_data/cn_data" # target_dir
GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
qlib.init(provider_uri=provider_uri, region=REG_CN)
###################################
# train model
###################################
# model initialization
model = init_instance_by_config(CSI300_GBDT_TASK["model"])
dataset = init_instance_by_config(CSI300_GBDT_TASK["dataset"])
model.fit(dataset)
# get model feature importance
feature_importance = model.get_feature_importance()
print("feature importance:")
print(feature_importance)

62
examples/model_rolling/task_manager_rolling.py
View File

@@ -17,63 +17,7 @@ from qlib.workflow.task.manage import TaskManager
from qlib.workflow.task.collect import RecorderCollector
from qlib.model.ens.group import RollingGroup
from qlib.model.trainer import TrainerRM
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": "csi100",
}
dataset_config = {
"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_config = [
{
"class": "SignalRecord",
"module_path": "qlib.workflow.record_temp",
},
{
"class": "SigAnaRecord",
"module_path": "qlib.workflow.record_temp",
},
]
# use lgb
task_lgb_config = {
"model": {
"class": "LGBModel",
"module_path": "qlib.contrib.model.gbdt",
},
"dataset": dataset_config,
"record": record_config,
}
# use xgboost
task_xgboost_config = {
"model": {
"class": "XGBModel",
"module_path": "qlib.contrib.model.xgboost",
},
"dataset": dataset_config,
"record": record_config,
}
from qlib.tests.config import CSI100_RECORD_LGB_TASK_CONFIG, CSI100_RECORD_XGBOOST_TASK_CONFIG
class RollingTaskExample:
@@ -85,11 +29,13 @@ class RollingTaskExample:
task_db_name="rolling_db",
experiment_name="rolling_exp",
task_pool="rolling_task",
task_config=[task_xgboost_config, task_lgb_config],
task_config=None,
rolling_step=550,
rolling_type=RollingGen.ROLL_SD,
):
# TaskManager config
if task_config is None:
task_config = [CSI100_RECORD_XGBOOST_TASK_CONFIG, CSI100_RECORD_LGB_TASK_CONFIG]
mongo_conf = {
"task_url": task_url,
"task_db_name": task_db_name,

62
examples/online_srv/online_management_simulate.py
View File

@@ -13,63 +13,7 @@ from qlib.workflow.online.manager import OnlineManager
from qlib.workflow.online.strategy import RollingStrategy
from qlib.workflow.task.gen import RollingGen
from qlib.workflow.task.manage import TaskManager
data_handler_config = {
"start_time": "2018-01-01",
"end_time": "2018-10-31",
"fit_start_time": "2018-01-01",
"fit_end_time": "2018-03-31",
"instruments": "csi100",
}
dataset_config = {
"class": "DatasetH",
"module_path": "qlib.data.dataset",
"kwargs": {
"handler": {
"class": "Alpha158",
"module_path": "qlib.contrib.data.handler",
"kwargs": data_handler_config,
},
"segments": {
"train": ("2018-01-01", "2018-03-31"),
"valid": ("2018-04-01", "2018-05-31"),
"test": ("2018-06-01", "2018-09-10"),
},
},
}
record_config = [
{
"class": "SignalRecord",
"module_path": "qlib.workflow.record_temp",
},
{
"class": "SigAnaRecord",
"module_path": "qlib.workflow.record_temp",
},
]
# use lgb model
task_lgb_config = {
"model": {
"class": "LGBModel",
"module_path": "qlib.contrib.model.gbdt",
},
"dataset": dataset_config,
"record": record_config,
}
# use xgboost model
task_xgboost_config = {
"model": {
"class": "XGBModel",
"module_path": "qlib.contrib.model.xgboost",
},
"dataset": dataset_config,
"record": record_config,
}
from qlib.tests.config import CSI100_RECORD_LGB_TASK_CONFIG, CSI100_RECORD_XGBOOST_TASK_CONFIG
class OnlineSimulationExample:
@@ -84,7 +28,7 @@ class OnlineSimulationExample:
rolling_step=80,
start_time="2018-09-10",
end_time="2018-10-31",
tasks=[task_xgboost_config, task_lgb_config],
tasks=None,
):
"""
Init OnlineManagerExample.
@@ -101,6 +45,8 @@ class OnlineSimulationExample:
end_time (str, optional): the end time of simulating. Defaults to "2018-10-31".
tasks (dict or list[dict]): a set of the task config waiting for rolling and training
"""
if tasks is None:
tasks = [CSI100_RECORD_XGBOOST_TASK_CONFIG, CSI100_RECORD_LGB_TASK_CONFIG]
self.exp_name = exp_name
self.task_pool = task_pool
self.start_time = start_time

