liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-13 07:46:53 +08:00
Code Activity

online serving V9 middle status

Browse Source
This commit is contained in:
lzh222333
2021-04-28 09:23:07 +00:00
parent 42f510024c
commit 40cf83e557
9 changed files with 721 additions and 135 deletions
Download Patch File Download Diff File Expand all files Collapse all files

81
examples/online_srv/online_management_simulate.py
View File

@@ -1,20 +1,23 @@
import fire
import qlib
from qlib.model.ens.ensemble import ens_workflow
from qlib.model.trainer import DelayTrainerR, DelayTrainerRM, TrainerRM
from qlib.workflow import R
from qlib.workflow.online.manager import RollingOnlineManager
from qlib.workflow.online.simulator import OnlineSimulator
from qlib.workflow.task.collect import RecorderCollector
from qlib.workflow.task.gen import RollingGen, task_generator
from qlib.workflow.task.manage import TaskManager
from qlib.workflow.task.utils import list_recorders
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
"""
This examples is about the OnlineManager and OnlineSimulator based on rolling tasks.
The OnlineManager will focus on the updating of your online models.
The OnlineSimulator will focus on the simulating real updating routine of your online models.
"""
import fire
import qlib
from qlib.model.ens.ensemble import ens_workflow
from qlib.model.trainer import DelayTrainerR, DelayTrainerRM, TrainerRM
from qlib.workflow import R
from qlib.workflow.online.manager import OnlineM # RollingOnlineManager
from qlib.workflow.online.strategy import OnlineStrategy, RollingAverageStrategy
from qlib.workflow.task.collect import RecorderCollector
from qlib.workflow.task.gen import RollingGen, task_generator
from qlib.workflow.task.manage import TaskManager
from qlib.workflow.task.utils import list_recorders
data_handler_config = {
@@ -105,6 +108,8 @@ class OnlineSimulationExample:
"""
self.exp_name = exp_name
self.task_pool = task_pool
self.start_time = start_time
self.end_time = end_time
mongo_conf = {
"task_url": task_url,
"task_db_name": task_db_name,
@@ -115,17 +120,18 @@ class OnlineSimulationExample:
) # The rolling tasks generator, modify_end_time is false because we just need simulate to 2018-10-31.
self.trainer = DelayTrainerRM(self.exp_name, self.task_pool)
self.task_manager = TaskManager(self.task_pool) # A good way to manage all your tasks
self.rolling_online_manager = RollingOnlineManager(
experiment_name=exp_name,
rolling_gen=self.rolling_gen,
trainer=self.trainer,
self.rolling_online_manager = OnlineM(
RollingAverageStrategy(
exp_name, task_template=tasks, rolling_gen=self.rolling_gen, trainer=self.trainer, need_log=False
),
begin_time=self.start_time,
need_log=False,
) # The OnlineManager based on Rolling
self.onlinesimulator = OnlineSimulator(
start_time=start_time,
end_time=end_time,
online_manager=self.rolling_online_manager,
)
# self.onlinesimulator = OnlineSimulator(
# start_time=start_time,
# end_time=end_time,
# online_manager=self.rolling_online_manager,
# )
self.tasks = tasks
# Reset all things to the first status, be careful to save important data
@@ -137,37 +143,16 @@ class OnlineSimulationExample:
for rid in exp.list_recorders():
exp.delete_recorder(rid)
for rid in list_recorders(
RollingOnlineManager.SIGNAL_EXP, lambda x: True if x.info["name"] == self.exp_name else False
):
for rid in list_recorders("OnlineManagerSignals", lambda x: True if x.info["name"] == self.exp_name else False):
exp.delete_recorder(rid)
# Run this firstly to see the workflow in OnlineManager
def first_train(self):
print("========== first train ==========")
self.reset()
self.rolling_online_manager.first_train(self.tasks)
# Run this secondly to see the simulating in OnlineSimulator
def simulate(self):
print("========== simulate ==========")
self.onlinesimulator.simulate()
print(self.rolling_online_manager.collect_artifact())
print("========== online models ==========")
recs_dict = self.onlinesimulator.online_models()
for time, recs in recs_dict.items():
print(f"{str(time[0])} to {str(time[1])}:")
for rec in recs:
print(rec.info["id"])
print("========== online signals ==========")
print(self.rolling_online_manager.get_signals())
# Run this to run all workflow automaticly
def main(self):
self.first_train()
self.simulate()
self.reset()
print("========== simulate ==========")
self.rolling_online_manager.simulate(end_time=self.end_time)
print(self.rolling_online_manager.get_collector()())
print(self.rolling_online_manager.get_online_history(self.exp_name))
if __name__ == "__main__":

