Download example.py from zeechimp/hv-chemical-classifier: direct link, hf CLI and curl.
- Browser
- Download file 6.71 kB
-
https://huggingface.co/zeechimp/hv-chemical-classifier/resolve/main/example.py
- Command line
-
hf download hf://zeechimp/hv-chemical-classifier/example.py
-
curl -L -o example.py https://huggingface.co/zeechimp/hv-chemical-classifier/resolve/main/example.py
6.71 kB
| #!/usr/bin/env python3 | |
| """ | |
| example.py β Usage demonstrations for hv_chemical_classifier. | |
| NumPy only. | |
| """ | |
| import numpy as np | |
| from hv_chemical_classifier import ( | |
| Hypothesis, EvidenceChannel, ChemicalClassifier, | |
| adaptive_tempering, true_voi, correlation_discount, | |
| make_paleo_scenario, | |
| ) | |
| def demo_basic(): | |
| print("=" * 72) | |
| print("Demo 1 β basic classification") | |
| print("=" * 72) | |
| print() | |
| hyp, ch = make_paleo_scenario() | |
| clf = ChemicalClassifier(hyp, saturation_mode='per_species') | |
| for c in ch: | |
| clf.add_channel(c) | |
| # Observe a strong sauropod-like signal | |
| clf.observe('femur_morphology', 2) | |
| clf.observe('tooth_shape', 0) | |
| clf.observe('bone_density', 2) | |
| r = clf.classify() | |
| print(f" Winner: {r['winner']}") | |
| print(f" Posterior: " + | |
| ", ".join(f"{h.name}={p:.3f}" | |
| for h, p in zip(clf.hypotheses, r['posterior']))) | |
| print() | |
| def demo_ambivalence(): | |
| print("=" * 72) | |
| print("Demo 2 β honest refusal via multi-seed bistability") | |
| print("=" * 72) | |
| print() | |
| hyp, ch = make_paleo_scenario() | |
| clf = ChemicalClassifier(hyp, saturation_mode='per_species') | |
| for c in ch: | |
| clf.add_channel(c) | |
| # Weak, ambiguous signal | |
| clf.observe('femur_morphology', 1) | |
| clf.observe('tooth_shape', 1) | |
| r = clf.classify_multiseed(n_seeds=20, n_steps=500) | |
| print(f" Verdict: {r['verdict']}") | |
| print(f" Ambiguous: {r['ambiguous']}") | |
| print(f" Winner counts: {r['winner_counts']}") | |
| print() | |
| def demo_tempering(): | |
| print("=" * 72) | |
| print("Demo 3 β adaptive tempering") | |
| print("=" * 72) | |
| print() | |
| # Sharp vs weak specimen | |
| for label, obs in [ | |
| ('sharp', {'femur_morphology': 2, 'tooth_shape': 0, | |
| 'bone_density': 2, 'cortical_thickness': 2}), | |
| ('weak', {'femur_morphology': 1, 'tooth_shape': 1}), | |
| ]: | |
| hyp, ch = make_paleo_scenario() | |
| clf = ChemicalClassifier(hyp, saturation_mode='per_species') | |
| for c in ch: | |
| clf.add_channel(c) | |
| for k, v in obs.items(): | |
| clf.observe(k, v) | |
| log_lik = clf.raw_log_likelihoods() | |
| alpha = adaptive_tempering(log_lik) | |
| r = clf.classify(apply_tempering=True) | |
| print(f" {label:<8s} Ξ± = {alpha:.3f} winner = {r['winner']}") | |
| print() | |
| def demo_discount(): | |
| print("=" * 72) | |
| print("Demo 4 β correlation discount") | |
| print("=" * 72) | |
| print() | |
| for label, group in [('independent', None), ('correlated', 'group')]: | |
| hyp = [Hypothesis('A', prior=0.5), Hypothesis('B', prior=0.5)] | |
| channels = [ | |
| EvidenceChannel(f'ch{i}', | |
| np.array([[0.6, 0.4], [0.4, 0.6]]), | |
| cost=1.0, correlation_group=group) | |
| for i in range(5) | |
| ] | |
| clf = ChemicalClassifier(hyp, saturation_mode='per_species') | |
| for c in channels: | |
| clf.add_channel(c) | |
| for c in channels: | |
| clf.observe(c.name, 1) | |
| log_lik = clf.raw_log_likelihoods( | |
| apply_discount=(label == 'correlated')) | |
| raw_odds = float(log_lik[1] - log_lik[0]) | |
