stefan-jansen--machine-learning-for-trading
wehub-resource-sync
73 行
2.3 KiB
Docker
73 行
2.3 KiB
Docker
# ML4T Benchmark Environment (Full)
|
|
# Storage benchmarks with ALL database clients including ArcticDB
|
|
#
|
|
# WARNING: Requires x86_64 architecture
|
|
# Apple Silicon users: Use `benchmark` profile instead, or build with:
|
|
# docker compose build --platform linux/amd64 benchmark-full
|
|
#
|
|
# Usage:
|
|
# docker compose --profile benchmark-full build benchmark-full
|
|
# docker compose --profile benchmark-full run --rm benchmark-full python 02_financial_data_universe/18_storage_benchmark_database.py
|
|
|
|
FROM python:3.14-slim
|
|
|
|
ENV DEBIAN_FRONTEND=noninteractive
|
|
ENV TZ=UTC
|
|
|
|
# Install system dependencies
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
build-essential \
|
|
curl \
|
|
git \
|
|
libhdf5-dev \
|
|
pkg-config \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# Install uv for fast package management
|
|
COPY --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/uv
|
|
|
|
# Create non-root user
|
|
RUN useradd -m -s /bin/bash ml4t
|
|
|
|
# Create venv
|
|
RUN python -m venv /opt/ml4t
|
|
|
|
# Copy and install dependencies
|
|
WORKDIR /build
|
|
COPY envs/benchmark/pyproject.full.toml /build/pyproject.toml
|
|
|
|
# Install dependencies (includes ArcticDB)
|
|
RUN /opt/ml4t/bin/pip install --no-cache-dir pip setuptools wheel && \
|
|
/opt/ml4t/bin/pip install --no-cache-dir /build
|
|
|
|
WORKDIR /app
|
|
ENV PATH="/opt/ml4t/bin:$PATH"
|
|
ENV PYTHONPATH="/app"
|
|
|
|
# Jupyter configuration
|
|
ENV JUPYTER_ENABLE_LAB=yes
|
|
RUN mkdir -p /etc/jupyter && \
|
|
echo "c.ServerApp.token = ''" >> /etc/jupyter/jupyter_server_config.py && \
|
|
echo "c.ServerApp.password = ''" >> /etc/jupyter/jupyter_server_config.py && \
|
|
echo "c.ServerApp.allow_origin = '*'" >> /etc/jupyter/jupyter_server_config.py
|
|
|
|
# Status script
|
|
RUN echo '#!/bin/bash\n\
|
|
echo "============================================"\n\
|
|
echo "ML4T Benchmark Environment (Full)"\n\
|
|
echo "============================================"\n\
|
|
echo "Platform: $(uname -s) $(uname -m)"\n\
|
|
echo ""\n\
|
|
echo "All benchmarks available:"\n\
|
|
echo " - Parquet (PyArrow)"\n\
|
|
echo " - DuckDB"\n\
|
|
echo " - HDF5 (PyTables)"\n\
|
|
echo " - ArcticDB"\n\
|
|
echo " - ClickHouse"\n\
|
|
echo " - TimescaleDB"\n\
|
|
echo " - QuestDB"\n\
|
|
echo " - InfluxDB"\n\
|
|
echo "============================================"' > /usr/local/bin/benchmark-status && chmod +x /usr/local/bin/benchmark-status
|
|
|
|
CMD ["jupyter", "lab", "--ip=0.0.0.0", "--no-browser"]
|