File size: 7,826 Bytes
6f3905f | 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 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 | """
xp2: effect of training-data quality on CombiLatent performance.
For each percentile p in {5, 10, 15, ..., 95}:
1. Build a dataset from the xp1 exhaustive_9_6 raw data by removing
the top-p% best schedules (lowest makespan values).
2. Train the surrogate (n_embd=40, n_head=4, n_layer=2, all other
hyper-parameters identical to xp1's best config).
3. Run Phase-2 latent optimisation (no metropolized filling).
Run from: src/xp2/
"""
import os
import sys
import json
import shutil
import math
import numpy as np
from tqdm import tqdm
# ββ make xp1 modules importable ββββββββββββββββββββββββββββββββββββββββββββββ
XP1_DIR = os.path.abspath(os.path.join(os.path.dirname(__file__), "../xp1"))
sys.path.insert(0, XP1_DIR)
from train import train
from recover_schedules import recover_schedules
# ββ paths βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
RAW_DATA_DIR = os.path.abspath(os.path.join(XP1_DIR, "outputs/exhaustive_9_6"))
XP2_OUT_ROOT = os.path.join(os.path.dirname(__file__), "outputs/exhaustive_9_6")
N_EMBD = 40
N_HEAD = 4
N_LAYER = 2
PERCENTILES = list(range(5, 100, 5)) # [5, 10, 15, ..., 95]
# ββ dataset processing ββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
def process_dataset_pct(raw_data_dir, output_dir, top_pct, train_ratio=0.9, seed=97):
"""
Build a processed (train/val split) dataset from the raw exhaustive data
by removing the best `top_pct`% schedules (lowest makespan values).
Files written to output_dir:
schedules_train.npy, makespans_train.npy
schedules_val.npy, makespans_val.npy
metadata.json, pfsp_instance.npy
neh_makespan.npy, cds_makespan.npy, palmer_makespan.npy, min_makespan.npy
"""
if os.path.exists(os.path.join(output_dir, "metadata.json")):
print(f" [process] already done β skipping {output_dir}")
return
os.makedirs(output_dir, exist_ok=True)
# load raw data
schedules = np.load(os.path.join(raw_data_dir, "schedules.npy"))
makespans = np.load(os.path.join(raw_data_dir, "makespans.npy")) # (N, nb_jobs)
with open(os.path.join(raw_data_dir, "metadata.json")) as f:
metadata = json.load(f)
ms = makespans[:, -1] # final makespan per schedule
# remove the top-pct% best (lowest) makespans
n_total = len(ms)
n_remove = math.floor(top_pct / 100 * n_total)
sorted_idx = np.argsort(ms)
remove_set = set(sorted_idx[:n_remove].tolist())
keep_mask = np.array([i not in remove_set for i in range(n_total)])
schedules = schedules[keep_mask]
makespans = makespans[keep_mask]
ms = makespans[:, -1]
n_kept = len(schedules)
print(f" [process] top_pct={top_pct}%: removed {n_remove}, kept {n_kept} schedules")
# save min makespan of remaining data
np.save(os.path.join(output_dir, "min_makespan.npy"), ms.min())
# stratified train/val split by makespan value
np.random.seed(seed)
unique_ms = np.unique(ms)
train_idx_list, val_idx_list = [], []
for m in unique_ms:
group = np.where(ms == m)[0]
np.random.shuffle(group)
n_train = max(1, int(len(group) * train_ratio))
if n_train >= len(group):
train_idx_list.append(group)
else:
train_idx_list.append(group[:n_train])
val_idx_list.append(group[n_train:])
train_indices = np.concatenate(train_idx_list)
val_indices = np.concatenate(val_idx_list) if val_idx_list else np.array([], dtype=int)
np.save(os.path.join(output_dir, "schedules_train.npy"), schedules[train_indices])
np.save(os.path.join(output_dir, "makespans_train.npy"), makespans[train_indices])
np.save(os.path.join(output_dir, "schedules_val.npy"), schedules[val_indices])
np.save(os.path.join(output_dir, "makespans_val.npy"), makespans[val_indices])
# metadata
split_meta = metadata.copy()
split_meta["nb_train_samples"] = len(train_indices)
split_meta["nb_val_samples"] = len(val_indices)
split_meta["data_source"] = raw_data_dir
split_meta["top_pct_removed"] = top_pct
split_meta["n_removed"] = int(n_remove)
split_meta["n_kept"] = int(n_kept)
with open(os.path.join(output_dir, "metadata.json"), "w") as f:
json.dump(split_meta, f, indent=4)
# copy static files from raw dir
for fname in ["pfsp_instance.npy", "neh_makespan.npy",
"cds_makespan.npy", "palmer_makespan.npy"]:
shutil.copy(os.path.join(raw_data_dir, fname),
os.path.join(output_dir, fname))
print(f" [process] done β {n_train} train / {len(val_indices)} val samples")
# ββ main loop βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
for pct in (outer:=tqdm(PERCENTILES, desc="Percentiles")):
outer.set_description(f"top_pct={pct}%")
data_dir = os.path.join(XP2_OUT_ROOT, f"top_pct_{pct}")
model_dir = os.path.join(data_dir, f"train_nEmbd{N_EMBD}_nHead{N_HEAD}_nLayer{N_LAYER}")
rs_dir = os.path.join(model_dir, "recover_no_mf")
# ββ Stage 1: process dataset ββββββββββββββββββββββββββββββββββββββββββββββ
process_dataset_pct(
raw_data_dir=RAW_DATA_DIR,
output_dir=data_dir,
top_pct=pct,
)
# ββ Stage 2: train surrogate ββββββββββββββββββββββββββββββββββββββββββββββ
train(
testing=False,
seed=97,
data_dir=data_dir,
n_embd=N_EMBD,
n_head=N_HEAD,
n_layer=N_LAYER,
intermediate_schedules=True,
dropout=0.0,
ff_width=4,
train_batch_size=512,
val_batch_size=256,
nb_epochs=5,
early_stopping_patience=15,
checkpoint_interval_ratio=1.0,
decay_lr=True,
lr_partitions_ratios=[0.66],
init_lr=1e-4,
max_lr=1e-3,
min_lr=5e-5,
lr_warmup_iters_ratio=0.1,
lr_decay_iters_ratio=0.95,
beta1=0.9,
beta2=0.95,
weight_decay=10.0,
grad_clip=1.0,
compile=False,
compile_mode="default",
save_only_last_checkpoint=True,
output_dir=model_dir,
)
# ββ Stage 3: Phase-2 latent optimisation (no mf) ββββββββββββββββββββββββββ
recover_schedules(
testing=False,
seed=97,
init_mode="random",
n_optimization_steps=2000,
epsilon=0.01,
nb_sinkhorn_iters=40,
decay_ls=False,
ls_partitions_ratios=[0.66],
init_ls=2.0,
max_ls=10,
min_ls=0.1,
ls_warmup_iters_ratio=0.2,
ls_decay_iters_ratio=0.90,
decay_lr=True,
lr_partitions_ratios=[0.66],
init_lr=1e-2,
max_lr=1e-1,
min_lr=1e-4,
lr_warmup_iters_ratio=0.1,
lr_decay_iters_ratio=0.90,
checkpoint_interval=1,
data_dir=data_dir,
model_dir=model_dir,
output_dir=rs_dir,
apply_metropolized_filling=False,
mf_patience=10,
mf_fifo_size=50,
mf_penalty_strength=1.0,
mf_min_delta=0.05,
)
|