模型服務

MLflow 入門

Weston Bassler

Senior MLOps Engineer

MLflow Models

標準化模型封裝
記錄模型
模型評估

模型部署

機器學習生命週期

¹ datacamp.com

REST API

/ping－健康檢查
/health－健康檢查
/version－取得 MLflow 版本
/invocations－模型評分
連接埠 5000

Invocations 端點

/invocations

No,Name,Subject
1,Bill Johnson,English
2,Gary Valentine,Mathematics

Content-Type:application/json 或 application/csv

{
    "1": {
        "No": "1",
        "Name": "Bill Johnson",
        "Subject": "English"
    },
    "2": {
        "No": "2",
        "Name": "Gary Valentine",
        "Subject": "Mathematics"
    }
}

CSV 格式

pandas DataFrame
pandas_df.to_csv()

JSON 格式

dataframe_split－以 split 方向的 pandas DataFrame
dataframe_records－以 records 方向的 pandas DataFrame

DataFrame split

# DataFrame split 方向
{
  "dataframe_split": {
      "columns": ["sex", "age", "weight"],
      "data": [["male", 23, 160], ["female", 33, 120]]
  }
}

提供模型服務

# MLflow 服務指令
mlflow models serve --help
Usage: mlflow models serve [OPTIONS]

Serve URI

# 本機檔案系統
mlflow models serve -m relative/path/to/local/model

# Run ID
mlflow models serve -m runs:/<mlflow_run_id>/artifacts/model

# AWS S3
mlflow models serve -m s3://my_bucket/path/to/model

服務範例

# 從 run 提供模型服務
mlflow models serve -m runs:/e84a122920de4bdeaedb54146deeb429/artifacts/model

2023/03/12 16:28:28 INFO mlflow.models.flavor_backend_registry: 
Selected backend for flavor 'python_function'
2023/03/12 16:28:28 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'
[2023-03-12 16:28:29 -0400] [48431] [INFO] Starting gunicorn 20.1.0
[2023-03-12 16:28:29 -0400] [48431] [INFO] Listening at: http://127.0.0.1:5000 
(48431)
[2023-03-12 16:28:29 -0400] [48431] [INFO] Using worker: sync
[2023-03-12 16:28:29 -0400] [48432] [INFO] Booting worker with pid: 48432

Invocations 請求

# 傳送 dataframe_split 方向的負載給 MLflow
curl http://127.0.0.1:5000/invocations -H 'Content-Type: application/json' -d '{
  "dataframe_split": {
      "columns": ["sex", "age", "weight"],
      "data": [["male", 23, 160], ["female", 33, 120]]
  }
}'

{"predictions": [1, 0]}

一起來練習吧！

MLflow 入門