import torch, numpy as np, os, subprocess
from pathlib import Path
import sys

ZSY = '/root/siton-data-2849d4ce327c4ccfb233ce33868fe7fe/zsy'
DATA = Path(ZSY + '/multimodal_affect/data')
ok = []; fail = []

def chk(name, cond, detail=''):
    mark = 'OK  ' if cond else 'FAIL'
    print(f'  [{mark}] {name}: {detail}')
    (ok if cond else fail).append(name)

print('=== Phase 0 Acceptance Check ===')

# GPU
g = torch.cuda.device_count()
chk('4x GPU', g == 4, str(g) + ' GPUs')

# packages
import transformers, librosa, timm, sklearn, wandb, stable_baselines3, gymnasium
for name, mod in [
    ('transformers', transformers), ('librosa', librosa), ('timm', timm),
    ('sklearn', sklearn), ('wandb', wandb), ('sb3', stable_baselines3), ('gymnasium', gymnasium)
]:
    chk(name, True, getattr(mod, '__version__', 'ok'))

# datasets
for ds, mods in [
    ('iemocap', ['text', 'audio', 'vision', 'labels']),
    ('mosi',    ['text', 'audio', 'vision', 'labels']),
    ('meld',    ['text', 'labels']),
]:
    all_ok = all((DATA / ds / (s + '_' + m + '.npy')).exists()
                 for s in ['train', 'val', 'test'] for m in mods)
    if all_ok:
        sample = np.load(str(DATA / ds / 'train_labels.npy'))
        chk(ds + ' features', True, 'train N=' + str(sample.shape[0]))
    else:
        missing = [s + '_' + m for s in ['train', 'val', 'test'] for m in mods
                   if not (DATA / ds / (s + '_' + m + '.npy')).exists()]
        chk(ds + ' features', False, 'missing: ' + str(missing[:3]))

# noise variants
noisy = DATA / 'iemocap_noisy'
n_var = len([x for x in noisy.iterdir() if x.is_dir()]) if noisy.exists() else 0
chk('noise 8 variants', n_var == 8, str(n_var) + '/8')

# git
r = subprocess.run(['git', '-C', ZSY + '/multimodal_affect', 'log', '--oneline', '-3'],
                   capture_output=True, text=True)
log_oneline = r.stdout.strip().replace('\n', ' | ')
chk('git history', r.returncode == 0, log_oneline)

# disk
r2 = subprocess.run(['df', '-h', ZSY], capture_output=True, text=True)
for line in r2.stdout.splitlines()[1:]:
    parts = line.split()
    if len(parts) >= 4:
        chk('disk free', True, 'avail=' + parts[3] + ' use=' + parts[4])

print()
print('Result: ' + str(len(ok)) + ' OK / ' + str(len(fail)) + ' FAIL')
if not fail:
    print('Phase 0 PASS - ready for Phase 1')
else:
    print('FAIL items: ' + str(fail))