65
examples/online_srv/rolling_online_management.py
View File

@@ -17,62 +17,7 @@ from qlib.workflow import R
from qlib.workflow.online.strategy import RollingStrategy
from qlib.workflow.task.gen import RollingGen
from qlib.workflow.online.manager import OnlineManager
data_handler_config = {
"start_time": "2013-01-01",
"end_time": "2020-09-25",
"fit_start_time": "2013-01-01",
"fit_end_time": "2014-12-31",
"instruments": "csi100",
}
dataset_config = {
"class": "DatasetH",
"module_path": "qlib.data.dataset",
"kwargs": {
"handler": {
"class": "Alpha158",
"module_path": "qlib.contrib.data.handler",
"kwargs": data_handler_config,
},
"segments": {
"train": ("2013-01-01", "2014-12-31"),
"valid": ("2015-01-01", "2015-12-31"),
"test": ("2016-01-01", "2020-07-10"),
},
},
}
record_config = [
{
"class": "SignalRecord",
"module_path": "qlib.workflow.record_temp",
},
{
"class": "SigAnaRecord",
"module_path": "qlib.workflow.record_temp",
},
]
# use lgb model
task_lgb_config = {
"model": {
"class": "LGBModel",
"module_path": "qlib.contrib.model.gbdt",
},
"dataset": dataset_config,
"record": record_config,
}
# use xgboost model
task_xgboost_config = {
"model": {
"class": "XGBModel",
"module_path": "qlib.contrib.model.xgboost",
},
"dataset": dataset_config,
"record": record_config,
}
from qlib.tests.config import CSI100_RECORD_XGBOOST_TASK_CONFIG, CSI100_RECORD_LGB_TASK_CONFIG
class RollingOnlineExample:
@@ -83,9 +28,13 @@ class RollingOnlineExample:
task_url="mongodb://10.0.0.4:27017/",
task_db_name="rolling_db",
rolling_step=550,
tasks=[task_xgboost_config],
add_tasks=[task_lgb_config],
tasks=None,
add_tasks=None,
):
if add_tasks is None:
add_tasks = [CSI100_RECORD_LGB_TASK_CONFIG]
if tasks is None:
tasks = [CSI100_RECORD_XGBOOST_TASK_CONFIG]
mongo_conf = {
"task_url": task_url, # your MongoDB url
"task_db_name": task_db_name, # database name

49
examples/online_srv/update_online_pred.py
View File

@@ -7,56 +7,19 @@ There are two parts including first_train and update_online_pred.
Firstly, we will finish the training and set the trained models to the `online` models.
Next, we will finish updating online predictions.
"""
import copy
import fire
import qlib
from qlib.config import REG_CN
from qlib.model.trainer import task_train
from qlib.workflow.online.utils import OnlineToolR
from qlib.tests.config import CSI300_GBDT_TASK
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": "csi100",
}
task = copy.deepcopy(CSI300_GBDT_TASK)
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",
},
task["record"] = {
"class": "SignalRecord",
"module_path": "qlib.workflow.record_temp",
}

8
examples/rolling_process_data/workflow.py
View File

@@ -4,13 +4,11 @@
import qlib
import fire
import pickle
import pandas as pd
from datetime import datetime
from qlib.config import REG_CN
from qlib.data.dataset.handler import DataHandlerLP
from qlib.contrib.data.handler import Alpha158
from qlib.utils import exists_qlib_data, init_instance_by_config
from qlib.utils import init_instance_by_config
from qlib.tests.data import GetData
@@ -24,9 +22,7 @@ class RollingDataWorkflow:
def _init_qlib(self):
"""initialize qlib"""
provider_uri = "~/.qlib/qlib_data/cn_data" # target_dir
if not exists_qlib_data(provider_uri):
print(f"Qlib data is not found in {provider_uri}")
GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
qlib.init(provider_uri=provider_uri, region=REG_CN)
def _dump_pre_handler(self, path):

11
examples/run_all_model.py
View File

@@ -5,13 +5,11 @@ import os
import sys
import fire
import time
import venv
import glob
import shutil
import signal
import inspect
import tempfile
import traceback
import functools
import statistics
import subprocess
@@ -23,8 +21,7 @@ from pprint import pprint
import qlib
from qlib.config import REG_CN
from qlib.workflow import R
from qlib.workflow.cli import workflow
from qlib.utils import exists_qlib_data
from qlib.tests.data import GetData
# init qlib
@@ -39,12 +36,8 @@ exp_manager = {
"default_exp_name": "Experiment",
},
}
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.joinpath("scripts")))
from get_data import GetData
GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
qlib.init(provider_uri=provider_uri, region=REG_CN, exp_manager=exp_manager)
# decorator to check the arguments

7
examples/workflow_by_code.py
View File

@@ -12,10 +12,7 @@ if __name__ == "__main__":
# use default data
provider_uri = "~/.qlib/qlib_data/cn_data" # target_dir
if not exists_qlib_data(provider_uri):
print(f"Qlib data is not found in {provider_uri}")
GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
qlib.init(provider_uri=provider_uri, region=REG_CN)
market = "csi300"
@@ -112,7 +109,7 @@ if __name__ == "__main__":
# 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)
R.save_objects(**{"params.pkl": model})