xgboost
This commit is contained in:
152
.old/train.py
Normal file
152
.old/train.py
Normal file
@@ -0,0 +1,152 @@
|
||||
import pandas as pd
|
||||
import json, os, sys
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.optim as optim
|
||||
from sklearn.preprocessing import StandardScaler
|
||||
|
||||
MAX_MARGIN_LIMIT = 10
|
||||
|
||||
class DifficultyNet(nn.Module):
|
||||
def __init__(self, input_dim):
|
||||
super(DifficultyNet, self).__init__()
|
||||
self.net = nn.Sequential(
|
||||
nn.Linear(input_dim, 128),
|
||||
nn.BatchNorm1d(128),
|
||||
nn.ReLU(),
|
||||
nn.Dropout(0.4),
|
||||
nn.Linear(128, 64),
|
||||
nn.ReLU(),
|
||||
nn.Dropout(0.3),
|
||||
nn.Linear(64, 32),
|
||||
nn.ReLU(),
|
||||
nn.Linear(32, 1),
|
||||
nn.Sigmoid()
|
||||
)
|
||||
|
||||
def forward(self, x):
|
||||
return self.net(x)
|
||||
|
||||
def train(script_dir, working_dir, data_dir, train_count, val_count, margin, val_iterations):
|
||||
device = torch.device("mps" if torch.backends.mps.is_available() else "cpu")
|
||||
print(f"🚀 Using Device: {device}")
|
||||
|
||||
# 데이터 로드 및 병합
|
||||
factors_path = os.path.join(working_dir, 'factors.json')
|
||||
if not os.path.exists(factors_path):
|
||||
os.system(f"bun run {os.path.join(script_dir, 'factorize.ts')} {data_dir} {working_dir}")
|
||||
|
||||
df_feat = pd.read_json(factors_path)
|
||||
df_meas = pd.read_csv(os.path.join(data_dir, 'measure.csv'))
|
||||
df_meas['diff'] = df_meas['diff'].replace('ura', 'edit')
|
||||
df_feat['songno'], df_meas['songno'] = df_feat['songno'].astype(int), df_meas['songno'].astype(int)
|
||||
df = pd.merge(df_feat, df_meas, on=['songno', 'diff'])
|
||||
|
||||
exclude_cols = ['songno', 'diff', 'title', 'course', '상수', 'predicted_measure', 'error']
|
||||
X_cols = [c for c in df_feat.columns if c not in exclude_cols]
|
||||
|
||||
scaler = StandardScaler()
|
||||
df[X_cols] = scaler.fit_transform(df[X_cols])
|
||||
with open(os.path.join(working_dir, 'scaler.json'), 'w') as f:
|
||||
json.dump({'mean': scaler.mean_.tolist(), 'std': scaler.scale_.tolist(), 'cols': X_cols}, f)
|
||||
|
||||
model_path = os.path.join(working_dir, 'model.pth')
|
||||
margin = float(margin)
|
||||
val_iterations = int(val_iterations)
|
||||
|
||||
model = DifficultyNet(len(X_cols)).to(device)
|
||||
attempt = 1
|
||||
|
||||
while True:
|
||||
print(f"\n[Attempt {attempt}] " + "-"*40)
|
||||
if os.path.exists(model_path):
|
||||
try: model.load_state_dict(torch.load(model_path, map_location=device))
|
||||
except: pass
|
||||
|
||||
train_df = df.sample(n=min(int(train_count), len(df)))
|
||||
X_train = torch.FloatTensor(train_df[X_cols].values).to(device)
|
||||
y_train = torch.FloatTensor(((train_df['상수'].values - 1) / 11)).unsqueeze(1).to(device)
|
||||
|
||||
base_lr = 0.001
|
||||
optimizer = optim.Adam(model.parameters(), lr=base_lr, weight_decay=1e-5)
|
||||
criterion = nn.L1Loss()
|
||||
|
||||
model.train()
|
||||
epoch = 0
|
||||
while True:
|
||||
optimizer.zero_grad()
|
||||
preds_train = model(X_train)
|
||||
loss = criterion(preds_train, y_train) # MSELoss 권장
|
||||
loss.backward()
|
||||
optimizer.step()
|
||||
|
||||
# 현재 학습 데이터에 대한 오차 분석
|
||||
with torch.no_grad():
|
||||
diff = torch.abs((preds_train * 12 + 0.5) - (y_train * 12 + 0.5))
|
||||
train_mae = torch.mean(diff).item()
|
||||
train_max = torch.max(diff).item()
|
||||
|
||||
if epoch % 1000 == 0:
|
||||
print(f" - Ep {epoch:5d} | MAE: {train_mae:.4f} | MAX: {train_max:.4f}")
|
||||
|
||||
# ✅ 조건 강화: MAE뿐만 아니라 MAX도 어느 정도 잡혔을 때만 검증으로 이동
|
||||
if train_mae < margin and train_max < (margin * MAX_MARGIN_LIMIT):
|
||||
print(f" ✅ Train Goal Reached (MAE: {train_mae} < {margin:.4f}, MAX: {train_max:.4f} < {(margin * MAX_MARGIN_LIMIT):.4f}). Moving to Val.")
