Files
Streamlit_NBA/streamlit_app/utils/db.py
T
2026-10-28 02:37:56 -05:00

63 lines
2.1 KiB
Python

from pathlib import Path
import duckdb
import pandas as pd
import streamlit as st
def get_db_path() -> Path:
"""Resolve local DuckDB file path across reports and data/DB locations."""
repo_root = Path(__file__).resolve().parent.parent.parent
candidates = [
repo_root / "dbt_nba" / "reports" / "sources" / "nba" / "dbt_nba.duckdb",
repo_root / "data" / "DB" / "dbt_nba.duckdb",
Path("dbt_nba/reports/sources/nba/dbt_nba.duckdb"),
Path("data/DB/dbt_nba.duckdb"),
]
for path in candidates:
if path.exists():
return path.resolve()
return candidates[0]
@st.cache_resource
def get_connection():
"""Persistent read-only DuckDB connection."""
db_path = get_db_path()
if not db_path.exists():
st.error(
f"Database file not found at `{db_path}`. "
"Run `./scripts/run_app.sh --sync` or `./scripts/pipeline.sh` to initialize."
)
st.stop()
return duckdb.connect(str(db_path), read_only=True)
@st.cache_data(ttl=3600)
def query(sql: str, params: list | None = None) -> pd.DataFrame:
"""Execute SQL (optionally parameterized) and return cached DataFrame."""
conn = get_connection()
if params:
return conn.execute(sql, params).df()
return conn.execute(sql).df()
@st.cache_data(ttl=3600)
def get_seasons() -> pd.DataFrame:
"""Return available seasons ordered most recent first."""
return query(
"SELECT season_start_year, season_display "
"FROM main_marts.dim_seasons "
"ORDER BY season_start_year DESC"
)
def get_selected_season() -> tuple[int, str]:
"""Return (season_start_year, season_display) from session state."""
seasons = get_seasons()
season_options = seasons["season_start_year"].tolist()
season_labels = dict(zip(seasons["season_start_year"], seasons["season_display"]))
if "season" not in st.session_state or st.session_state["season"] not in season_labels:
st.session_state["season"] = season_options[0]
season = st.session_state["season"]
return season, season_labels[season]