liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-11 23:06:58 +08:00
Code Activity

trainer & group & collect & ensemble

Browse Source
This commit is contained in:
lzh222333
2021-04-02 04:27:14 +00:00
parent edcd7b1ff9
commit bd7a1c11b9
12 changed files with 319 additions and 261 deletions
Download Patch File Download Diff File Expand all files Collapse all files

58
qlib/workflow/task/collect.py
View File

@@ -1,49 +1,54 @@
from abc import abstractmethod
from typing import Callable, Union
import pandas as pd
from qlib import get_module_logger
from qlib.workflow.task.utils import list_recorders
class Collector:
"""The collector to collect different results based on experiment backend and ensemble method"""
"""The collector to collect different results"""
def collect(self, ensemble, get_group_key_func, *args, **kwargs):
"""To collect the results, we need to get the experiment record firstly and divided them into
different groups. Then use ensemble methods to merge the group.
def collect(self, *args, **kwargs):
"""Collect the results and return a dict like {key: things}
Args:
ensemble (Ensemble): an instance of Ensemble
get_group_key_func (Callable): a function to get the group of a experiment record
Returns:
dict: the dict after collected.
For example:
{"prediction": pd.Series}
{"IC": {"Xgboost": pd.Series, "LSTM": pd.Series}}
......
"""
raise NotImplementedError(f"Please implement the `collect` method.")
class RecorderCollector(Collector):
def __init__(self, exp_name, artifacts_path={"pred": "pred.pkl", "IC": "sig_analysis/ic.pkl"}) -> None:
def __init__(
self, exp_name, artifacts_path={"pred": "pred.pkl", "IC": "sig_analysis/ic.pkl"}, rec_key_func=None
) -> None:
"""init RecorderCollector
Args:
exp_name (str): the name of Experiment
artifacts_path (dict, optional): The artifacts name and its path in Recorder. Defaults to {"pred": "pred.pkl", "IC": "sig_analysis/ic.pkl"}.
rec_key_func (Callable): a function to get the key of a recorder. If None, use recorder id.
"""
self.exp_name = exp_name
self.artifacts_path = artifacts_path
if rec_key_func is None:
rec_key_func = lambda rec: rec.info["id"]
self._get_key = rec_key_func
def collect(self, ensemble, get_group_key_func, artifacts_key=None, rec_filter_func=None):
"""Collect different artifacts based on recorder after filtering and ensemble method.
Group recorder by get_group_key_func.
def collect(self, artifacts_key=None, rec_filter_func=None): # ensemble, get_group_key_func,
"""Collect different artifacts based on recorder after filtering.
Args:
ensemble (Ensemble): an instance of Ensemble
get_group_key_func (Callable): a function to get the group of a experiment record
artifacts_key (str or List, optional): the artifacts key you want to get. Defaults to None.
artifacts_key (str or List, optional): the artifacts key you want to get. If None, get all artifacts.
rec_filter_func (Callable, optional): filter the recorder by return True or False. Defaults to None.
Returns:
dict: the dict after collected.
dict: the dict after collected like {artifact: {rec_key: object}}
"""
if artifacts_key is None:
artifacts_key = self.artifacts_path.keys()
@@ -51,22 +56,13 @@ class RecorderCollector(Collector):
if isinstance(artifacts_key, str):
artifacts_key = [artifacts_key]
# prepare_ensemble
ensemble_dict = {}
for key in artifacts_key:
ensemble_dict.setdefault(key, {})
collect_dict = {}
# filter records
recs_flt = list_recorders(self.exp_name, rec_filter_func)
for _, rec in recs_flt.items():
group_key = get_group_key_func(rec)
rec_key = self._get_key(rec)
for key in artifacts_key:
artifact = rec.load_object(self.artifacts_path[key])
ensemble_dict[key][group_key] = artifact
collect_dict.setdefault(key, {})[rec_key] = artifact
if isinstance(artifacts_key, str):
return ensemble(ensemble_dict[artifacts_key])
collect_dict = {}
for key in artifacts_key:
collect_dict[key] = ensemble(ensemble_dict[key])
return collect_dict
return collect_dict