|
||||
break
|
||||
|
||||
epoch += 1
|
||||
if epoch > 50000:
|
||||
print(" ⚠️ Timed out. Resampling...")
|
||||
break
|
||||
|
||||
if train_mae >= margin:
|
||||
torch.save(model.state_dict(), model_path)
|
||||
attempt += 1
|
||||
continue
|
||||
|
||||
# 3. 검증 단계
|
||||
print(f"3. Validating {val_iterations} iterations...")
|
||||
model.eval()
|
||||
all_passed = True
|
||||
with torch.no_grad():
|
||||
for i in range(1, val_iterations + 1):
|
||||
val_df = df.sample(n=min(int(val_count), len(df)))
|
||||
X_val = torch.FloatTensor(val_df[X_cols].values).to(device)
|
||||
y_val_raw = val_df['상수'].values
|
||||
preds = model(X_val) * 12 + 0.5
|
||||
y_val_tensor = torch.FloatTensor(y_val_raw).unsqueeze(1).to(device)
|
||||
diff_tensor = torch.abs(preds - y_val_tensor)
|
||||
mae = torch.mean(diff_tensor).item()
|
||||
max_error = torch.max(diff_tensor).item()
|
||||
|
||||
|
||||
# csv 저장
|
||||
# preds를 CPU 넘파이로 변환하고 1차원으로 펴주는 과정이 포함되어야 합니다.
|
||||
preds_np = preds.detach().cpu().numpy().flatten() if torch.is_tensor(preds) else preds
|
||||
|
||||
res_df = val_df[['songno', 'diff', '상수']].copy()
|
||||
res_df['predicted_measure'] = preds_np
|
||||
res_df['error'] = np.abs(preds_np - y_val_raw)
|
||||
|
||||
output_file = os.path.join(working_dir, f'validate_result_{i}.csv')
|
||||
res_df.to_csv(output_file, index=False)
|
||||
|
||||
if mae <= margin and max_error <= (margin * MAX_MARGIN_LIMIT):
|
||||
print(f" [Iter {i}] ✅ PASS (MAE: {mae:.4f}, MAX: {max_error:.4f})")
|
||||
else:
|
||||
print(f" [Iter {i}] ❌ FAIL (MAE: {mae:.4f} > {margin} || MAX: {max_error:.4f} > {margin * MAX_MARGIN_LIMIT})")
|
||||
all_passed = False
|
||||
break
|
||||
|
||||
if all_passed:
|
||||
print(f"\n✨ Final Success!")
|
||||
torch.save(model.state_dict(), model_path)
|
||||
return
|
||||
else:
|
||||
torch.save(model.state_dict(), model_path)
|
||||
attempt += 1
|
||||
|
||||
if __name__ == "__main__":
|
||||
if len(sys.argv) < 8: sys.exit(1)
|
||||
train(*sys.argv[1:8])
|
||||
Reference in New Issue
Block a user