mirror of
https://github.com/NicolasBohn/NexQuant.git
synced 2026-07-29 00:17:44 +00:00
7f4c2d18c6
* refine ds modal for more cases: eval and es * update model template * prompts for model and ensemble * fix a bug * fix a bug * init: ds workflow evovingstrategy * Adding ensemble (#505) * Initial Draft * Updating logic for init * Revising * Successful Testing * Updating to use the latest & right class * bug: bug-fixing for testing * data science loop changes * data science loop base * ds loop feedback * fix * remove measure_time because it's duplicated (in LoopBase) * add the knowledge query for data_loader & feature * edit ds workflow evaluator * data_loader bug fix * stop evolving when all tasks completed * llm app change * fix break all complete strategy * Adding queried knowledge (#508) Co-authored-by: XianBW <36835909+XianBW@users.noreply.github.com> * fix loop bug * ds workflow evaluator; test; refine prompts * workflow spec * fix ci * feature task changes * ds loop change * fix a bug in feat * add query knowledge for model and workflow * llm_debug info(for show) using pickle instead of json * remove NextLoopException * loop change * coder raise CoderError when all sub_tasks failed * rename code_dict to file_dict in FBWorkspace * add CoSTEER unittest * now show self.version in Task.get_task_information(), simplify CoSTEER sub tasks definition * remove some properties in ModelTask, add model_type in it. * fix llm app bug * llm web app bug fix * ds loop bug fix * fix: give component code to feature&ens eval * loop catch error bug * rename load_from_raw_data to load_data * feat: Add debug data creation functionality for data science scenarios * support local folder (#511) * support local folder * remove unnecessary random * KaggleScen Subclass * small fix * use template for style description * update default scen to kaggle * update sample data script * make sure frac < 1 * fix a bug * feature spec changes * fix * changeimport order * clear unnecessary std outputs * fix a typo * create sample folder after unzip kaggle data * feature/model test script update * Align the data types across modules. * fix a bug in model eval * show line number * move sample entry point to app * spec & model prompt changes * Refine the competition specification to address the data type problem and the coherence issue. * fix some bugs * add file filter in FBworkspace.code property * support non-binary prediction * avoid too much warnings * fix a bug in ensemble module * filtered the knowledge query in all modules * delete RAG in idea proposal * refine the code in ensemble * show exp workspace in llm_st * exp_gen bug fix * feedback bug fix * use `feature` instead of `feat01` * Trace & method of judging if exp is completed change * fix a bug in package calling and execute ci * fix code * bug fix * bug fix * fix a bug * fix some bugs * fix a bug * refactor: Enhance error handling and feedback in data science loop * support different use_azure on chat and embedding models * multi-model proposal logic * fix a small syntax error * loopBase and some changes * ensemble scores change * fbworkspace.code -> .all_codes * use all model codes in workflow coder * check scores.csv's keys(model_names) * model name changes * add a todo in ensemble test * sota_exp changes * give model info in exp gen * add runner time limit * config using debug data or not in evals * exp to feedback base * add feature code when writing model task * small problem * copying during sampling * update * refactor: Simplify code handling and improve workspace management * model part output fix * print model's execution time * bug fix * ensemble test fix * ens small change * ens_test bug fix * Refine partial expansion logic to display only a few subfolders when their structure is uniform, improving readability in nested directories. * several update on prompts * sample subfolders * Filter the stdout after code execution to remove irrelevant information e.g. progress bars, whitespace characters, excessive line breaks. * Add some more prompts and comments * several update on the first init rounds * model timeout as error * fix pattern of getting model codes in workspace * small bux fix on model prompts * remove get_code_with_key since we have regex pattern * fix: Correct tqdm progress bar update logic in LoopBase class * feat: Add diff generation and enhance feedback mechanism in data science loop * update some fix to model and workflow prompts * refine the logic of progress bar filter * add last_successful_exp in exp_gen * fix a one line bug * add a hint in prompt * fix data sample for bms * fix data sample for bms * hypothesis small fix * crawler readme update * fix component gen * fix bug * annotation change * load description.md if it exists * refactor: Simplify SOTA description handling in feedback and prompts * refactor: Use shared templates for feedback and experiment descriptions * change webapp for model codes changes * update proposal * add