cancerag/.dockerignore at main · omicscodeathon/cancerag · 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
# Python
__pycache__/
*.py[cod]
*$py.class
*.so
.Python
*.egg-info/
dist/
build/

# Virtual environments
venv/
env/
.venv/

# IDE
.vscode/
.idea/
*.swp
*.swo

# Jupyter
.ipynb_checkpoints/

# Logs
*.log

# Data directories we don't need at build time
data/raw/
data/interim/docking_results/
data/pdb/
data/external/

# Exclude heavy intermediate ML outputs from the build context. Only the
# deployable joblibs (selection_decision.json + *_final*.joblib +
# label_encoder.joblib + advanced/) are needed by ModernBiasPredictor.
data/processed/ml_models/cv_results/
data/processed/ml_models/baselines/
data/processed/ml_models/interpretability/
data/processed/ml_models/selector_ablation/
data/processed/ml_models/mlruns/

# Stage-04/05 work directories — only their distilled artefacts
# (data/processed/receptors_pdbqt/ + binding_sites.json) are needed.
data/processed/.docking_work/
data/processed/.docking_work_smoke/
data/processed/.docking_work_smoke_*/
data/processed/.redock_work/

# Test files
test_*.py
*_test.py
tests/

# Documentation (except key docs)
*.md
!README.md
!inference_app/DOCKING_FIX.md

# Git
.git/
.gitignore

# OS
.DS_Store
Thumbs.db

# Temporary files
*.tmp
*.temp
.cache/

# Large model files we don't need (keep only the 4 main ones)
results/models/advanced/
results/models/advanced_improved/
results/models/improved/
results/models/extra_trees.pkl
results/models/gradient_boosting.pkl
results/models/random_forest_deep.pkl
results/models/stacking_ensemble.pkl
results/models/voting_ensemble.pkl

# Notebooks and scripts
notebooks/
scripts/