mirror of
https://github.com/NicolasBohn/NexQuant.git
synced 2026-07-28 16:07:46 +00:00
Xu Yang
f7c1c4fd74
* rename meta_tpl * use a isolated coder to deal with model feature selection and refine the structure * fix CI * fix: fix some errors in scenario.py, proposal.py and runner.py and several complex competition scenarios(#365) * fix several bugs in proposal and runner * fix a bug in feedback-prize-english-language-learning * fix some bugs and templates * fix the bug in optiver and nlp problem * delete unnecessary codes * remove unnecessary codes * complete forest and s4e8 * push * feedback & s4e8 & forest * optiver finished * s3e11 & s3e26 * s4e9 finished * sf-crime finished * the last one finished --------- Co-authored-by: WinstonLiyt <104308117+WinstonLiyt@users.noreply.github.com> Co-authored-by: WinstonLiyte <1957922024@qq.com>
73 lines
2.8 KiB
Python
73 lines
2.8 KiB
Python
import json
|
|
from pathlib import Path
|
|
|
|
from jinja2 import Environment, StrictUndefined
|
|
|
|
from rdagent.components.coder.factor_coder.CoSTEER import FactorCoSTEER
|
|
from rdagent.components.coder.model_coder.CoSTEER import ModelCoSTEER
|
|
from rdagent.core.developer import Developer
|
|
from rdagent.core.prompts import Prompts
|
|
from rdagent.oai.llm_utils import APIBackend
|
|
from rdagent.scenarios.kaggle.experiment.kaggle_experiment import (
|
|
KG_SELECT_MAPPING,
|
|
KGModelExperiment,
|
|
)
|
|
|
|
KGModelCoSTEER = ModelCoSTEER
|
|
KGFactorCoSTEER = FactorCoSTEER
|
|
|
|
prompt_dict = Prompts(file_path=Path(__file__).parent.parent / "prompts.yaml")
|
|
|
|
DEFAULT_SELECTION_CODE = """
|
|
import pandas as pd
|
|
def select(X: pd.DataFrame) -> pd.DataFrame:
|
|
\"""
|
|
Select relevant features. To be used in fit & predict function.
|
|
\"""
|
|
if X.columns.nlevels == 1:
|
|
return X
|
|
{% if feature_index_list is not none %}
|
|
X = X.loc[:, X.columns.levels[0][{{feature_index_list}}].tolist()]
|
|
{% endif %}
|
|
X.columns = ["_".join(str(col)).strip() for col in X.columns.values]
|
|
return X
|
|
"""
|
|
|
|
|
|
class KGModelFeatureSelectionCoder(Developer[KGModelExperiment]):
|
|
def develop(self, exp: KGModelExperiment) -> KGModelExperiment:
|
|
target_model_type = exp.sub_tasks[0].model_type
|
|
assert target_model_type in KG_SELECT_MAPPING
|
|
if len(exp.experiment_workspace.data_description) == 1:
|
|
code = (
|
|
Environment(undefined=StrictUndefined)
|
|
.from_string(DEFAULT_SELECTION_CODE)
|
|
.render(feature_index_list=None)
|
|
)
|
|
else:
|
|
system_prompt = (
|
|
Environment(undefined=StrictUndefined)
|
|
.from_string(prompt_dict["model_feature_selection"]["system"])
|
|
.render(scenario=self.scen.get_scenario_all_desc(), model_type=exp.sub_tasks[0].model_type)
|
|
)
|
|
user_prompt = (
|
|
Environment(undefined=StrictUndefined)
|
|
.from_string(prompt_dict["model_feature_selection"]["user"])
|
|
.render(feature_groups=[desc[0] for desc in exp.experiment_workspace.data_description])
|
|
)
|
|
|
|
chosen_index = json.loads(
|
|
APIBackend().build_messages_and_create_chat_completion(
|
|
user_prompt=user_prompt, system_prompt=system_prompt, json_mode=True
|
|
)
|
|
).get("Selected Group Index", [i + 1 for i in range(len(exp.experiment_workspace.data_description))])
|
|
chosen_index_to_list_index = [i - 1 for i in chosen_index]
|
|
|
|
code = (
|
|
Environment(undefined=StrictUndefined)
|
|
.from_string(DEFAULT_SELECTION_CODE)
|
|
.render(feature_index_list=chosen_index_to_list_index)
|
|
)
|
|
exp.experiment_workspace.inject_code(**{KG_SELECT_MAPPING[target_model_type]: code})
|
|
return exp
|