mirror of
https://github.com/allaunthefox/Research-Stack.git
synced 2026-07-31 03:05:21 +00:00
allaun
475f6319ea
This squashes all local history (768 commits) onto the scrubbed PR #90 baseline. Individual commits were lost during filter-repo corruption; the working tree content is preserved intact. Build: N/A (working tree state only)
204 lines
7.7 KiB
Python
204 lines
7.7 KiB
Python
#!/usr/bin/env python3
|
||
"""
|
||
Parse arbitrary physical equations into shape-index entries.
|
||
Handles SymPy expressions, plain text, and CALPHAD .tdb format.
|
||
|
||
Usage:
|
||
python3 equation_shape_parser.py --input /path/to/equations.txt
|
||
python3 equation_shape_parser.py --propnet # scan Propnet models
|
||
"""
|
||
|
||
import hashlib
|
||
import json
|
||
import os
|
||
import re
|
||
import sys
|
||
from collections import defaultdict
|
||
from datetime import datetime, timezone
|
||
|
||
Q16_SCALE = 65536
|
||
|
||
# ─── Shape signature from equation structure ─────────────────────────────────
|
||
|
||
def classify_equation(eq_str: str, name: str = "", source: str = "") -> dict:
|
||
"""Extract FAMM shape signature from an equation string."""
|
||
n_ops = len(re.findall(r'[+\-*/^]', eq_str))
|
||
n_vars = len(set(re.findall(r'\b([a-zα-ω][a-zα-ω0-9]*)\b', eq_str.lower())))
|
||
n_parens = eq_str.count('(') + eq_str.count(')')
|
||
has_trig = len(re.findall(r'sin|cos|tan|exp|log|sqrt', eq_str.lower()))
|
||
has_diff = len(re.findall(r'diff|grad|curl|div|laplacian|\b∂', eq_str))
|
||
complexity = len(eq_str.strip())
|
||
|
||
# Sidon graph estimation
|
||
graph_size = max(2, min(n_vars + has_trig + has_diff, 8))
|
||
sidon_addr = [1 << i for i in range(graph_size)]
|
||
n_pairs = graph_size * (graph_size - 1) // 2
|
||
if n_pairs > 0:
|
||
sums = set()
|
||
for i in range(graph_size):
|
||
for j in range(i + 1, graph_size):
|
||
sums.add(sidon_addr[i] + sidon_addr[j])
|
||
sumset_density = len(sums) / n_pairs
|
||
sums_list = sorted(sums)
|
||
else:
|
||
sumset_density = 1.0
|
||
sums_list = []
|
||
|
||
# FAMM classification
|
||
structural_noise = min(1.0, n_parens / max(1, complexity * 0.05))
|
||
raw_closure = 1.0 / max(1.0, n_ops * 0.05 + has_trig * 0.1 + has_diff * 0.2)
|
||
closure_frac = min(raw_closure, 1.0)
|
||
scar_pressure = 1.0 - closure_frac
|
||
|
||
spectral_raw = int(closure_frac * 4 * Q16_SCALE)
|
||
max_raw = int(4 * Q16_SCALE)
|
||
signal_threshold = int(2 * Q16_SCALE)
|
||
|
||
r = Q16_SCALE if spectral_raw >= max_raw else 0
|
||
g = (spectral_raw - signal_threshold) * Q16_SCALE // (max_raw - signal_threshold) if spectral_raw >= signal_threshold else 0
|
||
b = spectral_raw * Q16_SCALE // signal_threshold if spectral_raw < signal_threshold else 0
|
||
|
||
rrc_shape = "CognitiveLoadField" if r > 0 else (
|
||
"SignalShapedRouteCompiler" if g > 0 else "NoiseFloor"
|
||
)
|
||
famm_state = "HOLD" if scar_pressure > 0.85 else (
|
||
"INSPECT" if scar_pressure > 0.5 else "ACCEPT"
|
||
)
|
||
|
||
return {
|
||
"name": name,
|
||
"source": source,
|
||
"equation": eq_str.strip()[:200],
|
||
"constraint_graph": {
|
||
"n_ops": n_ops, "n_vars": n_vars, "n_parens": n_parens,
|
||
"has_trig": bool(has_trig), "has_diff": bool(has_diff),
|
||
"graph_size": graph_size, "complexity_chars": complexity,
|
||
},
|
||
"sidon_signature": {
|
||
"addresses": sidon_addr, "pairwise_sums": sums_list,
|
||
"n_pairs": n_pairs, "unique_sums": len(sums),
|
||
"sumset_density": round(sumset_density, 4),
|
||
"noise_ratio": round(structural_noise, 4),
|
||
},
|
||
"famm": {
|
||
"closure_fraction": round(closure_frac, 4),
|
||
"scar_pressure": round(scar_pressure, 4),
|
||
"famm_state": famm_state, "rrc_shape": rrc_shape,
|
||
"rgb": {"r": r, "g": g, "b": b},
|
||
},
|
||
}
|
||
|
||
|
||
# ─── Propnet parser ──────────────────────────────────────────────────────────
|
||
|
||
def parse_propnet_models(propnet_path: str) -> list[dict]:
|
||
"""Parse SymPy equations from Propnet model files."""
