()
| 8 | |
| 9 | |
| 10 | def bootstrap(): |
| 11 | repo_path = pathlib.Path(__file__).parent.absolute() / "feature_repo" |
| 12 | project_name = pathlib.Path(__file__).parent.absolute().name |
| 13 | data_path = repo_path / "data" |
| 14 | data_path.mkdir(exist_ok=True) |
| 15 | |
| 16 | print(" 🎬 Setting up sample IMDB movie data for RAG demonstration...") |
| 17 | |
| 18 | parquet_file = data_path / "raw_movies.parquet" |
| 19 | |
| 20 | if parquet_file.exists(): |
| 21 | try: |
| 22 | df = pd.read_parquet(parquet_file) |
| 23 | print(f" ✅ Sample dataset ready with {len(df)} movies") |
| 24 | print(" 💡 For full dataset (48K+ movies), see README.md") |
| 25 | except Exception as e: |
| 26 | print(f" ⚠️ Could not read sample dataset: {e}") |
| 27 | else: |
| 28 | print(" ⚠️ Sample dataset not found, creating minimal example...") |
| 29 | sample_data = pd.DataFrame( |
| 30 | { |
| 31 | "id": ["tt0111161", "tt0068646", "tt0468569", "tt0071562", "tt0050083"], |
| 32 | "Name": [ |
| 33 | "The Shawshank Redemption", |
| 34 | "The Godfather", |
| 35 | "The Dark Knight", |
| 36 | "The Godfather Part II", |
| 37 | "12 Angry Men", |
| 38 | ], |
| 39 | "Description": [ |
| 40 | "Two imprisoned men bond over a number of years, finding solace and eventual redemption through acts of common decency.", |
| 41 | "The aging patriarch of an organized crime dynasty transfers control of his clandestine empire to his reluctant son.", |
| 42 | "When the menace known as the Joker wreaks havoc and chaos on the people of Gotham, Batman must accept one of the greatest psychological and physical tests.", |
| 43 | "The early life and career of Vito Corleone in 1920s New York City is portrayed, while his son, Michael, expands and tightens his grip on the family crime syndicate.", |
| 44 | "A jury holdout attempts to prevent a miscarriage of justice by forcing his colleagues to reconsider the evidence.", |
| 45 | ], |
| 46 | "Director": [ |
| 47 | "Frank Darabont", |
| 48 | "Francis Ford Coppola", |
| 49 | "Christopher Nolan", |
| 50 | "Francis Ford Coppola", |
| 51 | "Sidney Lumet", |
| 52 | ], |
| 53 | "Genres": [ |
| 54 | "Drama", |
| 55 | "Crime, Drama", |
| 56 | "Action, Crime, Drama", |
| 57 | "Crime, Drama", |
| 58 | "Crime, Drama", |
| 59 | ], |
| 60 | "RatingValue": [9.3, 9.2, 9.0, 9.0, 9.0], |
| 61 | "DatePublished": pd.to_datetime( |
| 62 | [ |
| 63 | "1994-09-23", |
| 64 | "1972-03-24", |
| 65 | "2008-07-18", |
| 66 | "1974-12-20", |
| 67 | "1957-04-10", |
no test coverage detected