Running MLOPS Zoomcamp on GCP
conda create -n <name_of_enviornment> python=3.9
conda activate <name_of_enviornment>
- Create requirements.txt
- do the following pip install -r requirements.txt
if pip install requirements.txt does not work then do the following
cat requirements.txt | sed -e '/^\s*#.$/d' -e '/^\s$/d' | xargs -n 1 python -m pip install
pip list
mlflow ui --backend-store-uri sqlite:///mlflow.db
The port at 5000 should be free, if not. Then run the following command
lsof -i :5000 and then kill -9 <port_number>
-
Clear the 5000 port
-
Close anything in it with the following commmand a. lsof -i :5000 b. kill -9 <port_number>
-
Open the models folder created earlier.
-
Move there
-
Run the following command mlflow ui --backend-store-uri sqlite:///mlflow.db