gistfile1.txt

# /// script
# requires-python = ">=3.12"
# dependencies = ["pandas", "pyarrow"]
# ///
"""
Section 1 of the article: the feature registry.

Run with:
    uv run scripts/feature_store/01_registry.py
"""

from dataclasses import dataclass
from typing import Literal


@dataclass(frozen=True)
class Feature:
    name: str
    entity: str
    dtype: Literal["int", "float", "str"]
    source: str  # path to a Parquet file or a SQL view


REGISTRY: dict[str, Feature] = {
    "user_segment": Feature("user_segment", "user_id", "str", "data/user_segment.parquet"),
    "watch_count_30d": Feature("watch_count_30d", "user_id", "int", "data/watch_count_30d.parquet"),
    "last_genre": Feature("last_genre", "user_id", "str", "data/last_genre.parquet"),
}


if __name__ == "__main__":
    print("Registered features:")
    for name, f in REGISTRY.items():
        print(f"  {name:>16}  entity={f.entity}  dtype={f.dtype}  source={f.source}")