feat: Add comprehensive Python testing infrastructure

.gitignore

@@ -150,3 +150,6 @@ dmypy.json
 
 # asdf tool versions
 .tool-versions
+
+# Claude Code settings
+.claude/*

pyproject.toml

@@ -0,0 +1,137 @@
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.poetry]
+name = "codefuse-eval"
+version = "0.1.0"
+description = "CodeFuse evaluation framework for code generation models"
+authors = ["CodeFuse Team"]
+readme = "README.md"
+packages = [{include = "codefuseEval"}, {include = "codefuseEval_202503"}]
+package-mode = false
+
+[tool.poetry.dependencies]
+python = ">=3.8,<3.11"
+tqdm = "4.65.0"
+fire = "0.5.0"
+statistics = "1.0.3.5"
+datasets = "2.12.0"
+pyzmq = "25.0.0"
+gensim = "4.2.0"
+regex = "2023.3.23"
+setuptools = "65.6.3"
+cpm_kernels = "1.0.11"
+deepspeed = "0.8.3"
+huggingface-hub = "0.16.4"
+numpy = "^1.22.0"
+matplotlib = "^3.5.0"
+DateTime = "4.7"
+openai = "0.23.0"
+pandas = "^1.4.0"
+pandas-datareader = "0.10.0"
+pathlib = "1.0.1"
+scikit-learn = "^1.0.0"
+scipy = "^1.7.0"
+seaborn = "0.11.2"
+statsmodels = "0.13.2"
+tensorflow = "2.12.0"
+tokenizers = "0.13.3"
+torch = "2.0.0"
+xgboost = "1.6.2"
+Pillow = "9.2.0"
+sacrebleu = "2.3.1"
+unbabel-comet = "2.0.2"
+tree_sitter = "0.2.1"
+bert_score = "0.3.13"
+jiwer = "3.0.1"
+nltk = "3.8.1"
+faiss-cpu = "1.7.4"
+rouge_chinese = "1.0.3"
+jieba = "0.42.1"
+gin-config = "0.5.0"
+absl-py = "1.4.0"
+rouge_score = "0.1.2"
+sacremoses = "0.0.53"
+trectools = "0.0.49"
+transformers = "4.32.0"
+accelerate = "0.20.3"
+evaluate = "0.4.0"
+pydantic = "1.10.9"
+
+[tool.poetry.group.test.dependencies]
+pytest = "^7.4.0"
+pytest-cov = "^4.1.0"
+pytest-mock = "^3.11.1"
+
+[tool.poetry.scripts]
+test = "pytest"
+tests = "pytest"
+
+[tool.pytest.ini_options]
+minversion = "6.0"
+addopts = [
+    "--strict-markers",
+    "--strict-config",
+    "--cov=codefuseEval",
+    "--cov=codefuseEval_202503",
+    "--cov-report=html",
+    "--cov-report=xml",
+    "--cov-report=term-missing",
+    "--cov-fail-under=80"
+]
+testpaths = ["tests"]
+python_files = ["test_*.py", "*_test.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+markers = [
+    "unit: marks tests as unit tests",
+    "integration: marks tests as integration tests", 
+    "slow: marks tests as slow running"
+]
+filterwarnings = [
+    "ignore::DeprecationWarning",
+    "ignore::PendingDeprecationWarning"
+]
+
+[tool.coverage.run]
+source = ["codefuseEval", "codefuseEval_202503"]
+omit = [
+    "*/tests/*",
+    "*/test_*",
+    "*/__pycache__/*",
+    "*/migrations/*",
+    "*/venv/*",
+    "*/.venv/*",
+    "*/build/*",
+    "*/dist/*",
+    "*/docker/*",
+    "*/figures/*",
+    "*/data/*",
+    "*/result/*",
+    "*/script/*"
+]
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "if self.debug:",
+    "if settings.DEBUG",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if 0:",
+    "if __name__ == .__main__.:",
+    "class .*\\bProtocol\\):",
+    "@(abc\\.)?abstractmethod"
+]
+ignore_errors = true
+show_missing = true
+skip_covered = false
+precision = 2
+
+[tool.coverage.html]
+directory = "htmlcov"
+
+[tool.coverage.xml]
+output = "coverage.xml"

pyproject.toml.backup

@@ -0,0 +1,89 @@
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.poetry]
+name = "codefuse-eval-testing"
+version = "0.1.0"
+description = "CodeFuse evaluation framework for code generation models - Testing Setup"
+authors = ["CodeFuse Team"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.11"
+pytest = "^7.4.0"
+pytest-cov = "^4.1.0"
+pytest-mock = "^3.11.1"
+pandas = "^2.0.0"
+numpy = "^1.24.0"
+
+[tool.poetry.scripts]
+test = "pytest"
+tests = "pytest"
+
+[tool.pytest.ini_options]
+minversion = "6.0"
+addopts = [
+    "--strict-markers",
+    "--strict-config",
+    "--cov=tests",
+    "--cov-report=html",
+    "--cov-report=xml",
+    "--cov-report=term-missing",
+    "--cov-fail-under=80"
+]
+testpaths = ["tests"]
+python_files = ["test_*.py", "*_test.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+markers = [
+    "unit: marks tests as unit tests",
+    "integration: marks tests as integration tests", 
+    "slow: marks tests as slow running"
+]
+filterwarnings = [
+    "ignore::DeprecationWarning",
+    "ignore::PendingDeprecationWarning"
+]
+
+[tool.coverage.run]
+source = ["tests"]
+omit = [
+    "*/tests/*",
+    "*/test_*",
+    "*/__pycache__/*",
+    "*/migrations/*",
+    "*/venv/*",
+    "*/.venv/*",
+    "*/build/*",
+    "*/dist/*",
+    "*/docker/*",
+    "*/figures/*",
+    "*/data/*",
+    "*/result/*",
+    "*/script/*"
+]
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "if self.debug:",
+    "if settings.DEBUG",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if 0:",
+    "if __name__ == .__main__.:",
+    "class .*\\bProtocol\\):",
+    "@(abc\\.)?abstractmethod"
+]
+ignore_errors = true
+show_missing = true
+skip_covered = false
+precision = 2
+
+[tool.coverage.html]
+directory = "htmlcov"
+
+[tool.coverage.xml]
+output = "coverage.xml"