4306f76ddb
- c6111_extract: roles_for() 동적 생성, COLUMN_EXCEPTIONS per-prefix - c6111_prodmap/shadow/startup/rolling: --data/--prefix CLI 인자 지원 - run_column.py: 5개 컬럼 전 파이프라인 실행 래퍼 - c6111_shutdown.py: detect_cutoffs + shutdown_milestones (lookback 1200) - c6111_operator_assist.py: OOD 게이트 + shadow 리플레이 - c6111_export_model.py: 선형근사 JSON export - SteamAdvisor.cs: Predict+ClassifyMode+InEnvelope (NaN guard, Ood fix) - SteamAdvisorController: GET/POST /api/steam/predict - appsettings.json/Program.cs: DI 등록 - docs: 작업지시서 현황 갱신, 진단보고서 작성 (3 MED/8 LOW, 100% 정확도)
81 lines
2.8 KiB
Python
81 lines
2.8 KiB
Python
"""
|
|
모델 JSON export → C# SteamAdvisor에서 로드.
|
|
|
|
선형근사(1안): GBM 대신 LinearRegression 계수 export.
|
|
steam = w0 + w1*feed + w2*product + w3*T_C
|
|
valve_inv(flow) = poly3 → OP
|
|
|
|
사용법:
|
|
python3 c6111_export_model.py --data c6111_data.pkl --prefix c6111
|
|
"""
|
|
import argparse
|
|
import json
|
|
import numpy as np
|
|
import pandas as pd
|
|
from sklearn.linear_model import LinearRegression
|
|
|
|
BASE = "/home/windpacer/projects/hc900_ax/scripts/analysis/"
|
|
FEATURES = ["feed", "product", "T_C"]
|
|
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("--data", default=BASE + "c6111_data.pkl")
|
|
parser.add_argument("--prefix", default="c6111")
|
|
parser.add_argument("--output", help="JSON 출력 경로 (기본: scripts/analysis/{prefix}_model.json)")
|
|
args = parser.parse_args()
|
|
df = pd.read_pickle(args.data)
|
|
|
|
prod = df[df["mode"] == "PROD"].copy()
|
|
prod = prod[(prod["feed"] > 50) & (prod["steam_flow"] > 10) & (prod["steam_op"] > 1)]
|
|
prod = prod.dropna(subset=FEATURES + ["steam_op", "steam_flow"])
|
|
ops = (prod.set_index("dtat").resample("6h").median(numeric_only=True)
|
|
.dropna(subset=["steam_flow", "feed"]))
|
|
ops = ops[ops["feed"] > 50]
|
|
|
|
# 선형 모델
|
|
lr = LinearRegression()
|
|
lr.fit(ops[FEATURES].values, ops["steam_flow"].values)
|
|
r2 = lr.score(ops[FEATURES].values, ops["steam_flow"].values)
|
|
print(f"선형 steam_flow R² = {r2:.4f} (GBM 대비 비교용)")
|
|
|
|
# 밸브 역특성: steam_flow → steam_op (3차)
|
|
vp = np.polyfit(prod["steam_flow"], prod["steam_op"], 3)
|
|
|
|
# Envelope (1%, 99%)
|
|
lo = ops[FEATURES].quantile(0.01)
|
|
hi = ops[FEATURES].quantile(0.99)
|
|
|
|
# GBM feature importance (참고용)
|
|
try:
|
|
from sklearn.ensemble import GradientBoostingRegressor
|
|
gbm = GradientBoostingRegressor(n_estimators=200, max_depth=2,
|
|
learning_rate=0.05, random_state=0)
|
|
gbm.fit(ops[FEATURES].values, ops["steam_flow"].values)
|
|
gbm_r2 = gbm.score(ops[FEATURES].values, ops["steam_flow"].values)
|
|
except Exception:
|
|
gbm_r2 = None
|
|
|
|
model = {
|
|
"column": args.prefix,
|
|
"features": FEATURES,
|
|
"linear_coeffs": lr.coef_.tolist(),
|
|
"intercept": lr.intercept_,
|
|
"linear_r2": round(r2, 4),
|
|
"gbm_r2": round(gbm_r2, 4) if gbm_r2 else None,
|
|
"valve_poly": vp.tolist(),
|
|
"envelope_lo": {c: round(float(lo[c]), 1) for c in FEATURES},
|
|
"envelope_hi": {c: round(float(hi[c]), 1) for c in FEATURES},
|
|
"n_operating_points": len(ops),
|
|
"n_prod_rows": len(prod),
|
|
}
|
|
out = args.output or (BASE + f"{args.prefix}_model.json")
|
|
with open(out, "w") as f:
|
|
json.dump(model, f, indent=2)
|
|
print(f"\n모델 export: {out}")
|
|
print(json.dumps(model, indent=2))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|