Start Machine Learning project.

Creating conda environment

conda create -p venv python==3.7 -y
conda activate venv/

OR

conda activate venv
pip install -r requirements.txt

To setup CI/CD pipeline in heroku we need 3 information

  1. HEROKU_EMAIL = abc@gmail.com
  2. HEROKU_API_KEY = <>
  3. HEROKU_APP_NAME = ml-regression-app

BUILD DOCKER IMAGE

docker build -t <image_name>:<tagname> .

Note: Image name for docker must be lowercase

To list docker image

docker images

Run docker image

docker run -p 5000:5000 -e PORT=5000 f8c749e73678

To check running container in docker

docker ps

Tos stop docker conatiner

docker stop <container_id>
python setup.py install

Install ipykernel

pip install ipykernel

Data Drift: When your datset stats gets change we call it as data drift