steps.txt

echo "# DVC-ML-Demo-AIops" >> README.md
git init
git add README.md
git commit -m "first commit"
git branch -M main
git remote add origin https://github.com/sidh1603/DVC-ML-Demo-AIops.git
git push -u origin main


## steps ##

conda create -n dvc-ml python-3.7 -y
conda activate dvc-ml
git init
git remote add origin https://github.com/sidh1603/DVC-ML-Demo-AIops.git
git branch -M main

touch .gitignore
touch README.md

on .gitignore file make the changes add .idea/

after changing 
git status
git add .
git commit -m ""
git push origin main

touch requirements.txt
in requirements file add dvc,pandas, scikit-learn

pip install -r requirements.txt

git status
git add requirements.txt
git commit -m "requirements added"

git push origin main

dvc init

mkdir -p src/utils

touch src/utils/__init__.py

touch src/__init__.py

touch params.yaml dvc.yaml

mkdir config
in config folder make a file config.yaml

git add .
git commit -m ""
git push origin main


in config.yaml file 
add the path where our data is

data_source: http://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-red.csv

artifacts:
   artifacts_dir: artifacts
   raw_local_dir: raw_local_dir
   raw_local_file: data.csv
   
now in src folder make 1 file

touch src/stage_01_load_save.py

now in utils create a file

touch src/utils/all_utils.py

then make a changes in all_utils.py

import yaml
import os

def read_yaml(path_to_yaml: str) -> dict:
    with open(path_to_yaml) as yaml_file:
        content = yaml.safe_load(yaml_file)

    return content

def create_directory(dirs: list):
    for dir_path in dirs:
        os.makedirs(dir_path, exist_ok = True)
        print(f"directory is created at {dir_path}")
		
		
create a setup file 
touch setup.py

from setuptools import setup

with open("README.md", "r", encoding="utf-8") as f:
    long_description = f.read()

setup(
    name="src",
    version="0.0.1",
    author="siddharth rana",
    description="A small package for dvc ml pipeline demo",
    long_description=long_description,
    long_description_content_type="text/markdown",
    url="https://github.com/sidh1603/DVC-ML-Demo-AIops.git",
    author_email="sidhu.rana34@gmail.com",
    packages=["src"],
    python_requires=">=3.7",
    install_requires=[
        'dvc',
        'pandas',
        'scikit-learn'
    ]
)


after creating a setup file make a small change in requirements file 
add # local packages -
-e .

pip install -r requirements.txt

now go to stage_01_load_save.py file and make the changes
from src.utils.all_utils import read_yaml, create_directory
import argparse
import pandas as pd
import os

def get_data(config_path):
    config = read_yaml(config_path)

    remote_data_path = config["data_source"]
    df = pd.read_csv(remote_data_path, sep=";")

    # save dataset in the local directory
    # create path to directory: artifacts/raw_local_dir/data.csv
    artifacts_dir = config["artifacts"]['artifacts_dir']
    raw_local_dir = config["artifacts"]['raw_local_dir']
    raw_local_file = config["artifacts"]['raw_local_file']

    raw_local_dir_path = os.path.join(artifacts_dir, raw_local_dir)

    create_directory(dirs= [raw_local_dir_path])

    raw_local_file_path = os.path.join(raw_local_dir_path, raw_local_file)
    
    df.to_csv(raw_local_file_path, sep=",", index=False)



if __name__ == '__main__':
    args = argparse.ArgumentParser()

    args.add_argument("--config", "-c", default="config/config.yaml")

    parsed_args = args.parse_args()

    get_data(config_path=parsed_args.config)


now use the command to run this stage_01_load_save file
python src/stage_01_load_save.py