| from collections.abc import Iterable |
|
|
| import numpy as np |
| from scipy.sparse import csr_matrix |
| from sklearn.base import BaseEstimator, TransformerMixin |
|
|
| from .structural_features import FEATURE_NAMES, featurize |
|
|
| TOOL_WORDS = ( |
| "search", |
| "look up", |
| "lookup", |
| "latest", |
| "current", |
| "today", |
| "news", |
| "weather", |
| "price", |
| "stock", |
| "score", |
| "live", |
| "fetch", |
| "browse", |
| "web", |
| "internet", |
| "calendar", |
| "schedule", |
| "concert", |
| "trending", |
| "recent", |
| "up-to-date", |
| ) |
|
|
|
|
| TOOL_STRUCT_FEATURE_NAMES = list(FEATURE_NAMES) + ["has_tool", "tool_count"] |
|
|
|
|
| class ToolStruct(BaseEstimator, TransformerMixin): |
| """19 structural features plus two tool-dependency cues.""" |
|
|
| def fit(self, X: Iterable[str], y: np.ndarray | None = None) -> "ToolStruct": |
| return self |
|
|
| def transform(self, X: Iterable[str]) -> csr_matrix: |
| rows = [self._featurize(text) for text in X] |
|
|
| return csr_matrix(np.asarray(rows, dtype=np.float64)) |
|
|
| @staticmethod |
| def _featurize(text: str) -> list[float]: |
| source = text if isinstance(text, str) else "" |
| hits = sum(source.lower().count(phrase) for phrase in TOOL_WORDS) |
|
|
| return featurize(source) + [float(hits > 0), float(hits)] |
|
|
