สภาพแวดล้อมที่ทำซ้ำได้ด้วย Docker สำหรับการเรียนรู้ของเครื่อง

The Reproducibility Problem in ML

Docker Concepts: Image, Container, Layer

# Basic Docker commands for ML workflows

# Build an image from Dockerfile in current directory
# docker build -t my-ml-trainer:v1 .

# Run a training script inside the container
# docker run --rm --gpus all my-ml-trainer:v1 python train.py

# List running containers
# docker ps

# Inspect image layers (shows what changed at each step)
# docker history my-ml-trainer:v1

Writing a Dockerfile for ML Training

# Dockerfile
# FROM python:3.11-slim
#
# WORKDIR /app
#
# # Copy and install dependencies first (layer caching)
# COPY requirements.txt .
# RUN pip install --no-cache-dir -r requirements.txt
#
# # Copy training code
# COPY train.py .
# COPY data/ data/
#
# # Default command
# CMD ['python', 'train.py']

print('Dockerfile structure shown above (Python comment).')

Pinning Dependencies in requirements.txt

# requirements.txt (pinned versions for reproducibility)
# scikit-learn==1.4.2
# numpy==1.26.4
# pandas==2.2.1
# matplotlib==3.8.4
# mlflow==2.13.0
# torch==2.3.0
# transformers==4.40.2
# xgboost==2.0.3
# lightgbm==4.3.0
# imbalanced-learn==0.12.2
# joblib==1.4.2

# Generate from your current environment:
# pip freeze > requirements.txt

Docker Layer Caching for Fast Rebuilds

# Optimised Dockerfile layer order
# FROM python:3.11-slim
#
# WORKDIR /app
#
# # Step 1: Install system packages (rarely changes)
# RUN apt-get update && apt-get install -y git && rm -rf /var/lib/apt/lists/*
#
# # Step 2: Install Python deps (changes only when requirements.txt changes)
# COPY requirements.txt .
# RUN pip install --no-cache-dir -r requirements.txt
#
# # Step 3: Copy code (changes most often -- put last)
# COPY . .
#
# CMD ['python', 'train.py']

print('Layer order shown above.')

GPU Support: CUDA Docker Images

# Dockerfile for GPU training with PyTorch
# FROM nvidia/cuda:12.1-cudnn8-runtime-ubuntu22.04
#
# # Install Python
# RUN apt-get update && apt-get install -y python3.11 python3-pip
# RUN ln -s /usr/bin/python3.11 /usr/bin/python
#
# WORKDIR /app
# COPY requirements.txt .
# RUN pip install --no-cache-dir -r requirements.txt
# COPY train.py .
#
# CMD ['python', 'train.py']

# Run with GPU:
# docker run --rm --gpus all my-gpu-trainer:v1
print('GPU Dockerfile structure shown above.')

Passing Configuration via Environment Variables

import os

# In train.py -- read config from environment variables
LEARNING_RATE = float(os.getenv('LEARNING_RATE', '0.001'))
N_ESTIMATORS = int(os.getenv('N_ESTIMATORS', '100'))
MAX_DEPTH = int(os.getenv('MAX_DEPTH', '5'))
OUTPUT_DIR = os.getenv('OUTPUT_DIR', '/app/outputs')

print(f'Training with lr={LEARNING_RATE}, n={N_ESTIMATORS}, depth={MAX_DEPTH}')

# Run with custom config:
# docker run -e LEARNING_RATE=0.01 -e N_ESTIMATORS=200 my-ml-trainer:v1

Mounting Volumes for Data and Outputs

# Mount host data/ and outputs/ into container
# docker run --rm \
#   -v /host/path/data:/app/data:ro \
#   -v /host/path/outputs:/app/outputs \
#   -e N_ESTIMATORS=200 \
#   my-ml-trainer:v1

# In train.py, read from /app/data and write to /app/outputs
import os

data_dir = '/app/data'
output_dir = '/app/outputs'
os.makedirs(output_dir, exist_ok=True)

print('Data dir:', os.listdir(data_dir) if os.path.exists(data_dir) else 'not mounted')

Multi-Stage Builds: Slim Production Images

# Multi-stage Dockerfile
# --- Stage 1: Build ---
# FROM python:3.11 AS builder
# WORKDIR /app
# COPY requirements.txt .
# RUN pip install --no-cache-dir --user -r requirements.txt
#
# --- Stage 2: Runtime ---
# FROM python:3.11-slim
# WORKDIR /app
# COPY --from=builder /root/.local /root/.local
# COPY serve.py .
# COPY model/ model/
# ENV PATH=/root/.local/bin:$PATH
#
# CMD ['python', 'serve.py']

print('Multi-stage Dockerfile shown above.')

Running MLflow Inside Docker

import os
import mlflow
from sklearn.ensemble import RandomForestClassifier

# Read from environment (set by docker run -e)
MLFLOW_URI = os.getenv('MLFLOW_TRACKING_URI', 'http://localhost:5000')
mlflow.set_tracking_uri(MLFLOW_URI)
mlflow.set_experiment('docker_training')

with mlflow.start_run():
    n_est = int(os.getenv('N_ESTIMATORS', '100'))
    mlflow.log_param('n_estimators', n_est)

    clf = RandomForestClassifier(n_estimators=n_est, random_state=42)
    # clf.fit(X_train, y_train)  -- assume data is mounted
    # acc = accuracy_score(y_test, clf.predict(X_test))
    # mlflow.log_metric('accuracy', acc)
    # mlflow.sklearn.log_model(clf, 'model')
    print('Logged to:', MLFLOW_URI)

Pushing Images to a Registry

# Tag and push to Docker Hub
# docker tag my-ml-trainer:v1 yourusername/my-ml-trainer:v1
# docker push yourusername/my-ml-trainer:v1

# Tag and push to AWS ECR
# aws ecr get-login-password --region eu-west-1 | \
#   docker login --username AWS --password-stdin 123456789.dkr.ecr.eu-west-1.amazonaws.com
# docker tag my-ml-trainer:v1 123456789.dkr.ecr.eu-west-1.amazonaws.com/my-ml-trainer:v1
# docker push 123456789.dkr.ecr.eu-west-1.amazonaws.com/my-ml-trainer:v1

print('Registry push commands shown above.')

Quick Check

Lesson Recap