nba_analysis_project/Dockerfile.gpu at main · cmunch1/nba_analysis_project · 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
# NBA Analysis Project - Docker Image (GPU-enabled)
# Multi-stage build for optimized image size with CUDA support

# Stage 1: Builder - Install dependencies
FROM nvidia/cuda:12.1.0-cudnn8-devel-ubuntu22.04 as builder

# Install Python 3.11
RUN apt-get update && apt-get install -y --no-install-recommends \
    python3.11 \
    python3.11-dev \
    python3-pip \
    gcc \
    g++ \
    git \
    && rm -rf /var/lib/apt/lists/*

# Make python3.11 the default
RUN update-alternatives --install /usr/bin/python python /usr/bin/python3.11 1 && \
    update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.11 1

# Install uv (fast Python package installer)
RUN pip install --no-cache-dir uv

# Set working directory
WORKDIR /build

# Copy dependency files (README.md required by pyproject.toml)
COPY pyproject.toml uv.lock README.md ./

# Install Python dependencies into /build/.venv
# This will install GPU-enabled versions of torch, xgboost, etc.
RUN uv sync --frozen

# Stage 2: Runtime - Minimal image with CUDA runtime
FROM nvidia/cuda:12.1.0-cudnn8-runtime-ubuntu22.04

# Install Python 3.11 and runtime dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    python3.11 \
    python3-pip \
    chromium-browser \
    chromium-chromedriver \
    && rm -rf /var/lib/apt/lists/*

# Make python3.11 the default
RUN update-alternatives --install /usr/bin/python python /usr/bin/python3.11 1 && \
    update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.11 1

# Create non-root user for security
RUN useradd -m -u 1000 nba && \
    mkdir -p /app && \
    chown -R nba:nba /app

# Set working directory
WORKDIR /app

# Copy Python virtual environment from builder
COPY --from=builder --chown=nba:nba /build/.venv /app/.venv

# Copy application code
COPY --chown=nba:nba src/ ./src/
COPY --chown=nba:nba configs/ ./configs/
COPY --chown=nba:nba scripts/ ./scripts/
COPY --chown=nba:nba pyproject.toml ./

# Create data directories
RUN mkdir -p \
    data/cumulative_scraped \
    data/newly_scraped \
    data/processed \
    data/engineered \
    data/predictions \
    data/dashboard \
    logs \
    mlruns \
    && chown -R nba:nba data logs mlruns

# Switch to non-root user
USER nba

# Add virtual environment to PATH
ENV PATH="/app/.venv/bin:$PATH"
ENV PYTHONPATH="/app:$PYTHONPATH"

# Environment variables (override at runtime)
ENV MLFLOW_TRACKING_URI="file:///app/mlruns"
ENV PYTHONUNBUFFERED=1

# CUDA environment variables
ENV CUDA_VISIBLE_DEVICES="0"
ENV NVIDIA_VISIBLE_DEVICES="all"
ENV NVIDIA_DRIVER_CAPABILITIES="compute,utility"

# Default command runs the full pipeline
CMD ["python", "-m", "src.nba_app.inference.main"]

# Health check (for container orchestration)
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
    CMD python -c "import sys; sys.exit(0)"