| print(f" {label:<12s} raw log-odds = {raw_odds:+.4f}") | |
| print() | |
| def demo_voi(): | |
| print("=" * 72) | |
| print("Demo 5 β true VOI (which channel to run next?)") | |
| print("=" * 72) | |
| print() | |
| hyp, ch = make_paleo_scenario() | |
| clf = ChemicalClassifier(hyp, saturation_mode='per_species') | |
| for c in ch: | |
| clf.add_channel(c) | |
| # Partial evidence | |
| clf.observe('femur_morphology', 1) | |
| a = clf.effective_rates() | |
| clf.reset_concentrations() | |
| traj, _ = clf.evolve(a, 300, 0.02) | |
| p = traj[-1] / traj[-1].sum() | |
| candidates = ['tooth_shape', 'bone_density', | |
| 'cortical_thickness', 'joint_geometry'] | |
| voi = true_voi(clf, p, candidates) | |
| print(f" Current posterior: " + | |
| ", ".join(f"{h.name}={p[i]:.3f}" | |
| for i, h in enumerate(clf.hypotheses))) | |
| print() | |
| print(f" {'channel':<22s} {'VOI/cost':>10s}") | |
| print(" " + "-" * 36) | |
| for name, r in sorted(voi.items(), key=lambda x: -x[1]['voi_per_cost']): | |
| print(f" {name:<22s} {r['voi_per_cost']:>10.5f}") | |
| print() | |
| def demo_messenger(): | |
| print("=" * 72) | |
| print("Demo 6 β pairwise messenger as confidence signal") | |
| print("=" * 72) | |
| print() | |
| # Scenario: clear winner | |
| hyp, ch = make_paleo_scenario() | |
| clf = ChemicalClassifier(hyp, saturation_mode='per_species') | |
| for c in ch: | |
| clf.add_channel(c) | |
| clf.observe('femur_morphology', 2) | |
| clf.observe('tooth_shape', 0) | |
| clf.observe('bone_density', 2) | |
| a = clf.effective_rates() | |
| clf.reset_concentrations() | |
| traj, M = clf.evolve(a, 500, 0.02, track_messenger=True) | |
| print(f" Scenario: clear winner") | |
| print(f" Peak messenger: {M.max():.4f} at step {int(np.argmax(M))}") | |
| print(f" Final messenger: {M[-1]:.6f}") | |
| print() | |
| # Peak occurs during the transition, then decays | |
| peak_idx = int(np.argmax(M)) | |
| print(f" Messenger trajectory (every 50 steps):") | |
| for t in range(0, 500, 50): | |
| bar = "β" * int(M[t] * 40) | |
| print(f" step {t:>3d} M = {M[t]:.4f} {bar}") | |
| print() | |
| def demo_stopping(): | |
| print("=" * 72) | |
| print("Demo 7 β entropy stopping vs max-posterior stopping") | |
| print("=" * 72) | |
| print() | |
| hyp, ch = make_paleo_scenario() | |
| clf = ChemicalClassifier(hyp, saturation_mode='per_species') | |
| for c in ch: | |
| clf.add_channel(c) | |
| clf.observe('femur_morphology', 2) | |
| clf.observe('tooth_shape', 0) | |
| clf.observe('bone_density', 2) | |
| clf.observe('cortical_thickness', 2) | |
| a = clf.effective_rates() | |
| clf.reset_concentrations() | |
| traj, _ = clf.evolve(a, 500, 0.02) | |
| threshold = 0.85 | |
| stop_step = None | |
| for t in range(len(traj)): | |
| H = traj[t] | |
| p = H / H.sum() | |
| if p.max() > threshold: | |
| stop_step = t | |
| break | |
| print(f" Threshold: max posterior > {threshold}") | |
| print(f" Stopping step: {stop_step}") | |
| print() | |
| print(f" {'step':>5s} {'max p':>8s} {'entropy':>10s} {'stop?':>6s}") | |
| print(" " + "-" * 36) | |
| for t in [0, 50, 100, 150, 200, 300, 499]: | |
| H = traj[t] | |
| p = H / H.sum() | |
| p = np.maximum(p, 1e-12) | |
| ent = -np.sum(p * np.log(p)) | |
| stopped = "β" if (stop_step is not None and t >= stop_step) else "" | |
| print(f" {t:>5d} {p.max():>8.4f} {ent:>10.4f} {stopped:>6s}") | |
| print() | |
| def main(): | |
| demo_basic() | |
| demo_ambivalence() | |
| demo_tempering() | |
| demo_discount() | |
| demo_voi() | |
| demo_messenger() | |
| demo_stopping() | |
| if __name__ == "__main__": | |
| main() |