timeout message for docker run output * fix * refine the code in docker time processing * use .shape instead of len() when do shape eval * won't change size during iteration * support bson sample * sample support jsonl and bson * add former_code to coder prompts * a little speed us in debug data creating * filter progress bar when eval ens and main * avoid costeer makes no change to former code * fix several log error * add timeout judge threshold * fix some bugs in the evaluation of component output shapes * File structure for supporting litellm (#517) Co-authored-by: Young <afe.young@gmail.com> * ignore submission and show processing * ignore submission and show processing * add efficiency notice * refactor: Enhance error message with detailed feedback summary * refactor: Simplify component handling in DSExpGen class * refactor: Update code structure and add docstring for clarity * reserve one sample to each label in data sampling * add Evaluation info * refine costeer code to avoid giving same code twice * use raw_description as plain text * add a prompt hint to avoid same dict key * model task name bug in first model exp gen * fix a typo * add some debug info in costeer tests * task init change * enhance data sampling * refine the code in data_loader * more reasonable loop * fix a bug in data folder description * add error msg & traceback to execution feedback * fix llm error msg detection * add task information to costeer eval & add cache to docker run(use zipfile to store the whole workspace) * fix CI first round * fix CI second round * use txt to store test script to avoid pytest * remove zipfile in requirements * add azure.identity to requirements * ignore debug web page * component test changes * remove redundent task_desc in model coder * feat: Add APE module and prompts for automated prompt engineering * fix: Update .gitignore and improve text formatting in eval.py * refactor: Update print output and improve code comments and imports * style: Fix string formatting and import order in ape.py and fmt.py * exclude ape * add a data folder notice * reduce unnecessary output to stdout * refine the code of describe_data_folder * fix ci * style: streamlit style update (#522) * streamlit style update * fix import * fix format * fix llm_st loop progress bar * debugapp small change * fix model str * refine some prompts * fix model str * fix CI * refine the logic associated with the data_folder * fix ci * small change * set filter_progress_bar as default in execute * model proposal with workflow * add submission check in workflow eval * fix bug * small change * fix CI * fix CI * refactor: Move generate_diff to utils and update DSExpGen logic * more reasonable prompt describing metric direction * fix a minor jinja2 bug * quick fix exp_gen bugs * fix the following bug * fix * fix some bugs * remove workflow from model * add pending_tasks_list in data science to enable coding model and workflow * refine the code for handling JSON-formatted data descriptions * assert with information * ensure correct csv file name * add logging to help record the output * log competition * add log tag for debug llm app * test: Test ds refactor ll (#523) * fix bugs to former scenario * fix a bug because coding in rdloop changed * fix the bug when feedback gets no hypothesis * fix trace structure * change all trace hist when merging hypothesis to experiments * ignore some error in ruff * fix kaggle scenario bugs * refine one line * another bug * another small bug * fix ui bugs * chage kaggle train.py path --------- Co-authored-by: Xu Yang <peteryang@vip.qq.com> * fix CI * Update rdagent/app/data_science/loop.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * add samplecsv into spec prompts * fix CI --------- Co-authored-by: TPLin22 <tplin2@163.com> Co-authored-by: yuanteli <1957922024@qq.com> Co-authored-by: Xisen Wang <118058822+xisen-w@users.noreply.github.com> Co-authored-by: Bowen Xian <xianbowen@outlook.com> Co-authored-by: Xu Yang <peteryang@vip.qq.com> Co-authored-by: XianBW <36835909+XianBW@users.noreply.github.com> Co-authored-by: Tim <illking@foxmail.com> Co-authored-by: 炼金术师华华 <37462254+YeewahChan@users.noreply.github.com> Co-authored-by: Linlang <30293408+SunsetWolf@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
291 lines
10 KiB
Python
291 lines
10 KiB
Python
from __future__ import annotations
|
|
|
|
import os
|
|
import platform
|
|
import re
|
|
import shutil
|
|
import typing
|
|
import uuid
|
|
from abc import ABC, abstractmethod
|
|
from collections.abc import Sequence
|
|
from copy import deepcopy
|
|
from pathlib import Path
|
|
from typing import Any, Generic, TypeVar
|
|
|
|
from rdagent.core.conf import RD_AGENT_SETTINGS
|
|
from rdagent.utils import filter_progress_bar
|
|
|
|
if typing.TYPE_CHECKING:
|
|
from rdagent.core.proposal import Hypothesis
|
|
from rdagent.utils.env import Env
|
|
|
|
"""
|
|
This file contains the all the class about organizing the task in RD-Agent.
