gsd-scratch-work/pyproject.toml at main · strycker/gsd-scratch-work · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
[build-system]
requires = ["setuptools>=68", "wheel"]
build-backend = "setuptools.build_meta"

[project]
name = "trading-crab-lib"
version = "0.1.0"
description = "Market regime classification and prediction pipeline"
readme = "README.md"
license = "MIT"
requires-python = ">=3.10"
classifiers = [
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Python :: 3.13",
    "Programming Language :: Python :: 3.14",
]
dependencies = [
    # Data
    "pandas>=2.0",
    "numpy>=1.25",
    "pyarrow>=14.0",          # parquet I/O
    # Data ingestion
    "fredapi>=0.5",
    "requests>=2.31",
    "beautifulsoup4>=4.12",
    "lxml>=4.9",              # fast HTML parser for BS4
    # Feature engineering / ML
    "scikit-learn>=1.4",
    "scipy>=1.11",
    # Config
    "pyyaml>=6.0",
    # Visualization
    "matplotlib>=3.8",
    "seaborn>=0.13",
    # Reporting (optional — add API key later)
    "python-dotenv>=1.0",
    "yfinance>=0.2",              # ETF price history for step 06
    "certifi>=2024.0",            # SSL CA bundle used by curl_cffi / yfinance
]

[project.urls]
Homepage = "https://github.com/strycker/gsd-scratch-work"
Repository = "https://github.com/strycker/gsd-scratch-work"

[project.optional-dependencies]
dev = [
    "pytest>=8.0",
    "pytest-cov",
    "ruff>=0.9",
    "hdbscan>=0.8",  # optional clustering backend; unit tests in test_density.py
    "ipykernel",
    "jupyterlab",
    "build>=1.0",
    "twine>=5.0",
]
# Alternative / fallback ETF price data sources (used when yfinance fails).
# Phase 3 — stooq via pandas-datareader: free, no API key, daily data back to ~1993.
# Phase 4 — OpenBB: wraps multiple providers (cboe free; fmp/tiingo need API keys).
data-extras = [
    "pandas-datareader>=0.10",
    "openbb>=4.1",
]
# Optional clustering backends and elbow detection utilities.
# hdbscan — hierarchical DBSCAN; more robust than DBSCAN for varying densities.
# kneed   — KneeLocator for automated elbow/knee detection on inertia curves.
clustering-extras = [
    "hdbscan>=0.8",
    "kneed>=0.8",
]

[tool.setuptools.packages.find]
where = ["src"]

[tool.setuptools.package-data]
trading_crab_lib = ["py.typed"]

[tool.pytest.ini_options]
testpaths = ["tests"]
pythonpath = ["src", "."]
markers = [
    "smoke: slow integration (e.g. venv + wheel)",
    "network: test may download packages via pip",
    "wheel_smoke: pip wheel + venv install smoke (opt-in: RUN_WHEEL_SMOKE=1)",
    "pipeline_ingest_smoke: slow mocked pipelines/01_ingest smoke (opt-in: RUN_PIPELINE_INGEST_SMOKE=1 or --pipeline-ingest-smoke)",
]
filterwarnings = [
    # pandas_datareader still uses distutils LooseVersion (upstream; data-extras dep)
    "ignore:distutils Version classes are deprecated:DeprecationWarning:pandas_datareader",
]

[tool.ruff]
target-version = "py310"
line-length = 100
extend-exclude = ["legacy"]

[tool.ruff.lint]
select = [
    "E",      # pycodestyle errors
    "W",      # pycodestyle warnings
    "F",      # pyflakes
    "I",      # isort
    "UP",     # pyupgrade
    "B",      # flake8-bugbear
]
ignore = [
    "E501",   # line length — use formatter / line-length instead
]

[tool.ruff.lint.per-file-ignores]
# Imports after sys.path / lazy matplotlib backend (must stay ordered)
"run_pipeline.py" = ["E402"]
"pipelines/*.py" = ["E402"]
"src/trading_crab_lib/plotting.py" = ["E402"]

[tool.ruff.lint.isort]
known-first-party = ["trading_crab_lib"]