模型部署

MLflow 入门

Weston Bassler

Senior MLOps Engineer

机器学习生命周期

机器学习生命周期步骤

1 datacamp.com
MLflow 入门

模型版本与阶段

  • 模型版本

    • 版本 +1

  • 模型阶段

    • Staging
    • Production
    • Archived

模型版本与阶段

MLflow 入门

部署模型的方式

加载模型

# MLflow flavor
mlflow.FLAVOR.load_model()

提供服务

# MLflow 命令行服务
mlflow models serve
MLflow 入门

Models URI

约定

models:/

模型版本

models:/model_name/version

模型阶段

models:/model_name/stage
MLflow 入门

加载模型

# Import flavor
import mlflow.FLAVOR


# Load version
mlflow.FLAVOR.load_model("models:/model_name/version")


# Load stage
mlflow.FLAVOR.load_model("models:/model_name/stage")
MLflow 入门

加载模型示例

# Import flavor
import mlflow.sklearn


# 加载处于 Staging 的 Unicorn 模型
model = mlflow.sklearn.load_model("models:/Unicorn/Staging")

# 打印模型
model

LogisticRegression()

# 推理
model.predict(data)
MLflow 入门

模型服务

# 将 Unicorn 模型以 Production 阶段提供服务
mlflow models serve -m "models:/Unicorn/Production"

2023/03/26 15:07:00 INFO mlflow.models.flavor_backend_registry: 
Selected backend for flavor 'python_function'
2023/03/26 15:07:00 INFO mlflow.pyfunc.backend: === Running command 'exec gunicorn 
--timeout=60 -b 127.0.0.1:5000 -w 1 ${GUNICORN_CMD_ARGS} -- 
mlflow.pyfunc.scoring_server.wsgi:app'
[2023-03-26 15:07:00 -0400] [86409] [INFO] Starting gunicorn 20.1.0
[2023-03-26 15:07:00 -0400] [86409] [INFO] Listening at: http://127.0.0.1:5000
[2023-03-26 15:07:00 -0400] [86409] [INFO] Using worker: sync
[2023-03-26 15:07:00 -0400] [86410] [INFO] Booting worker with pid: 86410
MLflow 入门

Invocations 端点

api

http://localhost:5000/invocations

  • 格式
    • CSV
    • JSON
1 Flaticon.com
MLflow 入门

CSV 格式

pandas_df.to_csv()

JSON 格式

{
  "dataframe_split": {
      "columns": ["R&D Spend", "Administration", "Marketing Spend", "State"],
      "data": [["165349.20", 136897.80, 471784.10, 1]]
  }
}
MLflow 入门

模型预测

# 向 invocations 端点发送负载
curl http://127.0.0.1:5000/invocations -H 'Content-Type: application/json' -d
{
  "dataframe_split": {
      "columns": ["R&D Spend", "Administration", "Marketing Spend", "State"],
      "data": [["165349.20", 136897.80, 471784.10, 1]]
  }
}

[[104055.1842384]]
MLflow 入门

Passons à la pratique!

MLflow 入门

Preparing Video For Download...