dvc

import os import subprocess import dvc.api # --- CLI Setup (normally run in shell) --- # This part simulates initial DVC project setup if not already done. # In a real scenario, you'd run these in your terminal. def setup_dvc_project(): if not os.path.exists('dvc_quickstart_repo'): os.makedirs('dvc_quickstart_repo') os.chdir('dvc_quickstart_repo') if not os.path.exists('.git'): subprocess.run(['git', 'init', '-b', 'main'], check=True) # Ensure dvc is initialized if not os.path.exists('.dvc'): subprocess.run(['dvc', 'init'], check=True) subprocess.run(['git', 'add', '.dvcignore', '.dvc/config', '.dvc/.gitignore'], check=True) subprocess.run(['git', 'commit', '-m', 'Initialize DVC'], check=True) # Create a dummy data file with open('data.csv', 'w') as f: f.write('col1,col2\n1,A\n2,B\n3,C\n') # Add data to DVC and commit the .dvc file to Git subprocess.run(['dvc', 'add', 'data.csv'], check=True) subprocess.run(['git', 'add', 'data.csv.dvc'], check=True) subprocess.run(['git', 'commit', '-m', 'Add data.csv'], check=True) print("DVC project setup complete in 'dvc_quickstart_repo'") os.chdir('..') # Go back to original directory # Run the setup setup_dvc_project() # --- Python API Usage --- # Now, demonstrate reading the DVC-tracked file programmatically repo_path = 'dvc_quickstart_repo' file_path = 'data.csv' try: # Read the content of the DVC-tracked file # dvc.api will automatically handle fetching from cache or remote if needed content = dvc.api.read( path=file_path, repo=repo_path, rev='HEAD' # Or a specific Git commit/tag/branch ) print(f"\nContent of {file_path} from DVC repo '{repo_path}':\n{content}") # Example: Reading a specific parameter from params.yaml if it existed # (This example assumes no params.yaml is set up in the quickstart for simplicity) # params_content = dvc.api.read(path='params.yaml', repo=repo_path, rev='HEAD') # import yaml # params = yaml.safe_load(params_content) # print(f"Parameters: {params}") except Exception as e: print(f"An error occurred while reading DVC-tracked file: {e}")