패스트캠퍼스 챌린지 38일차

• Local 에서 Feast Server 실행하기
  • Server 실행

pip install feast
feast init feature_repo
cd feature_repo
feast apply

feast materialize-incremental $(date +%Y-%m-%d)
feast serve

"""
feast.errors.ExperimentalFeatureNotEnabled: 
You are attempting to use an experimental feature that is not enabled. 
Please run `feast alpha enable python_feature_server`
"""

curl 을 이용해 Query 실행

curl -X POST \
  "http://localhost:6566/get-online-features" \
  -d '{
    "features": [
      "driver_hourly_stats:conv_rate",
      "driver_hourly_stats:acc_rate",
      "driver_hourly_stats:avg_daily_trips"
    ],
    "entities": {
      "driver_id": [1001, 1002, 1003]
    }
  }'

Docker Container 로 Feast Server 실행하기
Build the docker image

mkdir -p docker
cd docker
sudo vim requirements.txt

requirement.txt 생성

# requirement.txt
feast
scikit-learn
mlflow

Dockerfile 생성

• syntax=[원격 저장소의 이미지 레퍼런스]

# syntax=docker/dockerfile:1
FROM jupyter/base-notebook
WORKDIR /home/jovyan
COPY . /home/jovyan

RUN pip3 install -r requirements.txt

USER jovyan
RUN feast init feature_repo && \
		cd feature_repo && \
		feast apply && \
		feast materialize-incremental $(date +%Y-%m-%d) && \
		feast alpha enable python_feature_server

COPY feature_server.py /opt/conda/lib/python3.9/site-packages/feast/feature_server.py
CMD [ "/bin/sh", "-c", "cd /home/jovyan/feature_repo && feast serve"]

WORKDIR /home/jovyan

 

#직장인인강 #직장인자기계발 #패스트캠퍼스후기#온라인패키지:머신러닝서비스구축을위한실전MLOps#머신러닝서비스구축을위한실전MLOps온라인패키지Online.
https://bit.ly/37BpXiC

 

패스트캠퍼스 [직장인 실무교육]

본 포스팅은 패스트캠퍼스 환급 챌린지 참여를 위해 작성되었습니다.