Instructions to use Zipeng365/WISP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use Zipeng365/WISP with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("Zipeng365/WISP", "sklearn_model.joblib") ) # only load pickle files from sources you trust # read more about it here https://skops.readthedocs.io/en/stable/persistence.html - Notebooks
- Google Colab
- Kaggle
Download tests/test_search_shared.py from Zipeng365/WISP: direct link, hf CLI and curl.
- Browser
- Download file 4.71 kB
-
https://huggingface.co/Zipeng365/WISP/resolve/main/tests/test_search_shared.py
- Command line
-
hf download hf://Zipeng365/WISP/tests/test_search_shared.py
-
curl -L -o test_search_shared.py https://huggingface.co/Zipeng365/WISP/resolve/main/tests/test_search_shared.py
4.71 kB
| import json | |
| import tempfile | |
| import unittest | |
| from pathlib import Path | |
| import numpy as np | |
| from threadpoolctl import threadpool_limits | |
| from wisp.core.data import HARData | |
| from wisp.core.metrics import classification_report_dict | |
| from wisp.search.cascade import evaluate_candidate_cascade | |
| from wisp.search.grammar import initial_candidates | |
| from wisp_fast.search import evaluate_recipes, fit_search, make_candidate | |
| from wisp_fast.search_metrics import search_report | |
| from wisp_fast.search_cache import SearchFeatures | |
| from wisp_fast import features as fx | |
| def splits(): | |
| rng=np.random.default_rng(55) | |
| def build(subject): | |
| y=np.resize([0,0,1,1,3,3],24) | |
| x=rng.normal(size=(len(y),32,3))+np.sin(np.arange(32)[None,:,None]*(1+y[:,None,None])*.4) | |
| return HARData(x,y,subject=np.repeat([subject,subject+1],12), | |
| time_index=np.tile(np.arange(12),2),label_names=list("abcd")) | |
| return build(1),build(3) | |
| class SharedSearchTests(unittest.TestCase): | |
| def test_scorer_search_semantics(self): | |
| for a,b in [([0,0,2,3],[0,1,1,2]),([2,2,2],[1,1,1]),([3],[3]),([0,3],[0,3])]: | |
| r=classification_report_dict(a,b) | |
| s=search_report(a,b) | |
| for k in ("weighted_f1","worst_class_f1","accuracy","balanced_accuracy","macro_f1"): | |
| self.assertAlmostEqual(r[k],s[k],places=14) | |
| self.assertEqual(r["confusion_matrix"],s["confusion_matrix"]) | |
| self.assertEqual(r["per_class_f1"],s["per_class_f1"]) | |
| def test_memoed_physics_is_seed_safe(self): | |
| data,_=splits() | |
| cache=SearchFeatures(16,[data.X]) | |
| for seed in (1,2,1): | |
| model=fx.InvariantPhysicsFeatureExtractor(random_state=seed).fit(data.X) | |
| expect=model.transform(data.X) | |
| got=cache.transform([model],data.X)[0] | |
| np.testing.assert_array_equal(expect,got) | |
| self.assertGreater(cache.hits,1) | |
| def test_stress_panel_and_full_metric_pairing(self): | |
| a,b=splits() | |
| specs=initial_candidates(seed=42) | |
| with threadpool_limits(1): | |
| scored,stats=evaluate_recipes(specs,a,b,mode="turbo",cost_weight=0,cache_mb=20) | |
| for spec,(status,r) in zip(specs,scored): | |
| # Match controller runtime injection, including one tree job. | |
| spec.params["n_jobs"]=1 | |
| ref=evaluate_candidate_cascade(spec,a,b,cost_weight=0, | |
| estimator_factory=lambda d:make_candidate(d,mode="turbo")).to_dict() | |
| self.assertNotEqual(status,"failed",msg=r) | |
| self.assertEqual(ref["confusion_matrix"],r["confusion_matrix"]) | |
| self.assertAlmostEqual(ref["cascade_score"],r["cascade_score"],places=14) | |
| self.assertEqual(ref["cascade_stages"][2]["metrics"]["stress_reports"], | |
| r["cascade_stages"][2]["metrics"]["stress_reports"]) | |
| self.assertGreater(stats["hits"],0) | |
| def test_no_refit_and_zero_stress(self): | |
| a,b=splits() | |
| with tempfile.TemporaryDirectory() as tmp,threadpool_limits(1): | |
| m,s=fit_search("wisp_evolution",a,b,mode="turbo",output=Path(tmp)/"run", | |
| evaluations=3,stress_count=0,robustness_weight=0,refit=False) | |
| self.assertIsNone(m) | |
| self.assertEqual(s["stress_count"],0) | |
| self.assertEqual(s["cached_stress"],[]) | |
| self.assertEqual(s["n_evaluated"],3) | |
| class ScopeTests(unittest.TestCase): | |
| def test_cis_scope(self): | |
| a,b=splits() | |
| with tempfile.TemporaryDirectory() as tmp,threadpool_limits(1): | |
| for method in ("wisp_random","wisp_evolution"): | |
| _,s=fit_search(method,a,b,mode="turbo",output=Path(tmp)/method,evaluations=11, | |
| population=6,family_scope="cis",refit=False,cost_weight=0) | |
| self.assertEqual(s["family_scope"],"cis") | |
| rows=Path(tmp,method,"program_database.jsonl").read_text().splitlines() | |
| self.assertEqual({json.loads(l)["spec"]["name"] for l in rows},{"state_rocket_interval_hmm"}) | |
| def test_related_scope(self): | |
| a,b=splits() | |
| allowed={"state_rocket_interval_hmm","rocket_sketch_ridge_hmm","posterior_cpu_ensemble"} | |
| with tempfile.TemporaryDirectory() as tmp,threadpool_limits(1): | |
| for method in ("wisp_random","wisp_evolution"): | |
| fit_search(method,a,b,output=Path(tmp)/method,mode="turbo",evaluations=10,population=6, | |
| family_scope="cis-related",refit=False) | |
| rows=Path(tmp,method,"program_database.jsonl").read_text().splitlines() | |
| self.assertEqual({json.loads(l)["spec"]["name"] for l in rows},allowed) | |