|
|
"""
|
|
|
|
|
|
class AbsTask(ABC):
|
|
def __init__(self, name: str, version: int = 1) -> None:
|
|
"""
|
|
The version of the task, default is 1
|
|
Because qlib tasks execution and kaggle tasks execution are different, we need to distinguish them.
|
|
TODO: We may align them in the future.
|
|
"""
|
|
self.version = version
|
|
self.name = name
|
|
|
|
@abstractmethod
|
|
def get_task_information(self) -> str:
|
|
"""
|
|
Get the task information string to build the unique key
|
|
"""
|
|
|
|
|
|
class Task(AbsTask):
|
|
def __init__(self, name: str, version: int = 1, description: str = "") -> None:
|
|
super().__init__(name, version)
|
|
self.description = description
|
|
|
|
def get_task_information(self) -> str:
|
|
return f"Task Name: {self.name}\nDescription: {self.description}"
|
|
|
|
def __repr__(self) -> str:
|
|
return f"<{self.__class__.__name__} {self.name}>"
|
|
|
|
|
|
ASpecificTask = TypeVar("ASpecificTask", bound=Task)
|
|
|
|
|
|
class Workspace(ABC, Generic[ASpecificTask]):
|
|
"""
|
|
A workspace is a place to store the task implementation. It evolves as the developer implements the task.
|
|
To get a snapshot of the workspace, make sure call `copy` to get a copy of the workspace.
|
|
"""
|
|
|
|
def __init__(self, target_task: ASpecificTask | None = None) -> None:
|
|
self.target_task: ASpecificTask | None = target_task
|
|
|
|
@abstractmethod
|
|
def execute(self, *args: Any, **kwargs: Any) -> object | None:
|
|
error_message = "execute method is not implemented."
|
|
raise NotImplementedError(error_message)
|
|
|
|
@abstractmethod
|
|
def copy(self) -> Workspace:
|
|
error_message = "copy method is not implemented."
|
|
raise NotImplementedError(error_message)
|
|
|
|
@property
|
|
@abstractmethod
|
|
def all_codes(self) -> str:
|
|
"""
|
|
Get all the code files in the workspace as a single string.
|
|
"""
|
|
|
|
|
|
ASpecificWS = TypeVar("ASpecificWS", bound=Workspace)
|
|
|
|
|
|
class WsLoader(ABC, Generic[ASpecificTask, ASpecificWS]):
|
|
@abstractmethod
|
|
def load(self, task: ASpecificTask) -> ASpecificWS:
|
|
error_message = "load method is not implemented."
|
|
raise NotImplementedError(error_message)
|
|
|
|
|
|
class FBWorkspace(Workspace):
|
|
"""
|
|
File-based task workspace
|
|
|
|
The implemented task will be a folder which contains related elements.
|
|
- Data
|
|
- Code Workspace
|
|
- Output
|
|
- After execution, it will generate the final output as file.
|
|
|
|
A typical way to run the pipeline of FBWorkspace will be:
|
|
(We didn't add it as a method due to that we may pass arguments into
|
|
`prepare` or `execute` based on our requirements.)
