Yijia-Xiao
e3bc872982
Clear the deferred full-repo lint backlog so the whole tree passes the strict ruff select (E,W,F,I,B,UP,C4,SIM). Mechanical fixes dominate: import sorting, pep585/604 annotations, dropped dead imports, and whitespace. The few semantic changes are behavior-preserving: declare __all__ on the agent_utils and alpha_vantage re-export hubs; expand 'from x import *' to explicit names; use immutable tuple defaults instead of mutable list defaults; contextlib.suppress for try/except/pass; and narrow an over-broad assertRaises.
49 lines
1.7 KiB
Python
49 lines
1.7 KiB
Python
"""Shared 5-tier rating vocabulary and a deterministic heuristic parser.
|
|
|
|
The same five-tier scale (Buy, Overweight, Hold, Underweight, Sell) is used by:
|
|
- The Research Manager (investment plan recommendation)
|
|
- The Portfolio Manager (final position decision)
|
|
- The signal processor (rating extracted for downstream consumers)
|
|
- The memory log (rating tag stored alongside each decision entry)
|
|
|
|
Centralising it here avoids drift between those call sites.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import re
|
|
|
|
# Canonical, ordered 5-tier scale (most bullish to most bearish).
|
|
RATINGS_5_TIER: tuple[str, ...] = (
|
|
"Buy", "Overweight", "Hold", "Underweight", "Sell",
|
|
)
|
|
|
|
_RATING_SET = {r.lower() for r in RATINGS_5_TIER}
|
|
|
|
# Matches "Rating: X" / "rating - X" / "Rating: **X**" — tolerates markdown
|
|
# bold wrappers and either a colon or hyphen separator.
|
|
_RATING_LABEL_RE = re.compile(r"rating.*?[:\-][\s*]*(\w+)", re.IGNORECASE)
|
|
|
|
|
|
def parse_rating(text: str, default: str = "Hold") -> str:
|
|
"""Heuristically extract a 5-tier rating from prose text.
|
|
|
|
Two-pass strategy:
|
|
1. Look for an explicit "Rating: X" label (tolerant of markdown bold).
|
|
2. Fall back to the first 5-tier rating word found anywhere in the text.
|
|
|
|
Returns a Title-cased rating string, or ``default`` if no rating word appears.
|
|
"""
|
|
for line in text.splitlines():
|
|
m = _RATING_LABEL_RE.search(line)
|
|
if m and m.group(1).lower() in _RATING_SET:
|
|
return m.group(1).capitalize()
|
|
|
|
for line in text.splitlines():
|
|
for word in line.lower().split():
|
|
clean = word.strip("*:.,")
|
|
if clean in _RATING_SET:
|
|
return clean.capitalize()
|
|
|
|
return default
|