refactor: reorganize modules

ChenZiHong-Gavin · ChenZiHong-Gavin · commit b5a1b091df6e · 2025-04-17T16:39:57.000+08:00
diff --git a/.gitignore b/.gitignore
@@ -1,7 +1,178 @@
-__pycache__
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
 .env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
 cache
-*.log
 *.pyc
 *.html
-.idea/
diff --git a/graphgen/configs/config.yaml.example b/graphgen/configs/config.yaml.example
diff --git a/graphgen/configs/graphgen_config.yaml b/graphgen/configs/graphgen_config.yaml
@@ -3,7 +3,7 @@ input_file: resources/examples/raw_demo.jsonl
 tokenizer: cl100k_base
 quiz_samples: 2
 traverse_strategy:
-  qa_form: atomic
+  qa_form: open
   bidirectional: true
   difficulty_order:
   - medium
diff --git a/graphgen/evaluate.py b/graphgen/evaluate.py
@@ -5,8 +5,8 @@
 import argparse
 import pandas as pd
 from dotenv import load_dotenv
-from graphgen.models import LengthEvaluator, MTLDEvaluator, RewardEvaluator, TextPair, UniEvaluator
-from graphgen.utils import logger, set_logger
+from .models import LengthEvaluator, MTLDEvaluator, RewardEvaluator, TextPair, UniEvaluator
+from .utils import logger, set_logger
 
 sys_path = os.path.abspath(os.path.dirname(__file__))
 set_logger(os.path.join(sys_path, "cache", "logs", "evaluate.log"))
diff --git a/graphgen/generate.py b/graphgen/generate.py
@@ -5,18 +5,20 @@
 import yaml
 from dotenv import load_dotenv
 
-from graphgen.graphgen import GraphGen
-from graphgen.models import OpenAIModel, Tokenizer, TraverseStrategy
-from graphgen.utils import set_logger
+from .graphgen import GraphGen
+from .models import OpenAIModel, Tokenizer, TraverseStrategy
+from .utils import set_logger
 
 sys_path = os.path.abspath(os.path.dirname(__file__))
-unique_id = int(time.time())
-set_logger(os.path.join(sys_path, "cache", "logs", f"graphgen_{unique_id}.log"), if_stream=False)
-config_path = os.path.join(sys_path, "cache", "data", "graphgen", str(unique_id), f"config-{unique_id}.yaml")
 
 load_dotenv()
 
-def save_config(global_config):
+def set_working_dir(folder):
+    os.makedirs(folder, exist_ok=True)
+    os.makedirs(os.path.join(folder, "data", "graphgen"), exist_ok=True)
+    os.makedirs(os.path.join(folder, "logs"), exist_ok=True)
+
+def save_config(config_path, global_config):
     if not os.path.exists(os.path.dirname(config_path)):
         os.makedirs(os.path.dirname(config_path))
     with open(config_path, "w", encoding='utf-8') as config_file:
@@ -28,7 +30,19 @@ def save_config(global_config):
                         help='Config parameters for GraphGen.',
                         default='graphgen_config.yaml',
                         type=str)
+    parser.add_argument('--output_dir',
+                        help='Output directory for GraphGen.',
+                        default=sys_path,
+                        required=True,
+                        type=str)
+
     args = parser.parse_args()
+
+    working_dir = args.output_dir
+    set_working_dir(working_dir)
+    unique_id = int(time.time())
+    set_logger(os.path.join(working_dir, "logs", f"graphgen_{unique_id}.log"), if_stream=False)
+
     with open(args.config_file, "r", encoding='utf-8') as f:
         config = yaml.load(f, Loader=yaml.FullLoader)
 
@@ -59,6 +73,7 @@ def save_config(global_config):
     )
 
     graph_gen = GraphGen(
+        working_dir=working_dir,
         unique_id=unique_id,
         synthesizer_llm_client=synthesizer_llm_client,
         trainee_llm_client=trainee_llm_client,
@@ -77,4 +92,5 @@ def save_config(global_config):
 
     graph_gen.traverse()
 
-    save_config(config)
+    path = os.path.join(working_dir, "data", "graphgen", str(unique_id), f"config-{unique_id}.yaml")
+    save_config(path, config)
diff --git a/graphgen/judge.py b/graphgen/judge.py
@@ -3,8 +3,8 @@
 import asyncio
 from dotenv import load_dotenv
 
-from graphgen.models import NetworkXStorage, JsonKVStorage, OpenAIModel
-from graphgen.operators import judge_statement
+from .models import NetworkXStorage, JsonKVStorage, OpenAIModel
+from .operators import judge_statement
 
 sys_path = os.path.abspath(os.path.dirname(__file__))
 
diff --git a/scripts/evaluate.sh b/scripts/evaluate.sh
@@ -1,4 +1,4 @@
-python3 evaluate.py --folder cache/data \
+python3 -m graphgen.evaluate --folder cache/data \
                     --output cache/output \
                     --reward "OpenAssistant/reward-model-deberta-v3-large-v2,BAAI/IndustryCorpus2_DataRater" \
                     --uni MingZhong/unieval-sum \
diff --git a/scripts/generate.sh b/scripts/generate.sh
@@ -1 +1 @@
-python3 generate.py --config_file configs/graphgen_config.yaml
+python3 -m graphgen.generate --config_file graphgen/configs/graphgen_config.yaml --output_dir cache/
diff --git a/scripts/judge.sh b/scripts/judge.sh
@@ -1,2 +1,2 @@
-python3 judge.py  --input cache \
+python3 -m graphgen.judge  --input cache \
                   --output cache/output/new_graph.graphml \
diff --git a/webui/app.py b/webui/app.py
@@ -204,7 +204,7 @@ def run_graphgen(*arguments: list, progress=gr.Progress()):
             <img src="https://img.shields.io/github/stars/open-sciencelab/GraphGen?style=social" alt="GitHub Stars">
         </a>
         <a href="https://arxiv.org/xxxxx">
-            <img src="https://img.shields.io/badge/arXiv-2401.00001-yellow" alt="arXiv">
+            <img src="https://img.shields.io/badge/arXiv-xxxxx-yellow" alt="arXiv">
         </a>
     </div>
     """)

Original file line number	Diff line number	Diff line change
`@@ -1 +1 @@`
`1`		`-python3 generate.py --config_file configs/graphgen_config.yaml`
	`1`	`+python3 -m graphgen.generate --config_file graphgen/configs/graphgen_config.yaml --output_dir cache/`
Original file line number	Diff line number	Diff line change
`@@ -1,2 +1,2 @@`
`1`		`-python3 judge.py --input cache \`
	`1`	`+python3 -m graphgen.judge --input cache \`
`2`	`2`	`--output cache/output/new_graph.graphml \`