Spaces:
Sleeping
Sleeping
File size: 2,510 Bytes
906c392 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 | """
Minimal script: run the DL 5-fold CV exactly as train_deep_classifiers.py
does, but also save the raw out-of-fold probability array per model to
models/dl_oof_probs.npz, so ensemble_model.py can build a real ensemble
without retraining DL models a second time.
Usage:
python -m app.training.dump_dl_oof
"""
from __future__ import annotations
import sys
import time
from pathlib import Path
import numpy as np
sys.path.insert(0, str(Path(__file__).resolve().parents[2]))
from sklearn.metrics import roc_auc_score
from sklearn.model_selection import StratifiedKFold
from app.training.train_deep_classifiers import (
DeepMLP, Conv1DClassifier, ResidualMLP, AttentionMLP,
load_data, train_one_fold, set_seed, SEED, N_FOLDS, DEVICE,
)
MODELS_DIR = Path(__file__).resolve().parents[2] / "models"
FEATURES_CSV = Path("D:/CrownCode/DataSet/features.csv")
MODEL_CLASSES = {
"Deep MLP (512-256-128-64)": DeepMLP,
"1D-CNN": Conv1DClassifier,
"Residual MLP (3 blocks)": ResidualMLP,
"Attention MLP": AttentionMLP,
}
def main() -> None:
print(f"Device: {DEVICE}", flush=True)
X, y, feature_cols = load_data(FEATURES_CSV)
print(f"Samples: {len(y)}, Features: {X.shape[1]}", flush=True)
cv = StratifiedKFold(n_splits=N_FOLDS, shuffle=True, random_state=SEED)
fold_assignments = list(cv.split(X, y))
oof: dict[str, np.ndarray] = {}
for name, cls in MODEL_CLASSES.items():
print(f"\n{'='*60}\n {name}\n{'='*60}", flush=True)
t0 = time.time()
all_probs = np.zeros(len(y))
for fold, (train_idx, val_idx) in enumerate(fold_assignments):
set_seed(SEED + fold)
model = cls(X.shape[1])
fold_t0 = time.time()
auc, probs = train_one_fold(model, X[train_idx], y[train_idx], X[val_idx], y[val_idx])
all_probs[val_idx] = probs
print(f" Fold {fold+1}/{N_FOLDS}: AUC={auc:.4f} ({time.time()-fold_t0:.1f}s)", flush=True)
oof[name] = all_probs
total_auc = roc_auc_score(y, all_probs)
print(f" => Overall OOF AUC={total_auc:.4f} ({time.time()-t0:.1f}s total)", flush=True)
out_path = MODELS_DIR / "dl_oof_probs.npz"
np.savez(out_path, y=y, **{name.replace(" ", "_").replace("(", "").replace(")", "").replace("-", "_"): probs
for name, probs in oof.items()})
print(f"\nSaved: {out_path}", flush=True)
print("Keys:", list(np.load(out_path).keys()))
if __name__ == "__main__":
main()
|