|
|
|
|
.. code-block:: python
|
|
|
|
def run_pipeline(self, **files: str):
|
|
self.prepare()
|
|
self.inject_files(**files)
|
|
self.execute()
|
|
|
|
"""
|
|
|
|
def __init__(self, *args: Any, **kwargs: Any) -> None:
|
|
super().__init__(*args, **kwargs)
|
|
self.file_dict: dict[str, Any] = (
|
|
{}
|
|
) # The code injected into the folder, store them in the variable to reproduce the former result
|
|
self.workspace_path: Path = RD_AGENT_SETTINGS.workspace_path / uuid.uuid4().hex
|
|
|
|
@staticmethod
|
|
def _format_code_dict(code_dict: dict[str, str]) -> str:
|
|
"""
|
|
Helper function to format the code dictionary into a string.
|
|
"""
|
|
code_string = ""
|
|
for file_name, code in code_dict.items():
|
|
code_string += f"\nFile Path: {file_name}\n```\n{code}\n```"
|
|
return code_string
|
|
|
|
@property
|
|
def all_codes(self) -> str:
|
|
"""
|
|
Get all the code files in the workspace as a single string, excluding test files.
|
|
"""
|
|
filtered_dict = {k: v for k, v in self.file_dict.items() if k.endswith(".py") and "test" not in k}
|
|
return self._format_code_dict(filtered_dict)
|
|
|
|
def get_codes(self, pattern: str) -> str:
|
|
"""
|
|
Get code files matching a specific pattern as a single string, excluding test files.
|
|
"""
|
|
filtered_dict = {
|
|
k: v for k, v in self.file_dict.items() if re.search(pattern, k) and k.endswith(".py") and "test" not in k
|
|
}
|
|
return self._format_code_dict(filtered_dict)
|
|
|
|
def prepare(self) -> None:
|
|
"""
|
|
Prepare the workspace except the injected code
|
|
- Data
|
|
- Documentation
|
|
typical usage of `*args, **kwargs`:
|
|
Different methods shares the same data. The data are passed by the arguments.
|
|
"""
|
|
self.workspace_path.mkdir(parents=True, exist_ok=True)
|
|
|
|
@staticmethod
|
|
def link_all_files_in_folder_to_workspace(data_path: Path, workspace_path: Path) -> None:
|
|
data_path = Path(data_path).absolute() # in case of relative path that will be invalid when we change cwd.
|
|
workspace_path = Path(workspace_path)
|
|
for data_file_path in data_path.iterdir():
|
|
workspace_data_file_path = workspace_path / data_file_path.name
|
|
if workspace_data_file_path.exists():
|
|
workspace_data_file_path.unlink()
|
|
if platform.system() == "Linux":
|
|
os.symlink(data_file_path, workspace_data_file_path)
|
|
if platform.system() == "Windows":
|
|
os.link(data_file_path, workspace_data_file_path)
|
|
|
|
DEL_KEY = "__DEL__"
|
|
|
|
def inject_files(self, **files: str) -> None:
|
|
"""
|
|
Inject the code into the folder.
|
|
{
|
|
<file name1>: <code>, // indicate writing <code> into <file name>
|
|
(create new file or replace existing file)
|
|
<file name2>: "__DEL__" // indicate removing file name2. When we want to replace a file to a new one,
|
|
we usually use this
|
|
}
|
|
"""
|
|
self.prepare()
|
|
for k, v in files.items():
|
|
target_file_path = self.workspace_path / k # Define target_file_path before using it
|
|
if v == self.DEL_KEY: # Use self.DEL_KEY to access the class variable
|
|
if target_file_path.exists():
|
|
target_file_path.unlink() # Unlink the file if it exists
|
|
self.file_dict.pop(k, None) # Safely remove the key from file_dict
|
|
else:
|
|
self.file_dict[k] = v
|
|
target_file_path.parent.mkdir(parents=True, exist_ok=True)
|
|
target_file_path.write_text(v)
|
|
|
|
def get_files(self) -> list[Path]:
|
|
"""
|
|
Get the environment description.