76
examples/online_srv/rolling_online_management.py
View File

@@ -1,21 +1,22 @@
import os
from pathlib import Path
import pickle
import fire
import qlib
from qlib.workflow import R
from qlib.workflow.task.gen import RollingGen
from qlib.workflow.task.manage import TaskManager
from qlib.workflow.online.manager import RollingOnlineManager
from qlib.workflow.task.utils import list_recorders
from qlib.model.trainer import TrainerRM
"""
This example show how RollingOnlineManager works with rolling tasks.
There are two parts including first train and routine.
Firstly, the RollingOnlineManager will finish the first training and set trained models to `online` models.
Next, the RollingOnlineManager will finish a routine process, including update online prediction -> prepare signals -> prepare tasks -> prepare new models -> reset online models
"""
import os
from pathlib import Path
import pickle
import fire
import qlib
from qlib.workflow import R
from qlib.workflow.online.strategy import OnlineStrategy, RollingAverageStrategy
from qlib.workflow.task.gen import RollingGen
from qlib.workflow.task.manage import TaskManager
from qlib.workflow.online.manager import OnlineM
from qlib.workflow.task.utils import list_recorders
from qlib.model.trainer import TrainerRM
from pprint import pprint
data_handler_config = {
"start_time": "2013-01-01",
@@ -77,58 +78,65 @@ task_xgboost_config = {
class RollingOnlineExample:
def __init__(
self,
exp_name="rolling_exp",
task_pool="rolling_task",
provider_uri="~/.qlib/qlib_data/cn_data",
region="cn",
task_url="mongodb://10.0.0.4:27017/",
task_db_name="rolling_db",
rolling_step=550,
tasks=[task_xgboost_config, task_lgb_config],
):
self.exp_name = exp_name
self.task_pool = task_pool
mongo_conf = {
"task_url": task_url, # your MongoDB url
"task_db_name": task_db_name, # database name
}
qlib.init(provider_uri=provider_uri, region=region, mongo=mongo_conf)
self.rolling_online_manager = RollingOnlineManager(
experiment_name=exp_name,
rolling_gen=RollingGen(step=rolling_step, rtype=RollingGen.ROLL_SD),
trainer=TrainerRM(self.exp_name, self.task_pool),
)
self.tasks = tasks
self.rolling_step = rolling_step
strategy = []
for task in tasks:
name_id = task["model"]["class"] + "_" + str(self.rolling_step)
strategy.append(
RollingAverageStrategy(
name_id,
task,
RollingGen(step=rolling_step, rtype=RollingGen.ROLL_SD),
TrainerRM(experiment_name=name_id, task_pool=name_id),
)
)
self.rolling_online_manager = OnlineM(strategy)
_ROLLING_MANAGER_PATH = ".rolling_manager" # the RollingOnlineManager will dump to this file, for it will be loaded when calling routine.
# Reset all things to the first status, be careful to save important data
def reset(self):
print("========== reset ==========")
TaskManager(self.task_pool).remove()
exp = R.get_exp(experiment_name=self.exp_name)
for rid in exp.list_recorders():
exp.delete_recorder(rid)
for task in self.tasks:
name_id = task["model"]["class"] + "_" + str(self.rolling_step)
TaskManager(name_id).remove()
exp = R.get_exp(experiment_name=name_id)
for rid in exp.list_recorders():
exp.delete_recorder(rid)
if os.path.exists(self._ROLLING_MANAGER_PATH):
os.remove(self._ROLLING_MANAGER_PATH)
if os.path.exists(self._ROLLING_MANAGER_PATH):
os.remove(self._ROLLING_MANAGER_PATH)
for rid in list_recorders(
RollingOnlineManager.SIGNAL_EXP, lambda x: True if x.info["name"] == self.exp_name else False
):
exp.delete_recorder(rid)
for rid in list_recorders("OnlineManagerSignals", lambda x: True if x.info["name"] == name_id else False):
exp.delete_recorder(rid)
def first_run(self):
print("========== first_run ==========")
self.reset()
self.rolling_online_manager.first_train([task_xgboost_config, task_lgb_config])
self.rolling_online_manager.first_train()
self.rolling_online_manager.to_pickle(self._ROLLING_MANAGER_PATH)
print(self.rolling_online_manager.collect_artifact())
print(self.rolling_online_manager.get_collector()())
def routine(self):
print("========== routine ==========")
with Path(self._ROLLING_MANAGER_PATH).open("rb") as f:
self.rolling_online_manager = pickle.load(f)
self.rolling_online_manager.routine()
print(self.rolling_online_manager.collect_artifact())
print(self.rolling_online_manager.get_collector()())
def main(self):
self.first_run()

22
examples/online_srv/update_online_pred.py
View File

@@ -1,16 +1,14 @@
"""
This example show how OnlineTool works when we need update prediction.
There are two parts including first_train and update_online_pred.
Firstly, we will finish the training and set the trained model to `online` model.
Next, we will finish updating online prediction.
"""
import fire
import qlib
from qlib.config import REG_CN
from qlib.model.trainer import task_train
from qlib.workflow.online.manager import OnlineManagerR
from qlib.workflow.task.utils import list_recorders
"""
This example show how OnlineManager works when we need update prediction.
There are two parts including first_train and update_online_pred.
Firstly, the RollingOnlineManager will finish the first training and set the trained model to `online` model.
Next, the RollingOnlineManager will finish updating online prediction
"""
from qlib.workflow.online.utils import OnlineToolR
data_handler_config = {
"start_time": "2008-01-01",
@@ -65,15 +63,15 @@ class UpdatePredExample:
):
qlib.init(provider_uri=provider_uri, region=region)
self.experiment_name = experiment_name
self.online_manager = OnlineManagerR(self.experiment_name)
self.online_tool = OnlineToolR(self.experiment_name)
self.task_config = task_config
def first_train(self):
rec = task_train(self.task_config, experiment_name=self.experiment_name)
self.online_manager.reset_online_tag(rec) # set to online model
self.online_tool.reset_online_tag(rec) # set to online model
def update_online_pred(self):
self.online_manager.update_online_pred()
self.online_tool.update_online_pred()
def main(self):
self.first_train()