|
||
results = []
|
||
models_dir = os.path.join(propnet_path, "propnet", "models", "python")
|
||
if not os.path.isdir(models_dir):
|
||
return results
|
||
|
||
for fname in sorted(os.listdir(models_dir)):
|
||
if not fname.endswith(".py") or fname == "__init__.py":
|
||
continue
|
||
fpath = os.path.join(models_dir, fname)
|
||
with open(fpath) as f:
|
||
content = f.read()
|
||
# Extract equation strings
|
||
eqs = re.findall(r'["\']([^"\']*(?:=|=|≈)[^"\']*)["\']', content)
|
||
eqs += re.findall(r'Eq\([^)]+\)', content)
|
||
for eq in eqs[:5]:
|
||
sig = classify_equation(eq, name=fname.replace(".py", ""), source="propnet")
|
||
results.append(sig)
|
||
return results
|
||
|
||
|
||
# ─── Plain text equation parser ──────────────────────────────────────────────
|
||
|
||
def parse_equation_file(filepath: str) -> list[dict]:
|
||
"""Parse equations from a plain text file (one per line, or name=eq format)."""
|
||
results = []
|
||
with open(filepath) as f:
|
||
for line in f:
|
||
line = line.strip()
|
||
if not line or line.startswith("#") or line.startswith("//"):
|
||
continue
|
||
if "=" in line:
|
||
parts = line.split("=", 1)
|
||
name = parts[0].strip()
|
||
eq = parts[1].strip()
|
||
else:
|
||
name = f"eq_{len(results)}"
|
||
eq = line
|
||
sig = classify_equation(eq, name=name, source=filepath)
|
||
results.append(sig)
|
||
return results
|
||
|
||
|
||
# ─── CALPHAD .tdb parser ────────────────────────────────────────────────────
|
||
|
||
def parse_tdb_file(filepath: str) -> list[dict]:
|
||
"""Parse thermodynamic equations from CALPHAD .tdb format."""
|
||
results = []
|
||
with open(filepath, errors="replace") as f:
|
||
content = f.read()
|
||
# Extract polynomial expressions (G = ...)
|
||
eqs = re.findall(r'G\s*=\s*[^;]+', content)
|
||
for eq in eqs[:50]:
|
||
sig = classify_equation(eq[:200], name="tdb_gibbs", source=filepath)
|
||
results.append(sig)
|
||
return results
|
||
|
||
|
||
# ─── Main ────────────────────────────────────────────────────────────────────
|
||
|
||
def main():
|
||
import argparse
|
||
ap = argparse.ArgumentParser()
|
||
ap.add_argument("--input", help="Input equation file (plain text)")
|
||
ap.add_argument("--tdb", help="Input CALPHAD .tdb file")
|
||
ap.add_argument("--propnet", action="store_true", help="Scan Propnet models")
|
||
ap.add_argument("--out", default="equation_shape_index.json")
|
||
args = ap.parse_args()
|
||
|
||
all_results = []
|
||
|
||
if args.propnet:
|
||
for p in ["/home/allaun/propnet_db", "/home/allaun/Research Stack/../propnet_db"]:
|
||
if os.path.isdir(p):
|
||
all_results.extend(parse_propnet_models(p))
|
||
print(f"Parsed {len(all_results)} equations from Propnet")
|
||
|
||
if args.input and os.path.isfile(args.input):
|
||
all_results.extend(parse_equation_file(args.input))
|
||
print(f"Parsed {len(all_results)} equations from {args.input}")
|
||
|
||
if args.tdb and os.path.isfile(args.tdb):
|
||
all_results.extend(parse_tdb_file(args.tdb))
|
||
print(f"Parsed {len(all_results)} TDB equations")
|
||
|
||
# Build shape index
|
||
shape_dist = defaultdict(int)
|
||
for r in all_results:
|
||
shape_dist[r["famm"]["rrc_shape"]] += 1
|
||
|
||
index = {
|
||
"meta": {
|
||
"source": "equation_parser",
|
||
"total_equations": len(all_results),
|
||
"shape_distribution": dict(shape_dist),
|
||
"built_at": datetime.now(timezone.utc).isoformat(),
|
||
"schema": "equation_shape_index_v1",
|
||
},
|
||
"equations": all_results,
|
||
}
|
||
|
||
with open(args.out, "w") as f:
|
||
json.dump(index, f, indent=2)
|
||
|
||
print(f"\nShape distribution: {dict(shape_dist)}")
|
||
print(f"Output: {args.out}")
|
||
|
||
|
||
if __name__ == "__main__":
|
||
main()
|