liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-14 08:16:54 +08:00
Code Activity

format code

Browse Source
This commit is contained in:
lzh222333
2021-03-10 17:06:08 +00:00
parent e2f58274ba
commit 2ca2071d95
2 changed files with 34 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

75
examples/taskmanager/task_manager_rolling.py
View File

@@ -9,53 +9,37 @@ data_handler_config = {
"end_time": "2020-08-01", "end_time": "2020-08-01",
"fit_start_time": "2008-01-01", "fit_start_time": "2008-01-01",
"fit_end_time": "2014-12-31", "fit_end_time": "2014-12-31",
"instruments": 'csi100', "instruments": "csi100",
} }
dataset_config = { dataset_config = {
"class": "DatasetH", "class": "DatasetH",
"module_path": "qlib.data.dataset", "module_path": "qlib.data.dataset",
"kwargs": { "kwargs": {
"handler": { "handler": {"class": "Alpha158", "module_path": "qlib.contrib.data.handler", "kwargs": data_handler_config,},
"class": "Alpha158", "segments": {
"module_path": "qlib.contrib.data.handler", "train": ("2008-01-01", "2014-12-31"),
"kwargs": data_handler_config, "valid": ("2015-01-01", "2016-12-31"),
}, "test": ("2017-01-01", "2020-08-01"),
"segments": {
"train": ("2008-01-01", "2014-12-31"),
"valid": ("2015-01-01", "2016-12-31"),
"test": ("2017-01-01", "2020-08-01"),
},
}, },
} },
}
record_config = [ record_config = [
{ {"class": "SignalRecord", "module_path": "qlib.workflow.record_temp",},
"class": "SignalRecord", {"class": "SigAnaRecord", "module_path": "qlib.workflow.record_temp",},
"module_path": "qlib.workflow.record_temp",
},
{
"class": "SigAnaRecord",
"module_path": "qlib.workflow.record_temp",
}
] ]
# use lgb # use lgb
task_lgb_config = { task_lgb_config = {
"model": { "model": {"class": "LGBModel", "module_path": "qlib.contrib.model.gbdt",},
"class": "LGBModel",
"module_path": "qlib.contrib.model.gbdt",
},
"dataset": dataset_config, "dataset": dataset_config,
"record": record_config, "record": record_config,
} }
# use xgboost # use xgboost
task_xgboost_config = { task_xgboost_config = {
"model": { "model": {"class": "XGBModel", "module_path": "qlib.contrib.model.xgboost",},
"class": "XGBModel",
"module_path": "qlib.contrib.model.xgboost",
},
"dataset": dataset_config, "dataset": dataset_config,
"record": record_config, "record": record_config,
} }
@@ -64,17 +48,17 @@ provider_uri = "~/.qlib/qlib_data/cn_data" # target_dir
qlib.init(provider_uri=provider_uri, region=REG_CN) qlib.init(provider_uri=provider_uri, region=REG_CN)
C["mongo"] = { C["mongo"] = {
"task_url" : "mongodb://localhost:27017/", # maybe you need to change it to your url "task_url": "mongodb://localhost:27017/", # maybe you need to change it to your url
"task_db_name" : "rolling_db" "task_db_name": "rolling_db",
} }
exp_name = 'rolling_exp' # experiment name, will be used as the experiment in MLflow exp_name = "rolling_exp" # experiment name, will be used as the experiment in MLflow
task_pool = 'rolling_task' # task pool name, will be used as the document in MongoDB task_pool = "rolling_task" # task pool name, will be used as the document in MongoDB
tasks = task_generator( tasks = task_generator(
task_xgboost_config, # default task name task_xgboost_config, # default task name
RollingGen(step=550,rtype=RollingGen.ROLL_SD), # generate different date segment RollingGen(step=550, rtype=RollingGen.ROLL_SD), # generate different date segment
task_lgb=task_lgb_config # use "task_lgb" as the task name task_lgb=task_lgb_config, # use "task_lgb" as the task name
) )
# Uncomment next two lines to see the generated tasks # Uncomment next two lines to see the generated tasks
@@ -82,26 +66,29 @@ tasks = task_generator(
# pprint(tasks) # pprint(tasks)
tm = TaskManager(task_pool=task_pool) tm = TaskManager(task_pool=task_pool)
tm.create_task(tasks) # all tasks will be saved to MongoDB tm.create_task(tasks) # all tasks will be saved to MongoDB
from qlib.workflow.task.manage import run_task from qlib.workflow.task.manage import run_task
from qlib.workflow.task.collect import TaskCollector from qlib.workflow.task.collect import TaskCollector
from qlib.model.trainer import task_train from qlib.model.trainer import task_train
run_task(task_train, task_pool, experiment_name=exp_name) # all tasks will be trained using "task_train" method run_task(task_train, task_pool, experiment_name=exp_name) # all tasks will be trained using "task_train" method
def get_task_key(task_config): def get_task_key(task_config):
task_key = task_config["task_key"] task_key = task_config["task_key"]
rolling_end_timestamp = task_config["dataset"]["kwargs"]["segments"]["test"][1] rolling_end_timestamp = task_config["dataset"]["kwargs"]["segments"]["test"][1]
return task_key, rolling_end_timestamp.strftime('%Y-%m-%d') return task_key, rolling_end_timestamp.strftime("%Y-%m-%d")
def my_filter(task_config): def my_filter(task_config):
# only choose the results of "task_lgb" and test in 2019 from all tasks # only choose the results of "task_lgb" and test in 2019 from all tasks
task_key, rolling_end = get_task_key(task_config) task_key, rolling_end = get_task_key(task_config)
if task_key=="task_lgb" and rolling_end.startswith('2019'): if task_key == "task_lgb" and rolling_end.startswith("2019"):
return True return True
return False return False
# name tasks by "get_task_key" and filter tasks by "my_filter" # name tasks by "get_task_key" and filter tasks by "my_filter"
pred_rolling = TaskCollector.collect_predictions(exp_name, get_task_key, my_filter) pred_rolling = TaskCollector.collect_predictions(exp_name, get_task_key, my_filter)
pred_rolling pred_rolling

4
qlib/workflow/task/collect.py
View File

@@ -11,7 +11,9 @@ class TaskCollector:
@staticmethod @staticmethod
def collect_predictions( def collect_predictions(
experiment_name: str, get_key_func, filter_func=None, experiment_name: str,
get_key_func,
filter_func=None,
): ):
""" """