|
|
|
|
To be general, we only return a list of filenames.
|
|
How to summarize the environment is the responsibility of the Developer.
|
|
"""
|
|
return list(self.workspace_path.iterdir())
|
|
|
|
def inject_code_from_folder(self, folder_path: Path) -> None:
|
|
"""
|
|
Load the workspace from the folder
|
|
"""
|
|
for file_path in folder_path.rglob("*"):
|
|
if file_path.suffix in (".py", ".yaml", ".md"):
|
|
relative_path = file_path.relative_to(folder_path)
|
|
self.inject_files(**{str(relative_path): file_path.read_text()})
|
|
|
|
def copy(self) -> FBWorkspace:
|
|
"""
|
|
copy the workspace from the original one
|
|
"""
|
|
return deepcopy(self)
|
|
|
|
def clear(self) -> None:
|
|
"""
|
|
Clear the workspace
|
|
"""
|
|
shutil.rmtree(self.workspace_path, ignore_errors=True)
|
|
self.file_dict = {}
|
|
|
|
def execute(self, env: Env | None = None, entry: str | None = None) -> object | None:
|
|
"""
|
|
Before each execution, make sure to prepare and inject code
|
|
"""
|
|
self.prepare()
|
|
self.inject_files(**self.file_dict)
|
|
# TODO: env should be not None in new design (no code can run without environment)
|
|
if env is not None and entry is not None:
|
|
return filter_progress_bar(env.run(entry, str(self.workspace_path)))
|
|
return None
|
|
|
|
def __str__(self) -> str:
|
|
return f"Workspace[{self.workspace_path=}" + (
|
|
"]" if self.target_task is None else f",{self.target_task.name=}]"
|
|
)
|
|
|
|
|
|
ASpecificWSForExperiment = TypeVar("ASpecificWSForExperiment", bound=Workspace)
|
|
ASpecificWSForSubTasks = TypeVar("ASpecificWSForSubTasks", bound=Workspace)
|
|
|
|
|
|
class Experiment(
|
|
ABC,
|
|
Generic[ASpecificTask, ASpecificWSForExperiment, ASpecificWSForSubTasks],
|
|
):
|
|
"""
|
|
The experiment is a sequence of tasks and the implementations of the tasks after generated by the Developer.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
sub_tasks: Sequence[ASpecificTask],
|
|
based_experiments: Sequence[ASpecificWSForExperiment] = [],
|
|
hypothesis: Hypothesis | None = None,
|
|
) -> None:
|
|
self.hypothesis: Hypothesis | None = hypothesis # Experiment is optionally generated by hypothesis
|
|
self.sub_tasks: Sequence[ASpecificTask] = sub_tasks
|
|
self.sub_workspace_list: list[ASpecificWSForSubTasks | None] = [None] * len(self.sub_tasks)
|
|
# TODO:
|
|
# It will be used in runner in history
|
|
# If we implement the whole workflow, we don't have to use it, then we remove it.
|
|
self.based_experiments: Sequence[ASpecificWSForExperiment] = based_experiments
|
|
|
|
self.result: object = None # The result of the experiment, can be different types in different scenarios.
|
|
self.sub_results: dict[str, float] = (
|
|
{}
|
|
) # TODO: in Kaggle, now sub results are all saved in self.result, remove this in the future.
|
|
self.experiment_workspace: ASpecificWSForExperiment | None = None
|
|
|
|
|
|
ASpecificExp = TypeVar("ASpecificExp", bound=Experiment)
|
|
|
|
TaskOrExperiment = TypeVar("TaskOrExperiment", Task, Experiment)
|
|
|
|
|
|
class Loader(ABC, Generic[TaskOrExperiment]):
|
|
@abstractmethod
|
|
def load(self, *args: Any, **kwargs: Any) -> TaskOrExperiment:
|
|
err_msg = "load method is not implemented."
|
|
raise NotImplementedError(err_msg)
|